[Examples] Add vLLM container example (#3694)

* add docker example

* fix link

llm/vllm/README.md

@@ -33,6 +33,8 @@ sky launch -c vllm-llama2 serve-openai-api.yaml --env HF_TOKEN=YOUR_HUGGING_FACE
 ```bash
 sky launch -c vllm-llama2 serve-openai-api.yaml --gpus V100:1 --env HF_TOKEN=YOUR_HUGGING_FACE_API_TOKEN
 ```
+**Tip**: You can also use the vLLM docker container for faster setup. Refer to [serve-openai-api-docker.yaml](https://github.com/skypilot-org/skypilot/tree/master/llm/vllm/serve-openai-api-docker.yaml) for more.
+
 2. Check the IP for the cluster with:
 ```
 IP=$(sky status --ip vllm-llama2)

llm/vllm/serve-openai-api-docker.yaml

@@ -0,0 +1,20 @@
+envs:
+  MODEL_NAME: meta-llama/Llama-2-7b-chat-hf
+  HF_TOKEN: # TODO: Fill with your own huggingface token, or use --env to pass.
+
+resources:
+  image_id: docker:vllm/vllm-openai:latest
+  accelerators: {L4:1, A10G:1, A10:1, A100:1, A100-80GB:1}
+  ports:
+    - 8000
+
+setup: |
+  conda deactivate
+  python3 -c "import huggingface_hub; huggingface_hub.login('${HF_TOKEN}')"
+
+run: |
+  conda deactivate
+  echo 'Starting vllm openai api server...'
+  python -m vllm.entrypoints.openai.api_server \
+    --model $MODEL_NAME --tokenizer hf-internal-testing/llama-tokenizer \
+    --host 0.0.0.0