Skip to content
Server

fix: allow mixed turbo/q8_0 KV cache types in CUDA flash-attention selection #12

Sign in to view logs

fix: allow mixed turbo/q8_0 KV cache types in CUDA flash-attention selection

fix: allow mixed turbo/q8_0 KV cache types in CUDA flash-attention selection #12

Triggered via pull request July 18, 2026 22:30
@thecodacusthecodacus
synchronize #3
fable5/turbo-fattn-vec-routing
Status Success
Total duration 20m 38s
Artifacts –

server.yml

on: pull_request
ubuntu
17m 9s
ubuntu
windows
20m 18s
windows
Fit to window
Zoom out
Zoom in