add

0d99ae1f · silencealiang · c271aaae · 0d99ae1f · 0d99ae1f · 0d99ae1f
Commit 0d99ae1f authored Mar 14, 2025 by silencealiang
20 changed files
--- a/megatron/core/models/common/vision_module/__init__.py
+++ b/megatron/core/models/common/vision_module/__init__.py
--- a/megatron/core/models/common/vision_module/vision_module.py
+++ b/megatron/core/models/common/vision_module/vision_module.py
--- a/megatron/core/models/gpt/__init__.py
+++ b/megatron/core/models/gpt/__init__.py
--- a/megatron/core/models/gpt/gpt_layer_specs.py
+++ b/megatron/core/models/gpt/gpt_layer_specs.py
--- a/megatron/core/models/gpt/gpt_model.py
+++ b/megatron/core/models/gpt/gpt_model.py
--- a/megatron/core/models/gpt/moe_module_specs.py
+++ b/megatron/core/models/gpt/moe_module_specs.py
--- a/megatron/core/models/mamba/__init__.py
+++ b/megatron/core/models/mamba/__init__.py
--- a/megatron/core/models/mamba/mamba_layer_specs.py
+++ b/megatron/core/models/mamba/mamba_layer_specs.py
--- a/megatron/core/models/mamba/mamba_model.py
+++ b/megatron/core/models/mamba/mamba_model.py
--- a/megatron/core/models/multimodal/__init__.py
+++ b/megatron/core/models/multimodal/__init__.py
--- 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