Skip to content

GitLab

Unverified Commit 8b5fe6eb authored by Simon Mo's avatar Simon Mo Committed by GitHub
Browse files

[CI] Clean up actions: remove helm, publish workflows and improve pr … (#23377)

parent 800349c2
Show whitespace changes
Inline Side-by-side
Showing with 40 additions and 211 deletions
.github/workflows/lint-and-deploy.yaml deleted 100644 → 0
View file @ 800349c2
name: Lint and Deploy Charts
on: pull_request
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
permissions:
contents: read
jobs:
lint-and-deploy:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
- name: Set up Helm
uses: azure/setup-helm@b9e51907a09c216f16ebe8536097933489208112 # v4.3.0
with:
version: v3.14.4
#Python is required because ct lint runs Yamale and yamllint which require Python.
- uses: actions/setup-python@42375524e23c412d93fb67b49958b491fce71c38 # v5.4.0
with:
python-version: '3.13'
- name: Set up chart-testing
uses: helm/chart-testing-action@0d28d3144d3a25ea2cc349d6e59901c4ff469b3b # v2.7.0
with:
version: v3.10.1
- name: Run chart-testing (lint)
run: ct lint --target-branch ${{ github.event.repository.default_branch }} --chart-dirs examples/online_serving/chart-helm --charts examples/online_serving/chart-helm
- name: Setup minio
run: |
docker network create vllm-net
docker run -d -p 9000:9000 --name minio --net vllm-net \
-e "MINIO_ACCESS_KEY=minioadmin" \
-e "MINIO_SECRET_KEY=minioadmin" \
-v /tmp/data:/data \
-v /tmp/config:/root/.minio \
minio/minio server /data
export AWS_ACCESS_KEY_ID=minioadmin
export AWS_SECRET_ACCESS_KEY=minioadmin
export AWS_EC2_METADATA_DISABLED=true
mkdir opt-125m
cd opt-125m && curl -O -Ls "https://huggingface.co/facebook/opt-125m/resolve/main/{pytorch_model.bin,config.json,generation_config.json,merges.txt,special_tokens_map.json,tokenizer_config.json,vocab.json}" && cd ..
aws --endpoint-url http://127.0.0.1:9000/ s3 mb s3://testbucket
aws --endpoint-url http://127.0.0.1:9000/ s3 cp opt-125m/ s3://testbucket/opt-125m --recursive
- name: Create kind cluster
uses: helm/kind-action@a1b0e391336a6ee6713a0583f8c6240d70863de3 # v1.12.0
- name: Build the Docker image vllm cpu
run: docker buildx build -f docker/Dockerfile.cpu -t vllm-cpu-env .
- name: Configuration of docker images, network and namespace for the kind cluster
run: |
docker pull amazon/aws-cli:2.6.4
kind load docker-image amazon/aws-cli:2.6.4 --name chart-testing
kind load docker-image vllm-cpu-env:latest --name chart-testing
docker network connect vllm-net "$(docker ps -aqf "name=chart-testing-control-plane")"
kubectl create ns ns-vllm
- name: Run chart-testing (install)
run: |
export AWS_ACCESS_KEY_ID=minioadmin
export AWS_SECRET_ACCESS_KEY=minioadmin
sleep 30 && kubectl -n ns-vllm logs -f "$(kubectl -n ns-vllm get pods | awk '/deployment/ {print $1;exit}')" &
helm install --wait --wait-for-jobs --timeout 5m0s --debug --create-namespace --namespace=ns-vllm test-vllm examples/online_serving/chart-helm -f examples/online_serving/chart-helm/values.yaml --set secrets.s3endpoint=http://minio:9000 --set secrets.s3bucketname=testbucket --set secrets.s3accesskeyid=$AWS_ACCESS_KEY_ID --set secrets.s3accesskey=$AWS_SECRET_ACCESS_KEY --set resources.requests.cpu=1 --set resources.requests.memory=4Gi --set resources.limits.cpu=2 --set resources.limits.memory=5Gi --set image.env[0].name=VLLM_CPU_KVCACHE_SPACE --set image.env[1].name=VLLM_LOGGING_LEVEL --set image.env[2].name=VLLM_CPU_CI_ENV --set-string image.env[0].value="1" --set-string image.env[1].value="DEBUG" --set-string image.env[2].value="1" --set-string extraInit.s3modelpath="opt-125m/" --set-string 'resources.limits.nvidia\.com/gpu=0' --set-string 'resources.requests.nvidia\.com/gpu=0' --set-string image.repository="vllm-cpu-env"
- name: curl test
run: |
kubectl -n ns-vllm port-forward service/test-vllm-service 8001:80 &
sleep 10
CODE="$(curl -v -f --location http://localhost:8001/v1/completions \
--header "Content-Type: application/json" \
--data '{
"model": "opt-125m",
"prompt": "San Francisco is a",
"max_tokens": 7,
"temperature": 0
}'):$CODE"
echo "$CODE"
.github/workflows/publish.yml deleted 100644 → 0
View file @ 800349c2
# This workflow will upload a Python Package to Release asset
# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions
name: Create Release
on:
push:
tags:
- v*
# Needed to create release and upload assets
permissions:
contents: write
jobs:
release:
# Retrieve tag and create release
name: Create Release
runs-on: ubuntu-latest
outputs:
upload_url: ${{ steps.create_release.outputs.upload_url }}
steps:
- name: Checkout
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Extract branch info
shell: bash
run: |
echo "release_tag=${GITHUB_REF#refs/*/}" >> "$GITHUB_ENV"
- name: Create Release
id: create_release
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
env:
RELEASE_TAG: ${{ env.release_tag }}
with:
github-token: "${{ secrets.GITHUB_TOKEN }}"
script: |
const script = require('.github/workflows/scripts/create_release.js')
await script(github, context, core)
# NOTE(simon): No longer build wheel using GitHub Actions. See buildkite's release workflow.
# wheel:
# name: Build Wheel
# runs-on: ${{ matrix.os }}
# needs: release
# strategy:
# fail-fast: false
# matrix:
# os: ['ubuntu-20.04']
# python-version: ['3.9', '3.10', '3.11', '3.12']
# pytorch-version: ['2.4.0'] # Must be the most recent version that meets requirements/cuda.txt.
# cuda-version: ['11.8', '12.1']
# steps:
# - name: Checkout
# uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
# - name: Setup ccache
# uses: hendrikmuhs/ccache-action@ed74d11c0b343532753ecead8a951bb09bb34bc9 # v1.2.14
# with:
# create-symlink: true
# key: ${{ github.job }}-${{ matrix.python-version }}-${{ matrix.cuda-version }}
# - name: Set up Linux Env
# if: ${{ runner.os == 'Linux' }}
# run: |
# bash -x .github/workflows/scripts/env.sh
# - name: Set up Python
# uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0
# with:
# python-version: ${{ matrix.python-version }}
# - name: Install CUDA ${{ matrix.cuda-version }}
# run: |
# bash -x .github/workflows/scripts/cuda-install.sh ${{ matrix.cuda-version }} ${{ matrix.os }}
# - name: Install PyTorch ${{ matrix.pytorch-version }} with CUDA ${{ matrix.cuda-version }}
# run: |
# bash -x .github/workflows/scripts/pytorch-install.sh ${{ matrix.python-version }} ${{ matrix.pytorch-version }} ${{ matrix.cuda-version }}
# - name: Build wheel
# shell: bash
# env:
# CMAKE_BUILD_TYPE: Release # do not compile with debug symbol to reduce wheel size
# run: |
# bash -x .github/workflows/scripts/build.sh ${{ matrix.python-version }} ${{ matrix.cuda-version }}
# wheel_name=$(find dist -name "*whl" -print0 | xargs -0 -n 1 basename)
# asset_name=${wheel_name//"linux"/"manylinux1"}
# echo "wheel_name=${wheel_name}" >> "$GITHUB_ENV"
# echo "asset_name=${asset_name}" >> "$GITHUB_ENV"
# - name: Upload Release Asset
# uses: actions/upload-release-asset@e8f9f06c4b078e705bd2ea027f0926603fc9b4d5 # v1.0.2
# env:
# GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
# with:
# upload_url: ${{ needs.release.outputs.upload_url }}
# asset_path: ./dist/${{ env.wheel_name }}
# asset_name: ${{ env.asset_name }}
# asset_content_type: application/*
# (Danielkinz): This last step will publish the .whl to pypi. Warning: untested
# - name: Publish package
# uses: pypa/gh-action-pypi-publish@release/v1.8
# with:
# repository-url: https://test.pypi.org/legacy/
# password: ${{ secrets.PYPI_API_TOKEN }}
# skip-existing: true
.github/workflows/reminder_comment.yml
View file @ 8b5fe6eb
......@@ -12,16 +12,45 @@ jobs:
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
with:
script: |
github.rest.issues.createComment({
try {
// Get the PR author
const prAuthor = context.payload.pull_request.user.login;
// Check if this is the author's first PR in this repository
const { data: allPRs } = await github.rest.pulls.list({
owner: context.repo.owner,
repo: context.repo.repo,
state: 'all',
per_page: 100
});
// Filter to find PRs by this author
const authorPRs = allPRs.filter(pr => pr.user.login === prAuthor);
console.log(`Found ${authorPRs.length} PRs by ${prAuthor}`);
// Only post comment if this is the first PR (only one PR by this author)
if (authorPRs.length === 1) {
console.log(`Posting welcome comment for first-time contributor: ${prAuthor}`);
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: context.issue.number,
body: '👋 Hi! Thank you for contributing to the vLLM project.\n\n' +
'💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.\n\n' +
'Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run `fastcheck` CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your `fastcheck` build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping `simon-mo` or `khluu` to add you in our Buildkite org.\n\n' +
'Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run `fastcheck` CI which starts running only a small and essential subset of CI tests to quickly catch errors. \n\n' +
'You ask your reviewers to trigger select CI tests on top of `fastcheck` CI. \n\n' +
'Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.\n\n' +
'To run CI, PR reviewers can either: Add `ready` label to the PR or enable auto-merge.\n\n' +
'If you have any questions, please reach out to us on Slack at https://slack.vllm.ai.\n\n' +
'🚀'
})
});
} else {
console.log(`Skipping comment for ${prAuthor} - not their first PR (${authorPRs.length} PRs found)`);
}
} catch (error) {
console.error('Error checking PR history or posting comment:', error);
// Don't fail the workflow, just log the error
}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment