LICENSE
README.md
pyproject.toml
setup.py
megatron/core/__init__.py
megatron/core/enums.py
megatron/core/inference_params.py
megatron/core/model_parallel_config.py
megatron/core/package_info.py
megatron/core/parallel_state.py
megatron/core/utils.py
megatron/core/datasets/__init__.py
megatron/core/datasets/blended_dataset.py
megatron/core/datasets/blended_megatron_dataset_builder.py
megatron/core/datasets/blended_megatron_dataset_config.py
megatron/core/datasets/gpt_dataset.py
megatron/core/datasets/indexed_dataset.py
megatron/core/datasets/megatron_dataset.py
megatron/core/datasets/utils.py
megatron/core/dist_checkpointing/__init__.py
megatron/core/dist_checkpointing/core.py
megatron/core/dist_checkpointing/dict_utils.py
megatron/core/dist_checkpointing/mapping.py
megatron/core/dist_checkpointing/optimizer.py
megatron/core/dist_checkpointing/serialization.py
megatron/core/dist_checkpointing/utils.py
megatron/core/dist_checkpointing/strategies/__init__.py
megatron/core/dist_checkpointing/strategies/base.py
megatron/core/dist_checkpointing/strategies/tensorstore.py
megatron/core/dist_checkpointing/strategies/two_stage.py
megatron/core/dist_checkpointing/strategies/zarr.py
megatron/core/distributed/__init__.py
megatron/core/distributed/distributed_data_parallel.py
megatron/core/distributed/finalize_model_grads.py
megatron/core/distributed/grad_buffer.py
megatron/core/fusions/__init__.py
megatron/core/fusions/fused_bias_dropout.py
megatron/core/fusions/fused_bias_gelu.py
megatron/core/fusions/fused_layer_norm.py
megatron/core/fusions/fused_softmax.py
megatron/core/models/__init__.py
megatron/core/models/T5/__init__.py
megatron/core/models/T5/t5_model.py
megatron/core/models/T5/t5_spec.py
megatron/core/models/bert/__init__.py
megatron/core/models/bert/bert_layer_specs.py
megatron/core/models/bert/bert_lm_head.py
megatron/core/models/bert/bert_model.py
megatron/core/models/bert/pooler.py
megatron/core/models/common/__init__.py
megatron/core/models/common/embeddings/__init__.py
megatron/core/models/common/embeddings/language_model_embedding.py
megatron/core/models/common/embeddings/rotary_pos_embedding.py
megatron/core/models/common/language_module/__init__.py
megatron/core/models/common/language_module/language_module.py
megatron/core/models/gpt/__init__.py
megatron/core/models/gpt/gpt_layer_specs.py
megatron/core/models/gpt/gpt_model.py
megatron/core/models/retro/__init__.py
megatron/core/models/retro/base_attention.py
megatron/core/models/retro/config.py
megatron/core/models/retro/decoder_attention.py
megatron/core/models/retro/decoder_spec.py
megatron/core/models/retro/encoder_attention.py
megatron/core/models/retro/encoder_spec.py
megatron/core/models/retro/model.py
megatron/core/pipeline_parallel/__init__.py
megatron/core/pipeline_parallel/p2p_communication.py
megatron/core/pipeline_parallel/schedules.py
megatron/core/tensor_parallel/__init__.py
megatron/core/tensor_parallel/cross_entropy.py
megatron/core/tensor_parallel/data.py
megatron/core/tensor_parallel/layers.py
megatron/core/tensor_parallel/mappings.py
megatron/core/tensor_parallel/random.py
megatron/core/tensor_parallel/utils.py
megatron/core/transformer/__init__.py
megatron/core/transformer/attention.py
megatron/core/transformer/dot_product_attention.py
megatron/core/transformer/enums.py
megatron/core/transformer/identity_op.py
megatron/core/transformer/mlp.py
megatron/core/transformer/module.py
megatron/core/transformer/spec_utils.py
megatron/core/transformer/switch_mlp.py
megatron/core/transformer/transformer_block.py
megatron/core/transformer/transformer_config.py
megatron/core/transformer/transformer_layer.py
megatron/core/transformer/utils.py
megatron/core/transformer/custom_layers/__init__.py
megatron/core/transformer/custom_layers/transformer_engine.py
megatron_core.egg-info/PKG-INFO
megatron_core.egg-info/SOURCES.txt
megatron_core.egg-info/dependency_links.txt
megatron_core.egg-info/top_level.txt