Skip to content

feat: Add int8 KV cache compression with head-major layout and async pipelining#229

Open
naalo2 wants to merge 11 commits into
GeeeekExplorer:mainfrom
naalo2:main
Open

feat: Add int8 KV cache compression with head-major layout and async pipelining#229
naalo2 wants to merge 11 commits into
GeeeekExplorer:mainfrom
naalo2:main

Commits

Commits on May 8, 2026