Update sglang info

deployment_guide.md

@@ -1,6 +1,6 @@
 # Intern-S1-Pro Deployment Guide
 
-The Intern-S1-Pro release is a 1T parameter model stored in FP8 format. Deployment requires at least two 8-GPU H200 nodes, with either of the following configurations:
+The Intern-S1-Pro release is a 1T parameter model stored in FP8 format. Deployment requires at least **two 8-GPU H200** nodes, with either of the following configurations:
 
 - Tensor Parallelism (TP)
 - Data Parallelism (DP) + Expert Parallelism (EP)
@@ -126,6 +126,8 @@ vllm serve internlm/Intern-S1-Pro \
 
 ## SGLang
 
+You can use the docker image `lmsysorg/sglang:dev` to deploy. Refer to [using-docker](https://docs.sglang.io/get_started/install.html#method-3-using-docker) for more.
+
 - Tensor Parallelism + Expert Parallelism
 
 ```bash