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

Reorganize CI and test files (#9027)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-08-10 12:30:06 -07:00
committed by GitHub
parent b58ae7a2a0
commit 2c7f01bc89
66 changed files with 161 additions and 195 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/execute-notebook.yml vendored
View File

@@ -24,7 +24,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
pip install -r docs/requirements.txt
apt-get update && apt-get install -y pandoc parallel retry
ln -sf "$(which python3)" /usr/bin/python

2
.github/workflows/experiment-runner.yml vendored
View File

@@ -21,7 +21,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
- name: Test experiment runner
timeout-minutes: 120

6
.github/workflows/nightly-test-amd.yml vendored
View File

@@ -28,14 +28,14 @@ jobs:
- name: Setup docker
run: |
touch github_summary.md
bash scripts/amd_ci_start_container.sh
bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Nightly Test
run: |
bash scripts/amd_ci_exec.sh -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" python3 run_suite.py --suite nightly-amd --timeout-per-file 7200
bash scripts/ci/amd_ci_exec.sh -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" python3 run_suite.py --suite nightly-amd --timeout-per-file 7200
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY

2
.github/workflows/nightly-test.yml vendored
View File

@@ -24,7 +24,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 120

4
.github/workflows/pr-benchmark-rust.yml vendored
View File

@@ -31,7 +31,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_rust.sh
bash scripts/ci/ci_install_rust.sh
- name: Cache Rust dependencies
uses: actions/cache@v4
@@ -78,7 +78,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_rust.sh
bash scripts/ci/ci_install_rust.sh
- name: Cache Rust dependencies
uses: actions/cache@v4

84
.github/workflows/pr-test-amd.yml vendored
View File

@@ -36,19 +36,19 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Evaluate Accuracy
timeout-minutes: 30
run: |
bash scripts/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
bash scripts/amd_ci_exec.sh python3 test_eval_fp8_accuracy.py
bash scripts/amd_ci_exec.sh python3 models/test_qwen_models.py
bash scripts/ci/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_eval_accuracy_large.py
bash scripts/ci/amd_ci_exec.sh python3 test_eval_fp8_accuracy.py
bash scripts/ci/amd_ci_exec.sh python3 models/test_qwen_models.py
accuracy-test-2-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -62,17 +62,17 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Evaluate accuracy (TP=2)
timeout-minutes: 30
run: |
bash scripts/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_moe_eval_accuracy_large.py
bash scripts/ci/amd_ci_exec.sh -e SGLANG_USE_AITER=0 python3 test_moe_eval_accuracy_large.py
mla-test-1-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -86,17 +86,17 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: MLA TEST
timeout-minutes: 30
run: |
bash scripts/amd_ci_exec.sh python3 test_mla.py
bash scripts/ci/amd_ci_exec.sh python3 test_mla.py
performance-test-1-gpu-part-1-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -110,33 +110,33 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Benchmark single latency
timeout-minutes: 20
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_small
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_default
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_small
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_bs1_default
- name: Benchmark online latency
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_default
- name: Benchmark offline throughput
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default
- name: Benchmark offline throughput (Non-streaming, small batch size)
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_non_stream_small_batch_size
performance-test-1-gpu-part-2-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -150,27 +150,27 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Benchmark offline throughput (w/o RadixAttention)
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_without_radix_cache
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_without_radix_cache
- name: Benchmark offline throughput (w/ Triton)
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_with_triton_attention_backend
- name: Benchmark offline throughput (w/ FP8)
timeout-minutes: 15
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
bench-test-2-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -184,37 +184,37 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Benchmark dummy grok (TP=2)
timeout-minutes: 30
run: |
bash scripts/amd_ci_exec.sh python3 models/test_dummy_grok_models.py
bash scripts/ci/amd_ci_exec.sh python3 models/test_dummy_grok_models.py
- name: Benchmark single latency (TP=2)
timeout-minutes: 25
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_moe_tp2_bs1
- name: Benchmark single latency + torch.compile (TP=2)
timeout-minutes: 25
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_torch_compile_tp2_bs1
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_one_batch.TestBenchOneBatch.test_torch_compile_tp2_bs1
- name: Benchmark offline throughput (TP=2)
timeout-minutes: 25
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_default
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_default
- name: Benchmark offline throughput (w/o RadixAttention) (TP=2)
timeout-minutes: 25
run: |
bash scripts/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
bash scripts/ci/amd_ci_exec.sh python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
unit-test-backend-1-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -230,17 +230,17 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 50
run: |
bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 7
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 7
unit-test-backend-2-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -254,17 +254,17 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 40
run: |
bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-2-gpu-amd
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-2-gpu-amd
unit-test-backend-8-gpu-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -278,22 +278,22 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/amd_ci_install_dependency.sh
run: bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 60
run: |
bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-8-gpu-amd --timeout-per-file 3600
bash scripts/ci/amd_ci_exec.sh python3 run_suite.py --suite per-commit-8-gpu-amd --timeout-per-file 3600
- name: Run CustomAllReduce test
timeout-minutes: 20
run: |
bash scripts/amd_ci_exec.sh -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 -m unittest test_custom_allreduce.TestCustomAllReduce
bash scripts/ci/amd_ci_exec.sh -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 -m unittest test_custom_allreduce.TestCustomAllReduce
unit-test-sgl-kernel-amd:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
@@ -308,13 +308,13 @@ jobs:
uses: actions/checkout@v4
- name: Start CI container
run: bash scripts/amd_ci_start_container.sh
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/amd_ci_install_dependency.sh
bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 10

6
.github/workflows/pr-test-npu.yml vendored
View File

@@ -34,7 +34,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/npu_ci_install_dependency.sh
bash scripts/ci/npu_ci_install_dependency.sh
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
@@ -63,7 +63,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/npu_ci_install_dependency.sh
bash scripts/ci/npu_ci_install_dependency.sh
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy
@@ -92,7 +92,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/npu_ci_install_dependency.sh
bash scripts/ci/npu_ci_install_dependency.sh
# copy required file from our daily cache
cp ~/.cache/modelscope/hub/datasets/otavia/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json /tmp
# copy download through proxy

8
.github/workflows/pr-test-pd-router.yml vendored
View File

@@ -5,13 +5,13 @@ on:
branches: [ main ]
paths:
- 'python/sglang/srt/disaggregation/**'
- 'scripts/ci_start_disaggregation_servers.sh'
- 'scripts/ci/ci_start_disaggregation_servers.sh'
- 'sgl-router/**'
pull_request:
branches: [ main ]
paths:
- 'python/sglang/srt/disaggregation/**'
- 'scripts/ci_start_disaggregation_servers.sh'
- 'scripts/ci/ci_start_disaggregation_servers.sh'
- 'sgl-router/**'
workflow_dispatch:
@@ -44,7 +44,7 @@ jobs:
- name: Setup Rust
run: |
bash scripts/ci_install_rust.sh
bash scripts/ci/ci_install_rust.sh
- name: Cache Rust dependencies
uses: actions/cache@v4
@@ -132,7 +132,7 @@ jobs:
id: start_servers
run: |
echo "Starting disaggregation servers..."
bash scripts/ci_start_disaggregation_servers.sh &
bash scripts/ci/ci_start_disaggregation_servers.sh &
SERVER_PID=$!
echo "server_pid=$SERVER_PID" >> $GITHUB_OUTPUT

4
.github/workflows/pr-test-rust.yml vendored
View File

@@ -25,7 +25,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_rust.sh
bash scripts/ci/ci_install_rust.sh
- name: Run fmt
run: |
@@ -64,7 +64,7 @@ jobs:
- name: Install rust dependencies
run: |
bash scripts/ci_install_rust.sh
bash scripts/ci/ci_install_rust.sh
- name: Build python binding
run: |

4
.github/workflows/pr-test-sgl-kernel.yml vendored
View File

@@ -84,7 +84,7 @@ jobs:
- name: Install
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu126 && pip3 install pytest
pip3 uninstall sgl-kernel -y || true
pip3 install sgl-kernel/dist/*whl --force-reinstall --no-deps
@@ -116,7 +116,7 @@ jobs:
- name: Install
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu126
pip3 uninstall sgl-kernel -y || true
pip3 install sgl-kernel/dist/*whl --force-reinstall --no-deps

26
.github/workflows/pr-test.yml vendored
View File

@@ -52,7 +52,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 10
@@ -76,7 +76,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
@@ -96,7 +96,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 30
@@ -120,7 +120,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 20
@@ -144,7 +144,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 20
@@ -164,7 +164,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
- name: Benchmark single latency
timeout-minutes: 10
@@ -216,7 +216,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
- name: Benchmark offline throughput (w/o RadixAttention)
timeout-minutes: 10
@@ -260,7 +260,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
- name: Benchmark single latency (TP=2)
timeout-minutes: 10
@@ -310,7 +310,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
git clone https://github.com/merrymercy/human-eval.git
cd human-eval
pip install -e .
@@ -333,7 +333,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
git clone https://github.com/merrymercy/human-eval.git
cd human-eval
pip install -e .
@@ -356,7 +356,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_deepep.sh
bash scripts/ci/ci_install_deepep.sh
- name: Run test
timeout-minutes: 20
@@ -376,7 +376,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_deepep.sh
bash scripts/ci/ci_install_deepep.sh
- name: Run test
timeout-minutes: 20
@@ -398,7 +398,7 @@ jobs:
- name: Install dependencies
run: |
IS_BLACKWELL=1 bash scripts/ci_install_dependency.sh
IS_BLACKWELL=1 bash scripts/ci/ci_install_dependency.sh
- name: Run test
timeout-minutes: 20

17
.github/workflows/release-docs.yml vendored
View File

@@ -24,29 +24,28 @@ jobs:
- name: Install dependencies
run: |
find /public_sglang_ci/runner-a-gpu-1/_work/_tool/Python/3.10.13/x64/lib/python3.10/site-packages -name "sgl-kernel*" -exec rm -rf {} + || true
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
pip install -r docs/requirements.txt
apt-get update
apt-get install -y pandoc
apt-get update && apt-get install -y parallel retry
apt-get update && apt-get install -y pandoc parallel retry
ln -sf "$(which python3)" /usr/bin/python
- name: Setup Jupyter Kernel
run: |
python -m ipykernel install --user --name python3 --display-name "Python 3"
- name: Execute notebooks and push to documents
env:
GITHUB_TOKEN: ${{ secrets.DOCUMENTATION_PAT_TOKEN }}
- name: Execute notebooks
timeout-minutes: 40
run: |
cd docs
make clean
make compile
- name: Push HTML to sgl-project.github.io
run: |
cd docs
make html
python3 wrap_run_llm.py
cd _build/html
git clone https://$GITHUB_TOKEN@github.com/sgl-project/sgl-project.github.io.git ../sgl-project.github.io --depth 1

2
.github/workflows/vllm-dependency-test.yml vendored
View File

@@ -29,7 +29,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
bash scripts/ci/ci_install_dependency.sh
pip install "vllm==0.10.0"
pip install "openai==1.99.1"
pip install "bitsandbytes>=0.44.0"