Update vllm info

Seems sth wrong with vLLM TP deployment, remove it for now. And add detailed information about vllm docker image.

deployment_guide.md

@@ -59,25 +59,7 @@ lmdeploy serve api_server \
 
 ## vLLM
 
-- Tensor Parallelism + Expert Parallelism
-
-```bash
-# start ray on node 0 and node 1
-
-# node 0
-export VLLM_ENGINE_READY_TIMEOUT_S=10000
-vllm serve internlm/Intern-S1-Pro \
-    --tensor-parallel-size 16 \
-    --enable-expert-parallel \
-    --distributed-executor-backend ray \
-    --max-model-len 65536 \
-    --trust-remote-code \
-    --reasoning-parser deepseek_r1 \
-    --enable-auto-tool-choice \
-    --tool-call-parser hermes
-```
-
-- Data Parallelism + Expert Parallelism
+You can use the vLLM nightly-built docker image `vllm/vllm-openai:nightly` to deploy. Refer to [using-docker](https://docs.vllm.ai/en/latest/deployment/docker/?h=docker) for more.
 
 ```bash
 # node 0