[Feature] Unify quant ops (#6021)

* quant stash

* blockwise_quant

* rm tensor.cut

* tp ok

* add paddle swiglu

* 21B test ok

* pre-commit

* fix ut error

* fix block quant

* edit whl

* e baseline

* e baseline 2

* chore: remove extra whitespace in test_EB_VL_Lite_serving.py

* chore: keep paddlepaddle-xpu unchanged

---------

Co-authored-by: Yuanle Liu <yuanlehome@163.com>
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
This commit is contained in:
fxyfxy777
2026-01-24 16:09:36 +08:00
committed by GitHub
parent 13ad267ab8
commit 9a48206d62
18 changed files with 85 additions and 45 deletions
+1 -1
View File
@@ -173,7 +173,7 @@ jobs:
elif [[ "${PADDLEVERSION}" != "" ]];then
python -m pip install paddlepaddle-gpu==${PADDLEVERSION} -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
else
python -m pip install paddlepaddle-gpu==3.3.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
python -m pip install https://paddle-qa.bj.bcebos.com/paddle-pipeline/Release-TagBuild-Training-Linux-Gpu-Cuda12.6-Cudnn9.5-Trt10.5-Mkl-Avx-Gcc11-SelfBuiltPypiUse/latest/paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
fi
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple