{"uuid": "c1bef909-1862-49a8-a251-449b2b68a531", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768432619386316032, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b854474d-3673-4756-8880-63ef7ba79f12", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768432729340635904, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2d942d4e-3b45-45e1-9258-6d9a59f1510f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768432825308583936, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "4476f265-c6f1-4bb4-adff-426309d69ecd", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768432953262728960, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "dbb8dca8-5cb6-4f86-b055-66611be1c06b", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Gemma3nForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768433253655924992, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "15b6c6a0-dec8-4c17-9b64-da64e9040377", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Gemma3nForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768433753267461888, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "5b5a13c2-29cc-4de0-b661-39fa79e11346", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Gemma3nForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768433940349328896, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "79a09e9b-1b45-4d6d-8484-f97f1d6b6f40", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768434246964911872, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "32a70aba-cba8-48ba-adc2-18e5d734e0b1", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768434389954049024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b0821020-60aa-48f1-9d84-8e33d95e242b", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Gemma3nForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768435620765497088, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d8fd00d1-9669-4585-9a3f-96de782408d4", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768438246257960960, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3b0e33c6-2644-4b73-888d-a17b2fea2ff0", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768452588053765120, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "c5933951-4f13-4440-8e6d-1fa02f777d22", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768452932732145152, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6be781f9-5be9-4c81-afad-56511f0a0c43", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Gemma3nForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768453117628567808, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "980bd7b6-da0d-410e-a989-20f5fff828f5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768453418871066112, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "932f5f46-a1c1-45e2-a451-9ee771a279d5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768506906810067968, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "932f5f46-a1c1-45e2-a451-9ee771a279d5", "log_time": 1768507506979842048}
{"uuid": "932f5f46-a1c1-45e2-a451-9ee771a279d5", "log_time": 1768508107171841024}
{"uuid": "932f5f46-a1c1-45e2-a451-9ee771a279d5", "log_time": 1768508707390779904}
{"uuid": "27dae317-d659-4ae6-87f3-056f2b8040da", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Gemma3nForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768509027629349888, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "27dae317-d659-4ae6-87f3-056f2b8040da", "log_time": 1768509627768156160}
{"uuid": "ce7a432e-6f5e-42a9-867d-58488936e00d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "GPT2Model", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768534222056972032, "source": "production", "dtype": "torch.float16", "block_size": 16, "gpu_memory_utilization": 0.1, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "ef3e5ed9-def7-4b5a-8c81-e1b7050af8bf", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768534298141968896, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "589d3ec9-7010-4401-8ea3-4b1165c56260", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768534469733916160, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "a9e1d9ac-5316-49ac-8d90-85cafbc08e82", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_ATTENTION_BACKEND\": null, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Gemma3nForConditionalGeneration", "vllm_version": "0.13.0", "context": "ENGINE_CONTEXT", "log_time": 1768535058579088896, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "8e07ccdd-09ce-45b9-8786-bf04e07e3484", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771027765105777920, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771027878769551104, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771028478975269120}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771029079173750016}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771029679297239040}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771030279510301952}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771030879701783808}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771031479877174016}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771032080097181184}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771032680317667072}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771033280532367104}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771033880756155136}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771034480967873024}
{"uuid": "98bdf75a-67e9-417f-8c11-498a46bce1dc", "log_time": 1771035081185720832}
{"uuid": "99c84788-8402-4dc4-b23b-e9f80e0bc5f6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771035623463659008, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "325ea1ec-4321-49f2-8afe-7b70956c594c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771037190836796160, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "bcdbb48e-10c8-4055-93dc-f2778035935c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771037580337146880, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "cc38bffc-e83b-4dd5-8149-5297a137ec61", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771037894470904064, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "cc38bffc-e83b-4dd5-8149-5297a137ec61", "log_time": 1771038494660105984}
{"uuid": "cc38bffc-e83b-4dd5-8149-5297a137ec61", "log_time": 1771039094871531008}
{"uuid": "18e76029-e071-429e-8041-6d91e05fcf91", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771039293213340928, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "23f709ce-b5ef-4109-9134-929687c0ac45", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771039293675041792, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "564f17d0-d943-4861-9859-13af0c1ff98f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771039294016356096, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "564f17d0-d943-4861-9859-13af0c1ff98f", "log_time": 1771039894311662848}
{"uuid": "8cc61fe4-1bc2-4e6a-8c03-6b0c6f0674e1", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771040493596705792, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "7508f095-d3b9-4609-95f2-577873c452f8", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771040494019228928, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "7508f095-d3b9-4609-95f2-577873c452f8", "log_time": 1771041094277199872}
{"uuid": "ccc39a3d-554e-4604-abd1-503b083bda95", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771041633055905024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "217657ed-4c2b-471f-acef-71a03cf38703", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771041633412193024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "4d9fd236-e3ca-4fa9-b9c3-062febb4ec10", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771041633564333056, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "7508f095-d3b9-4609-95f2-577873c452f8", "log_time": 1771041694406748928}
{"uuid": "7508f095-d3b9-4609-95f2-577873c452f8", "log_time": 1771042294612029952}
{"uuid": "dc65423d-0c5d-4416-9e29-4e7fd52638a7", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771042906193634048, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "dc65423d-0c5d-4416-9e29-4e7fd52638a7", "log_time": 1771043506409254144}
{"uuid": "dc65423d-0c5d-4416-9e29-4e7fd52638a7", "log_time": 1771044106529999872}
{"uuid": "4ad5e0d2-9a3e-4dab-ae48-18af3539add1", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771044587756140032, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d75f190d-5037-47e9-9595-91020ed7a569", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771044716445682176, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771044851131598848, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771045451363112960}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771046051495232000}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771046651622558208}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771047251748531968}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771047851873444096}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771048451997467136}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771049052117571072}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771049652330972928}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771050252513767936}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771050852675550976}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771051452799331072}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771052053002063872}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771052653136387072}
{"uuid": "3306e8df-a5ac-40f9-ad7b-125ca1696bf3", "log_time": 1771053253364167936}
{"uuid": "2027a0eb-44a2-4506-9c85-2651a9d88035", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771053354066701824, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.125, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2027a0eb-44a2-4506-9c85-2651a9d88035", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771053372563056896, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.125, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6a4ad5cd-1d9b-49a5-8fec-81cc6383a148", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771053844447127040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2142dadd-d847-45e7-8126-ffcd7a0741df", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771054095658050048, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3fad2e59-ca70-4510-8f5c-83b3f887392d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771054358030530816, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "c17c7626-632b-4679-abd0-0fffeee04048", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771054650024705792, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "c17c7626-632b-4679-abd0-0fffeee04048", "log_time": 1771055250232759040}
{"uuid": "c17c7626-632b-4679-abd0-0fffeee04048", "log_time": 1771055850445203968}
{"uuid": "c17c7626-632b-4679-abd0-0fffeee04048", "log_time": 1771056450664216064}
{"uuid": "e0259101-1748-47dd-9ee6-5f863fc00079", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771056649194993920, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e0259101-1748-47dd-9ee6-5f863fc00079", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771056667881826048, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e0259101-1748-47dd-9ee6-5f863fc00079", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771056687412295168, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "10958d25-5ee0-4d7c-aa27-d1dedfaf3228", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771057293255790848, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771057293414583040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "9c4cc0bf-1ce5-4b55-99e9-54683f836c5f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771057293576441088, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771057314378833152, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "10958d25-5ee0-4d7c-aa27-d1dedfaf3228", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771057314746299904, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771057334436626944, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "10958d25-5ee0-4d7c-aa27-d1dedfaf3228", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771057334900742144, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "log_time": 1771057893676926976}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "log_time": 1771057914712743168}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "log_time": 1771057934698770944}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "log_time": 1771058493817733888}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "log_time": 1771058514933076992}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "log_time": 1771058534902863872}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "log_time": 1771059094034703872}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "log_time": 1771059115141295872}
{"uuid": "34f0f3bf-6f30-4c62-b8dd-6b160a69351c", "log_time": 1771059135086280192}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771059530304954880, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771059549114653184, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771059568005775872, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.09999999999999999, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771060130573720064}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771060149402915072}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771060168271020032}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771060730743931904}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771060749646161152}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771060768427286016}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771061330865850880}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771061349768201216}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771061368642388224}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771061931013191936}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771061949977861888}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771061968800285184}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771062531232156928}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771062550180016896}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771062569000822016}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771063131460623872}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771063150384694016}
{"uuid": "b27f1637-b1a0-4697-b999-2a51eab3c2e4", "log_time": 1771063169234257920}
{"uuid": "ca382f7e-cfbe-46ad-bf7a-62583ecdfe5b", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771287278550324992, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "eef77049-f954-415b-a0df-16cc15c503e3", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771287362494772992, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "efd0e098-c872-4aba-b766-31307eb0c0ed", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771287418211105024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "8a92d160-76c7-4c46-9119-7924b8a3ca95", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771287720224931072, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "73c477fb-3bc7-4ff6-9d29-9889d1865286", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771287851123771904, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "ca382f7e-cfbe-46ad-bf7a-62583ecdfe5b", "log_time": 1771287878847238144}
{"uuid": "73a459a2-e100-46b7-8251-3820e2a81a80", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771287909803877120, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "181755a1-2f9d-4b6f-9464-fe0628e492ed", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771288099723157760, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "053e7f0f-fbde-49b5-bce5-41417644a092", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771288223053953792, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "5b6507ca-c840-4ddd-8b9f-d2a30e1be109", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771288364370501120, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6e3e2ccc-7137-4b76-b244-5cebdc34f417", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771288434732260096, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "73a459a2-e100-46b7-8251-3820e2a81a80", "log_time": 1771288509936944896}
{"uuid": "9e2cfcf7-0553-4c04-9abf-9bb7a7eae111", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771288602881526016, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "181755a1-2f9d-4b6f-9464-fe0628e492ed", "log_time": 1771288699909310976}
{"uuid": "896410f3-1c15-45ed-9bcd-4a4ae26d92d3", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771289090217538048, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "73a459a2-e100-46b7-8251-3820e2a81a80", "log_time": 1771289110145880064}
{"uuid": "9e2cfcf7-0553-4c04-9abf-9bb7a7eae111", "log_time": 1771289203150521088}
{"uuid": "181755a1-2f9d-4b6f-9464-fe0628e492ed", "log_time": 1771289300046502144}
{"uuid": "e33e924f-cab7-479b-85c5-0a9fa13d3665", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771289316869059072, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "01e7f3ae-d348-428a-86e5-ac37b715fac3", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771289357856972032, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "7518f59b-05dc-4fe7-9661-4cbb7360ba65", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771289386297885952, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "914daa53-2a50-44f9-9a31-32d9ac9e67ba", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771289529220890880, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "7bbf7a77-8823-4284-b256-1b597366ab82", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771289574749552896, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "20f69c12-a35b-456c-b16c-afee7e507a42", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771289641592473088, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.15, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "896410f3-1c15-45ed-9bcd-4a4ae26d92d3", "log_time": 1771289690530558976}
{"uuid": "73a459a2-e100-46b7-8251-3820e2a81a80", "log_time": 1771289710357804032}
{"uuid": "9e2cfcf7-0553-4c04-9abf-9bb7a7eae111", "log_time": 1771289803331604992}
{"uuid": "d15fbcc8-e28f-4f43-8763-dc9aec6d571b", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771289899759159040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.1, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "181755a1-2f9d-4b6f-9464-fe0628e492ed", "log_time": 1771289900267132160}
{"uuid": "31520b1a-7668-4a50-b90e-d80f2d6112e3", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771289948524882944, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.1, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "a679e1f6-d3c5-425f-9854-87a622004065", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771290543712110080, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.1, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2f51974f-619d-42b1-9eaf-d103c067841d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771290667856434944, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.1, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "91243d5c-9f7c-4ac6-8cd1-02ba1c50a9ce", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771290908097886208, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.5, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771291006444717056, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.5, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771291606667175168}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771292206918003968}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771292807081310976}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771293407298074112}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771294007539824128}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771294607794667008}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771295207996800000}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771295808156521984}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771296408313467136}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771297008475225088}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771297608725276928}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771298208901348096}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771298809150511104}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771299409414177792}
{"uuid": "529e8df4-a13e-4396-ad6a-8ef5208c15a0", "log_time": 1771300009634198784}
{"uuid": "57972914-9f85-4801-8dc7-08e5ba829f25", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771300359914465792, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.5, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e37b0f18-dbbe-49bf-aa33-88fb3f3e7cf0", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771300942837299968, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.5, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "7d714ac2-e95b-4804-8acf-1760b8e3c145", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771301219444622080, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.5, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "04542f9c-ff90-496d-ae0f-43cd32496f69", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771301481542243840, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "10dc6f4f-b4ac-4b68-8a14-8ed8fd72548d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771301753027142912, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e0c05062-d5ba-4b12-a820-6e1ffd3797bc", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771301886854796032, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "9a045e0e-b22e-4d57-8861-e6ec15158fae", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771302124980367872, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6fe46ed3-f3a6-404f-a19f-fee68fac63f5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771302181607857920, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "58b124db-684c-436a-9108-29ae4c5fa1c7", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771302322530767872, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "8bde227d-2a3e-4e3d-8c2b-480ec07b5d48", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771302489307516160, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.125, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "8bde227d-2a3e-4e3d-8c2b-480ec07b5d48", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771302508242630912, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.125, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "a06ac668-9baa-4f08-b0b3-d20dbf519225", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771302619800206848, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e1c472d7-ba1b-4c74-b75d-f6e7de4119b8", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771302660327159040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "9a559a6e-5646-4bc5-9ee1-449192d7990a", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771302856072076032, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "241e6353-ac72-4110-9452-0216e954524f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771302968393803008, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "4a0dd6e9-9dcf-44a0-83ad-0942dc833d69", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771317042600832000, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "8e132ae5-1833-49f2-831d-e025570d8af5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771317229116705024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e729af5e-8e5c-44c2-9194-45e318ce33ca", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771317361960445952, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771317443650918912, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6a3cce00-5223-4500-83bb-4ac510173e12", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771317698481307904, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.6, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771318043909227008}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771318644076805120}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771319244244627968}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771319844492225024}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771320444739438080}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771321044989968896}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771321645237127936}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771322245469165056}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771322845704303104}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771323445869154816}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771324046118567936}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771324646273454848}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771325246516699136}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771325846767166976}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771326446976013824}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771327047201033216}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771327647410254080}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771328247659145216}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771328847909477888}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771329448154964992}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771330048389223168}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771330648640163840}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771331248837171968}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771331849029154048}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771332449189160192}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771333049442717184}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771333649677753856}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771334249923856896}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771334850181165056}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771335450373192192}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771336050565217024}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771336650794644224}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771337250945459968}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771337851178155008}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771338451430962944}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771339051589894912}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771339651746264832}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771340251965197056}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771340852195066880}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771341452442835200}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771342052696120064}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771342652935008000}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771343253183149056}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771343853468797952}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771344453719667968}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771345053974397952}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771345654224487168}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771346254471921920}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771346854730247936}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771347454993062912}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771348055248153856}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771348655495856896}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771349255741234176}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771349855994155776}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771350456244263936}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771351056494419968}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771351656748146944}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771352256998942976}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771352857246993920}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771353457528146944}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771354057733169920}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771354657972796928}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771355258235055872}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771355858438509824}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771356458614046208}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771357058893903872}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771357659133446912}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771358259589153024}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771358859836463872}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771359460045294080}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771360060261146112}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771360660510156032}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771361260766144000}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771361860924324096}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771362461155064064}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771363061407313152}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771363661568124160}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771364261782053888}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771364862022914048}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771365462282417920}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771366062530631168}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771366662779988992}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771367263000137984}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771367863181176832}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771368463430077952}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771369063587849984}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771369663841212928}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771370264005182976}
{"uuid": "197c40a9-a378-4b5c-a811-6aebe36bf095", "log_time": 1771370864227181056}
{"uuid": "ab83e1e4-0674-4e15-a4d9-562031698525", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771371275371073024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "037e2057-4ec7-4ecc-9cc0-2c6cd1f0d851", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771371330180658176, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "fd15bbea-58fe-4ddc-a7be-4c1a5a66079d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771371418522230016, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "85811d11-6189-4ec8-8219-96cbb47ab1a3", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373097806665984, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f7c463b5-41e0-4920-ae5b-79ccf5a0b60c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373159701495040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f7c463b5-41e0-4920-ae5b-79ccf5a0b60c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373178119458816, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "07ddfa6e-111d-4ea4-ad8b-79bece1e2cc9", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373299130717952, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "eb64af67-8646-4636-a0b5-c1249799785c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373354020420096, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "18af63d2-050d-4c3b-90ad-62ae81f9c2e1", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373415339774976, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "bb1eea03-d201-4b25-9fac-77c4dde20da3", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373475046478080, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d4bd0b86-418f-41e4-be3a-f6635df9b0d9", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373644703824896, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "56580a80-103c-4252-b410-9f514742ccc9", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373688688134912, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "8ee9f67b-67b0-4027-aff6-47b43e24b31f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373896506861056, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "94a0ee80-63d6-4be6-bfbd-7bd2cd86cee5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771373974020456960, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "de91d6ef-6f34-488a-8eee-142f5b5a0844", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771374022093880832, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "897eab8e-83dc-416f-b60c-85d2a9c6ccf9", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771374133787877120, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b05d275e-f670-4ecb-b9a1-5b13b67c1716", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771374184256777984, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2e30c0ce-5097-4dc4-b139-015e47ec8ddd", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771374255879933952, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2e45ab25-5719-4c18-a92b-0a1bbe6907f9", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771374324902586880, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d2f88ff4-2b31-4e1b-94f1-1dbec5a86bd6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771374392251912192, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6723e708-94d2-4db3-81e9-80ab5dfdf194", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771374448075525120, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "dfb14565-f535-41dd-884e-c3afd9cf57bd", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771374529299832064, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d4cd4572-a806-4541-a396-9415537cd801", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771374609151900160, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "47209049-1706-4cce-80b7-64d759d46f38", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771376114499656960, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e633e985-19fc-4972-b18f-12fdf962e7c4", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771376179180770048, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6ba67fc2-8730-49e4-b12b-8fbed0fb2191", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771376251583740928, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "65b18048-e515-4d24-941c-fd1f7741fd1a", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771376252082663168, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "242015c3-e96d-4685-97eb-10270521e131", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771376281376316160, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "87f40f45-f168-4c1a-9a60-a8c50dbd52fa", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771376355489135872, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "5fe67691-d619-444d-a651-a2b42a7ff443", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771376846539699968, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "9f412970-6901-4aa3-8b0b-54ca9aea95cc", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771376896877079040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "823171dd-af86-4742-948b-e9a51d99f4ac", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771376954996653056, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.4, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "08687666-6a82-44f2-9ec0-7ff0bc6d4f5f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771377008151619072, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.4, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "5d1f0805-c042-4482-a388-89cf139b155d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771377054558301952, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "959d66be-6970-43f8-ba1f-57a2fe3805f1", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771377101815136000, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "20c215d1-a8eb-4806-a08e-a3b1810fe6c5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771438893314667008, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "51b632d8-d541-4b50-9614-4a0a9c5f32f5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771438938228450048, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0ec99f0a-da0f-43b7-ad9d-3f76802ac82d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771438984508364032, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d4e112b4-2632-42f6-82af-bc7235370fbd", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439122511892992, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2d4c5ce9-dc87-4643-b1dd-b9ee8f4ab25e", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439160614768128, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "1f84a0be-ddc0-4451-abcc-39a3a33c7e12", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439201088335104, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6aa554b7-d45d-45e5-b712-07c4c3edbf90", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439240767076864, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "5bc1d591-3690-4695-aa6e-78b273976985", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439284163840000, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "fde9d62f-aad9-4a4a-b1bb-96b43823470f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439323334150144, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "61c16c88-f8f3-43ea-be70-008e8ddcb701", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439566382661120, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "cbd79454-3dcd-4390-9cff-ed6edcdbd75c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439607467742976, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "01556175-487b-4b07-a2e0-e10a082c5d07", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439660235708928, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6696b032-c825-4a53-88be-a1b3a107b769", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439698450452992, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "91f02efe-02f9-499e-bfdd-ed223c3dd451", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439775486340096, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b3de2c10-98f7-41e3-86b3-586c0e0706b5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439816710107136, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "947bec64-0b88-4ca4-9864-8e6df2a21204", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439856382621952, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e8ac74bb-07f3-41d3-bdd1-526865f7b56a", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771439919253688064, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "82dacd42-a321-4e83-bc5d-8e43e4328004", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771440038286169088, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "82484aa9-def2-4cf2-b8de-cc99ba79f110", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771440308399133952, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3f1dae08-7f42-4c0d-b1f4-4825d9201ee6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771440355599618816, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771440464930955776, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "5d8b08d7-c6cb-4d9f-a884-e4a144eb20d4", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771440728755403008, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "df38cd56-c8a8-46a9-96f2-eac47d7e4361", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771440794963905024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "c0831e1d-b555-4b4f-ac1d-ee6e4cbe27c1", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771440853147245824, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f5621e86-e609-4d03-9853-758ddc4c4b3e", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771440943806201088, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e9a79d7c-20d2-448e-b563-5027b16fd508", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771441001130093056, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771441065185462016}
{"uuid": "4ae50168-57d2-4412-9d2e-2467a9f9f7da", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771441108658287104, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6b8ebf6f-6157-420b-9289-19fe678eaae0", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771441172348832000, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "ed68575b-5e05-46f9-aaa7-8db66a710868", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771441241267087104, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771441665346391808}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771442265601540096}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771442865828483072}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771443466074147072}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771444066329051904}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771444666501238016}
{"uuid": "8fe982d0-33a0-4705-a9f8-ccd36cc65f24", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771444682179512064, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771445266761416960}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771445866984985088}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771446467173209856}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771447067440037888}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771447667677176832}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771448267909244160}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771448868143209984}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771449468356427008}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771450068566451968}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771450668841206016}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771451269083854080}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771451869326749952}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771452469564678912}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771453069810488064}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771453670071259904}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771454270277175040}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771454870454358016}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771455470621148160}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771456070779187968}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771456671018164992}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771457271240876800}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771457871371893760}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771458471592184064}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771459071807782912}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771459671931555072}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771460272050889984}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771460872268189952}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771461472495066880}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771462072713164032}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771462672849252096}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771463273083611136}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771463873275947008}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771464473511152128}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771465073736270848}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771465673890904064}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771466274032519168}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771466874245170176}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771467474463668224}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771468074687534080}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771468674900695040}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771469275121538048}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771469875345238016}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771470475488253184}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771471075730770176}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771471675951144960}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771472276120604160}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771472876345120000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771473476566497024}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771474076776025088}
{"uuid": "ba61e86e-1c0e-4e24-b70b-ce775c56bc42", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771474577877840128, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771474676991149824}
{"uuid": "78f23a6b-0f6c-4c9c-ba5f-e337760cf985", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771474678182030080, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d5a7bd65-ea3f-46fa-afd3-4061576a5bd6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771474755114939904, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "645310ec-6daa-4e68-be99-9eb04aefe585", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771474857182972928, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "135bee03-2a7e-459c-9fbf-1ef0f276019b", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771474959134834176, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771475277151436032}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771475877292615936}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771476477458915072}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771477077698577920}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771477677930998016}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771478278164513024}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771478878383198976}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771479478594784000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771480078799845888}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771480678948652032}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771481279122416128}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771481879343152128}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771482479549382912}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771483079777542144}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771483679941169920}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771484280161154048}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771484880387152896}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771485480547992832}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771486080711926016}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771486680929560064}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771487281137236224}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771487881358139136}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771488481485899008}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771489081628271104}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771489681748950016}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771490281967863040}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771490882190195200}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771491482385210112}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771492082602153984}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771492682760344064}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771493282935874048}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771493883085287168}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771494483308523008}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771495083525908992}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771495683745038080}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771496283939016960}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771496884070820096}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771497484295737088}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771498084475009792}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771498684693181952}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771499284915505920}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771499885062857984}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771500485275845120}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771501085395404032}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771501685587300096}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771502285801732096}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771502886138885888}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771503486412427776}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771504086633316096}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771504686793143040}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771505287017106944}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771505887238227968}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771506487459721984}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771507087618916096}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771507687840150016}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771508288057032192}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771508888205713152}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771509488433170176}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771510088648670976}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771510688823267072}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771511289040669952}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771511889194249984}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771512489419166976}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771513089605159168}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771513689838785024}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771514290051634944}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771514890312030976}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771515490487113984}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771516090640598016}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771516690879631104}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771517291100691200}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771517891323501056}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771518491538886912}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771519091770503168}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771519691991560960}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771520292120160000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771520892331769856}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771521492553244160}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771522092684520960}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771522692810125056}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771523293039992064}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771523893268591872}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771524493486560000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771525093710170112}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771525693929174016}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771526294067501056}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771526894284160000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771527494458424064}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771528094618993920}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771528694846157056}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771529294970361088}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771529895175015936}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771530495320837120}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771531095520129024}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771531695688576000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771532295878062848}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771532896121443072}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771533496364327936}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771534096582534144}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771534696817547008}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771535297027331072}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771535897257968896}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771536497464762880}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771537097687869184}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771537697830683904}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771538298053167104}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771538898193089024}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771539498381235968}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771540098566770176}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771540698785478144}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771541298981689856}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771541899181513984}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771542499407892992}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771543099558814976}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771543699692686080}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771544299886432768}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771544900014781952}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771545500261897984}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771546100479971840}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771546700609581824}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771547300737929216}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771547900967412992}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771548501125200128}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771549101350848000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771549701573186048}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771550301722707968}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771550901941682944}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771551502076688128}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771552102239622144}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771552702462373120}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771553302601903872}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771553902819211008}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771554502996067072}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771555103212825088}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771555703365081088}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771556303546835968}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771556903766513152}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771557503903764992}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771558104076584960}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771558704295170048}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771559304493021952}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771559904715774976}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771560504845089792}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771561104979377920}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771561705105285888}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771562305309737984}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771562905528989952}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771563505653728000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771564105878931968}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771564706096966912}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771565306246674944}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771565906467650816}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771566506590791936}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771567106749156096}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771567706980150016}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771568307204166912}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771568907368262144}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771569507525486080}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771570107713280000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771570707931313152}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771571308102014976}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771571908275230976}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771572508505253120}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771573108628176896}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771573708848268032}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771574309063069184}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771574909291271936}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771575509513751040}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771576109744171008}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771576709965800960}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771577310176951040}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771577910298647040}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771578510513148928}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771579110649580032}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771579710872160000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771580311097826048}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771580911222568960}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771581511343271936}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771582111564704768}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771582711783337216}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771583311932321024}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771583912056459008}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771584512241892096}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771585112459438080}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771585712631730176}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771586312823390976}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771586912948962048}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771587513175508992}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771588113384832000}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771588713610930944}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771589313737193216}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771589913925178112}
{"uuid": "e80a43a4-9de6-42d4-a9d0-f8f04ec25670", "log_time": 1771590514077665024}
{"uuid": "b9ad64cf-69de-41f8-a265-20ebc892330f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralStreamingGeneration", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771591501550374144, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "4f640252-0041-4d5a-a39f-0fde96492f5e", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771591711683187968, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "75a4cc35-a477-44ad-9394-b71654a732c7", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771592102498248192, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e1e91c64-9465-46b4-8e0d-4d8c11b258b1", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771592805514575872, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "52d4ca20-4f73-4bb3-9422-6d4a45b74b47", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771592909401992960, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "9003c6f5-fb40-41b6-8509-db8701e84296", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771593134405050880, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d70e2dd7-a5f5-49cb-9f6d-b2882fc0d5a3", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771593315961847040, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "10067cef-c942-4422-929f-c5fe4cb2e12f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771593596453174016, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "03bd276a-df74-4b8b-86ce-aa816476e6c8", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771593923419920896, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "03bd276a-df74-4b8b-86ce-aa816476e6c8", "log_time": 1771594523653213952}
{"uuid": "46fa891f-07d6-4bd7-af87-fa3a4967514e", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771594884569745152, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "46fa891f-07d6-4bd7-af87-fa3a4967514e", "log_time": 1771595484735742208}
{"uuid": "46fa891f-07d6-4bd7-af87-fa3a4967514e", "log_time": 1771596084983458048}
{"uuid": "46fa891f-07d6-4bd7-af87-fa3a4967514e", "log_time": 1771596685170636032}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771596726688210944, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771597326905745920}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771597927166310144}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771598527365807104}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771599127609159936}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771599727820556032}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771600328429939968}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771600928633891072}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771601528858853120}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771602129067601920}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771602729302910208}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771603329541205760}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771603929796133120}
{"uuid": "a5385931-c2cd-4a9a-869e-9d4b538acf78", "log_time": 1771604530048166912}
{"uuid": "8568c24c-3650-42f7-9e07-ba66f5d0c4a4", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771605227850362112, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": "fp8", "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "4047f613-2bf3-4e3b-a494-bc42d8358c33", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771605227994577920, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": "fp8", "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0cccc926-88e6-408c-a3ac-8346174079f5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "VoxtralRealtimeGeneration", "vllm_version": "0.16.0rc2.dev331+gb1c4f0b26", "context": "ENGINE_CONTEXT", "log_time": 1771607802745896960, "source": "production", "dtype": "torch.bfloat16", "block_size": null, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0cccc926-88e6-408c-a3ac-8346174079f5", "log_time": 1771608402949254144}
{"uuid": "0cccc926-88e6-408c-a3ac-8346174079f5", "log_time": 1771609003207406080}
{"uuid": "62056f5f-0df4-4089-bbbd-61380ec96247", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771825733936166912, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d2df0f39-da9c-4a91-ade8-3335863113c9", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771828576555425024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "68770cba-3957-48e3-a4fe-7382649e87e7", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771828699826544896, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "177eacf8-6adb-44b2-a5c7-bc6d7af71284", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771828796593175040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0dff81c2-3512-4fc1-8059-301c3ed65e3a", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771828911888251136, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "7a9df13c-8117-41d8-827c-f5cbd7c18260", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771828995149879040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2929b825-6188-4be8-8577-28fd99e3ec18", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771829095998215936, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "78f7f5c5-1fe5-4d1a-ba3c-99c5fa4c9353", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771829395376009984, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "1bc9c4c7-c3c6-4fea-8ebf-68a35304fdff", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771829615446930944, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "de760fc6-eabb-4084-a856-61fecffc0920", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771829777709495040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "11fe01a0-a6de-4ed7-ba8d-7b0b012fbf83", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771830309743470848, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "11fe01a0-a6de-4ed7-ba8d-7b0b012fbf83", "log_time": 1771830909992590848}
{"uuid": "a2cb863b-aaf2-472f-9b8d-a77365321a89", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771831292882091008, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "87fefc2b-5f92-4ae5-809d-ca440823a614", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771831438519140864, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "87fefc2b-5f92-4ae5-809d-ca440823a614", "log_time": 1771832039190224896}
{"uuid": "e77e48ab-dd11-4eb0-86ac-ad3a827af173", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771837091153726208, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "685103f4-0aaf-46c9-a67f-fc844a5f631f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771837143112230912, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f1c36add-da2c-476f-9dac-658eac1e9601", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771837431842150912, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f1c36add-da2c-476f-9dac-658eac1e9601", "log_time": 1771838033010668032}
{"uuid": "fb5bb630-7fcc-4a86-9154-370ac15b85a7", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771838081670254848, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "852c9dc7-3be1-46fb-88f5-bcb06b0ba392", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771838549355796224, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2a8b5d0b-d120-486a-8f3e-0a5cb7dffa3d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771838753724354048, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "5f3479be-cffc-490f-bfb0-3f7b6ad07fb2", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771839162769184000, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "5f3479be-cffc-490f-bfb0-3f7b6ad07fb2", "log_time": 1771839764373959168}
{"uuid": "5f3479be-cffc-490f-bfb0-3f7b6ad07fb2", "log_time": 1771840364542423040}
{"uuid": "f5e64c16-ed6a-408b-9f75-1201fd464611", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771840443775706112, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f5e64c16-ed6a-408b-9f75-1201fd464611", "log_time": 1771841043961280000}
{"uuid": "f5e64c16-ed6a-408b-9f75-1201fd464611", "log_time": 1771841644126071040}
{"uuid": "f5e64c16-ed6a-408b-9f75-1201fd464611", "log_time": 1771842244271595008}
{"uuid": "0a8817a0-3a65-4252-aa3c-8275847577c0", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771842521857541120, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "26ef2ced-ea54-4661-90b7-7cffbcf086b2", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771842913841773056, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "1f49cdb7-fb28-4653-8052-f30484d5ba35", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771843150060931840, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "1f49cdb7-fb28-4653-8052-f30484d5ba35", "log_time": 1771843750207702016}
{"uuid": "1f49cdb7-fb28-4653-8052-f30484d5ba35", "log_time": 1771844350405165824}
{"uuid": "1f49cdb7-fb28-4653-8052-f30484d5ba35", "log_time": 1771844950629604096}
{"uuid": "1f49cdb7-fb28-4653-8052-f30484d5ba35", "log_time": 1771845550789165056}
{"uuid": "1f49cdb7-fb28-4653-8052-f30484d5ba35", "log_time": 1771846150978934016}
{"uuid": "1f49cdb7-fb28-4653-8052-f30484d5ba35", "log_time": 1771846751171132160}
{"uuid": "1f49cdb7-fb28-4653-8052-f30484d5ba35", "log_time": 1771847351365172992}
{"uuid": "1f49cdb7-fb28-4653-8052-f30484d5ba35", "log_time": 1771847951525700096}
{"uuid": "1f49cdb7-fb28-4653-8052-f30484d5ba35", "log_time": 1771848551743055104}
{"uuid": "10ccf0e3-898d-4880-9912-6726f868a4e2", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771848982062812160, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0c29ad30-a841-4292-aba4-128aa4b53151", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771849236718066944, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0c29ad30-a841-4292-aba4-128aa4b53151", "log_time": 1771849836933389824}
{"uuid": "0c29ad30-a841-4292-aba4-128aa4b53151", "log_time": 1771850437081657856}
{"uuid": "0c29ad30-a841-4292-aba4-128aa4b53151", "log_time": 1771851037336576000}
{"uuid": "0c29ad30-a841-4292-aba4-128aa4b53151", "log_time": 1771851637581443072}
{"uuid": "0c29ad30-a841-4292-aba4-128aa4b53151", "log_time": 1771852237803145984}
{"uuid": "a3a8fb4d-017b-4b69-a0d4-6f6f283600a6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771852504984164864, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "20d8ad8d-5c4b-4cf1-a32c-425d615f5a52", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771852574813795072, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "20d8ad8d-5c4b-4cf1-a32c-425d615f5a52", "log_time": 1771853175981209088}
{"uuid": "20d8ad8d-5c4b-4cf1-a32c-425d615f5a52", "log_time": 1771853776235497984}
{"uuid": "20d8ad8d-5c4b-4cf1-a32c-425d615f5a52", "log_time": 1771854376485618176}
{"uuid": "d901dda2-4dbf-4ad7-9b23-f01e8216faba", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771854926636826112, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "9d83ed22-1400-4b1e-bb6a-8d4bc39d1923", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771855388128849152, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "21f1130d-4f5f-4ed7-94d7-e42dc66a5e47", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771855509665528064, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771855751916022016, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771856353541291008}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771856953820865024}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771857554060466944}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771858154259321088}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771858754484941056}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771859354709163008}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771859954961616896}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771860555125166848}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771861155350889984}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771861755581161984}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771862355773464064}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771862956003087104}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771863556201929984}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771864156422349056}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771864756592390144}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771865356813164032}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771865956997168128}
{"uuid": "f4f32843-e173-45bf-bd31-6221ebad7fd6", "log_time": 1771866557201847040}
{"uuid": "0a7c5ed4-b9db-4dfd-8415-cc8b37c9c48c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771869342306912000, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b1d7499f-5e63-477a-a06b-97490371e6f9", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771869482487881984, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b1d7499f-5e63-477a-a06b-97490371e6f9", "log_time": 1771870082717912064}
{"uuid": "ce40ab78-078c-4724-b50b-c0a996da0992", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771871710911815936, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3ccd9f7c-fcc9-4726-a70e-16f07d4ea07d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771873434112504064, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e336e380-febf-414e-93b7-c33ae7c4b5aa", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771873790093691136, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "575568a7-408b-403d-a118-b14b575247b6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771911652926526976, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "575568a7-408b-403d-a118-b14b575247b6", "log_time": 1771912253144347904}
{"uuid": "01427b47-013c-49ab-ac46-d51ca83db06a", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771912372175461120, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "01427b47-013c-49ab-ac46-d51ca83db06a", "log_time": 1771912973837261824}
{"uuid": "01427b47-013c-49ab-ac46-d51ca83db06a", "log_time": 1771913574085283072}
{"uuid": "e854bf83-c347-4901-b648-cf1bc98a179d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771913850642525952, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e854bf83-c347-4901-b648-cf1bc98a179d", "log_time": 1771914450913969152}
{"uuid": "5bb1f766-494e-461f-a089-f9565da65a36", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771914544564611072, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "cadd2c29-9feb-4ee5-98ab-4bdde20f5691", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771915124966553088, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "55504a8d-0154-4e8d-8173-bc28391ea54d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771915671808395008, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3968aafb-690c-424b-9b9a-d58fd34d1949", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771916201964740096, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "77367ec5-7488-4b3f-9dcd-1859165a8e4b", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771916299999489024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "a8066d66-f329-49c2-a85c-051111a83760", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771916544384493056, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "a8066d66-f329-49c2-a85c-051111a83760", "log_time": 1771917145558707968}
{"uuid": "ee9162fc-5376-4caa-b9d0-98e2b6e64f98", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771917301731817984, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "302bac3a-8f49-402f-bde9-5d0346ad80aa", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771917744027638016, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "302bac3a-8f49-402f-bde9-5d0346ad80aa", "log_time": 1771918344290189056}
{"uuid": "eb9e9de5-a67b-46ba-be09-3bc0f3c3e4e8", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771918697703815936, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "eb9e9de5-a67b-46ba-be09-3bc0f3c3e4e8", "log_time": 1771919299318871040}
{"uuid": "a439be46-fe4f-47b0-a50e-d0bfe083abcf", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771919364849736960, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "a439be46-fe4f-47b0-a50e-d0bfe083abcf", "log_time": 1771919965021277952}
{"uuid": "39d1886c-84a6-4bee-b9df-e4fc7000a3b5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771920308801871104, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "39d1886c-84a6-4bee-b9df-e4fc7000a3b5", "log_time": 1771920909988030976}
{"uuid": "39d1886c-84a6-4bee-b9df-e4fc7000a3b5", "log_time": 1771921510246472960}
{"uuid": "39d1886c-84a6-4bee-b9df-e4fc7000a3b5", "log_time": 1771922110488712960}
{"uuid": "39d1886c-84a6-4bee-b9df-e4fc7000a3b5", "log_time": 1771922710637521920}
{"uuid": "39d1886c-84a6-4bee-b9df-e4fc7000a3b5", "log_time": 1771923310801332992}
{"uuid": "39d1886c-84a6-4bee-b9df-e4fc7000a3b5", "log_time": 1771923910951639808}
{"uuid": "39d1886c-84a6-4bee-b9df-e4fc7000a3b5", "log_time": 1771924511127721984}
{"uuid": "39d1886c-84a6-4bee-b9df-e4fc7000a3b5", "log_time": 1771925111358274048}
{"uuid": "a6557ad6-1c0c-493e-b63b-e21b98830ee8", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771925154894300928, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "ea27263d-1094-48a7-8712-5959add05538", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771925232673892096, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "64bf30b1-09ac-460f-9655-d7e56a30425d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771925290044399872, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e2718f4c-87b5-42c3-b635-32ac9e995783", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771925542354678016, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f58a464e-24cf-45c5-950d-b0c28dbb9eba", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771925986644166912, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f58a464e-24cf-45c5-950d-b0c28dbb9eba", "log_time": 1771926586940375040}
{"uuid": "f58a464e-24cf-45c5-950d-b0c28dbb9eba", "log_time": 1771927187151814912}
{"uuid": "0c8cf8cf-092b-4ac7-b4b7-70ce0adc9413", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771928592150731008, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0c8cf8cf-092b-4ac7-b4b7-70ce0adc9413", "log_time": 1771929192344777216}
{"uuid": "0c8cf8cf-092b-4ac7-b4b7-70ce0adc9413", "log_time": 1771929792528747008}
{"uuid": "260b5005-ed77-4d35-850e-328f66438b23", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771930089541049088, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d9da1b5b-b674-4382-bb5a-13d2d6ec9c90", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771930097609615104, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "32d6570e-e1e4-407a-bcb3-e83248b2dcb6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771930768117361920, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "32d6570e-e1e4-407a-bcb3-e83248b2dcb6", "log_time": 1771931368383183872}
{"uuid": "32d6570e-e1e4-407a-bcb3-e83248b2dcb6", "log_time": 1771931968581208064}
{"uuid": "32d6570e-e1e4-407a-bcb3-e83248b2dcb6", "log_time": 1771932568773526784}
{"uuid": "8e43aba7-e9ba-4014-a4b3-5f7846a7f406", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771932990903227136, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "8e43aba7-e9ba-4014-a4b3-5f7846a7f406", "log_time": 1771933591109220096}
{"uuid": "8e43aba7-e9ba-4014-a4b3-5f7846a7f406", "log_time": 1771934191269203968}
{"uuid": "8e43aba7-e9ba-4014-a4b3-5f7846a7f406", "log_time": 1771934791514439936}
{"uuid": "8e43aba7-e9ba-4014-a4b3-5f7846a7f406", "log_time": 1771935391686900992}
{"uuid": "88f0a35a-c3ba-4bed-a159-4418a7d1961d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771935449894537984, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "9bd6685a-75bb-4e04-990d-5fce21c2b984", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771935555327685120, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "116a417e-f8f6-4771-a8ec-aa3f20edf55b", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771935752528417024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d5083076-98ab-45b5-8a8b-a7072b18934d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771936040612803072, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d5083076-98ab-45b5-8a8b-a7072b18934d", "log_time": 1771936640776315904}
{"uuid": "2b4ba479-142e-45cf-8573-8512b23dd18a", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771936701738426880, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "94bba40e-1df4-4275-bdea-273086c64d72", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771937146916992000, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e4c589b1-b617-46a0-ae79-6f357c99c53f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771937509627217920, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e4c589b1-b617-46a0-ae79-6f357c99c53f", "log_time": 1771938109829238784}
{"uuid": "e4c589b1-b617-46a0-ae79-6f357c99c53f", "log_time": 1771938710085277184}
{"uuid": "76df010d-8af6-4381-a8ce-6c242a594db1", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771938951018330112, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "4ea6d17d-4912-465e-abca-990090a831b8", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771939554578688000, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "4ea6d17d-4912-465e-abca-990090a831b8", "log_time": 1771940154768847104}
{"uuid": "61ecbb7d-2112-4a59-9569-450c187ee0ff", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771940553361340160, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "61ecbb7d-2112-4a59-9569-450c187ee0ff", "log_time": 1771941153541191168}
{"uuid": "eb0a44d0-8586-4b69-bd9e-03613fdc07b2", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771941210683547904, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2f60aae3-cc61-46a6-a92a-de47c4a3ea9f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771941371009128960, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "630c5c93-1450-4757-84b5-44b37eccfb0d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771941942614119168, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "630c5c93-1450-4757-84b5-44b37eccfb0d", "log_time": 1771942542898302976}
{"uuid": "d5da8ee0-a302-49c2-b256-2f0059234195", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771942958105022976, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d5da8ee0-a302-49c2-b256-2f0059234195", "log_time": 1771943558311624960}
{"uuid": "481e8179-0fe1-4607-87ef-52f97f22a4cf", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771944090482259968, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "90738897-521d-4062-a186-39023f38d24e", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771944323177251072, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e9c0d6f8-c5ce-489b-9f29-d1885fe4b550", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771944910390839040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3b904d6f-f3af-4106-864d-96bc21be9178", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771945309942512896, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e7d8a8a9-cb77-49c6-9b2b-5533be60d3d0", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771945609461512192, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e7d8a8a9-cb77-49c6-9b2b-5533be60d3d0", "log_time": 1771946209634633984}
{"uuid": "2d050381-ec22-4883-b2c5-e717d1c4bbf7", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771946680920492032, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "4f2bfdd1-dbe2-4ae4-8674-7db89d7684ec", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771946960255321088, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "a4dd57a6-c3c4-432e-bb5d-2210c284ff41", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771947211430891008, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "204b42b3-6eb2-4251-a6f5-5a31b4555e9e", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771947563542388992, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "204b42b3-6eb2-4251-a6f5-5a31b4555e9e", "log_time": 1771948163821568000}
{"uuid": "204b42b3-6eb2-4251-a6f5-5a31b4555e9e", "log_time": 1771948764073782016}
{"uuid": "a509f3dc-341d-4857-8ca5-d622cff3b14b", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771949264919326976, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b1b87c81-d154-4069-bec6-429b7d3d983d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771949388467881984, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3a3ec161-c876-4030-b6a7-5d64d9237c5e", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771949675112363008, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "ed744c5a-8b27-46b9-83c6-23dd8abdfac6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771949894687491840, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e773b4b4-9af4-4f8a-93df-43c62ea8ff48", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771950079522601984, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3dde0de9-a7b5-4c69-9627-90b5783f6252", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771950479311214080, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3dde0de9-a7b5-4c69-9627-90b5783f6252", "log_time": 1771951079572960000}
{"uuid": "3dde0de9-a7b5-4c69-9627-90b5783f6252", "log_time": 1771951679720833024}
{"uuid": "3dde0de9-a7b5-4c69-9627-90b5783f6252", "log_time": 1771952279957161984}
{"uuid": "3dde0de9-a7b5-4c69-9627-90b5783f6252", "log_time": 1771952880146137856}
{"uuid": "3dde0de9-a7b5-4c69-9627-90b5783f6252", "log_time": 1771953480303010816}
{"uuid": "3dde0de9-a7b5-4c69-9627-90b5783f6252", "log_time": 1771954080525976064}
{"uuid": "3dde0de9-a7b5-4c69-9627-90b5783f6252", "log_time": 1771954680752129024}
{"uuid": "fab253b7-ac65-4b7b-9027-f0eadc7ec69c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771955213372302080, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "068c7737-5a79-4ee1-8f56-b26dcb06b6b9", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771955352865730048, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "a9400a67-4c70-44c1-856c-c8759ee189cb", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771955918920445952, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "86ad088e-204d-41db-a772-1cb2efd5f45b", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771956205867427072, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e16d24d5-0f7b-49dc-a491-dc67cb8e8026", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771956598811932160, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f748a5f0-d6c3-4752-b1b4-0e192ab57af3", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771957064454458112, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f748a5f0-d6c3-4752-b1b4-0e192ab57af3", "log_time": 1771957664669388032}
{"uuid": "6ccf3e64-7e8c-479b-984b-c3a3155f29b3", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "ParallelHeadLfm2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1771958031194555136, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6ccf3e64-7e8c-479b-984b-c3a3155f29b3", "log_time": 1771958631429209088}
{"uuid": "6ccf3e64-7e8c-479b-984b-c3a3155f29b3", "log_time": 1771959231683161856}
{"uuid": "6ccf3e64-7e8c-479b-984b-c3a3155f29b3", "log_time": 1771959831898993920}
{"uuid": "6ccf3e64-7e8c-479b-984b-c3a3155f29b3", "log_time": 1771960432139977984}
{"uuid": "6ccf3e64-7e8c-479b-984b-c3a3155f29b3", "log_time": 1771961032334651904}
{"uuid": "6ccf3e64-7e8c-479b-984b-c3a3155f29b3", "log_time": 1771961632549152000}
{"uuid": "6ccf3e64-7e8c-479b-984b-c3a3155f29b3", "log_time": 1771962232792450048}
{"uuid": "6ccf3e64-7e8c-479b-984b-c3a3155f29b3", "log_time": 1771962833038241024}
{"uuid": "b5c9f5b4-5df2-4b81-9df7-45d69db2eb16", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1773254971006937088, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b5c9f5b4-5df2-4b81-9df7-45d69db2eb16", "log_time": 1773255571360368128}
{"uuid": "d7867b22-cce5-4f91-a967-890d166d769f", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen2ForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1773255639207415040, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.25, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d7867b22-cce5-4f91-a967-890d166d769f", "log_time": 1773256239547169024}
{"uuid": "d7867b22-cce5-4f91-a967-890d166d769f", "log_time": 1773256839844165120}
{"uuid": "d7867b22-cce5-4f91-a967-890d166d769f", "log_time": 1773257440089178112}
{"uuid": "d7867b22-cce5-4f91-a967-890d166d769f", "log_time": 1773258040355140864}
{"uuid": "d7867b22-cce5-4f91-a967-890d166d769f", "log_time": 1773258640597155072}
{"uuid": "d7867b22-cce5-4f91-a967-890d166d769f", "log_time": 1773259240844007936}
{"uuid": "d7867b22-cce5-4f91-a967-890d166d769f", "log_time": 1773259841052268032}
{"uuid": "d7867b22-cce5-4f91-a967-890d166d769f", "log_time": 1773260441200366080}
{"uuid": "e456aa97-6323-4ada-99a8-7e97a85276b9", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "LlamaForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1773524038852242944, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "LlamaForCausalLM", "vllm_version": "0.15.1", "context": "ENGINE_CONTEXT", "log_time": 1773524482811720960, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773525083034321152}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773525683168857088}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773526283372694016}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773526883593265152}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773527483752963072}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773528083974134016}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773528684104700928}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773529284223938048}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773529884429763072}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773530484567905024}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773531084741168128}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773531684896982784}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773532285109314048}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773532885324662016}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773533485506717952}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773534085638077952}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773534685829137920}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773535285975151104}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773535886117187072}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773536486269145088}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773537086469156864}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773537686661155072}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773538286786187776}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773538887006545152}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773539487173150976}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773540087291755008}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773540687516504064}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773541287740257024}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773541887933469952}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773542488077176064}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773543088262487808}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773543688389524992}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773544288603931904}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773544888733746176}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773545488876775936}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773546089009255936}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773546689144754944}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773547289365057024}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773547889493876992}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773548489713197056}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773549089935225088}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773549690137814016}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773550290357140992}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773550890579184896}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773551490799261184}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773552091022267136}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773552691187706112}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773553291317491968}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773553891525188096}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773554491745775104}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773555091964489984}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773555692090783232}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773556292217755136}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773556892439301888}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773557492660263168}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773558092819947008}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773558693038475008}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773559293254930944}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773559893380156160}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773560493596203008}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773561093718427904}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773561693940471808}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773562294061932032}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773562894190537984}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773563494323960064}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773564094542511872}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773564694758202112}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773565294962801920}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773565895088844032}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773566495220769024}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773567095438905088}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773567695570996992}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773568295712187904}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773568895935074048}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773569496069175040}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773570096286195968}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773570696501558016}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773571296721057792}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773571896841588992}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773572496998703872}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773573097227217920}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773573697363936000}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773574297491810048}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773574897713917952}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773575497929775104}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773576098147244032}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773576698289757952}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773577298505822976}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773577898649979136}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773578498821177856}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773579099043337984}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773579699260054016}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773580299391843072}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773580899522885120}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773581499644231168}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773582099860816128}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773582699989145088}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773583300209021952}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773583900333993984}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773584500553250048}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773585100677165056}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773585700896208896}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773586301023698176}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773586901161582080}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773587501354497792}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773588101539411968}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773588701759170048}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773589301912497920}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773589902074831872}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773590502311127808}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773591102436204800}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773591702663773952}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773592302796857088}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773592902979682048}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773593503100352000}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773594103317206016}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773594703440318976}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773595303572732928}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773595903749187840}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773596503914912000}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773597104078579968}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773597704299510016}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773598304512715008}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773598904739087104}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773599504965187072}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773600105189156096}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773600705327016960}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773601305494631936}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773601905657243904}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773602505839965184}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773603106005917184}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773603706210562048}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773604306430251008}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773604906564920832}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773605506770272000}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773606106992742912}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773606707132785920}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773607307264020992}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773607907443821824}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773608507657793024}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773609107872570112}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773609708000204032}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773610308229146112}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773610908353831168}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773611508570867968}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773612108701143040}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773612708994164992}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773613309126635008}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773613909345974016}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773614509476009984}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773615109646199040}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773615709779145984}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773616309896505088}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773616910062588928}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773617510198031872}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773618110325207040}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773618710520354048}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773619310653721088}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773619910789175040}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773620510949182976}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773621111138142208}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773621711288422144}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773622311453159936}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773622911593154048}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773623511772745984}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773624111893153024}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773624712053953792}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773625312226042880}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773625912446369792}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773626512579773952}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773627112708551936}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773627712836793856}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773628313021157120}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773628913152726784}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773629513286156032}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773630113495035904}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773630713625309952}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773631313844412928}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773631913992079872}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773632514179092992}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773633114332923904}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773633714457915904}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773634314601350912}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773634914792830976}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773635514932212224}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773636115083288832}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773636715239625984}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773637315427945984}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773637915589370112}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773638515723767040}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773639115937746944}
{"uuid": "6bc60469-8773-43bc-8321-b602d3032ccc", "log_time": 1773639716158906880}
{"uuid": "b236fd84-d6fc-414f-bb4a-01eaaf5a6e81", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSCode2Wav", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773658353204472064, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.2, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "c9d2e209-2bb6-4f36-974d-cb512fd7c1b7", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSTalkerForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773658353384370176, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.3, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b236fd84-d6fc-414f-bb4a-01eaaf5a6e81", "log_time": 1773658953407387904}
{"uuid": "c9d2e209-2bb6-4f36-974d-cb512fd7c1b7", "log_time": 1773658953593584896}
{"uuid": "b236fd84-d6fc-414f-bb4a-01eaaf5a6e81", "log_time": 1773659553634487040}
{"uuid": "c9d2e209-2bb6-4f36-974d-cb512fd7c1b7", "log_time": 1773659553805272064}
{"uuid": "b236fd84-d6fc-414f-bb4a-01eaaf5a6e81", "log_time": 1773660153854185216}
{"uuid": "c9d2e209-2bb6-4f36-974d-cb512fd7c1b7", "log_time": 1773660154012381952}
{"uuid": "b236fd84-d6fc-414f-bb4a-01eaaf5a6e81", "log_time": 1773660753993586176}
{"uuid": "c9d2e209-2bb6-4f36-974d-cb512fd7c1b7", "log_time": 1773660754203449088}
{"uuid": "0f9ce4a4-05c5-4194-b629-f221738177ed", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSCode2Wav", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773667446177936128, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.2, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "12d2a18c-621d-434c-942b-d164e50568c5", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSTalkerForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773667446344350208, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.3, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "67f9cac7-f499-4f1b-94e4-a70550dfa6ae", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSCode2Wav", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773667446957402112, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.2, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0cd96f4d-798e-4b34-a19c-062a8954a283", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSTalkerForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773667447182946048, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.3, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "e7dab7f4-877a-4a63-8ff8-6c5f37fac50e", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSCode2Wav", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773667447262136064, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.2, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "7aa7aa89-b92e-4f00-9971-108b671ef4bf", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSTalkerForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773667447320566784, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.3, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0f9ce4a4-05c5-4194-b629-f221738177ed", "log_time": 1773668046398952960}
{"uuid": "12d2a18c-621d-434c-942b-d164e50568c5", "log_time": 1773668046572689152}
{"uuid": "67f9cac7-f499-4f1b-94e4-a70550dfa6ae", "log_time": 1773668047219336960}
{"uuid": "0cd96f4d-798e-4b34-a19c-062a8954a283", "log_time": 1773668047397865984}
{"uuid": "7aa7aa89-b92e-4f00-9971-108b671ef4bf", "log_time": 1773668047527972096}
{"uuid": "e7dab7f4-877a-4a63-8ff8-6c5f37fac50e", "log_time": 1773668047696398080}
{"uuid": "0f9ce4a4-05c5-4194-b629-f221738177ed", "log_time": 1773668646580785152}
{"uuid": "12d2a18c-621d-434c-942b-d164e50568c5", "log_time": 1773668646793234944}
{"uuid": "67f9cac7-f499-4f1b-94e4-a70550dfa6ae", "log_time": 1773668647438735872}
{"uuid": "0cd96f4d-798e-4b34-a19c-062a8954a283", "log_time": 1773668647613033984}
{"uuid": "7aa7aa89-b92e-4f00-9971-108b671ef4bf", "log_time": 1773668647748429056}
{"uuid": "e7dab7f4-877a-4a63-8ff8-6c5f37fac50e", "log_time": 1773668647908454912}
{"uuid": "0f9ce4a4-05c5-4194-b629-f221738177ed", "log_time": 1773669246806308096}
{"uuid": "12d2a18c-621d-434c-942b-d164e50568c5", "log_time": 1773669247022579968}
{"uuid": "67f9cac7-f499-4f1b-94e4-a70550dfa6ae", "log_time": 1773669247656292864}
{"uuid": "0cd96f4d-798e-4b34-a19c-062a8954a283", "log_time": 1773669247837931008}
{"uuid": "7aa7aa89-b92e-4f00-9971-108b671ef4bf", "log_time": 1773669247967176960}
{"uuid": "e7dab7f4-877a-4a63-8ff8-6c5f37fac50e", "log_time": 1773669248129252864}
{"uuid": "a96830eb-952e-4cb7-bb42-df783d452e47", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSTalkerForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773671387856900096, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.3, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0a781538-f8c3-440b-bb19-48c31a94d441", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSCode2Wav", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773671388321393920, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.2, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "76d1c776-97a6-48b6-bd4b-e22b7356b447", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSCode2Wav", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773671951860781056, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.2, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f69a5315-2272-40a9-b7da-bd02c7e46e91", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSTalkerForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1773671952077581056, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.3, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "5b49f323-9236-4a59-b9ab-1c19e4ccbedc", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSTalkerForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774117115665483008, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.3, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "8883610d-660c-488e-9881-77f80883e19c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSCode2Wav", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774117115930702080, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.2, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "d9dca5c8-b805-4c58-a860-4e7ef0c1454c", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSTalkerForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774117610526201088, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.3, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "eb8d87d1-0afd-4aad-aa7b-0ac7dae496ad", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3TTSCode2Wav", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774117611082847232, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.2, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": false, "enforce_eager": true, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "6fca877c-2697-4ba0-946a-548a5727d4c2", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774479362098386944, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "27a88317-4583-40f9-b4ba-d2d2c0317f0a", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774479452747136000, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0a0596a6-66d5-4222-8095-368d43a5adbc", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774479667073366016, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "c97f56e6-744a-431c-af38-ee24ac73bb48", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774486084292519168, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "9a1352e4-61b8-4d87-86b9-7a2664db75a8", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774492303020297984, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "9249063e-3877-4e08-a6c4-15355e07f2ce", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774493591498810880, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "533cefca-e8f6-4eb7-ac82-300bdd38c9f6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774553524772752128, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "7b9733dd-8a72-448b-9ea4-a8e980fad6e6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774553760323062016, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "c9beb8f8-1176-40c2-a455-5b231540b97d", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774579898167756032, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "639498cc-b374-4160-aa3d-f134dae66334", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774639863837937152, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "2d371d1b-cdd7-4bf5-b45c-1d4f0ab7a797", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774679781236038912, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "f33c01b0-7cf9-4079-9a60-627353a0f5d2", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774768197122968832, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "0d2e285e-2956-4718-89da-df0b85cb861e", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ForCausalLM", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774855967151042048, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.5, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "3bd73a5c-607e-4917-8d4f-8be9731391b6", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ForCausalLM", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774856259083930880, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "356856cc-467a-4b96-8b85-fc031bb338be", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ForCausalLM", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774856416069796096, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.95, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "fp8", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "34d432d9-b758-40d2-8122-a5661e34d918", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ForCausalLM", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774856669087739904, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "fp8", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "33fa87b8-fd36-4e2b-94bf-8adf6ef96247", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ForCausalLM", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774856929385957888, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "fp8", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "ddfd1002-6ce5-457c-b186-ef292db8fc92", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ForCausalLM", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774856987265391104, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "fp8", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "fa707d76-798e-430c-ad29-c803f6f855a7", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ForCausalLM", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774857274156534016, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.9, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "fp8", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "fbb1a48a-ffae-4f8f-8ad5-0205e760f13e", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774969744346731776, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "b103a31c-4577-49fb-8c5d-c442f3101034", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774970621560754944, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "7649943c-b921-4857-accc-e4d4aba028cd", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774975416106563072, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774975735494787072, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774976335716704000}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774976935935004928}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774977536142532096}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774978136325692928}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774978736462115072}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774979336597239040}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774979936820168960}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774980537000238848}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774981137196194048}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774981737336630016}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774982337554788096}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774982937753427968}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774983537975422976}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774984138235558144}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774984738486183936}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774985338630238976}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774985938864211968}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774986539099200000}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774987139318962944}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774987739507708160}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774988339726171904}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774988939909218048}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774989540105763072}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774990140281722112}
{"uuid": "47f9df6e-7f9e-4741-aa15-1bc0274adcd2", "log_time": 1774990740491859968}
{"uuid": "b4f2f253-20ea-43dd-a284-cc654f3ffbda", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1774996167885530112, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}
{"uuid": "a73acc7e-dcc8-45b7-afde-01640b64db01", "provider": "UNKNOWN", "num_cpu": 16, "cpu_type": "AMD EPYC 7742 64-Core Processor", "cpu_family_model_stepping": "23,49,", "total_memory": 126711205888, "architecture": "x86_64", "platform": "Linux-6.8.0-57-generic-x86_64-with-glibc2.35", "cuda_runtime": "12.8", "gpu_count": 1, "gpu_type": "NVIDIA A100-SXM4-80GB", "gpu_memory_per_device": 85097971712, "env_var_json": "{\"VLLM_USE_MODELSCOPE\": false, \"VLLM_USE_FLASHINFER_SAMPLER\": null, \"VLLM_PP_LAYER_PARTITION\": null, \"VLLM_USE_TRITON_AWQ\": false, \"VLLM_ENABLE_V1_MULTIPROCESSING\": true}", "model_architecture": "Qwen3ASRForConditionalGeneration", "vllm_version": "0.16.0", "context": "ENGINE_CONTEXT", "log_time": 1775091405627841024, "source": "production", "dtype": "torch.bfloat16", "block_size": 16, "gpu_memory_utilization": 0.85, "kv_cache_memory_bytes": null, "quantization": null, "kv_cache_dtype": "auto", "enable_lora": false, "enable_prefix_caching": true, "enforce_eager": false, "disable_custom_all_reduce": false, "tensor_parallel_size": 1, "data_parallel_size": 1, "pipeline_parallel_size": 1, "enable_expert_parallel": false, "all2all_backend": "allgather_reducescatter", "kv_connector": null}