Update README.md

README.md

@@ -201,38 +201,32 @@ You can utilize one of the following LLM inference frameworks to create an OpenA
 
 #### [lmdeploy(>=0.9.2)](https://github.com/InternLM/lmdeploy)
 
-```bash
-lmdeploy serve api_server internlm/Intern-S1 --reasoning-parser intern-s1 --tool-call-parser intern-s1 --tp 8
+```
+lmdeploy serve api_server internlm/Intern-S1-FP8 --reasoning-parser intern-s1 --tool-call-parser intern-s1 --tp 4
 ```
 
 #### [vllm](https://github.com/vllm-project/vllm)
 
 ```bash
-vllm serve internlm/Intern-S1 --tensor-parallel-size 8 --trust-remote-code
+vllm serve internlm/Intern-S1-FP8 --tensor-parallel-size 4 --trust-remote-code
 ```
 
 #### [sglang](https://github.com/sgl-project/sglang)
 
+Supporting Intern-S1 with SGLang is still in progress. Please refer to this [PR](https://github.com/sgl-project/sglang/pull/8350).
+
 ```bash
-python3 -m sglang.launch_server \
-    --model-path internlm/Intern-S1 \
+CUDA_VISIBLE_DEVICES=0,1,2,3 \
+    python3 -m sglang.launch_server \
+    --model-path internlm/Intern-S1-FP8 \
     --trust-remote-code \
-    --tp 8 \
+    --tp 4 \
+    --port 8001 \
+    --mem-fraction-static 0.85 \
+    --enable-multimodal \
     --grammar-backend none
 ```
 
-#### ollama for local deployment:
-
-```bash
-# install ollama
-curl -fsSL https://ollama.com/install.sh | sh
-# fetch model
-ollama pull internlm/interns1
-# run model
-ollama run internlm/interns1
-# then use openai client to call on http://localhost:11434/v1
-```
-
 ## Advanced Usage
 
 ### Tool Calling