Skip to content

Support Opt-in FP8 KV Cache quantization with FA2-4 backend. - #129

Merged
bjf-frz merged 20 commits into
InferMatrixLab:mainfrom
0z5a:kv/fp8-kv-cache
Nov 18, 2026
Merged

bjf-frz merged 20 commits into
InferMatrixLab:mainfrom
0z5a:kv/fp8-kv-cache

Use native FlashAttention-4 FP8 for paged KV

f915e9d
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning and 1 notice
lint and CPU unit tests
succeeded Nov 18, 2026 in 2m 24s