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

[CI] Add codespell check for doc (#1314)

Browse Source 
Add codespell check test for doc only PR

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-06-20 16:48:14 +08:00
committed by GitHub
parent 761bd3d9d7
commit 45be1aac0c
2 changed files with 37 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
.github/doc_codespell.yaml vendored Normal file
View File

@@ -0,0 +1,33 @@
name: 'doc-codespell'
on:
pull_request:
branches:
- 'main'
- '*-dev'
paths:
- 'docs/**'
jobs:
codespell:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.10"]
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements-lint.txt
- name: Run codespell check
run: |
CODESPELL_EXCLUDES=('--skip' 'tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**')
CODESPELL_IGNORE_WORDS=('-L' 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn')
codespell --toml pyproject.toml "${CODESPELL_EXCLUDES[@]}" "${CODESPELL_IGNORE_WORDS[@]}"

8
docs/source/user_guide/quantization.md
View File

@@ -8,7 +8,7 @@ Since 0.9.0rc2 version, quantization feature is experimentally supported in vLLM
To quantize a model, users should install [ModelSlim](https://gitee.com/ascend/msit/blob/master/msmodelslim/README.md) which is the Ascend compression and acceleration tool. It is an affinity-based compression tool designed for acceleration, using compression as its core technology and built upon the Ascend platform.
Currently, only the specific tag [modelslim-VLLM-8.1.RC1.b020_001](https://gitee.com/ascend/msit/blob/modelslim-VLLM-8.1.RC1.b020_001/msmodelslim/README.md) of modelslim works with vLLM Ascend. Please do not install other version until modelslim master version is avaliable for vLLM Ascend in the future.
Currently, only the specific tag [modelslim-VLLM-8.1.RC1.b020_001](https://gitee.com/ascend/msit/blob/modelslim-VLLM-8.1.RC1.b020_001/msmodelslim/README.md) of modelslim works with vLLM Ascend. Please do not install other version until modelslim master version is available for vLLM Ascend in the future.
Install modelslim:
```bash
@@ -34,7 +34,7 @@ You can also download the quantized model that we uploaded. Please note that the
Once convert action is done, there are two important files generated.
1. [confg.json](https://www.modelscope.cn/models/vllm-ascend/DeepSeek-V2-Lite-W8A8/file/view/master/config.json?status=1). Please make sure that there is no `quantization_config` field in it.
1. [config.json](https://www.modelscope.cn/models/vllm-ascend/DeepSeek-V2-Lite-W8A8/file/view/master/config.json?status=1). Please make sure that there is no `quantization_config` field in it.
2. [quant_model_description.json](https://www.modelscope.cn/models/vllm-ascend/DeepSeek-V2-Lite-W8A8/file/view/master/quant_model_description.json?status=1). All the converted weights info are recorded in this file.
@@ -77,7 +77,7 @@ sampling_params = SamplingParams(temperature=0.6, top_p=0.95, top_k=40)
llm = LLM(model="{quantized_model_save_path}",
max_model_len=2048,
trust_remote_code=True,
# Enable quantization by specifing `quantization="ascend"`
# Enable quantization by specifying `quantization="ascend"`
quantization="ascend")
outputs = llm.generate(prompts, sampling_params)
@@ -90,7 +90,7 @@ for output in outputs:
### Online inference
```bash
# Enable quantization by specifing `--quantization ascend`
# Enable quantization by specifying `--quantization ascend`
vllm serve {quantized_model_save_path} --served-model-name "deepseek-v2-lite-w8a8" --max-model-len 2048 --quantization ascend --trust-remote-code
```