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/models/multimodal/llava_model.py
+++ b/megatron/core/models/multimodal/llava_model.py
--- a/megatron/core/models/multimodal/llava_spec.py
+++ b/megatron/core/models/multimodal/llava_spec.py
--- a/megatron/core/models/retro/__init__.py
+++ b/megatron/core/models/retro/__init__.py
--- a/megatron/core/models/retro/base_attention.py
+++ b/megatron/core/models/retro/base_attention.py
--- a/megatron/core/models/retro/config.py
+++ b/megatron/core/models/retro/config.py
--- a/megatron/core/models/retro/decoder_attention.py
+++ b/megatron/core/models/retro/decoder_attention.py
--- a/megatron/core/models/retro/decoder_spec.py
+++ b/megatron/core/models/retro/decoder_spec.py
--- a/megatron/core/models/retro/encoder_attention.py
+++ b/megatron/core/models/retro/encoder_attention.py
--- a/megatron/core/models/retro/encoder_spec.py
+++ b/megatron/core/models/retro/encoder_spec.py
--- a/megatron/core/models/retro/model.py
+++ b/megatron/core/models/retro/model.py
--- a/megatron/core/models/retro/utils.py
+++ b/megatron/core/models/retro/utils.py
--- a/megatron/core/models/vision/__init__.py
+++ b/megatron/core/models/vision/__init__.py
--- a/megatron/core/models/vision/clip_vit_model.py
+++ b/megatron/core/models/vision/clip_vit_model.py
--- a/megatron/core/models/vision/multimodal_projector.py
+++ b/megatron/core/models/vision/multimodal_projector.py
--- a/megatron/core/models/vision/radio.py
+++ b/megatron/core/models/vision/radio.py
--- a/megatron/core/models/vision/vit_layer_specs.py
+++ b/megatron/core/models/vision/vit_layer_specs.py
--- a/megatron/core/num_microbatches_calculator.py
+++ b/megatron/core/num_microbatches_calculator.py
--- a/megatron/core/optimizer/__init__.py
+++ b/megatron/core/optimizer/__init__.py
--- a/megatron/core/optimizer/clip_grads.py
+++ b/megatron/core/optimizer/clip_grads.py
--- a/megatron/core/optimizer/cpu_offloading/README.md
+++ b/megatron/core/optimizer/cpu_offloading/README.md