Skip to content

[PyTorch] DeepSeekV3Layer: full MoE transformer layer (MLA + DeepSeek MoE) - #36

Draft
pggPL wants to merge 7 commits into
mainfrom
deepseek_v3_layer
Draft

[PyTorch] DeepSeekV3Layer: full MoE transformer layer (MLA + DeepSeek MoE)#36
pggPL wants to merge 7 commits into
mainfrom
deepseek_v3_layer

Use fused MLA RoPE kernels in MultiLatentAttention

aa17c37
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar