diff --git a/config/manifests/regression-testing/vllm/multi-lora-deployment.yaml b/config/manifests/regression-testing/vllm/multi-lora-deployment.yaml
index 114cd9922..9c02d3571 100644
--- a/config/manifests/regression-testing/vllm/multi-lora-deployment.yaml
+++ b/config/manifests/regression-testing/vllm/multi-lora-deployment.yaml
@@ -14,7 +14,7 @@ spec:
     spec:
       containers:
         - name: vllm
-          image: "vllm/vllm-openai:latest"
+          image: "vllm/vllm-openai:v0.8.5"
           imagePullPolicy: Always
           command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
           args:
diff --git a/config/manifests/vllm/gpu-deployment.yaml b/config/manifests/vllm/gpu-deployment.yaml
index 16f938826..7ae591aec 100644
--- a/config/manifests/vllm/gpu-deployment.yaml
+++ b/config/manifests/vllm/gpu-deployment.yaml
@@ -14,7 +14,7 @@ spec:
     spec:
       containers:
         - name: vllm
-          image: "vllm/vllm-openai:latest"
+          image: "vllm/vllm-openai:v0.8.5"
           imagePullPolicy: Always
           command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
           args:
diff --git a/site-src/guides/inferencepool-rollout.md b/site-src/guides/inferencepool-rollout.md
index 98b3cc4cc..f3d929466 100644
--- a/site-src/guides/inferencepool-rollout.md
+++ b/site-src/guides/inferencepool-rollout.md
@@ -79,7 +79,7 @@ spec:
     spec:
       containers:
         - name: vllm
-          image: "vllm/vllm-openai:latest"
+          image: "vllm/vllm-openai:v0.8.5"
           imagePullPolicy: Always
           command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
           args: