Skip to content

Implementation of flash attention for native webgpu ep #1409

Implementation of flash attention for native webgpu ep

Implementation of flash attention for native webgpu ep #1409

Workflow file for this run

# Copyright (c) ONNX Project Contributors
#
# SPDX-License-Identifier: Apache-2.0
name: PR Checks
on:
pull_request:
branches:
- main
permissions: # set top-level default permissions as security best practice
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.event_name == 'workflow_dispatch' }}
cancel-in-progress: true
jobs:
auto-apply-fixes:
name: Suggest fixes
runs-on: ["self-hosted", "1ES.Pool=onnxruntime-github-Ubuntu2204-AMD-CPU"]
permissions:
contents: read
pull-requests: write
steps:
- uses: actions/checkout@v4
- name: Setup Python
uses: actions/setup-python@v5
with:
python-version: "3.10"
- name: Setup Rust
uses: actions-rs/toolchain@v1
with:
toolchain: stable
components: rustfmt
- name: Update PATH
run: |
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
- name: Install dependencies and run lintrunner on all files
run: |
python -m pip install --user -r requirements-dev.txt
python -m pip install --user lintrunner lintrunner-adapters
lintrunner init
set +e
lintrunner f --all-files -v
exit 0
- uses: parkerbxyz/suggest-changes@v2
with:
comment: 'You can commit the suggested changes from lintrunner.'