deepseekmirror/DeepSeek-V3
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-V3.git synced 2025-06-26 11:31:38 -04:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Merge pull request #903 from yixing1992/main

Browse Source 
Update README.md for Huawei Ascend NPU support modes
This commit is contained in:
Liyue Zhang 2025-06-16 14:50:08 +08:00 committed by GitHub
commit f6e34dd267
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -235,7 +235,7 @@ DeepSeek-V3 can be deployed locally using the following hardware and open-source
5. **vLLM**: Support DeepSeek-V3 model with FP8 and BF16 modes for tensor parallelism and pipeline parallelism. 5. **vLLM**: Support DeepSeek-V3 model with FP8 and BF16 modes for tensor parallelism and pipeline parallelism.
6. **LightLLM**: Supports efficient single-node or multi-node deployment for FP8 and BF16. 6. **LightLLM**: Supports efficient single-node or multi-node deployment for FP8 and BF16.
7. **AMD GPU**: Enables running the DeepSeek-V3 model on AMD GPUs via SGLang in both BF16 and FP8 modes. 7. **AMD GPU**: Enables running the DeepSeek-V3 model on AMD GPUs via SGLang in both BF16 and FP8 modes.
8. **Huawei Ascend NPU**: Supports running DeepSeek-V3 on Huawei Ascend devices. 8. **Huawei Ascend NPU**: Supports running DeepSeek-V3 on Huawei Ascend devices in both INT8 and BF16.
Since FP8 training is natively adopted in our framework, we only provide FP8 weights. If you require BF16 weights for experimentation, you can use the provided conversion script to perform the transformation. Since FP8 training is natively adopted in our framework, we only provide FP8 weights. If you require BF16 weights for experimentation, you can use the provided conversion script to perform the transformation.