[docs] standardize Hugging Face env var to `HF_TOKEN` (deprecates...

[docs] standardize Hugging Face env var to `HF_TOKEN` (deprecates `HUGGING_FACE_HUB_TOKEN`) (#27020)
Signed-off-by: Kay Yan <kay.yan@daocloud.io>

docs/deployment/docker.md

@@ -10,7 +10,7 @@ The image can be used to run OpenAI compatible server and is available on Docker
 ```bash
 docker run --runtime nvidia --gpus all \
     -v ~/.cache/huggingface:/root/.cache/huggingface \
-    --env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \
+    --env "HF_TOKEN=$HF_TOKEN" \
     -p 8000:8000 \
     --ipc=host \
     vllm/vllm-openai:latest \
@@ -22,7 +22,7 @@ This image can also be used with other container engines such as [Podman](https:
 ```bash
 podman run --device nvidia.com/gpu=all \
   -v ~/.cache/huggingface:/root/.cache/huggingface \
-  --env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \
+  --env "HF_TOKEN=$HF_TOKEN" \
   -p 8000:8000 \
   --ipc=host \
   docker.io/vllm/vllm-openai:latest \
@@ -128,7 +128,7 @@ To run vLLM with the custom-built Docker image:
 docker run --runtime nvidia --gpus all \
     -v ~/.cache/huggingface:/root/.cache/huggingface \
     -p 8000:8000 \
-    --env "HUGGING_FACE_HUB_TOKEN=<secret>" \
+    --env "HF_TOKEN=<secret>" \
     vllm/vllm-openai <args...>
 ```
 

docs/deployment/frameworks/lws.md

@@ -35,7 +35,7 @@ Deploy the following yaml file `lws.yaml`
               - name: vllm-leader
                 image: docker.io/vllm/vllm-openai:latest
                 env:
-                  - name: HUGGING_FACE_HUB_TOKEN
+                  - name: HF_TOKEN
                     value: <your-hf-token>
                 command:
                   - sh
@@ -83,7 +83,7 @@ Deploy the following yaml file `lws.yaml`
                     ephemeral-storage: 800Gi
                     cpu: 125
                 env:
-                  - name: HUGGING_FACE_HUB_TOKEN
+                  - name: HF_TOKEN
                     value: <your-hf-token>
                 volumeMounts:
                   - mountPath: /dev/shm

docs/deployment/k8s.md

@@ -82,7 +82,7 @@ Next, start the vLLM server as a Kubernetes Deployment and Service:
               "vllm serve meta-llama/Llama-3.2-1B-Instruct"
             ]
             env:
-            - name: HUGGING_FACE_HUB_TOKEN
+            - name: HF_TOKEN
               valueFrom:
                 secretKeyRef:
                   name: hf-token-secret
@@ -209,7 +209,7 @@ INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
                 "vllm serve mistralai/Mistral-7B-Instruct-v0.3 --trust-remote-code --enable-chunked-prefill --max_num_batched_tokens 1024"
               ]
               env:
-              - name: HUGGING_FACE_HUB_TOKEN
+              - name: HF_TOKEN
                 valueFrom:
                   secretKeyRef:
                     name: hf-token-secret
@@ -298,7 +298,7 @@ INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
                 "vllm serve mistralai/Mistral-7B-v0.3 --port 8000 --trust-remote-code --enable-chunked-prefill --max_num_batched_tokens 1024"
               ]
               env:
-              - name: HUGGING_FACE_HUB_TOKEN
+              - name: HF_TOKEN
                 valueFrom:
                   secretKeyRef:
                     name: hf-token-secret