Skip to content

[4/6] vLLM GDN/KDA state-only fake quantization - #2541

Draft
kaix-nv wants to merge 2 commits into
kaix/linear-attention-qat-examplefrom
kaix/linear-attention-vllm
Draft

kaix-nv wants to merge 2 commits into
kaix/linear-attention-qat-examplefrom
kaix/linear-attention-vllm