47 lines
1.0 KiB
YAML
47 lines
1.0 KiB
YAML
name: Accuracy Test
|
|
|
|
on:
|
|
push:
|
|
branches: [ main ]
|
|
paths:
|
|
- "python/sglang/**"
|
|
- "test/**"
|
|
pull_request:
|
|
branches: [ main ]
|
|
paths:
|
|
- "python/sglang/**"
|
|
- "test/**"
|
|
workflow_dispatch:
|
|
|
|
concurrency:
|
|
group: accuracy-test-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
accuracy-test:
|
|
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
|
|
runs-on: accuracy
|
|
|
|
steps:
|
|
- name: Checkout code
|
|
uses: actions/checkout@v3
|
|
|
|
- name: Install dependencies
|
|
run: |
|
|
source $HOME/venv/bin/activate
|
|
echo "$HOME/venv/bin" >> $GITHUB_PATH
|
|
|
|
pip install --upgrade pip
|
|
pip install -e "python[all]"
|
|
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
|
|
|
|
git clone https://github.com/merrymercy/human-eval.git
|
|
cd human-eval
|
|
pip install -e .
|
|
|
|
- name: Evaluate Accuracy
|
|
run: |
|
|
cd test/srt
|
|
python3 test_eval_accuracy_large.py
|
|
timeout-minutes: 10
|