add qwen

clusters/k3s-dgx/nim-service/qwen.yaml

@@ -0,0 +1,20 @@
+apiVersion: apps.nvidia.com/v1alpha1
+kind: NIMCache
+metadata:
+  name: qwen2.5-7b-instruct
+  namespace: nim-service
+spec:
+  source:
+    ngc:
+      modelPuller: nvcr.io/nim/qwen/qwen-2.5-7b-instruct:latest
+      pullSecret: ngc-secret
+      authSecret: ngc-api-secret
+      model:
+        engine: "vllm"
+        tensorParallelism: "1"
+  storage:
+    pvc:
+      create: true
+      size: "100Gi"
+      volumeAccessMode: ReadWriteOnce
+---