Merge pull request #28 from liu-cong/manifest

k8s-ci-robot · web-flow · commit ee249fbc09c5 · 2024-10-28T15:14:54.000Z
Update vllm deployment example to use 1 GPU as tensor parallelism is 1
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
