EngineX-Cambricon/enginex-mlu370-vllm
10
0
Fork 1
Code Issues Pull Requests Actions Projects Releases Wiki Activity

add qwen3

Browse Source
This commit is contained in:
Chranos
2026-02-04 17:22:39 +08:00
parent d1c0f68ab4
commit 8511fe8530
1932 changed files with 300426 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
vllm-v0.6.2/.github/workflows/actionlint.yml vendored Normal file
View File

@@ -0,0 +1,40 @@
name: Lint GitHub Actions workflows
on:
push:
branches:
- "main"
paths:
- '.github/workflows/*.ya?ml'
- '.github/workflows/actionlint.*'
- '.github/workflows/matchers/actionlint.json'
pull_request:
branches:
- "main"
paths:
- '.github/workflows/*.ya?ml'
- '.github/workflows/actionlint.*'
- '.github/workflows/matchers/actionlint.json'
env:
LC_ALL: en_US.UTF-8
defaults:
run:
shell: bash
permissions:
contents: read
jobs:
actionlint:
runs-on: ubuntu-latest
steps:
- name: "Checkout"
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
- name: "Run actionlint"
run: |
echo "::add-matcher::.github/workflows/matchers/actionlint.json"
tools/actionlint.sh -color

21
vllm-v0.6.2/.github/workflows/add_label_automerge.yml vendored Normal file
View File

@@ -0,0 +1,21 @@
name: Add label on auto-merge enabled
on:
pull_request_target:
types:
- auto_merge_enabled
jobs:
add-label-on-auto-merge:
runs-on: ubuntu-latest
steps:
- name: Add label
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
with:
script: |
github.rest.issues.addLabels({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: context.issue.number,
labels: ['ready']
})
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

53
vllm-v0.6.2/.github/workflows/clang-format.yml vendored Normal file
View File

@@ -0,0 +1,53 @@
name: clang-format
on:
# Trigger the workflow on push or pull request,
# but only for the main branch
push:
branches:
- main
paths:
- '**/*.h'
- '**/*.cpp'
- '**/*.cu'
- '**/*.cuh'
- '.github/workflows/clang-format.yml'
pull_request:
branches:
- main
paths:
- '**/*.h'
- '**/*.cpp'
- '**/*.cu'
- '**/*.cuh'
- '.github/workflows/clang-format.yml'
jobs:
clang-format:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.11"]
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install clang-format==18.1.5
- name: Running clang-format
run: |
EXCLUDES=(
'csrc/moe/topk_softmax_kernels.cu'
'csrc/quantization/gguf/ggml-common.h'
'csrc/quantization/gguf/dequantize.cuh'
'csrc/quantization/gguf/vecdotq.cuh'
'csrc/quantization/gguf/mmq.cuh'
'csrc/quantization/gguf/mmvq.cuh'
)
find csrc/ \( -name '*.h' -o -name '*.cpp' -o -name '*.cu' -o -name '*.cuh' \) -print \
| grep -vFf <(printf "%s\n" "${EXCLUDES[@]}") \
| xargs clang-format --dry-run --Werror

26
vllm-v0.6.2/.github/workflows/cleanup_pr_body.yml vendored Normal file
View File

@@ -0,0 +1,26 @@
name: Cleanup PR Body
on:
pull_request_target:
types: [opened, reopened, edited]
permissions:
pull-requests: write
jobs:
update-description:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Python
uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0
with:
python-version: '3.12'
- name: Update PR description
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: .github/scripts/cleanup_pr_body.sh "${{ github.event.number }}"

45
vllm-v0.6.2/.github/workflows/codespell.yml vendored Normal file
View File

@@ -0,0 +1,45 @@
name: codespell
on:
# Trigger the workflow on push or pull request,
# but only for the main branch
push:
branches:
- main
paths:
- "**/*.py"
- "**/*.md"
- "**/*.rst"
- pyproject.toml
- requirements-lint.txt
- .github/workflows/codespell.yml
pull_request:
branches:
- main
paths:
- "**/*.py"
- "**/*.md"
- "**/*.rst"
- pyproject.toml
- requirements-lint.txt
- .github/workflows/codespell.yml
jobs:
codespell:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.12"]
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements-lint.txt
- name: Spelling check with codespell
run: |
codespell --toml pyproject.toml

17
vllm-v0.6.2/.github/workflows/matchers/actionlint.json vendored Normal file
View File

@@ -0,0 +1,17 @@
{
"problemMatcher": [
{
"owner": "actionlint",
"pattern": [
{
"regexp": "^(?:\\x1b\\[\\d+m)?(.+?)(?:\\x1b\\[\\d+m)*:(?:\\x1b\\[\\d+m)*(\\d+)(?:\\x1b\\[\\d+m)*:(?:\\x1b\\[\\d+m)*(\\d+)(?:\\x1b\\[\\d+m)*: (?:\\x1b\\[\\d+m)*(.+?)(?:\\x1b\\[\\d+m)* \\[(.+?)\\]$",
"file": 1,
"line": 2,
"column": 3,
"message": 4,
"code": 5
}
]
}
]
}

16
vllm-v0.6.2/.github/workflows/matchers/mypy.json vendored Normal file
View File

@@ -0,0 +1,16 @@
{
"problemMatcher": [
{
"owner": "mypy",
"pattern": [
{
"regexp": "^(.+):(\\d+):\\s(error|warning):\\s(.+)$",
"file": 1,
"line": 2,
"severity": 3,
"message": 4
}
]
}
]
}

17
vllm-v0.6.2/.github/workflows/matchers/ruff.json vendored Normal file
View File

@@ -0,0 +1,17 @@
{
"problemMatcher": [
{
"owner": "ruff",
"pattern": [
{
"regexp": "^(.+?):(\\d+):(\\d+): (\\w+): (.+)$",
"file": 1,
"line": 2,
"column": 3,
"code": 4,
"message": 5
}
]
}
]
}

51
vllm-v0.6.2/.github/workflows/mypy.yaml vendored Normal file
View File

@@ -0,0 +1,51 @@
name: mypy
on:
# Trigger the workflow on push or pull request,
# but only for the main branch
push:
branches:
- main
paths:
- '**/*.py'
- '.github/workflows/mypy.yaml'
- 'tools/mypy.sh'
- 'pyproject.toml'
pull_request:
branches:
- main
# This workflow is only relevant when one of the following files changes.
# However, we have github configured to expect and require this workflow
# to run and pass before github with auto-merge a pull request. Until github
# allows more flexible auto-merge policy, we can just run this on every PR.
# It doesn't take that long to run, anyway.
#paths:
# - '**/*.py'
# - '.github/workflows/mypy.yaml'
# - 'tools/mypy.sh'
# - 'pyproject.toml'
jobs:
mypy:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.9", "3.10", "3.11", "3.12"]
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install mypy==1.11.1
pip install types-setuptools
pip install types-PyYAML
pip install types-requests
pip install types-setuptools
- name: Mypy
run: |
echo "::add-matcher::.github/workflows/matchers/mypy.json"
tools/mypy.sh 1 ${{ matrix.python-version }}

110
vllm-v0.6.2/.github/workflows/publish.yml vendored Normal file
View File

@@ -0,0 +1,110 @@
# 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)
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

21
vllm-v0.6.2/.github/workflows/reminder_comment.yml vendored Normal file
View File

@@ -0,0 +1,21 @@
name: PR Reminder Comment Bot
on:
pull_request_target:
types: [opened]
jobs:
pr_reminder:
runs-on: ubuntu-latest
steps:
- name: Remind to run full CI on PR
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
with:
script: |
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 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\nOnce 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 do one of these:\n- Add `ready` label to the PR\n- Enable auto-merge.\n\n🚀'
})
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

52
vllm-v0.6.2/.github/workflows/ruff.yml vendored Normal file
View File

@@ -0,0 +1,52 @@
name: ruff
on:
# Trigger the workflow on push or pull request,
# but only for the main branch
push:
branches:
- main
paths:
- "**/*.py"
- pyproject.toml
- requirements-lint.txt
- .github/workflows/matchers/ruff.json
- .github/workflows/ruff.yml
pull_request:
branches:
- main
# This workflow is only relevant when one of the following files changes.
# However, we have github configured to expect and require this workflow
# to run and pass before github with auto-merge a pull request. Until github
# allows more flexible auto-merge policy, we can just run this on every PR.
# It doesn't take that long to run, anyway.
#paths:
# - "**/*.py"
# - pyproject.toml
# - requirements-lint.txt
# - .github/workflows/matchers/ruff.json
# - .github/workflows/ruff.yml
jobs:
ruff:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.12"]
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements-lint.txt
- name: Analysing the code with ruff
run: |
echo "::add-matcher::.github/workflows/matchers/ruff.json"
ruff check --output-format github .
- name: Run isort
run: |
isort . --check-only

23
vllm-v0.6.2/.github/workflows/scripts/build.sh vendored Normal file
View File

@@ -0,0 +1,23 @@
#!/bin/bash
set -eux
python_executable=python$1
cuda_home=/usr/local/cuda-$2
# Update paths
PATH=${cuda_home}/bin:$PATH
LD_LIBRARY_PATH=${cuda_home}/lib64:$LD_LIBRARY_PATH
# Install requirements
$python_executable -m pip install -r requirements-build.txt -r requirements-cuda.txt
# Limit the number of parallel jobs to avoid OOM
export MAX_JOBS=1
# Make sure release wheels are built for the following architectures
export TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 8.9 9.0+PTX"
export VLLM_FA_CMAKE_GPU_ARCHES="80-real;90-real"
bash tools/check_repo.sh
# Build
$python_executable setup.py bdist_wheel --dist-dir=dist

20
vllm-v0.6.2/.github/workflows/scripts/create_release.js vendored Normal file
View File

@@ -0,0 +1,20 @@
// Uses Github's API to create the release and wait for result.
// We use a JS script since github CLI doesn't provide a way to wait for the release's creation and returns immediately.
module.exports = async (github, context, core) => {
try {
const response = await github.rest.repos.createRelease({
draft: false,
generate_release_notes: true,
name: process.env.RELEASE_TAG,
owner: context.repo.owner,
prerelease: true,
repo: context.repo.repo,
tag_name: process.env.RELEASE_TAG,
});
core.setOutput('upload_url', response.data.upload_url);
} catch (error) {
core.setFailed(error.message);
}
}

23
vllm-v0.6.2/.github/workflows/scripts/cuda-install.sh vendored Normal file
View File

@@ -0,0 +1,23 @@
#!/bin/bash
# Replace '.' with '-' ex: 11.8 -> 11-8
cuda_version=$(echo "$1" | tr "." "-")
# Removes '-' and '.' ex: ubuntu-20.04 -> ubuntu2004
OS=$(echo "$2" | tr -d ".\-")
# Installs CUDA
wget -nv "https://developer.download.nvidia.com/compute/cuda/repos/${OS}/x86_64/cuda-keyring_1.1-1_all.deb"
sudo dpkg -i cuda-keyring_1.1-1_all.deb
rm cuda-keyring_1.1-1_all.deb
sudo apt -qq update
sudo apt -y install "cuda-${cuda_version}" "cuda-nvcc-${cuda_version}" "cuda-libraries-dev-${cuda_version}"
sudo apt clean
# Test nvcc
PATH=/usr/local/cuda-$1/bin:${PATH}
nvcc --version
# Log gcc, g++, c++ versions
gcc --version
g++ --version
c++ --version

56
vllm-v0.6.2/.github/workflows/scripts/env.sh vendored Normal file
View File

@@ -0,0 +1,56 @@
#!/bin/bash
# This file installs common linux environment tools
export LANG C.UTF-8
# python_version=$1
sudo apt-get update && \
sudo apt-get install -y --no-install-recommends \
software-properties-common \
sudo apt-get install -y --no-install-recommends \
build-essential \
apt-utils \
ca-certificates \
wget \
git \
vim \
libssl-dev \
curl \
unzip \
unrar \
cmake \
net-tools \
sudo \
autotools-dev \
rsync \
jq \
openssh-server \
tmux \
screen \
htop \
pdsh \
openssh-client \
lshw \
dmidecode \
util-linux \
automake \
autoconf \
libtool \
net-tools \
pciutils \
libpci-dev \
libaio-dev \
libcap2 \
libtinfo5 \
fakeroot \
devscripts \
debhelper \
nfs-common
# Remove github bloat files to free up disk space
sudo rm -rf "/usr/local/share/boost"
sudo rm -rf "$AGENT_TOOLSDIRECTORY"
sudo rm -rf "/usr/share/dotnet"

15
vllm-v0.6.2/.github/workflows/scripts/pytorch-install.sh vendored Normal file
View File

@@ -0,0 +1,15 @@
#!/bin/bash
python_executable=python$1
pytorch_version=$2
cuda_version=$3
# Install torch
$python_executable -m pip install numpy pyyaml scipy ipython mkl mkl-include ninja cython typing pandas typing-extensions dataclasses setuptools && conda clean -ya
$python_executable -m pip install torch=="${pytorch_version}+cu${cuda_version//./}" --extra-index-url "https://download.pytorch.org/whl/cu${cuda_version//./}"
# Print version information
$python_executable --version
$python_executable -c "import torch; print('PyTorch:', torch.__version__)"
$python_executable -c "import torch; print('CUDA:', torch.version.cuda)"
$python_executable -c "from torch.utils import cpp_extension; print (cpp_extension.CUDA_HOME)"

37
vllm-v0.6.2/.github/workflows/shellcheck.yml vendored Normal file
View File

@@ -0,0 +1,37 @@
name: Lint shell scripts
on:
push:
branches:
- "main"
paths:
- '**/*.sh'
- '.github/workflows/shellcheck.yml'
pull_request:
branches:
- "main"
paths:
- '**/*.sh'
- '.github/workflows/shellcheck.yml'
env:
LC_ALL: en_US.UTF-8
defaults:
run:
shell: bash
permissions:
contents: read
jobs:
shellcheck:
runs-on: ubuntu-latest
steps:
- name: "Checkout"
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
- name: "Check shell scripts"
run: |
tools/shellcheck.sh

52
vllm-v0.6.2/.github/workflows/stale.yml vendored Normal file
View File

@@ -0,0 +1,52 @@
name: 'Close inactive issues and PRs'
on:
schedule:
# Daily at 1:30 AM UTC
- cron: '30 1 * * *'
jobs:
close-issues-and-pull-requests:
permissions:
issues: write
pull-requests: write
actions: write
runs-on: ubuntu-latest
steps:
- uses: actions/stale@28ca1036281a5e5922ead5184a1bbf96e5fc984e # v9.0.0
with:
# Increasing this value ensures that changes to this workflow
# propagate to all issues and PRs in days rather than months
operations-per-run: 1000
exempt-draft-pr: true
exempt-issue-labels: 'keep-open'
exempt-pr-labels: 'keep-open'
labels-to-add-when-unstale: 'unstale'
labels-to-remove-when-stale: 'unstale'
days-before-issue-stale: 90
days-before-issue-close: 30
stale-issue-label: 'stale'
stale-issue-message: >
This issue has been automatically marked as stale because it has not
had any activity within 90 days. It will be automatically closed if no
further activity occurs within 30 days. Leave a comment if
you feel this issue should remain open. Thank you!
close-issue-message: >
This issue has been automatically closed due to inactivity. Please
feel free to reopen if you feel it is still relevant. Thank you!
days-before-pr-stale: 90
days-before-pr-close: 30
stale-pr-label: 'stale'
stale-pr-message: >
This pull request has been automatically marked as stale because it
has not had any activity within 90 days. It will be automatically
closed if no further activity occurs within 30 days. Leave a comment
if you feel this pull request should remain open. Thank you!
close-pr-message: >
This pull request has been automatically closed due to inactivity.
Please feel free to reopen if you intend to continue working on it.
Thank you!

38
vllm-v0.6.2/.github/workflows/yapf.yml vendored Normal file
View File

@@ -0,0 +1,38 @@
name: yapf
on:
# Trigger the workflow on push or pull request,
# but only for the main branch
push:
branches:
- main
paths:
- "**/*.py"
- .github/workflows/yapf.yml
pull_request:
branches:
- main
paths:
- "**/*.py"
- .github/workflows/yapf.yml
jobs:
yapf:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.12"]
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@0b93645e9fea7318ecaed2b359559ac225c90a2b # v5.3.0
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install yapf==0.32.0
pip install toml==0.10.2
- name: Running yapf
run: |
yapf --diff --recursive .