mirror of
https://github.com/vllm-project/vllm-ascend.git
synced 2025-10-20 05:33:51 +08:00
### What this PR does / why we need it? - Adds the `mla_preprocess` custom kernel to provide an optimized pre-processing operator for Multi-head Latent Attention (MLA) on Ascend NPUs. - Wires the new kernel into the C++ extension pipeline so vLLM can invoke it directly, cutting Python-side tensor shuffling and memory copies that previously bottlenecked MLA compilation paths. ### Does this PR introduce any user-facing change? - No. The change only introduces a low-level kernel; public APIs and inference behavior remain unchanged. ### How was this patch tested? - Dedicated Ascend kernels are not covered by our CI yet, so no extra automated tests were added. Future MLA-focused regression runs will cover this path. - vLLM version: v0.11.0 Signed-off-by: Chen Chen <0109chenchen@gmail.com>
152 lines
4.9 KiB
YAML
152 lines
4.9 KiB
YAML
default_install_hook_types:
|
|
- pre-commit
|
|
- commit-msg
|
|
default_stages:
|
|
- pre-commit # Run locally
|
|
- manual # Run in CI
|
|
exclude: 'examples/.*' # Exclude examples from all hooks by default
|
|
repos:
|
|
- repo: https://github.com/codespell-project/codespell
|
|
rev: v2.4.1
|
|
hooks:
|
|
- id: codespell
|
|
args: [
|
|
--toml, pyproject.toml,
|
|
'--skip', 'tests/e2e/multicard/test_torchair_graph_mode.py,csrc/mla_preprocess/**,tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**,.github/**,typos.toml',
|
|
'-L', 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn,ArchType,AND'
|
|
]
|
|
additional_dependencies:
|
|
- tomli
|
|
- repo: https://github.com/google/yapf
|
|
rev: v0.43.0
|
|
hooks:
|
|
- id: yapf
|
|
args: [--in-place, --verbose]
|
|
# Keep the same list from yapfignore here to avoid yapf failing without any inputs
|
|
exclude: '(.github|benchmarks|examples|docs)/.*'
|
|
- repo: https://github.com/astral-sh/ruff-pre-commit
|
|
rev: v0.11.7
|
|
hooks:
|
|
- id: ruff
|
|
args: [--output-format, github, --fix]
|
|
- id: ruff-format
|
|
files: ^(benchmarks|examples)/.*
|
|
- repo: https://github.com/crate-ci/typos
|
|
rev: v1.32.0
|
|
hooks:
|
|
- id: typos
|
|
args: [
|
|
"--force-exclude",
|
|
"--exclude", "csrc/mla_preprocess/**"
|
|
]
|
|
- repo: https://github.com/PyCQA/isort
|
|
rev: 6.0.1
|
|
hooks:
|
|
- id: isort
|
|
# - repo: https://github.com/pre-commit/mirrors-clang-format
|
|
# rev: v20.1.3
|
|
# hooks:
|
|
# - id: clang-format
|
|
# files: ^csrc/.*\.(cpp|hpp|cc|hh|cxx|hxx)$
|
|
# types_or: [c++]
|
|
# args: [--style=google, --verbose]
|
|
- repo: https://github.com/jackdewinter/pymarkdown
|
|
rev: v0.9.29
|
|
hooks:
|
|
- id: pymarkdown
|
|
args: [fix]
|
|
- repo: https://github.com/rhysd/actionlint
|
|
rev: v1.7.7
|
|
hooks:
|
|
- id: actionlint
|
|
- repo: local
|
|
hooks:
|
|
# For local development, you can run mypy using tools/mypy.sh script if needed.
|
|
# - id: mypy-local
|
|
# name: Run mypy for local Python installation
|
|
# entry: tools/mypy.sh 0 "local"
|
|
# language: system
|
|
# types: [python]
|
|
# stages: [pre-commit] # Don't run in CI
|
|
- id: mypy-3.9 # TODO: Use https://github.com/pre-commit/mirrors-mypy when mypy setup is less awkward
|
|
name: Run mypy for Python 3.9
|
|
entry: tools/mypy.sh 1 "3.9"
|
|
# Use system python because vllm installation is required
|
|
language: system
|
|
types: [python]
|
|
stages: [manual] # Only run in CI
|
|
- id: mypy-3.10 # TODO: Use https://github.com/pre-commit/mirrors-mypy when mypy setup is less awkward
|
|
name: Run mypy for Python 3.10
|
|
entry: tools/mypy.sh 1 "3.10"
|
|
# Use system python because vllm installation is required
|
|
language: system
|
|
types: [python]
|
|
stages: [manual] # Only run in CI
|
|
- id: mypy-3.11 # TODO: Use https://github.com/pre-commit/mirrors-mypy when mypy setup is less awkward
|
|
name: Run mypy for Python 3.11
|
|
entry: tools/mypy.sh 1 "3.11"
|
|
# Use system python because vllm installation is required
|
|
language: system
|
|
types: [python]
|
|
stages: [manual] # Only run in CI
|
|
- id: mypy-3.12 # TODO: Use https://github.com/pre-commit/mirrors-mypy when mypy setup is less awkward
|
|
name: Run mypy for Python 3.12
|
|
entry: tools/mypy.sh 1 "3.12"
|
|
# Use system python because vllm installation is required
|
|
language: system
|
|
types: [python]
|
|
stages: [manual] # Only run in CI
|
|
# FIXME: enable shellcheck
|
|
# - id: shellcheck
|
|
# name: Lint shell scripts
|
|
# entry: tools/shellcheck.sh
|
|
# language: script
|
|
# types: [shell]
|
|
- id: png-lint
|
|
name: Lint PNG exports from excalidraw
|
|
entry: tools/png-lint.sh
|
|
language: script
|
|
types: [png]
|
|
- id: signoff-commit
|
|
name: Sign-off Commit
|
|
entry: bash
|
|
args:
|
|
- -c
|
|
- |
|
|
if ! grep -q "^Signed-off-by: $(git config user.name) <$(git config user.email)>" "$(git rev-parse --git-path COMMIT_EDITMSG)"; then
|
|
printf "\nSigned-off-by: $(git config user.name) <$(git config user.email)>\n" >> "$(git rev-parse --git-path COMMIT_EDITMSG)"
|
|
fi
|
|
language: system
|
|
verbose: true
|
|
stages: [commit-msg]
|
|
- id: check-filenames
|
|
name: Check for spaces in all filenames
|
|
entry: bash
|
|
args:
|
|
- -c
|
|
- 'git ls-files | grep " " && echo "Filenames should not contain spaces!" && exit 1 || exit 0'
|
|
language: system
|
|
always_run: true
|
|
pass_filenames: false
|
|
- id: enforce-import-regex-instead-of-re
|
|
name: Enforce import regex as re
|
|
entry: python tools/enforce_regex_import.py
|
|
language: python
|
|
types: [python]
|
|
pass_filenames: false
|
|
additional_dependencies: [regex]
|
|
- id: python-init
|
|
name: Enforce __init__.py in Python packages
|
|
entry: python tools/check_python_src_init.py
|
|
language: python
|
|
types: [python]
|
|
pass_filenames: false
|
|
# Keep `suggestion` last
|
|
- id: suggestion
|
|
name: Suggestion
|
|
entry: bash -c 'echo "To bypass pre-commit hooks, add --no-verify to git commit."'
|
|
language: system
|
|
verbose: true
|
|
pass_filenames: false
|
|
# Insert new entries above the `suggestion` entry
|