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

[Doc] Add stable modelslim branch (#2545)

Browse Source 
### What this PR does / why we need it?
The branch `br_release_MindStudio_8.1.RC2_TR5_20260624` is commercial
delivery version of modelslim in Q3, and has been verified available
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.10.1.1
- vLLM main:
7d67a9d9f9

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-08-27 09:05:46 +08:00
committed by GitHub
parent 8151a9d5a4
commit 042605f4b2
2 changed files with 8 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/source/tutorials/single_npu_qwen3_quantization.md
View File

@@ -32,11 +32,10 @@ see https://www.modelscope.cn/models/vllm-ascend/Qwen3-8B-W4A8
::: :::
```bash ```bash
git clone https://gitee.com/ascend/msit # The branch(br_release_MindStudio_8.1.RC2_TR5_20260624) has been verified
cd msit/msmodelslim git clone -b br_release_MindStudio_8.1.RC2_TR5_20260624 https://gitee.com/ascend/msit
# Optional, this commit has been verified cd msit/msmodelslim
git checkout f8ab35a772a6c1ee7675368a2aa4bafba3bedd1a
# Install by run this script # Install by run this script
bash install.sh bash install.sh

11
docs/source/user_guide/feature_guide/quantization.md
View File

@@ -11,11 +11,10 @@ To quantize a model, users should install [ModelSlim](https://gitee.com/ascend/m
Install modelslim: Install modelslim:
```bash ```bash
git clone https://gitee.com/ascend/msit # The branch(br_release_MindStudio_8.1.RC2_TR5_20260624) has been verified
cd msit/msmodelslim git clone -b br_release_MindStudio_8.1.RC2_TR5_20260624 https://gitee.com/ascend/msit
# Optional, this commit has been verified cd msit/msmodelslim
git checkout f8ab35a772a6c1ee7675368a2aa4bafba3bedd1a
bash install.sh bash install.sh
pip install accelerate pip install accelerate
@@ -100,12 +99,12 @@ Enable quantization by specifying `--quantization ascend`, for more details, see
### 1. How to solve the KeyError: 'xxx.layers.0.self_attn.q_proj.weight' problem? ### 1. How to solve the KeyError: 'xxx.layers.0.self_attn.q_proj.weight' problem?
First, make sure you specify `ascend` quantization method. Second, check if your model is converted by this `modelslim-VLLM-8.1.RC1.b020_001` modelslim version. Finally, if it still doesn't work, please First, make sure you specify `ascend` quantization method. Second, check if your model is converted by this `br_release_MindStudio_8.1.RC2_TR5_20260624` modelslim version. Finally, if it still doesn't work, please
submit a issue, maybe some new models need to be adapted. submit a issue, maybe some new models need to be adapted.
### 2. How to solve the error "Could not locate the configuration_deepseek.py"? ### 2. How to solve the error "Could not locate the configuration_deepseek.py"?
Please convert DeepSeek series models using `modelslim-VLLM-8.1.RC1.b020_001` modelslim, this version has fixed the missing configuration_deepseek.py error. Please convert DeepSeek series models using `br_release_MindStudio_8.1.RC2_TR5_20260624` modelslim, this version has fixed the missing configuration_deepseek.py error.
### 3. When converting deepseek series models with modelslim, what should you pay attention? ### 3. When converting deepseek series models with modelslim, what should you pay attention?