EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Balance test in CI (#1411)

Browse Source
This commit is contained in:
Lianmin Zheng
2024-09-12 23:29:44 -07:00
committed by GitHub
parent 9a903a8784
commit ad0ff62a4c
3 changed files with 27 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
.github/workflows/pr-test.yml vendored
View File

@@ -88,12 +88,37 @@ jobs:
pip install -e "python[all]"
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
- name: Benchmark Single Latency
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_bench_latency.TestBenchLatency.test_default
- name: Benchmark Online Latency
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default
- name: Benchmark Offline Throughput
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default
performance-test-1-gpu-part-2:
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[all]"
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
- name: Benchmark Offline Throughput (w/o RadixAttention)
timeout-minutes: 10
run: |
@@ -112,31 +137,6 @@ jobs:
cd test/srt
python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend
performance-test-1-gpu-part-2:
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[all]"
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
- name: Benchmark Single Latency
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_bench_latency.TestBenchLatency.test_default
- name: Benchmark Online Latency
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default
performance-test-2-gpu:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
runs-on: 2-gpu-runner