Skip to content

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

Draft
pggPL wants to merge 30 commits into
NVIDIA:mainfrom
pggPL:deepseek_v3_layer
Draft

[PyTorch] DeepSeekV3Layer: full MoE transformer layer (MLA + DeepSeek MoE)#3471
pggPL wants to merge 30 commits into
NVIDIA:mainfrom
pggPL:deepseek_v3_layer

Lint: use dict literals in models.deepseek_v3

610a1e2
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Sep 3, 2026 in 1s

DCO

All commits are signed off!

View more details on DCO