Commit 1e50759f authored by raojy's avatar raojy
Browse files

updata

parent 97576c49
......@@ -85,3 +85,23 @@ curl http://localhost:8000/v1/chat/completions \
<div align=center>
<img src="./doc/2.png"/>
</div>
### 精度
`DCU与GPU精度一致,推理框架:vllm。`
## 预训练权重[Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-Coder-Next)
| **模型名称** | **权重大小** | **DCU型号** | **最低卡数需求** | **下载地址** |
| :------------------: | :----------: | :------------: | :--------------: | :----------------------------------------------------------: |
| **Qwen3-Coder-Next** | 80B | K100AI、BW1000 | 4 | [Qwen3-Coder-Next](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct) |
## 源码仓库及问题反馈
- https://developer.sourcefind.cn/codes/modelzoo/qwen3_coder_next_vllm
## 参考资料
- https://github.com/QwenLM/Qwen3-Coder
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment