Six Whisper workers and six requested CPUs, so a batch chunk never queues a realtime turn

Dikirim

25 September 2026 pukul 17.36 UTC

Penulis

Kamo

Commit

b55020f

The acceptance run on k3m1 (4 realtime streams + 1 batch) measured p95 17.9 s: the batch held one of the 4 workers, so one turn waited behind a whole turn. Six workers run all five at once (Task 6 Step 7 fallback).