diff --git a/clusters/k3s-dgx/nim-service/qwen.yaml b/clusters/k3s-dgx/nim-service/qwen.yaml index 947d577..fc06171 100644 --- a/clusters/k3s-dgx/nim-service/qwen.yaml +++ b/clusters/k3s-dgx/nim-service/qwen.yaml @@ -59,7 +59,7 @@ spec: storage: nimCache: name: qwen36-27b-fp8 - profile: tensorrt_llm + profile: vllm replicas: 1 resources: limits: