diff --git a/clusters/k3s-dgx/nim-service/qwen.yaml b/clusters/k3s-dgx/nim-service/qwen.yaml index 6929e23..947d577 100644 --- a/clusters/k3s-dgx/nim-service/qwen.yaml +++ b/clusters/k3s-dgx/nim-service/qwen.yaml @@ -59,6 +59,7 @@ spec: storage: nimCache: name: qwen36-27b-fp8 + profile: tensorrt_llm replicas: 1 resources: limits: