Skip to content

perf(qwen27 cuda): reduce TTFT with prompt caching and state reuse - #2

Open
jrb-ai wants to merge 4 commits into
machinegenieorg:see-4347-qwen27-cudafrom
jrb-ai:perf/qwen27-exact-prompt-cache
Open

perf(qwen27 cuda): reduce TTFT with prompt caching and state reuse#2
jrb-ai wants to merge 4 commits into
machinegenieorg:see-4347-qwen27-cudafrom
jrb-ai:perf/qwen27-exact-prompt-cache

Commits

  1. Commits on Oct 11, 2026