Skip to content

Llama: support quantized KV cache export for Arm - #21574

Open
xingguo01 wants to merge 1 commit into
pytorch:mainfrom
xingguo01:llm-extension-arm-static-quantized-kv-cache
Open

Llama: support quantized KV cache export for Arm#21574
xingguo01 wants to merge 1 commit into
pytorch:mainfrom
xingguo01:llm-extension-arm-static-quantized-kv-cache

Commits

Commits on Aug 13, 2026