Skip to content

[PyTorch] DeepSeekV3Layer: full MoE transformer layer (MLA + DeepSeek MoE) - #3471

Open
pggPL wants to merge 59 commits into
NVIDIA:mainfrom
pggPL:deepseek_v3_layer
Open

pggPL wants to merge 59 commits into
NVIDIA:mainfrom
pggPL:deepseek_v3_layer

Let MoE EP ops allocate their data buffers

72abef7
Select commit
Loading
Failed to load commit list.