MANIFEST.in
README.md
pyproject.toml
setup.py
megatron/core/README.md
megatron/core/__init__.py
megatron/core/activations.py
megatron/core/config.py
megatron/core/config_logger.py
megatron/core/energy_monitor.py
megatron/core/enums.py
megatron/core/fp4_utils.py
megatron/core/fp8_utils.py
megatron/core/full_cuda_graph.py
megatron/core/hyper_comm_grid.py
megatron/core/inference_params.py
megatron/core/jit.py
megatron/core/model_parallel_config.py
megatron/core/msc_utils.py
megatron/core/nccl_allocator.py
megatron/core/num_microbatches_calculator.py
megatron/core/optimizer_param_scheduler.py
megatron/core/package_info.py
megatron/core/packed_seq_params.py
megatron/core/parallel_state.py
megatron/core/process_groups_config.py
megatron/core/requirements.txt
megatron/core/rerun_state_machine.py
megatron/core/safe_globals.py
megatron/core/timers.py
megatron/core/utils.py
megatron/core/datasets/__init__.py
megatron/core/datasets/bert_dataset.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/helpers.cpp
megatron/core/datasets/helpers.py
megatron/core/datasets/indexed_dataset.py
megatron/core/datasets/masked_dataset.py
megatron/core/datasets/megatron_dataset.py
megatron/core/datasets/megatron_tokenizer.py
megatron/core/datasets/multimodal_dataset.py
megatron/core/datasets/object_storage_utils.py
megatron/core/datasets/t5_dataset.py
megatron/core/datasets/utils.py
megatron/core/datasets/utils_s3.py
megatron/core/datasets/retro/__init__.py
megatron/core/datasets/retro/external_libs.py
megatron/core/datasets/retro/utils.py
megatron/core/datasets/retro/config/__init__.py
megatron/core/datasets/retro/config/bert_embedders.py
megatron/core/datasets/retro/config/config.py
megatron/core/datasets/retro/config/gpt_chunk_datasets.py
megatron/core/datasets/retro/config/tokenizers.py
megatron/core/datasets/retro/db/__init__.py
megatron/core/datasets/retro/db/build.py
megatron/core/datasets/retro/db/dataset.py
megatron/core/datasets/retro/db/utils.py
megatron/core/datasets/retro/index/__init__.py
megatron/core/datasets/retro/index/build.py
megatron/core/datasets/retro/index/factory.py
megatron/core/datasets/retro/index/index.py
megatron/core/datasets/retro/index/utils.py
megatron/core/datasets/retro/index/validate.py
megatron/core/datasets/retro/index/indexes/__init__.py
megatron/core/datasets/retro/index/indexes/faiss_base.py
megatron/core/datasets/retro/index/indexes/faiss_par_add.py
megatron/core/datasets/retro/query/__init__.py
megatron/core/datasets/retro/query/gpt_chunk_dataset.py
megatron/core/datasets/retro/query/multi_split_gpt_dataset.py
megatron/core/datasets/retro/query/query.py
megatron/core/datasets/retro/query/retro_dataset.py
megatron/core/datasets/retro/query/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/exchange_utils.py
megatron/core/dist_checkpointing/mapping.py
megatron/core/dist_checkpointing/optimizer.py
megatron/core/dist_checkpointing/serialization.py
megatron/core/dist_checkpointing/state_dict_utils.py
megatron/core/dist_checkpointing/tensor_aware_state_dict.py
megatron/core/dist_checkpointing/utils.py
megatron/core/dist_checkpointing/validation.py
megatron/core/dist_checkpointing/strategies/__init__.py
megatron/core/dist_checkpointing/strategies/async_utils.py
megatron/core/dist_checkpointing/strategies/base.py
megatron/core/dist_checkpointing/strategies/cached_metadata_filesystem_reader.py
megatron/core/dist_checkpointing/strategies/checkpointable.py
megatron/core/dist_checkpointing/strategies/common.py
megatron/core/dist_checkpointing/strategies/filesystem_async.py
megatron/core/dist_checkpointing/strategies/fully_parallel.py
megatron/core/dist_checkpointing/strategies/resharding.py
megatron/core/dist_checkpointing/strategies/state_dict_saver.py
megatron/core/dist_checkpointing/strategies/tensorstore.py
megatron/core/dist_checkpointing/strategies/torch.py
megatron/core/dist_checkpointing/strategies/two_stage.py
megatron/core/dist_checkpointing/strategies/zarr.py
megatron/core/distributed/__init__.py
megatron/core/distributed/data_parallel_base.py
megatron/core/distributed/distributed_data_parallel.py
megatron/core/distributed/distributed_data_parallel_config.py
megatron/core/distributed/finalize_model_grads.py
megatron/core/distributed/param_and_grad_buffer.py
megatron/core/distributed/reduce_scatter_with_fp32_accumulation.py
megatron/core/distributed/torch_fully_sharded_data_parallel.py
megatron/core/distributed/torch_fully_sharded_data_parallel_config.py
megatron/core/distributed/fsdp/__init__.py
megatron/core/distributed/fsdp/mcore_fsdp_adapter.py
megatron/core/distributed/fsdp/src/__init__.py
megatron/core/distributed/fsdp/src/megatron_fsdp/__init__.py
megatron/core/distributed/fsdp/src/megatron_fsdp/distributed_data_parallel_config.py
megatron/core/distributed/fsdp/src/megatron_fsdp/fully_shard.py
megatron/core/distributed/fsdp/src/megatron_fsdp/megatron_fsdp.py
megatron/core/distributed/fsdp/src/megatron_fsdp/package_info.py
megatron/core/distributed/fsdp/src/megatron_fsdp/param_and_grad_buffer.py
megatron/core/distributed/fsdp/src/megatron_fsdp/uneven_dtensor.py
megatron/core/distributed/fsdp/src/megatron_fsdp/utils.py
megatron/core/export/__init__.py
megatron/core/export/data_type.py
megatron/core/export/export_config.py
megatron/core/export/model_type.py
megatron/core/export/trtllm/__init__.py
megatron/core/export/trtllm/trt_model_config.py
megatron/core/export/trtllm/trt_model_type.py
megatron/core/export/trtllm/trtllm_helper.py
megatron/core/export/trtllm/trtllm_layers.py
megatron/core/export/trtllm/engine_builder/__init__.py
megatron/core/export/trtllm/engine_builder/trtllm_engine_builder.py
megatron/core/export/trtllm/model_to_trllm_mapping/__init__.py
megatron/core/export/trtllm/model_to_trllm_mapping/default_conversion_dict.py
megatron/core/export/trtllm/trtllm_weights_converter/__init__.py
megatron/core/export/trtllm/trtllm_weights_converter/distributed_trtllm_model_weights_converter.py
megatron/core/export/trtllm/trtllm_weights_converter/single_device_trtllm_model_weights_converter.py
megatron/core/export/trtllm/trtllm_weights_converter/utils.py
megatron/core/extensions/__init__.py
megatron/core/extensions/kitchen.py
megatron/core/extensions/transformer_engine.py
megatron/core/extensions/transformer_engine_spec_provider.py
megatron/core/fusions/__init__.py
megatron/core/fusions/fused_bias_dropout.py
megatron/core/fusions/fused_bias_geglu.py
megatron/core/fusions/fused_bias_gelu.py
megatron/core/fusions/fused_bias_swiglu.py
megatron/core/fusions/fused_cross_entropy.py
megatron/core/fusions/fused_indices_converter.py
megatron/core/fusions/fused_layer_norm.py
megatron/core/fusions/fused_mla_yarn_rope_apply.py
megatron/core/fusions/fused_pad_routing_map.py
megatron/core/fusions/fused_softmax.py
megatron/core/fusions/fused_weighted_squared_relu.py
megatron/core/inference/__init__.py
megatron/core/inference/async_stream.py
megatron/core/inference/batch_dimensions_utils.py
megatron/core/inference/common_inference_params.py
megatron/core/inference/communication_utils.py
megatron/core/inference/data_parallel_inference_coordinator.py
megatron/core/inference/headers.py
megatron/core/inference/inference_client.py
megatron/core/inference/inference_request.py
megatron/core/inference/sampling_params.py
megatron/core/inference/scheduler.py
megatron/core/inference/unified_memory.py
megatron/core/inference/utils.py
megatron/core/inference/contexts/__init__.py
megatron/core/inference/contexts/base_context.py
megatron/core/inference/contexts/dynamic_block_allocator.py
megatron/core/inference/contexts/dynamic_context.py
megatron/core/inference/contexts/fused_kv_append_kernel.py
megatron/core/inference/contexts/static_context.py
megatron/core/inference/contexts/attention_context/mamba_metadata.py
megatron/core/inference/contexts/attention_context/metadata_base.py
megatron/core/inference/contexts/attention_context/mha_metadata.py
megatron/core/inference/engines/__init__.py
megatron/core/inference/engines/abstract_engine.py
megatron/core/inference/engines/dynamic_engine.py
megatron/core/inference/engines/mcore_engine.py
megatron/core/inference/engines/static_engine.py
megatron/core/inference/model_inference_wrappers/__init__.py
megatron/core/inference/model_inference_wrappers/abstract_model_inference_wrapper.py
megatron/core/inference/model_inference_wrappers/inference_wrapper_config.py
megatron/core/inference/model_inference_wrappers/gpt/__init__.py
megatron/core/inference/model_inference_wrappers/gpt/gpt_inference_wrapper.py
megatron/core/inference/model_inference_wrappers/multimodal/vlm_inference_wrapper.py
megatron/core/inference/model_inference_wrappers/t5/__init__.py
megatron/core/inference/model_inference_wrappers/t5/t5_inference_wrapper.py
megatron/core/inference/text_generation_controllers/__init__.py
megatron/core/inference/text_generation_controllers/encoder_decoder_text_generation_controller.py
megatron/core/inference/text_generation_controllers/simple_text_generation_controller.py
megatron/core/inference/text_generation_controllers/text_generation_controller.py
megatron/core/inference/text_generation_controllers/vlm_text_generation_controller.py
megatron/core/inference/text_generation_server/__init__.py
megatron/core/inference/text_generation_server/run_mcore_engine.py
megatron/core/inference/text_generation_server/text_generation_server.py
megatron/core/inference/text_generation_server/tokenization.py
megatron/core/inference/text_generation_server/endpoints/common.py
megatron/core/inference/text_generation_server/endpoints/completions.py
megatron/core/models/__init__.py
megatron/core/models/backends.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/model_chunk_schedule_plan.py
megatron/core/models/common/embeddings/__init__.py
megatron/core/models/common/embeddings/language_model_embedding.py
megatron/core/models/common/embeddings/relative_pos_embedding.py
megatron/core/models/common/embeddings/rope_utils.py
megatron/core/models/common/embeddings/rotary_pos_embedding.py
megatron/core/models/common/embeddings/yarn_rotary_pos_embedding.py
megatron/core/models/common/language_module/__init__.py
megatron/core/models/common/language_module/language_module.py
megatron/core/models/common/vision_module/__init__.py
megatron/core/models/common/vision_module/vision_module.py
megatron/core/models/gpt/__init__.py
megatron/core/models/gpt/fine_grained_callables.py
megatron/core/models/gpt/gpt_layer_specs.py
megatron/core/models/gpt/gpt_model.py
megatron/core/models/gpt/moe_module_specs.py
megatron/core/models/gpt/heterogeneous/heterogeneous_layer_specs.py
megatron/core/models/huggingface/__init__.py
megatron/core/models/huggingface/clip_model.py
megatron/core/models/huggingface/module.py
megatron/core/models/huggingface/qwen_model.py
megatron/core/models/mamba/__init__.py
megatron/core/models/mamba/mamba_layer_specs.py
megatron/core/models/mamba/mamba_model.py
megatron/core/models/mimo/__init__.py
megatron/core/models/mimo/config/__init__.py
megatron/core/models/mimo/config/base_configs.py
megatron/core/models/mimo/model/__init__.py
megatron/core/models/mimo/model/base.py
megatron/core/models/mimo/submodules/audio.py
megatron/core/models/mimo/submodules/base.py
megatron/core/models/mimo/submodules/vision.py
megatron/core/models/multimodal/__init__.py
megatron/core/models/multimodal/context_parallel.py
megatron/core/models/multimodal/llava_model.py
megatron/core/models/multimodal/llava_spec.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/models/retro/utils.py
megatron/core/models/vision/__init__.py
megatron/core/models/vision/clip_vit_model.py
megatron/core/models/vision/multimodal_projector.py
megatron/core/models/vision/radio.py
megatron/core/models/vision/vit_layer_specs.py
megatron/core/optimizer/__init__.py
megatron/core/optimizer/clip_grads.py
megatron/core/optimizer/distrib_optimizer.py
megatron/core/optimizer/grad_scaler.py
megatron/core/optimizer/optimizer.py
megatron/core/optimizer/optimizer_config.py
megatron/core/optimizer/cpu_offloading/__init__.py
megatron/core/optimizer/cpu_offloading/hybrid_optimizer.py
megatron/core/pipeline_parallel/__init__.py
megatron/core/pipeline_parallel/bridge_communicator.py
megatron/core/pipeline_parallel/combined_1f1b.py
megatron/core/pipeline_parallel/p2p_communication.py
megatron/core/pipeline_parallel/schedules.py
megatron/core/pipeline_parallel/utils.py
megatron/core/post_training/__init__.py
megatron/core/post_training/modelopt/__init__.py
megatron/core/post_training/modelopt/layers.py
megatron/core/post_training/modelopt/gpt/__init__.py
megatron/core/post_training/modelopt/gpt/model_specs.py
megatron/core/post_training/modelopt/gpt/state_dict_hooks.py
megatron/core/post_training/modelopt/mamba/__init__.py
megatron/core/post_training/modelopt/mamba/model_specs.py
megatron/core/quantization/__init__.py
megatron/core/quantization/quant_config.py
megatron/core/quantization/utils.py
megatron/core/ssm/__init__.py
megatron/core/ssm/mamba_block.py
megatron/core/ssm/mamba_context_parallel.py
megatron/core/ssm/mamba_hybrid_layer_allocation.py
megatron/core/ssm/mamba_layer.py
megatron/core/ssm/mamba_mixer.py
megatron/core/ssm/mlp_layer.py
megatron/core/ssm/triton_cache_manager.py
megatron/core/tensor_parallel/__init__.py
megatron/core/tensor_parallel/cross_entropy.py
megatron/core/tensor_parallel/data.py
megatron/core/tensor_parallel/inference_layers.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/tokenizers/__init__.py
megatron/core/tokenizers/base_tokenizer.py
megatron/core/tokenizers/megatron_tokenizer.py
megatron/core/tokenizers/text/__init__.py
megatron/core/tokenizers/text/text_tokenizer.py
megatron/core/tokenizers/text/libraries/__init__.py
megatron/core/tokenizers/text/libraries/abstract_tokenizer.py
megatron/core/tokenizers/text/libraries/bytelevel_tokenizer.py
megatron/core/tokenizers/text/libraries/chat_template.py
megatron/core/tokenizers/text/libraries/huggingface_tokenizer.py
megatron/core/tokenizers/text/libraries/megatron_hf_tokenizer.py
megatron/core/tokenizers/text/libraries/null_tokenizer.py
megatron/core/tokenizers/text/libraries/sentencepiece_tokenizer.py
megatron/core/tokenizers/text/libraries/tiktoken_tokenizer.py
megatron/core/tokenizers/text/models/__init__.py
megatron/core/tokenizers/text/models/bert_tokenizer.py
megatron/core/tokenizers/text/models/default_tokenizer.py
megatron/core/tokenizers/text/models/gpt_tokenizer.py
megatron/core/tokenizers/text/models/mamba_tokenizer.py
megatron/core/tokenizers/text/models/retro_tokenizer.py
megatron/core/tokenizers/text/models/t5_tokenizer.py
megatron/core/tokenizers/text/utils/build_tokenizer.py
megatron/core/transformer/__init__.py
megatron/core/transformer/attention.py
megatron/core/transformer/cuda_graphs.py
megatron/core/transformer/dot_product_attention.py
megatron/core/transformer/enums.py
megatron/core/transformer/fsdp_dtensor_checkpoint.py
megatron/core/transformer/identity_op.py
megatron/core/transformer/mlp.py
megatron/core/transformer/module.py
megatron/core/transformer/multi_latent_attention.py
megatron/core/transformer/multi_token_prediction.py
megatron/core/transformer/pipeline_parallel_layer_layout.py
megatron/core/transformer/spec_utils.py
megatron/core/transformer/torch_layer_norm.py
megatron/core/transformer/torch_norm.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/transformer/heterogeneous/heterogeneous_config.py
megatron/core/transformer/heterogeneous/linear_replacements.py
megatron/core/transformer/moe/__init__.py
megatron/core/transformer/moe/experts.py
megatron/core/transformer/moe/fused_a2a.py
megatron/core/transformer/moe/grouped_gemm_util.py
megatron/core/transformer/moe/moe_layer.py
megatron/core/transformer/moe/moe_utils.py
megatron/core/transformer/moe/router.py
megatron/core/transformer/moe/shared_experts.py
megatron/core/transformer/moe/token_dispatcher.py
megatron/core/transformer/moe/upcycling_utils.py
megatron_core.egg-info/PKG-INFO
megatron_core.egg-info/SOURCES.txt
megatron_core.egg-info/dependency_links.txt
megatron_core.egg-info/requires.txt
megatron_core.egg-info/top_level.txt