Update README.md

README.md

@@ -1,12 +1,10 @@
 ---
 license: mit
-base_model:
-- deepseek-ai/DeepSeek-R1
-base_model_relation: quantized
+library_name: transformers
 ---
-# DeepSeek-V3.1-W4AFP8
+# DeepSeek-R1-AWQ-W4AFP8
 
-This model is a W4AFP8 quantized DeepSeek-V3.1 with AWQ quantizaton.   
+This model is a W4AFP8 quantized DeepSeek-R1 with AWQ quantizaton.   
 Releated PR：https://github.com/sgl-project/sglang/pull/8573    
 Releated Project: https://github.com/TMElyralab/sglang/tree/lyra_w4afp8    
 
@@ -47,6 +45,39 @@ Max ITL (ms):                            7819.3
 ==================================================
 ```
 
+## How To Use
+
+Mirror：lmsysorg/sglang:v0.4.6.post5-cu124    
+
+```
+# 1. Repo clone
+git clone https://github.com/TMElyralab/sglang && cd sglang
+git checkout lyra_w4afp8
+
+# 2. SGLang install
+pip install vllm==0.10.0
+pip install uv cmake
+pip install -e "python[all]"
+
+# 3. Recompile sgl-kernel
+cd sgl-kernel & make build
+
+# 4. Run SGLang
+python3 -m sglang.launch_server --model-path /path/to/DeepSeek-R1-AWQ-W4AFP8 --tp 8 --trust-remote-code --host 0.0.0.0 --port 8000 --mem-fraction-static 0.9 --quantization w4a8_machete --dtype half --cuda-graph-max-bs 128 --max-running-requests 128
+```
+
+
+## Citation
+We are TMElyralab, the Acceleration Team from Tencent Music Entertainment (TME).
+```
+@Misc{TMElyralab_2025,
+  author =       {Sa Xiao, Mian Peng, Haoxiong Su, Kangjian Wu, Bin Wu, Yibo Lu, Qiwen Mao, Wenjiang Zhou},
+  howpublished = {\url{https://github.com/TMElyralab}},
+  year =         {2025}
+}
+```
+
+
 ------
 <!-- markdownlint-disable first-line-h1 -->
 <!-- markdownlint-disable html -->