Enhance the test case for chunked prefill (#1785)

This commit is contained in:
Lianmin Zheng
2024-10-24 21:23:09 -07:00
committed by GitHub
parent 384d85ba35
commit 1701b0db31
6 changed files with 162 additions and 107 deletions

View File

@@ -33,7 +33,7 @@ jobs:
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
- name: Run test
timeout-minutes: 20
timeout-minutes: 10
run: |
cd test/lang
python3 run_suite.py --suite minimal
@@ -73,7 +73,7 @@ jobs:
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
- name: Run test
timeout-minutes: 30
timeout-minutes: 20
run: |
cd test/srt
python3 run_suite.py --suite minimal --range-begin 5 --range-end 17
@@ -93,10 +93,30 @@ jobs:
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
- name: Run test
timeout-minutes: 30
timeout-minutes: 20
run: |
cd test/srt
python3 run_suite.py --suite minimal --range-begin 17
python3 run_suite.py --suite minimal --range-begin 17 --range-end 20
unit-test-backend-part-4:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
runs-on: 1-gpu-runner
steps:
- name: Checkout code
uses: actions/checkout@v3
- name: Install dependencies
run: |
pip install --upgrade pip
pip install -e "python[dev]"
pip install transformers==4.45.2
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
- name: Run test
timeout-minutes: 20
run: |
cd test/srt
python3 run_suite.py --suite minimal --range-begin 20
performance-test-1-gpu-part-1:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
@@ -263,7 +283,7 @@ jobs:
finish:
needs: [
unit-test-frontend, unit-test-backend-part-1, unit-test-backend-part-2, unit-test-backend-part-3,
unit-test-frontend, unit-test-backend-part-1, unit-test-backend-part-2, unit-test-backend-part-3, unit-test-backend-part-4,
performance-test-1-gpu-part-1, performance-test-1-gpu-part-2, performance-test-2-gpu,
accuracy-test-1-gpu, accuracy-test-2-gpu
]