core
core.datasets
core.datasets.bert_dataset
core.datasets.blended_dataset
core.datasets.blended_megatron_dataset_builder
core.datasets.blended_megatron_dataset_config
core.datasets.gpt_dataset
core.datasets.indexed_dataset
core.datasets.masked_dataset
core.datasets.megatron_dataset
core.datasets.megatron_tokenizer
core.datasets.t5_dataset
core.datasets.utils
core.dist_checkpointing
core.dist_checkpointing.core
core.dist_checkpointing.dict_utils
core.dist_checkpointing.mapping
core.dist_checkpointing.optimizer
core.dist_checkpointing.serialization
core.dist_checkpointing.strategies
core.dist_checkpointing.strategies.base
core.dist_checkpointing.strategies.tensorstore
core.dist_checkpointing.strategies.two_stage
core.dist_checkpointing.strategies.zarr
core.dist_checkpointing.utils
core.distributed
core.distributed.distributed_data_parallel
core.distributed.finalize_model_grads
core.fusions.fused_bias_dropout
core.fusions.fused_bias_gelu
core.fusions.fused_cross_entropy
core.fusions.fused_layer_norm
core.fusions.fused_softmax
core.models
core.models.bert
core.models.bert.bert_model
core.models.gpt
core.models.gpt.gpt_model
core.models.T5
core.models.T5.t5_model
core.num_microbatches_calculator
core.optimizer_param_scheduler
core.pipeline_parallel
core.pipeline_parallel.p2p_communication
core.pipeline_parallel.schedules
core.tensor_parallel
core.tensor_parallel.cross_entropy
core.tensor_parallel.data
core.tensor_parallel.layers
core.tensor_parallel.mappings
core.tensor_parallel.random
core.tensor_parallel.utils
core.transformer
core.transformer.attention
core.transformer.dot_product_attention
core.transformer.enums
core.transformer.identity_op
core.transformer.mlp
core.transformer.module
core.transformer.transformer_block
core.transformer.transformer_config
core.transformer.transformer_layer
core.transformer.utils