Update vllm deployment example to use 1 GPU as tensor parallelism is 1

liu-cong · liu-cong · commit 948dbdce0d25 · 2024-10-22T09:53:28.000-07:00
diff --git a/examples/poc/manifests/vllm/vllm-lora-deployment.yaml b/examples/poc/manifests/vllm/vllm-lora-deployment.yaml
@@ -78,9 +78,9 @@ spec:
             timeoutSeconds: 1
           resources:
             limits:
-              nvidia.com/gpu: 2
+              nvidia.com/gpu: 1
             requests:
-              nvidia.com/gpu: 2
+              nvidia.com/gpu: 1
           volumeMounts:
             - mountPath: /data
               name: data
