Skip to content

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

Open
0z5a wants to merge 19 commits into
InferMatrixLab:mainfrom
0z5a:kv/fp8-kv-cache
Open

0z5a wants to merge 19 commits into
InferMatrixLab:mainfrom
0z5a:kv/fp8-kv-cache

Merge main and preserve FP8 scales in packed window attention

9ed813e
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 17, 2026 in 3m 27s