Upgrade version and use gpt2

2024-03-30 23:03:01 -04:00 · 2024-03-30 23:03:01 -04:00 · a263684284
commit a263684284
parent 5ca94dda0b
1 changed files with 2 additions and 2 deletions
--- a/vllm/vllm-deployment.yaml
+++ b/vllm/vllm-deployment.yaml
@ -16,7 +16,7 @@ spec:
      runtimeClassName: nvidia
      containers:
        - name: vllm-inference-server
-          image: vllm/vllm-openai:v0.3.3
+          image: vllm/vllm-openai:latest
          imagePullPolicy: IfNotPresent

          resources:
@ -33,7 +33,7 @@ spec:
                #args:
                #- while true; do sleep 2600; done
          command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
-          args: ["--model=mistralai/Mistral-7B-v0.1",
+          args: ["--model=openai-community/gpt2",
                 "--gpu-memory-utilization=0.95",
                 "--disable-log-requests",
                 "--trust-remote-code",