Files
sglang/.github/workflows/e2e-test.yml
2024-09-01 00:27:25 -07:00

97 lines
2.8 KiB
YAML

name: E2E Test
on:
push:
branches: [ main ]
paths:
- "python/sglang/**"
- "test/**"
pull_request:
branches: [ main ]
paths:
- "python/sglang/**"
- "test/**"
workflow_dispatch:
concurrency:
group: e2e-test-${{ github.ref }}
cancel-in-progress: true
jobs:
one-gpu:
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 Serving Throughput
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_serving_throughput.TestServingThroughput.test_default
- name: Benchmark Serving Latency
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_serving_latency.TestServingLatency.test_default
- name: Benchmark Serving Throughput (w/o RadixAttention)
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_serving_throughput.TestServingThroughput.test_default_without_radix_cache
- name: Benchmark Serving Throughput (w/o ChunkedPrefill)
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_serving_throughput.TestServingThroughput.test_default_without_chunked_prefill
two-gpu:
if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
runs-on: 2-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 Serving Throughput (TP=2)
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_moe_serving_throughput.TestServingThroughput.test_default
- name: Benchmark Serving Latency (TP=2)
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_moe_serving_latency.TestServingLatency.test_default
- name: Benchmark Serving Throughput (w/o RadixAttention) (TP=2)
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_moe_serving_throughput.TestServingThroughput.test_default_without_radix_cache
finish:
needs: [one-gpu, two-gpu]
runs-on: ubuntu-latest
steps:
- name: Finish
run: echo "This is an empty step to ensure that all jobs are completed."