Skip to content

perf(runtime): llama prewarm-on-focus, mid-prefill abort, and KV-reuse visibility#681

Merged
FuJacob merged 2 commits into
mainfrom
perf/llama-prewarm-abort
Jun 12, 2026
Merged

perf(runtime): llama prewarm-on-focus, mid-prefill abort, and KV-reuse visibility#681
FuJacob merged 2 commits into
mainfrom
perf/llama-prewarm-abort

review: stop prewarm from double-decoding on models that reject parti…

00c4968
Select commit
Loading
Failed to load commit list.