LICENSE
MANIFEST.in
README.md
setup.py
csrc/dp_core.cpp
galvatron/__init__.py
galvatron/core/__init__.py
galvatron/core/arguments.py
galvatron/core/comm_groups.py
galvatron/core/cost_model.py
galvatron/core/dataloader.py
galvatron/core/dynamic_programming.py
galvatron/core/hybrid_parallel_config.py
galvatron/core/hybrid_parallel_model.py
galvatron/core/initialize.py
galvatron/core/parallel.py
galvatron/core/profiler.py
galvatron/core/redistribute.py
galvatron/core/search_engine.py
galvatron/core/utils.py
galvatron/core/pipeline/__init__.py
galvatron/core/pipeline/grad_reduce.py
galvatron/core/pipeline/pipeline.py
galvatron/core/pipeline/sp_grad_reduce.py
galvatron/core/pipeline/utils.py
galvatron/core/tensor_parallel/__init__.py
galvatron/core/tensor_parallel/reset.py
galvatron/core/tensor_parallel/transformer.py
galvatron/core/tensor_parallel/utils.py
galvatron/models/__init__.py
galvatron/models/gpt_fa/GPTModel_hybrid_parallel.py
galvatron/models/gpt_fa/GPTModel_sequential.py
galvatron/models/gpt_fa/GPTModel_tensor_parallel.py
galvatron/models/gpt_fa/__init__.py
galvatron/models/gpt_fa/arguments.py
galvatron/models/gpt_fa/dataloader.py
galvatron/models/gpt_fa/profiler.py
galvatron/models/gpt_fa/search_dist.py
galvatron/models/gpt_fa/train.py
galvatron/models/gpt_fa/train_dist.py
galvatron/models/gpt_fa/train_dist_random.py
galvatron/models/gpt_fa/configs/computation_profiling_bf16_hidden1600_head32_seqlen1024.json
galvatron/models/gpt_fa/configs/computation_profiling_bf16_hidden2560_head32_seqlen2048.json
galvatron/models/gpt_fa/configs/computation_profiling_bf16_hidden4096_head32_seqlen2048.json
galvatron/models/gpt_fa/configs/galvatron_config_gpt-1.5b_2nodes_8gpus_per_node_40GB_bf16_3D_example.json
galvatron/models/gpt_fa/configs/galvatron_config_gpt-1.5b_2nodes_8gpus_per_node_40GB_bf16_example.json
galvatron/models/gpt_fa/configs/galvatron_config_gpt-2.7b_2nodes_8gpus_per_node_40GB_bf16_3D_example.json
galvatron/models/gpt_fa/configs/galvatron_config_gpt-2.7b_2nodes_8gpus_per_node_40GB_bf16_example.json
galvatron/models/gpt_fa/configs/galvatron_config_gpt-6.7b_2nodes_8gpus_per_node_40GB_bf16_3D_example.json
galvatron/models/gpt_fa/configs/galvatron_config_gpt-6.7b_2nodes_8gpus_per_node_40GB_bf16_example.json
galvatron/models/gpt_fa/configs/memory_profiling_bf16_hidden1600_head32_seqlen1024.json
galvatron/models/gpt_fa/configs/memory_profiling_bf16_hidden2560_head32_seqlen2048.json
galvatron/models/gpt_fa/configs/memory_profiling_bf16_hidden4096_head32_seqlen2048.json
galvatron/models/gpt_fa/meta_configs/__init__.py
galvatron/models/gpt_fa/meta_configs/config_utils.py
galvatron/models/gpt_fa/meta_configs/gpt-0.3b.json
galvatron/models/gpt_fa/meta_configs/gpt-1.5b.json
galvatron/models/gpt_fa/meta_configs/gpt-2.7b.json
galvatron/models/gpt_fa/meta_configs/gpt-6.7b.json
galvatron/models/gpt_hf/GPTModel_checkpoint.py
galvatron/models/gpt_hf/GPTModel_hybrid_parallel.py
galvatron/models/gpt_hf/GPTModel_sequential.py
galvatron/models/gpt_hf/GPTModel_tensor_parallel.py
galvatron/models/gpt_hf/__init__.py
galvatron/models/gpt_hf/arguments.py
galvatron/models/gpt_hf/dataloader.py
galvatron/models/gpt_hf/profiler.py
galvatron/models/gpt_hf/search_dist.py
galvatron/models/gpt_hf/train.py
galvatron/models/gpt_hf/train_dist.py
galvatron/models/gpt_hf/train_dist_random.py
galvatron/models/gpt_hf/configs/computation_profiling_bf16_hidden1600_head32_seqlen1024.json
galvatron/models/gpt_hf/configs/computation_profiling_bf16_hidden2560_head32_seqlen2048.json
galvatron/models/gpt_hf/configs/computation_profiling_bf16_hidden4096_head32.json
galvatron/models/gpt_hf/configs/computation_profiling_bf16_hidden4096_head32_seqlen2048.json
galvatron/models/gpt_hf/configs/galvatron_config_gpt-1.5b_2nodes_8gpus_per_node_40GB_bf16_3D_example.json
galvatron/models/gpt_hf/configs/galvatron_config_gpt-1.5b_2nodes_8gpus_per_node_40GB_bf16_example.json
galvatron/models/gpt_hf/configs/galvatron_config_gpt-2.7b_1nodes_8gpus_per_node_40GB_bf16_example.json
galvatron/models/gpt_hf/configs/galvatron_config_gpt-2.7b_2nodes_8gpus_per_node_40GB_bf16_3D_example.json
galvatron/models/gpt_hf/configs/galvatron_config_gpt-2.7b_2nodes_8gpus_per_node_40GB_bf16_example.json
galvatron/models/gpt_hf/configs/galvatron_config_gpt-6.7b_2nodes_8gpus_per_node_40GB_bf16_3D_example.json
galvatron/models/gpt_hf/configs/galvatron_config_gpt-6.7b_2nodes_8gpus_per_node_40GB_bf16_example.json
galvatron/models/gpt_hf/configs/memory_profiling_bf16_hidden1600_head32_seqlen1024.json
galvatron/models/gpt_hf/configs/memory_profiling_bf16_hidden2560_head32_seqlen2048.json
galvatron/models/gpt_hf/configs/memory_profiling_bf16_hidden4096_head32.json
galvatron/models/gpt_hf/configs/memory_profiling_bf16_hidden4096_head32_seqlen2048.json
galvatron/models/gpt_hf/meta_configs/__init__.py
galvatron/models/gpt_hf/meta_configs/config_utils.py
galvatron/models/gpt_hf/meta_configs/gpt-0.3b.json
galvatron/models/gpt_hf/meta_configs/gpt-1.5b.json
galvatron/models/gpt_hf/meta_configs/gpt-2.7b.json
galvatron/models/gpt_hf/meta_configs/gpt-6.7b.json
galvatron/models/llama_fa/LlamaModel_hybrid_parallel.py
galvatron/models/llama_fa/LlamaModel_sequential.py
galvatron/models/llama_fa/LlamaModel_tensor_parallel.py
galvatron/models/llama_fa/__init__.py
galvatron/models/llama_fa/arguments.py
galvatron/models/llama_fa/dataloader.py
galvatron/models/llama_fa/profiler.py
galvatron/models/llama_fa/search_dist.py
galvatron/models/llama_fa/train.py
galvatron/models/llama_fa/train_dist.py
galvatron/models/llama_fa/train_dist_random.py
galvatron/models/llama_fa/configs/computation_profiling_bf16_hidden4096_head32_seqlen2048.json
galvatron/models/llama_fa/configs/galvatron_config_llama-7b_2nodes_8gpus_per_node_40GB_bf16_3D_example.json
galvatron/models/llama_fa/configs/galvatron_config_llama-7b_2nodes_8gpus_per_node_40GB_bf16_example.json
galvatron/models/llama_fa/configs/memory_profiling_bf16_hidden4096_head32_seqlen2048.json
galvatron/models/llama_fa/meta_configs/__init__.py
galvatron/models/llama_fa/meta_configs/config_utils.py
galvatron/models/llama_fa/meta_configs/llama-13b.json
galvatron/models/llama_fa/meta_configs/llama-30b.json
galvatron/models/llama_fa/meta_configs/llama-7b.json
galvatron/models/llama_fa/meta_configs/llama2-70b.json
galvatron/models/llama_hf/LlamaModel_checkpoint.py
galvatron/models/llama_hf/LlamaModel_hybrid_parallel.py
galvatron/models/llama_hf/LlamaModel_sequential.py
galvatron/models/llama_hf/LlamaModel_tensor_parallel.py
galvatron/models/llama_hf/__init__.py
galvatron/models/llama_hf/arguments.py
galvatron/models/llama_hf/dataloader.py
galvatron/models/llama_hf/profiler.py
galvatron/models/llama_hf/search_dist.py
galvatron/models/llama_hf/train.py
galvatron/models/llama_hf/train_dist.py
galvatron/models/llama_hf/train_dist_random.py
galvatron/models/llama_hf/configs/computation_profiling_bf16_hidden4096_head32_seqlen2048.json
galvatron/models/llama_hf/configs/galvatron_config_hidden4096_head32_1nodes_8gpus_per_node_36GB_bf16_[tpconsec_off].json
galvatron/models/llama_hf/configs/galvatron_config_llama-7b_2nodes_8gpus_per_node_40GB_bf16_3D_example.json
galvatron/models/llama_hf/configs/galvatron_config_llama-7b_2nodes_8gpus_per_node_40GB_bf16_example.json
galvatron/models/llama_hf/configs/memory_profiling_bf16_hidden4096_head32_seqlen2048.json
galvatron/models/llama_hf/meta_configs/__init__.py
galvatron/models/llama_hf/meta_configs/config_utils.py
galvatron/models/llama_hf/meta_configs/llama-0.3b.json
galvatron/models/llama_hf/meta_configs/llama-13b.json
galvatron/models/llama_hf/meta_configs/llama-30b.json
galvatron/models/llama_hf/meta_configs/llama-7b.json
galvatron/models/llama_hf/meta_configs/llama2-70b.json
galvatron/models/llama_hf/meta_configs/qwen2.5-72b.json
galvatron/models/llama_hf/meta_configs/qwen2.5-7b.json
galvatron/profile_hardware/hardware_configs/allreduce_bandwidth_1nodes_4gpus_per_node.json
galvatron/profile_hardware/hardware_configs/allreduce_bandwidth_1nodes_8gpus_per_node.json
galvatron/profile_hardware/hardware_configs/allreduce_bandwidth_2nodes_8gpus_per_node.json
galvatron/profile_hardware/hardware_configs/overlap_coefficient.json
galvatron/profile_hardware/hardware_configs/p2p_bandwidth_1nodes_4gpus_per_node.json
galvatron/profile_hardware/hardware_configs/p2p_bandwidth_1nodes_8gpus_per_node.json
galvatron/profile_hardware/hardware_configs/p2p_bandwidth_2nodes_8gpus_per_node.json
galvatron/scripts/flash_attn_ops_install.sh
galvatron/site_package/__init__.py
galvatron/site_package/megatron/__init__.py
galvatron/site_package/megatron/core/__init__.py
galvatron/site_package/megatron/core/enums.py
galvatron/site_package/megatron/core/inference_params.py
galvatron/site_package/megatron/core/jit.py
galvatron/site_package/megatron/core/model_parallel_config.py
galvatron/site_package/megatron/core/package_info.py
galvatron/site_package/megatron/core/packed_seq_params.py
galvatron/site_package/megatron/core/parallel_state.py
galvatron/site_package/megatron/core/timers.py
galvatron/site_package/megatron/core/utils.py
galvatron/site_package/megatron/core/datasets/__init__.py
galvatron/site_package/megatron/core/datasets/bert_dataset.py
galvatron/site_package/megatron/core/datasets/blended_dataset.py
galvatron/site_package/megatron/core/datasets/blended_megatron_dataset_builder.py
galvatron/site_package/megatron/core/datasets/blended_megatron_dataset_config.py
galvatron/site_package/megatron/core/datasets/gpt_dataset.py
galvatron/site_package/megatron/core/datasets/indexed_dataset.py
galvatron/site_package/megatron/core/datasets/masked_dataset.py
galvatron/site_package/megatron/core/datasets/megatron_dataset.py
galvatron/site_package/megatron/core/datasets/megatron_tokenizer.py
galvatron/site_package/megatron/core/datasets/multimodal_dataset.py
galvatron/site_package/megatron/core/datasets/t5_dataset.py
galvatron/site_package/megatron/core/datasets/utils.py
galvatron/site_package/megatron/core/datasets/retro/__init__.py
galvatron/site_package/megatron/core/datasets/retro/external_libs.py
galvatron/site_package/megatron/core/datasets/retro/utils.py
galvatron/site_package/megatron/core/datasets/retro/config/__init__.py
galvatron/site_package/megatron/core/datasets/retro/config/bert_embedders.py
galvatron/site_package/megatron/core/datasets/retro/config/config.py
galvatron/site_package/megatron/core/datasets/retro/config/gpt_chunk_datasets.py
galvatron/site_package/megatron/core/datasets/retro/config/tokenizers.py
galvatron/site_package/megatron/core/datasets/retro/db/__init__.py
galvatron/site_package/megatron/core/datasets/retro/db/build.py
galvatron/site_package/megatron/core/datasets/retro/db/dataset.py
galvatron/site_package/megatron/core/datasets/retro/db/utils.py
galvatron/site_package/megatron/core/datasets/retro/index/__init__.py
galvatron/site_package/megatron/core/datasets/retro/index/build.py
galvatron/site_package/megatron/core/datasets/retro/index/factory.py
galvatron/site_package/megatron/core/datasets/retro/index/index.py
galvatron/site_package/megatron/core/datasets/retro/index/utils.py
galvatron/site_package/megatron/core/datasets/retro/index/validate.py
galvatron/site_package/megatron/core/datasets/retro/index/indexes/__init__.py
galvatron/site_package/megatron/core/datasets/retro/index/indexes/faiss_base.py
galvatron/site_package/megatron/core/datasets/retro/index/indexes/faiss_par_add.py
galvatron/site_package/megatron/core/datasets/retro/query/__init__.py
galvatron/site_package/megatron/core/datasets/retro/query/gpt_chunk_dataset.py
galvatron/site_package/megatron/core/datasets/retro/query/multi_split_gpt_dataset.py
galvatron/site_package/megatron/core/datasets/retro/query/query.py
galvatron/site_package/megatron/core/datasets/retro/query/retro_dataset.py
galvatron/site_package/megatron/core/datasets/retro/query/utils.py
galvatron/site_package/megatron/core/dist_checkpointing/__init__.py
galvatron/site_package/megatron/core/dist_checkpointing/core.py
galvatron/site_package/megatron/core/dist_checkpointing/dict_utils.py
galvatron/site_package/megatron/core/dist_checkpointing/mapping.py
galvatron/site_package/megatron/core/dist_checkpointing/optimizer.py
galvatron/site_package/megatron/core/dist_checkpointing/serialization.py
galvatron/site_package/megatron/core/dist_checkpointing/utils.py
galvatron/site_package/megatron/core/dist_checkpointing/strategies/__init__.py
galvatron/site_package/megatron/core/dist_checkpointing/strategies/base.py
galvatron/site_package/megatron/core/dist_checkpointing/strategies/filesystem_async.py
galvatron/site_package/megatron/core/dist_checkpointing/strategies/state_dict_saver.py
galvatron/site_package/megatron/core/dist_checkpointing/strategies/tensorstore.py
galvatron/site_package/megatron/core/dist_checkpointing/strategies/torch.py
galvatron/site_package/megatron/core/dist_checkpointing/strategies/two_stage.py
galvatron/site_package/megatron/core/dist_checkpointing/strategies/zarr.py
galvatron/site_package/megatron/core/distributed/__init__.py
galvatron/site_package/megatron/core/distributed/distributed_data_parallel.py
galvatron/site_package/megatron/core/distributed/finalize_model_grads.py
galvatron/site_package/megatron/core/distributed/param_and_grad_buffer.py
galvatron/site_package/megatron/core/fusions/__init__.py
galvatron/site_package/megatron/core/fusions/fused_bias_dropout.py
galvatron/site_package/megatron/core/fusions/fused_bias_geglu.py
galvatron/site_package/megatron/core/fusions/fused_bias_gelu.py
galvatron/site_package/megatron/core/fusions/fused_bias_swiglu.py
galvatron/site_package/megatron/core/fusions/fused_layer_norm.py
galvatron/site_package/megatron/core/fusions/fused_softmax.py
galvatron/site_package/megatron/core/inference/__init__.py
galvatron/site_package/megatron/core/inference/gpt/__init__.py
galvatron/site_package/megatron/core/inference/gpt/model_specs.py
galvatron/site_package/megatron/core/inference/gpt/state_dict_hooks.py
galvatron/site_package/megatron/core/models/__init__.py
galvatron/site_package/megatron/core/models/T5/__init__.py
galvatron/site_package/megatron/core/models/T5/t5_model.py
galvatron/site_package/megatron/core/models/T5/t5_spec.py
galvatron/site_package/megatron/core/models/bert/__init__.py
galvatron/site_package/megatron/core/models/bert/bert_layer_specs.py
galvatron/site_package/megatron/core/models/bert/bert_lm_head.py
galvatron/site_package/megatron/core/models/bert/bert_model.py
galvatron/site_package/megatron/core/models/bert/pooler.py
galvatron/site_package/megatron/core/models/common/__init__.py
galvatron/site_package/megatron/core/models/common/embeddings/__init__.py
galvatron/site_package/megatron/core/models/common/embeddings/language_model_embedding.py
galvatron/site_package/megatron/core/models/common/embeddings/rotary_pos_embedding.py
galvatron/site_package/megatron/core/models/common/language_module/__init__.py
galvatron/site_package/megatron/core/models/common/language_module/language_module.py
galvatron/site_package/megatron/core/models/common/vision_module/__init__.py
galvatron/site_package/megatron/core/models/common/vision_module/vision_module.py
galvatron/site_package/megatron/core/models/gpt/__init__.py
galvatron/site_package/megatron/core/models/gpt/gpt_layer_specs.py
galvatron/site_package/megatron/core/models/gpt/gpt_model.py
galvatron/site_package/megatron/core/models/multimodal/__init__.py
galvatron/site_package/megatron/core/models/multimodal/llava_model.py
galvatron/site_package/megatron/core/models/retro/__init__.py
galvatron/site_package/megatron/core/models/retro/base_attention.py
galvatron/site_package/megatron/core/models/retro/config.py
galvatron/site_package/megatron/core/models/retro/decoder_attention.py
galvatron/site_package/megatron/core/models/retro/decoder_spec.py
galvatron/site_package/megatron/core/models/retro/encoder_attention.py
galvatron/site_package/megatron/core/models/retro/encoder_spec.py
galvatron/site_package/megatron/core/models/retro/model.py
galvatron/site_package/megatron/core/models/retro/utils.py
galvatron/site_package/megatron/core/models/vision/__init__.py
galvatron/site_package/megatron/core/models/vision/clip_vit_model.py
galvatron/site_package/megatron/core/models/vision/multimodal_projector.py
galvatron/site_package/megatron/core/optimizer/__init__.py
galvatron/site_package/megatron/core/optimizer/clip_grads.py
galvatron/site_package/megatron/core/optimizer/distrib_optimizer.py
galvatron/site_package/megatron/core/optimizer/grad_scaler.py
galvatron/site_package/megatron/core/optimizer/optimizer.py
galvatron/site_package/megatron/core/optimizer/optimizer_config.py
galvatron/site_package/megatron/core/pipeline_parallel/__init__.py
galvatron/site_package/megatron/core/pipeline_parallel/p2p_communication.py
galvatron/site_package/megatron/core/pipeline_parallel/schedules.py
galvatron/site_package/megatron/core/tensor_parallel/__init__.py
galvatron/site_package/megatron/core/tensor_parallel/cross_entropy.py
galvatron/site_package/megatron/core/tensor_parallel/data.py
galvatron/site_package/megatron/core/tensor_parallel/layers.py
galvatron/site_package/megatron/core/tensor_parallel/mappings.py
galvatron/site_package/megatron/core/tensor_parallel/mappings_group.py
galvatron/site_package/megatron/core/tensor_parallel/random.py
galvatron/site_package/megatron/core/tensor_parallel/utils.py
galvatron/site_package/megatron/core/transformer/__init__.py
galvatron/site_package/megatron/core/transformer/attention.py
galvatron/site_package/megatron/core/transformer/dot_product_attention.py
galvatron/site_package/megatron/core/transformer/enums.py
galvatron/site_package/megatron/core/transformer/identity_op.py
galvatron/site_package/megatron/core/transformer/mlp.py
galvatron/site_package/megatron/core/transformer/module.py
galvatron/site_package/megatron/core/transformer/spec_utils.py
galvatron/site_package/megatron/core/transformer/transformer_block.py
galvatron/site_package/megatron/core/transformer/transformer_config.py
galvatron/site_package/megatron/core/transformer/transformer_layer.py
galvatron/site_package/megatron/core/transformer/utils.py
galvatron/site_package/megatron/core/transformer/custom_layers/__init__.py
galvatron/site_package/megatron/core/transformer/custom_layers/transformer_engine.py
galvatron/site_package/megatron/core/transformer/moe/__init__.py
galvatron/site_package/megatron/core/transformer/moe/experts.py
galvatron/site_package/megatron/core/transformer/moe/grouped_gemm_util.py
galvatron/site_package/megatron/core/transformer/moe/moe_layer.py
galvatron/site_package/megatron/core/transformer/moe/moe_utils.py
galvatron/site_package/megatron/core/transformer/moe/router.py
galvatron/site_package/megatron/core/transformer/moe/token_dispatcher.py
galvatron/site_package/megatron/inference/__init__.py
galvatron/site_package/megatron/inference/arguments.py
galvatron/site_package/megatron/inference/text_generation_server.py
galvatron/site_package/megatron/inference/gpt/__init__.py
galvatron/site_package/megatron/inference/gpt/model_provider.py
galvatron/site_package/megatron/inference/text_generation/__init__.py
galvatron/site_package/megatron/inference/text_generation/api.py
galvatron/site_package/megatron/inference/text_generation/beam_utils.py
galvatron/site_package/megatron/inference/text_generation/communication.py
galvatron/site_package/megatron/inference/text_generation/forward_step.py
galvatron/site_package/megatron/inference/text_generation/generation.py
galvatron/site_package/megatron/inference/text_generation/sampling.py
galvatron/site_package/megatron/inference/text_generation/tokenization.py
galvatron/site_package/megatron/legacy/__init__.py
galvatron/site_package/megatron/legacy/indexer.py
galvatron/site_package/megatron/legacy/data/__init__.py
galvatron/site_package/megatron/legacy/data/autoaugment.py
galvatron/site_package/megatron/legacy/data/biencoder_dataset_utils.py
galvatron/site_package/megatron/legacy/data/data_samplers.py
galvatron/site_package/megatron/legacy/data/dataset_utils.py
galvatron/site_package/megatron/legacy/data/ict_dataset.py
galvatron/site_package/megatron/legacy/data/image_folder.py
galvatron/site_package/megatron/legacy/data/multimodal_dataset.py
galvatron/site_package/megatron/legacy/data/orqa_wiki_dataset.py
galvatron/site_package/megatron/legacy/data/realm_dataset_utils.py
galvatron/site_package/megatron/legacy/data/realm_index.py
galvatron/site_package/megatron/legacy/data/vit_dataset.py
galvatron/site_package/megatron/legacy/fused_kernels/__init__.py
galvatron/site_package/megatron/legacy/model/__init__.py
galvatron/site_package/megatron/legacy/model/bert_model.py
galvatron/site_package/megatron/legacy/model/biencoder_model.py
galvatron/site_package/megatron/legacy/model/classification.py
galvatron/site_package/megatron/legacy/model/enums.py
galvatron/site_package/megatron/legacy/model/fused_bias_gelu.py
galvatron/site_package/megatron/legacy/model/fused_layer_norm.py
galvatron/site_package/megatron/legacy/model/fused_softmax.py
galvatron/site_package/megatron/legacy/model/gpt_model.py
galvatron/site_package/megatron/legacy/model/language_model.py
galvatron/site_package/megatron/legacy/model/module.py
galvatron/site_package/megatron/legacy/model/multiple_choice.py
galvatron/site_package/megatron/legacy/model/realm_model.py
galvatron/site_package/megatron/legacy/model/rms_norm.py
galvatron/site_package/megatron/legacy/model/t5_model.py
galvatron/site_package/megatron/legacy/model/transformer.py
galvatron/site_package/megatron/legacy/model/utils.py
galvatron/site_package/megatron/legacy/model/vision/__init__.py
galvatron/site_package/megatron/legacy/model/vision/classification.py
galvatron/site_package/megatron/legacy/model/vision/dino.py
galvatron/site_package/megatron/legacy/model/vision/esvit_swin_backbone.py
galvatron/site_package/megatron/legacy/model/vision/inpainting.py
galvatron/site_package/megatron/legacy/model/vision/knn_monitor.py
galvatron/site_package/megatron/legacy/model/vision/mit_backbone.py
galvatron/site_package/megatron/legacy/model/vision/swin_backbone.py
galvatron/site_package/megatron/legacy/model/vision/utils.py
galvatron/site_package/megatron/legacy/model/vision/vit_backbone.py
galvatron/site_package/megatron/training/__init__.py
galvatron/site_package/megatron/training/arguments.py
galvatron/site_package/megatron/training/checkpointing.py
galvatron/site_package/megatron/training/dist_signal_handler.py
galvatron/site_package/megatron/training/global_vars.py
galvatron/site_package/megatron/training/initialize.py
galvatron/site_package/megatron/training/log_handler.py
galvatron/site_package/megatron/training/microbatches.py
galvatron/site_package/megatron/training/optimizer_param_scheduler.py
galvatron/site_package/megatron/training/theoretical_memory_usage.py
galvatron/site_package/megatron/training/training.py
galvatron/site_package/megatron/training/utils.py
galvatron/site_package/megatron/training/yaml_arguments.py
galvatron/site_package/megatron/training/tokenizer/__init__.py
galvatron/site_package/megatron/training/tokenizer/bert_tokenization.py
galvatron/site_package/megatron/training/tokenizer/gpt2_tokenization.py
galvatron/site_package/megatron/training/tokenizer/tokenizer.py
galvatron/utils/__init__.py
galvatron/utils/config_utils.py
galvatron/utils/memory_utils.py
galvatron/utils/strategy_utils.py
galvatron/utils/training_utils.py
hetu_galvatron.egg-info/PKG-INFO
hetu_galvatron.egg-info/SOURCES.txt
hetu_galvatron.egg-info/dependency_links.txt
hetu_galvatron.egg-info/requires.txt
hetu_galvatron.egg-info/top_level.txt
tests/__init__.py
tests/conftest.py
tests/test_arguments.py
tests/utils.py
tests/core/__init__.py
tests/core/test_fsdp.py
tests/core/test_hybrid.py
tests/core/test_mixed_precision.py
tests/core/test_pp.py
tests/core/test_redistributed.py
tests/core/test_tp.py
tests/core/test_utils.py
tests/models/__init__.py
tests/models/test_dataloader.py
tests/models/test_model_correctness.py
tests/models/test_model_simple.py
tests/models/configs/__init__.py
tests/models/configs/get_config_json.py
tests/models/configs/gpt.py
tests/models/configs/llama.py
tests/utils/__init__.py
tests/utils/cost_args.py
tests/utils/init_dist.py
tests/utils/model_utils.py
tests/utils/parallel_config.py
tests/utils/profiler_configs.py
tests/utils/profiler_utils.py
tests/utils/runtime_args.py
tests/utils/search_args.py
tests/utils/search_configs.py