Files
flash-attention-prebuild-wh…/.github/workflows/test-self-hosted-linux.yml
T
2025-12-05 02:43:03 +09:00

31 lines
1.0 KiB
YAML

name: Test self-hosted Linux build
on:
workflow_dispatch:
jobs:
# #########################################################
# Build wheels with self-hosted runner
# #########################################################
build_wheels_self_hosted:
name: Build wheels and Upload (Linux x86_64, self-hosted runner)
uses: ./.github/workflows/_build_linux_self_host.yml
strategy:
fail-fast: false
matrix:
flash-attn-version: ["2.8.3"]
python-version: ["3.13", "3.13"]
torch-version: ["2.9.1"]
# https://developer.nvidia.com/cuda-toolkit-archive
cuda-version: ["13.0.1"]
runner: ["openci-runner-beta"]
use-container: [false]
with:
flash-attn-version: ${{ matrix.flash-attn-version }}
python-version: ${{ matrix.python-version }}
torch-version: ${{ matrix.torch-version }}
cuda-version: ${{ matrix.cuda-version }}
is-upload: false
runner: ${{ matrix.runner}}
use-container: ${{ matrix.use-container}}