Skip to content

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

Draft
kaix-nv wants to merge 1 commit into
kaix/linear-attention-decode-tritonfrom
kaix/linear-attention-vllm
Draft

[4/6] vLLM GDN/KDA state-only fake quantization#2541
kaix-nv wants to merge 1 commit into
kaix/linear-attention-decode-tritonfrom
kaix/linear-attention-vllm

Add vLLM GDN/KDA state-only fake quantization

bae8fa2
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Sep 29, 2026 in 1s

DCO

All commits are signed off!

View more details on DCO