fix(ai): set ollama warm-model limits

2026-06-29 14:33:32 -03:00 · 2026-06-29 14:33:32 -03:00 · b2b196ca8a
commit b2b196ca8a
parent 0dbfbba02c
1 changed files with 2 additions and 0 deletions
--- a/services/ai-llm/deployment.yaml
+++ b/services/ai-llm/deployment.yaml
@ -71,6 +71,8 @@ spec:
              memory: 2Gi
              nvidia.com/gpu.shared: 1
            limits:
+              cpu: "2"
+              memory: 4Gi
              nvidia.com/gpu.shared: 1
      containers:
        - name: ollama