Run Voxtral transcription worker with two jobs

README.md

@@ -60,6 +60,11 @@ AI-server compose snippet for Voxtral lives in
 - Start Voxtral:
   `docker compose -f docker-compose.yml -f docker-compose.audio.yml --profile voxtral-small up -d voxtral-small`
 
+In Kubernetes the dedicated transcription worker may claim more than one
+`voxtral-small` job at a time. This keeps download/upload/wait overhead from
+serializing the queue while Voxtral/vLLM still controls the actual GPU
+scheduling.
+
 ## API
 
 - `POST /api/v1/jobs` creates one job.

k8s/worker-deployment.yaml

@@ -100,7 +100,7 @@ spec:
             - name: WORKER_MODEL_PROFILES
               value: "voxtral-small"
             - name: WORKER_CLAIM_LIMIT
-              value: "1"
+              value: "2"
           envFrom:
             - configMapRef:
                 name: ai-service-config