Skip to content

Qwen3.5/3.8 on CUDA: decode 37-73% faster on #836's engine, bits unchanged (on #836) - #978

Closed
BobClawblaw wants to merge 39 commits into
ashhart:mainfrom
BobClawblaw:q35-speed
Closed

BobClawblaw wants to merge 39 commits into
ashhart:mainfrom
BobClawblaw:q35-speed

Commits

  1. Commits on Oct 16, 2026