Skip to content

feat: INT8 KV cache quantization (~48% memory reduction)#184

Open
dzhengAP wants to merge 1 commit into
GeeeekExplorer:mainfrom
dzhengAP:feature/int8-kv-cache
Open

feat: INT8 KV cache quantization (~48% memory reduction)#184
dzhengAP wants to merge 1 commit into
GeeeekExplorer:mainfrom
dzhengAP:feature/int8-kv-cache

Commits

Commits on Mar 9, 2026