EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[Doc] Fix quant documentation to make it reproducible (#2277)

Browse Source 
### What this PR does / why we need it?
Fixed the expression of msit for code clone

- vLLM version: v0.10.0
- vLLM main:
afa5b7ca0b

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-08-14 17:19:47 +08:00
committed by GitHub
parent c721ae6042
commit 2ad7e1251e
3 changed files with 9 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
docs/source/tutorials/single_npu_qwen3_quantization.md
View File

@@ -32,12 +32,15 @@ see https://www.modelscope.cn/models/vllm-ascend/Qwen3-8B-W4A8
:::
```bash
# Optional, this commit has been verified
git clone https://gitee.com/ascend/msit -b f8ab35a772a6c1ee7675368a2aa4bafba3bedd1a
git clone https://gitee.com/ascend/msit
cd msit/msmodelslim
# Optional, this commit has been verified
git checkout f8ab35a772a6c1ee7675368a2aa4bafba3bedd1a
# Install by run this script
bash install.sh
pip install accelerate
cd example/Qwen
# Original weight path, Replace with your local model path