mirror of
https://github.com/vllm-project/vllm-ascend.git
synced 2025-10-20 13:43:53 +08:00
ff37575936
### What this PR does / why we need it?
- Refacotr and integrate a unified `WeightPrefetchMethod`
- Integrate `qkv_proj.weight` and `o_proj.weight` in quantized Attention
modules
- Prefetching these weights ahead of matmul-like operators imporves
performance by reducing L2 cache transfer latency
### Does this PR introduce _any_ user-facing change?
Add a new config in `--additional-config` for configuration:
```json
{
"weight_prefetch_config": {
"enabled": false,
"prefetch_ratio": {
"attn": {
"qkv": 1.0,
"o": 1.0,
},
},
},
}
```
This feature is enabled by default, and can be disabled through this
configuration
### How was this patch tested?
- vLLM version: v0.11.0
---------
Signed-off-by: yuzhup <15705211260@163.com>
Signed-off-by: zhoux77899 <zhouxiang100@huawei.com>
Co-authored-by: yuzhup <15705211260@163.com>
vLLM Ascend Plugin documents
Live doc: https://vllm-ascend.readthedocs.io
Build the docs
# Install dependencies.
pip install -r requirements-docs.txt
# Build the docs.
make clean
make html
# Build the docs with translation
make intl
# Open the docs with your browser
python -m http.server -d _build/html/
Launch your browser and open:
- English version: http://localhost:8000
- Chinese version: http://localhost:8000/zh_CN