Skip to content

qwen CUDA: an integrated GPU keeps prompt states in device memory, without pinning a copy each save (#2043) - #2113

Merged
ashhart merged 3 commits into
ashhart:mainfrom
jschmied:qwen-cache-inplace
Nov 6, 2026
Merged

qwen CUDA: an integrated GPU keeps prompt states in device memory, without pinning a copy each save (#2043)#2113
ashhart merged 3 commits into
ashhart:mainfrom
jschmied:qwen-cache-inplace

Commits

  1. Commits on Nov 6, 2026