apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Feature] Unify quant ops (#6021)

Browse Source 
* 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
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/_accuracy_test.yml
+1 -1
View File
@@ -161,7 +161,7 @@ jobs:
-v "${CACHE_DIR}/ConfigDir:/root/.config" \
-e TZ="Asia/Shanghai" \
--gpus '"device='"${DEVICES}"'"' ${docker_image} /bin/bash -xc '
python -m pip install paddlepaddle-gpu==3.3.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
python -m pip install https://paddle-qa.bj.bcebos.com/paddle-pipeline/Release-TagBuild-Training-Linux-Gpu-Cuda12.6-Cudnn9.5-Trt10.5-Mkl-Avx-Gcc11-SelfBuiltPypiUse/latest/paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
.github/workflows/_base_test.yml
+1 -1
View File
@@ -186,7 +186,7 @@ jobs:
-v "${CACHE_DIR}/ConfigDir:/root/.config" \
-e TZ="Asia/Shanghai" \
--gpus '"device='"${DEVICES}"'"' ${docker_image} /bin/bash -xc '
python -m pip install paddlepaddle-gpu==3.3.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
python -m pip install https://paddle-qa.bj.bcebos.com/paddle-pipeline/Release-TagBuild-Training-Linux-Gpu-Cuda12.6-Cudnn9.5-Trt10.5-Mkl-Avx-Gcc11-SelfBuiltPypiUse/latest/paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
.github/workflows/_build_linux.yml
+1 -1
View File
@@ -173,7 +173,7 @@ jobs:
elif [[ "${PADDLEVERSION}" != "" ]];then
python -m pip install paddlepaddle-gpu==${PADDLEVERSION} -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
else
python -m pip install paddlepaddle-gpu==3.3.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
python -m pip install https://paddle-qa.bj.bcebos.com/paddle-pipeline/Release-TagBuild-Training-Linux-Gpu-Cuda12.6-Cudnn9.5-Trt10.5-Mkl-Avx-Gcc11-SelfBuiltPypiUse/latest/paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
fi
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
.github/workflows/_logprob_test_linux.yml
+2 -2
View File
@@ -156,7 +156,7 @@ jobs:
-v "${CACHE_DIR}/ConfigDir:/root/.config" \
-e TZ="Asia/Shanghai" \
--gpus '"device='"${DEVICES}"'"' ${docker_image} /bin/bash -xc '
python -m pip install paddlepaddle-gpu==3.3.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
python -m pip install https://paddle-qa.bj.bcebos.com/paddle-pipeline/Release-TagBuild-Training-Linux-Gpu-Cuda12.6-Cudnn9.5-Trt10.5-Mkl-Avx-Gcc11-SelfBuiltPypiUse/latest/paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
@@ -185,7 +185,7 @@ jobs:
-d "{\"messages\": [{\"role\": \"user\", \"content\": \"1+1=?\"}], \"logprobs\": true}"
set +e
rm -rf ./baseline_output
cp -r baseline/ERNIE-4.5-0.3B-Paddle ./baseline_output
cp -r baseline_24/ERNIE-4.5-0.3B-Paddle ./baseline_output
LOGPROB_EXIT_CODE=0
python3.10 lanucher.py --request_template TOKEN_LOGPROB --url http://localhost:${FD_API_PORT}/v1/chat/completions --case ./cases/demo.yaml --concurrency 1 --name demo --exe logprob || LOGPROB_EXIT_CODE=$?
echo "LOGPROB_EXIT_CODE=${LOGPROB_EXIT_CODE}" > /workspace/exit_code.env
.github/workflows/_pre_ce_test.yml
+1 -1
View File
@@ -172,7 +172,7 @@ jobs:
--gpus "\"device=${DEVICES}\"" ${docker_image} /bin/bash -c '
git config --global --add safe.directory /workspace/FastDeploy
cd FastDeploy
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
python -m pip install ${fd_wheel_url}
bash scripts/run_pre_ce.sh
'
.github/workflows/_stable_test.yml
+1 -1
View File
@@ -164,7 +164,7 @@ jobs:
-v "${CACHE_DIR}/ConfigDir:/root/.config" \
-e TZ="Asia/Shanghai" \
--gpus '"device='"${DEVICES}"'"' ${docker_image} /bin/bash -xc '
python -m pip install paddlepaddle-gpu==3.3.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
python -m pip install https://paddle-qa.bj.bcebos.com/paddle-pipeline/Release-TagBuild-Training-Linux-Gpu-Cuda12.6-Cudnn9.5-Trt10.5-Mkl-Avx-Gcc11-SelfBuiltPypiUse/latest/paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
pip config set global.index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
.github/workflows/_unit_test_coverage.yml
+1 -1
View File
@@ -203,7 +203,7 @@ jobs:
git config --global --add safe.directory /workspace/FastDeploy
cd FastDeploy
git diff origin/${BASE_REF}..HEAD --unified=0 > diff.txt
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
pip config set global.extra-index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
python -m pip install -r scripts/unittest_requirement.txt