Update README.md

[BugFix] Fix compatibility issues with vLLM 0.10.1

README.md

@@ -13,15 +13,16 @@ base_model:
 base_model_relation: quantized
 ---
 # Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8
-基础型 [Qwen3-Coder-30B-A3B-Instruct](https://www.modelscope.cn/models/Qwen3-Coder-30B-A3B-Instruct)
+Base model:[Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct)
+
+### 【vLLM 4-GPU Single Node Launch Command】
+<i>Note: When using 4 GPUs, you must include `--enable-expert-parallel` because expert tensor TP must be evenly divisible; for 2 GPUs this is not necessary.</i>
 
-### 【Vllm 启动命令】
-<i>注: 4卡启动该模型一定要跟`--enable-expert-parallel` ，否则其专家张量TP整除除不尽；2卡则不需要。 </i>
 ```
 CONTEXT_LENGTH=32768
 
 vllm serve \
-    tclf90/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8 \
+    QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8 \
     --served-model-name Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8 \
     --enable-expert-parallel \
     --swap-space 16 \
@@ -36,33 +37,35 @@ vllm serve \
     --port 8000
 ```
 
-### 【依赖】
+### 【Dependencies】
 
 ```
 vllm==0.10.0
 ```
 
-### 【模型更新日期】
-``` 
+### 【Model Update Date】
+```
+2025-08-19
+1.[BugFix] Fix compatibility issues with vLLM 0.10.1
 2025-08-01
-1. 首次commit
+1. Initial commit
 ```
 
-### 【模型列表】
+### 【Model Files】
 
-| 文件大小   | 最近更新时间       |
+| File Size | Last Updated |
 |--------|--------------|
 | `30GB` | `2025-08-01` |
 
 
-### 【模型下载】
+### 【Model Download】
 
 ```python
-from modelscope import snapshot_download
-snapshot_download('tclf90/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8', cache_dir="本地路径")
+from huggingface_hub import snapshot_download
+snapshot_download('QuantTrio/Qwen3-Coder-30B-A3B-Instruct-GPTQ-Int8', cache_dir="your_local_path")
 ```
 
-### 【介绍】
+### 【Overview】
 # Qwen3-Coder-30B-A3B-Instruct
 <a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
     <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>