Skip to content

[codestyle] Modular convert tools (#11129) #259

[codestyle] Modular convert tools (#11129)

[codestyle] Modular convert tools (#11129) #259

Workflow file for this run

# Disabled LLM CI workflow - manually enabled when needed

Check failure on line 1 in .github/workflows/llm.yml

View workflow run for this annotation

GitHub Actions / .github/workflows/llm.yml

Invalid workflow file

You have an error in your yaml syntax on line 1
name: LLM CI (DISABLED)
#on:
# pull_request:
# types: [opened, synchronize, reopened]
# branches: [develop]
# schedule:
# - cron: "2 0 * * *"
# workflow_call:
# inputs:
# run_downstream:
# required: true
# type: string
# image_name:
# required: true
# type: string
#concurrency:
# group: ${{ github.workflow }}-${{ github.event.pull_request.number }}
# cancel-in-progress: true
#env:
# PR_ID: ${{ github.event.pull_request.number }}
COMMIT_ID: ${{ github.event.pull_request.head.sha }}
TASK: paddlenlp-CI-${{ github.event.pull_request.number }}-llm
ci_scripts: /workspace/PaddleNLP/scripts/regression
BRANCH: ${{ github.event.pull_request.base.ref }}
AGILE_COMPILE_BRANCH: ${{ github.event.pull_request.base.ref }}
CI_name: llm-ci
no_proxy: "localhost,bj.bcebos.com,su.bcebos.com,bcebos.com,apiin.im.baidu.com,gitee.com,aliyun.com,.baidu.com,.tuna.tsinghua.edu.cn"
HF_ENDPOINT: https://hf-mirror.com
STUDIO_GIT_HOST: http://git.prod.idc-to-cloud.aistudio.baidu-int.com
PPNLP_HOME: /ssd1/paddlenlp
HF_DATASETS_CACHE: /ssd1/paddlenlp/huggingface/datasets
TRANSFORMERS_CACHE: /ssd1/paddlenlp/huggingface
CCACHE_DIR: /home/data/gzcfs/.ccache/gpubox
RUN_DOWNSTREAM: ${{ inputs.run_downstream }}
#defaults:
# run:
# shell: bash
#jobs:
# llm-ci:
# name: llm-ci (DISABLED)
runs-on: [self-hosted, ernie-8gpu]
steps:
- name: Determine Image Name
env:
IMAGE_NAME: ${{ inputs.image_name }}
run: |
if [[ -n "${IMAGE_NAME}" ]]; then
echo "IMAGE_NAME=${IMAGE_NAME}" >> "$GITHUB_ENV"
else
echo "IMAGE_NAME=iregistry.baidu-int.com/paddlecloud/base-images:paddlecloud-ubuntu18.04-gcc8.2-cuda11.8-cudnn8.6-nccl2.15.5-paddlenlp-latest" >> "$GITHUB_ENV"
fi
- name: Run Container
env:
work_dir: ${{ github.workspace }}
CACHE_DIR: /home/data/cfs/.cache
FLAGS_dynamic_static_unified_comm: "True"
python_version: "3.10"
paddle_whl: https://paddle-qa.bj.bcebos.com/paddle-pipeline/Develop-GpuSome-LinuxCentos-Gcc82-Cuda118-Cudnn86-Trt85-Py310-CINN-Compile/latest/paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
run: |
container_name=${TASK}-$(date +%Y%m%d-%H%M%S)
echo "container_name=${container_name}" >> "$GITHUB_ENV"
if [[ "$RUN_DOWNSTREAM" == "false" ]]; then
echo "Not in a pull_request or test_build event. Skipping..."
else
docker run -d -t --name ${container_name} --net=host -v /dev/shm:/dev/shm --shm-size=32G \
-v $work_dir/../../..:$work_dir/../../.. \
-v $work_dir:/workspace \
-v /home/.cache/pip:/home/.cache/pip \
-v /ssd1/paddlenlp:/ssd1/paddlenlp \
-v /home/data/gzcfs/.ccache/gpubox:/home/data/gzcfs/.ccache/gpubox \
-e BRANCH \
-e AGILE_COMPILE_BRANCH \
-e PR_ID \
-e COMMIT_ID \
-e work_dir \
-e ci_scripts \
-e no_proxy \
-e CI_name \
-e paddle_whl \
-e HF_ENDPOINT \
-e STUDIO_GIT_HOST \
-e PPNLP_HOME \
-e HF_DATASETS_CACHE \
-e TRANSFORMERS_CACHE \
-e CACHE_DIR \
-e FLAGS_dynamic_static_unified_comm \
-e python_version \
-w /workspace --runtime=nvidia $IMAGE_NAME
fi
- name: Download Code
env:
work_dir: ${{ github.workspace }}
run: |
if [[ "$RUN_DOWNSTREAM" == "false" ]]; then
echo "Not in a pull_request or test_build event. Skipping.."
else
docker exec -t $container_name /bin/bash -c '
rm -rf * .[^.]*
echo "Downloading PaddleNLP.tar.gz"
wget -q --no-proxy https://paddle-qa.bj.bcebos.com/CodeSync/develop/PaddleNLP.tar --no-check-certificate
echo "Extracting PaddleNLP.tar.gz"
tar xf PaddleNLP.tar && rm -rf PaddleNLP.tar
source $work_dir/../../../proxy
cd PaddleNLP
git config --global user.name "PaddleCI"
git config --global user.email "paddle_ci@example.com"
git pull
git submodule update --init --recursive --force
if [ -n "${PR_ID}" ]; then
git fetch origin pull/${PR_ID}/head
git checkout -b PR_${PR_ID} FETCH_HEAD
git remote add upstream https://github.com/PaddlePaddle/PaddleNLP.git
git fetch upstream ${BRANCH}
git merge ${BRANCH} --no-edit
git diff --numstat ${BRANCH} -- | awk "{print \$NF}"
else
echo "Not in a pull_request event. Skipping PR-specific operations."
fi
git log --pretty=oneline -10
'
fi
- name: Skip For Bug
run: |
if [[ "$RUN_DOWNSTREAM" == "false" ]]; then
echo "Not in a pull_request or test_build event. Skipping..."
else
docker exec -t $container_name /bin/bash -c '
cd /workspace/PaddleNLP
git revert f2477c07272d04244cd3287d1f21c70482a4a85f --no-edit # 套件PR#10413引入bug-待修复
git revert d74c950e15a35b7a100d1688c89318195cc83bca --no-edit # 框架升级后配合修改,当前因框架bug固定commit适配
'
fi
- name: Test
run: |
if [[ "$RUN_DOWNSTREAM" == "false" ]]; then
echo "Not in a pull_request or test_build event. Skipping..."
else
docker exec -t $container_name /bin/bash -c '
ldconfig
unlink /usr/bin/python3
ln -sf $(which python${python_version}) /usr/bin/python3
pip config set global.cache-dir "/home/.cache/pip"
set -e
source $work_dir/../../../proxy
cd /workspace/PaddleNLP && git config --global --add safe.directory $PWD
echo "Paddle PR#73283 PR#74484 import bug, set paddle_commit=8ae742 to skip "
export paddle_whl=https://paddle-qa.bj.bcebos.com/paddle-pipeline/Develop-GpuSome-LinuxCentos-Gcc82-Cuda118-Cudnn86-Trt85-Py310-CINN-Compile/8ae7423e99b2ea96e410968a0ebb3f1795e37205/paddlepaddle_gpu-0.0.0-cp310-cp310-linux_x86_64.whl
timeout 2h bash scripts/regression/run_ci.sh python${python_version} ${paddle_whl}
'
fi
- name: Upload Allure-reports & Logs
if: always()
env:
home_path: ${{ github.workspace }}/../../..
bos_file: ${{ github.workspace }}/../../../bos/BosClient.py
allure_file: ${{ github.workspace }}/../../../allure-2.19.0/bin/allure
run: |
if [[ "$RUN_DOWNSTREAM" == "false" ]]; then
echo "Not in a pull_request or test_build event. Skipping..."
else
docker exec -t $container_name /bin/bash -c '
unset http_proxy && unset https_proxy
if [ ! -f "${{ env.bos_file }}" ]; then
wget -q --no-proxy -O ${{ env.home_path }}/bos_new.tar.gz https://xly-devops.bj.bcebos.com/home/bos_new.tar.gz --no-check-certificate
mkdir ${{ env.home_path }}/bos
tar xf ${{ env.home_path }}/bos_new.tar.gz -C ${{ env.home_path }}/bos
fi
if [ ! -f "${{ env.allure_file }}" ]; then
wget -q --no-proxy -O ${{ env.home_path }}/allure-2.19.0.zip https://xly-devops.bj.bcebos.com/tools/allure-2.19.0.zip --no-check-certificate
unzip -q ${{ env.home_path }}/allure-2.19.0.zip -d ${{ env.home_path }}/
fi
if [[ "${{ env.RUN_DOWNSTREAM }}" == "" && -n "${PR_ID}" ]]; then
bos_prefix="${PR_ID}/${COMMIT_ID}"
elif [[ "${{ env.RUN_DOWNSTREAM }}" == "true" && -n "${PR_ID}" ]]; then
bos_prefix="${PR_ID}/${COMMIT_ID}/test_build"
else
bos_prefix="schedule/$(date +%Y%m%d)"
fi
cd /workspace/PaddleNLP/model_logs
for FILE in /workspace/PaddleNLP/model_logs/*; do
file=$(basename "$FILE")
python ${{ env.bos_file }} $file paddle-github-action/PR/PaddleNLP/llm/${bos_prefix}/logs
echo "$file: https://paddle-github-action.bj.bcebos.com/PR/PaddleNLP/llm/${bos_prefix}/logs/$file"
done
cd /workspace/PaddleNLP/
${{ env.allure_file }} generate result -o report
tar -czf products.tar.gz report model_logs
python ${{ env.bos_file }} products.tar.gz paddle-github-action/PR/PaddleNLP/llm/${bos_prefix}/logs
echo "products: https://paddle-github-action.bj.bcebos.com/PR/PaddleNLP/llm/${bos_prefix}/logs/products.tar.gz"
'
fi
- name: Terminate And Delete the Container
if: always()
run: |
docker rm -f ${{ env.container_name }} 2>/dev/null || true