Sampler cudagraph (#1253) #1
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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: | |
e2e-test: | |
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: | | |
python3 -m sglang.bench_latency --model meta-llama/Meta-Llama-3.1-8B-Instruct --batch-size 1 --input 128 --output 8 | |
- 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 |