Add nvidia runtime

2024-03-30 22:39:54 -04:00 · 2024-03-30 22:39:54 -04:00 · 28a5a521ee
commit 28a5a521ee
parent ab12752c83
1 changed files with 1 additions and 0 deletions
--- a/vllm/vllm-deployment.yaml
+++ b/vllm/vllm-deployment.yaml
@ -13,6 +13,7 @@ spec:
      labels:
        app: vllm-inference-server
    spec:
+      runtimeClassName: nvidia
      containers:
        - name: vllm-inference-server
          image: vllm/vllm-openai:v0.3.3