Skip to content

Add layer-wise KV-cache AutoQuant with forward KL - #2211

Draft
meenchen wants to merge 8 commits into
mainfrom
agent/kv-cache-autoquant-pr
Draft

Add layer-wise KV-cache AutoQuant with forward KL#2211
meenchen wants to merge 8 commits into
mainfrom
agent/kv-cache-autoquant-pr