升级0.12版本

2c63b5cd · wangxj · c271aaae · 2c63b5cd · 2c63b5cd · 2c63b5cd
Commit 2c63b5cd authored Mar 07, 2025 by wangxj
20 changed files
--- a/megatron/core/post_training/modelopt/mamba/model_specs.py
+++ b/megatron/core/post_training/modelopt/mamba/model_specs.py
--- a/megatron/core/requirements.txt
+++ b/megatron/core/requirements.txt
--- a/megatron/core/rerun_state_machine.py
+++ b/megatron/core/rerun_state_machine.py
--- a/megatron/core/ssm/__init__.py
+++ b/megatron/core/ssm/__init__.py
--- a/megatron/core/ssm/mamba_block.py
+++ b/megatron/core/ssm/mamba_block.py
--- a/megatron/core/ssm/mamba_hybrid_layer_allocation.py
+++ b/megatron/core/ssm/mamba_hybrid_layer_allocation.py
--- a/megatron/core/ssm/mamba_layer.py
+++ b/megatron/core/ssm/mamba_layer.py
--- a/megatron/core/ssm/mamba_mixer.py
+++ b/megatron/core/ssm/mamba_mixer.py
--- a/megatron/core/ssm/triton_cache_manager.py
+++ b/megatron/core/ssm/triton_cache_manager.py
--- a/megatron/core/tensor_parallel/__init__.py
+++ b/megatron/core/tensor_parallel/__init__.py
--- a/megatron/core/tensor_parallel/cross_entropy.py
+++ b/megatron/core/tensor_parallel/cross_entropy.py
--- a/megatron/core/tensor_parallel/data.py
+++ b/megatron/core/tensor_parallel/data.py
--- a/megatron/core/tensor_parallel/layers.py
+++ b/megatron/core/tensor_parallel/layers.py
--- a/megatron/core/tensor_parallel/mappings.py
+++ b/megatron/core/tensor_parallel/mappings.py
--- a/megatron/core/tensor_parallel/random.py
+++ b/megatron/core/tensor_parallel/random.py
--- a/megatron/core/tensor_parallel/utils.py
+++ b/megatron/core/tensor_parallel/utils.py
--- a/megatron/core/timers.py
+++ b/megatron/core/timers.py
--- a/megatron/core/transformer/__init__.py
+++ b/megatron/core/transformer/__init__.py
--- a/megatron/core/transformer/attention.py
+++ b/megatron/core/transformer/attention.py
--- a/megatron/core/transformer/cuda_graphs.py
+++ b/megatron/core/transformer/cuda_graphs.py