{"hash": "fb67acabdadf13fb5a498babee296d8abd8f0c3731774d35312200348ace1a09", "target": {"backend": "cuda", "arch": 80, "warp_size": 32}, "num_warps": 4, "num_ctas": 1, "num_stages": 3, "warp_size": 32, "maxnreg": null, "cluster_dims": [1, 1, 1], "ptx_version": null, "ptx_options": null, "ir_override": null, "enable_fp_fusion": true, "launch_cooperative_grid": false, "launch_pdl": false, "supported_fp8_dtypes": ["fp8e4b15", "fp8e5"], "deprecated_fp8_dot_operand_dtypes": [], "default_dot_input_precision": "tf32", "allowed_dot_input_precisions": ["tf32", "tf32x3", "ieee"], "max_num_imprecise_acc_default": 0, "extern_libs": [["libdevice", "/home/ubuntu/.local/lib/python3.10/site-packages/triton/backends/nvidia/lib/libdevice.10.bc"]], "debug": false, "backend_name": "cuda", "sanitize_overflow": true, "arch": "sm80", "instrumentation_mode": "", "triton_version": "3.5.1", "tensordesc_meta": [], "shared": 0, "tmem_size": 0, "global_scratch_size": 0, "global_scratch_align": 1, "profile_scratch_size": 0, "profile_scratch_align": 1, "name": "_causal_conv1d_update_kernel"}