# Copyright (c) 2025, NVIDIA CORPORATION.  All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from megatron.core.extensions.transformer_engine import TELayerNormColumnParallelLinear
from megatron.core.fusions.fused_bias_dropout import get_bias_dropout_add
from megatron.core.transformer import ModuleSpec, TransformerLayer, TransformerLayerSubmodules
from megatron.core.transformer.attention import SelfAttention, SelfAttentionSubmodules
from megatron.core.transformer.enums import AttnMaskType
from megatron.core.transformer.mlp import MLP, MLPSubmodules

from nemo.collections.nlp.models.language_modeling.megatron.gemma2.gemma2_modules import (
    Gemma2DotProductAttention,
    TERowParallelLinearLayerNorm,
)


def get_gemma2_layer_spec():
    return ModuleSpec(
        module=TransformerLayer,
        submodules=TransformerLayerSubmodules(
            self_attention=ModuleSpec(
                module=SelfAttention,
                params={"attn_mask_type": AttnMaskType.causal},
                submodules=SelfAttentionSubmodules(
                    linear_qkv=TELayerNormColumnParallelLinear,
                    core_attention=Gemma2DotProductAttention,  # use unfused SDPA for attn logit softcapping
                    linear_proj=TERowParallelLinearLayerNorm,  # post attn RMSNorm
                ),
            ),
            self_attn_bda=get_bias_dropout_add,
            mlp=ModuleSpec(
                module=MLP,
                submodules=MLPSubmodules(
                    linear_fc1=TELayerNormColumnParallelLinear,
                    linear_fc2=TERowParallelLinearLayerNorm,  # post mlp RMSNorm
                ),
            ),
            mlp_bda=get_bias_dropout_add,
        ),
    )