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

Змішані

25 вересня 2026 р. о 17:36 UTC

Авторизація

Kamo

Про нас

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).