Update README.md
#52
by
eggyhj
- opened
README.md
CHANGED
|
@@ -42,9 +42,11 @@ For more details about Qwen, please refer to the [GitHub](https://github.com/Qwe
|
|
| 42 |
* python 3.8及以上版本
|
| 43 |
* pytorch 1.12及以上版本，推荐2.0及以上版本
|
| 44 |
* 建议使用CUDA 11.4及以上（GPU用户、flash-attention用户等需考虑此选项）
|
|
|
|
| 45 |
* python 3.8 and above
|
| 46 |
* pytorch 1.12 and above, 2.0 and above are recommended
|
| 47 |
* CUDA 11.4 and above are recommended (this is for GPU users, flash-attention users, etc.)
|
|
|
|
| 48 |
<br>
|
| 49 |
|
| 50 |
## 依赖项（Dependency）
|
|
|
|
| 42 |
* python 3.8及以上版本
|
| 43 |
* pytorch 1.12及以上版本，推荐2.0及以上版本
|
| 44 |
* 建议使用CUDA 11.4及以上（GPU用户、flash-attention用户等需考虑此选项）
|
| 45 |
+
* 在 酷睿™/至强® 或 Arc™ GPU 上部署量化模型时，建议使用 [OpenVINO™ Toolkit](https://docs.openvino.ai/2023.3/gen_ai_guide.html)
|
| 46 |
* python 3.8 and above
|
| 47 |
* pytorch 1.12 and above, 2.0 and above are recommended
|
| 48 |
* CUDA 11.4 and above are recommended (this is for GPU users, flash-attention users, etc.)
|
| 49 |
+
* When deploy on Core™/Xeon® or with Arc™ GPU, [OpenVINO™ Toolkit](https://docs.openvino.ai/2023.3/gen_ai_guide.html) is recommended
|
| 50 |
<br>
|
| 51 |
|
| 52 |
## 依赖项（Dependency）
|