diff --git a/k8s/apps/llm-serving/reasoning.yaml b/k8s/apps/llm-serving/reasoning.yaml index 353bff0..c14febf 100644 --- a/k8s/apps/llm-serving/reasoning.yaml +++ b/k8s/apps/llm-serving/reasoning.yaml @@ -79,7 +79,7 @@ spec: resources: limits: cpu: '16' - memory: 24Gi + memory: 36Gi nvidia.com/gpu: '1' requests: cpu: '8'