diff --git a/llamacpp/deployment-stt.yaml b/llamacpp/deployment-stt.yaml index 1d955be..1915dfb 100644 --- a/llamacpp/deployment-stt.yaml +++ b/llamacpp/deployment-stt.yaml @@ -64,12 +64,15 @@ spec: - name: wyoming containerPort: 10300 resources: + # faster-whisper `small` is ~244M params (fp16 ~500 MiB weights) + # plus CTranslate2 runtime / workspace buffers during decode. + # 1 GiB OOM-kills during model load; 2 GiB gives headroom. requests: cpu: "100m" - memory: "256Mi" + memory: "512Mi" limits: cpu: "1000m" - memory: "1Gi" + memory: "2Gi" volumeMounts: - name: data mountPath: /data