275 lines
8.6 KiB
YAML
275 lines
8.6 KiB
YAML
name: PR Test
|
|
|
|
on:
|
|
push:
|
|
branches: [ main ]
|
|
paths:
|
|
- "python/sglang/**"
|
|
- "test/**"
|
|
pull_request:
|
|
branches: [ main ]
|
|
paths:
|
|
- "python/sglang/**"
|
|
- "test/**"
|
|
workflow_dispatch:
|
|
|
|
concurrency:
|
|
group: pr-test-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
unit-test-frontend:
|
|
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==4.44
|
|
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
|
|
|
|
- name: Run test
|
|
timeout-minutes: 20
|
|
run: |
|
|
cd test/lang
|
|
python3 run_suite.py --suite minimal
|
|
|
|
unit-test-backend-part-1:
|
|
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==4.44
|
|
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 0 --range-end 7
|
|
|
|
unit-test-backend-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[dev]"
|
|
pip install transformers==4.44
|
|
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 7 --range-end 14
|
|
|
|
unit-test-backend-part-3:
|
|
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==4.44
|
|
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 14
|
|
|
|
performance-test-1-gpu-part-1:
|
|
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 transformers==4.44
|
|
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
|
|
|
|
- name: Benchmark Offline Throughput (Non-streaming, small batch size)
|
|
timeout-minutes: 10
|
|
run: |
|
|
cd test/srt
|
|
python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
|
|
|
|
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 transformers==4.44
|
|
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
|
|
|
|
- name: Benchmark Offline Throughput (w/o RadixAttention)
|
|
timeout-minutes: 10
|
|
run: |
|
|
cd test/srt
|
|
python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_without_radix_cache
|
|
|
|
- name: Benchmark Offline Throughput (w/ Triton)
|
|
timeout-minutes: 10
|
|
run: |
|
|
cd test/srt
|
|
python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend
|
|
|
|
- name: Benchmark Offline Throughput (w/ FP8)
|
|
timeout-minutes: 10
|
|
run: |
|
|
cd test/srt
|
|
python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
|
|
|
|
performance-test-2-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 transformers==4.44
|
|
pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall
|
|
|
|
- name: Benchmark Offline Throughput (TP=2)
|
|
timeout-minutes: 10
|
|
run: |
|
|
cd test/srt
|
|
python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_default
|
|
|
|
- name: Benchmark Offline Throughput (w/o RadixAttention) (TP=2)
|
|
timeout-minutes: 10
|
|
run: |
|
|
cd test/srt
|
|
python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
|
|
|
|
- name: Benchmark Single Latency (TP=2)
|
|
timeout-minutes: 10
|
|
run: |
|
|
cd test/srt
|
|
python3 -m unittest test_bench_latency.TestBenchLatency.test_moe_default
|
|
|
|
accuracy-test-1-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 transformers==4.44
|
|
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
|
|
timeout-minutes: 20
|
|
run: |
|
|
cd test/srt
|
|
python3 test_eval_accuracy_large.py
|
|
|
|
accuracy-test-2-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 transformers==4.44
|
|
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 (TP=2)
|
|
timeout-minutes: 20
|
|
run: |
|
|
cd test/srt
|
|
python3 test_moe_eval_accuracy_large.py
|
|
|
|
- name: Evaluate MLA Accuracy (TP=2)
|
|
timeout-minutes: 10
|
|
run: |
|
|
cd test/srt
|
|
python3 test_mla.py
|
|
python3 test_mla_fp8.py
|
|
|
|
# Temporarily disabled
|
|
#- name: Evaluate Data Parallelism Accuracy (TP=2)
|
|
# timeout-minutes: 10
|
|
# run: |
|
|
# cd test/srt
|
|
# python3 test_data_parallelism.py
|
|
|
|
finish:
|
|
needs: [
|
|
unit-test-frontend, unit-test-backend-part-1, unit-test-backend-part-2, unit-test-backend-part-3,
|
|
performance-test-1-gpu-part-1, performance-test-1-gpu-part-2, performance-test-2-gpu,
|
|
accuracy-test-1-gpu, accuracy-test-2-gpu
|
|
]
|
|
runs-on: ubuntu-latest
|
|
steps:
|
|
- name: Finish
|
|
run: echo "This is an empty step to ensure that all jobs are completed."
|