Skip to content

qwen3_5 cuda: --kv-cache fp8, e4m3 attention caches with a scale a row - #886

Merged
ashhart merged 39 commits into
ashhart:mainfrom
BobClawblaw:cuda-kv-fp8
Oct 18, 2026
Merged

qwen3_5 cuda: --kv-cache fp8, e4m3 attention caches with a scale a row#886
ashhart merged 39 commits into
ashhart:mainfrom
BobClawblaw:cuda-kv-fp8

Commits

  1. Commits on Oct 16, 2026