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

Clean up server_args.py to have a dedicated function for model specific adjustments (#8983)

Browse Source
This commit is contained in:
Lianmin Zheng
2025-08-08 19:56:50 -07:00
committed by GitHub
parent 23f2afb2ce
commit 706bd69cc5
24 changed files with 201 additions and 340 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.github/workflows/execute-notebook.yml vendored
View File

@@ -26,10 +26,7 @@ jobs:
run: |
bash scripts/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

2
.github/workflows/pr-test-pd-router.yml vendored
View File

@@ -1,4 +1,4 @@
name: Test Disaggregation Mode
name: PR Test (PD Router)
on:
push:

74
.github/workflows/pr-test.yml vendored
View File

@@ -61,7 +61,7 @@ jobs:
python3 run_suite.py --suite per-commit
unit-test-backend-1-gpu:
needs: check-changes
needs: [check-changes, unit-test-frontend]
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false &&
needs.check-changes.outputs.src == 'true'
@@ -85,7 +85,7 @@ jobs:
python3 run_suite.py --suite per-commit --auto-partition-id ${{ matrix.part }} --auto-partition-size 10
unit-test-backend-2-gpu:
needs: check-changes
needs: [check-changes, unit-test-frontend]
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false &&
needs.check-changes.outputs.src == 'true'
@@ -105,7 +105,7 @@ jobs:
python3 run_suite.py --suite per-commit-2-gpu
unit-test-backend-4-gpu:
needs: [check-changes, unit-test-frontend, unit-test-backend-2-gpu]
needs: [check-changes, unit-test-backend-2-gpu]
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false &&
needs.check-changes.outputs.src == 'true'
@@ -125,7 +125,7 @@ jobs:
python3 run_suite.py --suite per-commit-4-gpu
unit-test-backend-8-gpu:
needs: [check-changes, unit-test-frontend, unit-test-backend-2-gpu]
needs: [check-changes, unit-test-backend-2-gpu]
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false &&
needs.check-changes.outputs.src == 'true'
@@ -245,7 +245,7 @@ jobs:
python3 -m unittest test_bench_serving.TestBenchServing.test_vlm_online_latency
performance-test-2-gpu:
needs: check-changes
needs: [check-changes, unit-test-backend-2-gpu]
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false &&
needs.check-changes.outputs.src == 'true'
@@ -282,13 +282,13 @@ jobs:
cd test/srt
python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
- name: Benchmark offline decode throughput (PP=2)
- name: Benchmark offline PP decode throughput (PP=2)
timeout-minutes: 10
run: |
cd test/srt
python3 -m unittest test_bench_serving.TestBenchServing.test_pp_offline_throughput_default_decode
- name: Benchmark offline prefill throughput (PP=2)
- name: Benchmark offline PP prefill throughput (PP=2)
timeout-minutes: 10
run: |
cd test/srt
@@ -318,7 +318,7 @@ jobs:
python3 test_eval_accuracy_large.py
accuracy-test-2-gpu:
needs: check-changes
needs: [check-changes, accuracy-test-1-gpu]
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false &&
needs.check-changes.outputs.src == 'true'
@@ -341,7 +341,7 @@ jobs:
python3 test_moe_eval_accuracy_large.py
unit-test-deepep-4-gpu:
needs: check-changes
needs: [check-changes, unit-test-backend-2-gpu]
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false &&
needs.check-changes.outputs.src == 'true'
@@ -361,7 +361,7 @@ jobs:
python3 run_suite.py --suite per-commit-4-gpu-deepep
unit-test-deepep-8-gpu:
needs: [check-changes, unit-test-deepep-4-gpu]
needs: [check-changes, unit-test-backend-2-gpu]
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false &&
needs.check-changes.outputs.src == 'true'
@@ -380,12 +380,38 @@ jobs:
cd test/srt
python3 run_suite.py --suite per-commit-8-gpu-deepep
unit-test-backend-8-gpu-b200:
needs: [check-changes, unit-test-backend-2-gpu]
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false &&
needs.check-changes.outputs.src == 'true'
runs-on: b200-runner
strategy:
fail-fast: false
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
IS_BLACKWELL=1 bash scripts/ci_install_dependency.sh
- name: Run test
timeout-minutes: 20
run: |
cd test/srt
python3 run_suite.py --suite per-commit-8-gpu-b200 --auto-partition-id 0 --auto-partition-size 1
pr-test-finish:
needs: [
check-changes,
unit-test-frontend, unit-test-backend-1-gpu, unit-test-backend-2-gpu, unit-test-backend-4-gpu,
unit-test-backend-8-gpu, performance-test-1-gpu-part-1, performance-test-1-gpu-part-2, performance-test-2-gpu,
accuracy-test-1-gpu, accuracy-test-2-gpu, unit-test-deepep-4-gpu, unit-test-deepep-8-gpu,
unit-test-frontend, unit-test-backend-1-gpu,
unit-test-backend-2-gpu, unit-test-backend-4-gpu, unit-test-backend-8-gpu,
performance-test-1-gpu-part-1, performance-test-1-gpu-part-2, performance-test-2-gpu,
accuracy-test-1-gpu, accuracy-test-2-gpu,
unit-test-deepep-4-gpu, unit-test-deepep-8-gpu,
unit-test-backend-8-gpu-b200,
]
if: needs.check-changes.outputs.src == 'true'
runs-on: ubuntu-latest
@@ -401,25 +427,3 @@ jobs:
done
echo "All jobs completed successfully"
exit 0
unit-test-backend-8-gpu-b200:
needs: [check-changes, unit-test-frontend, unit-test-backend-2-gpu]
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
github.event.pull_request.draft == false &&
needs.check-changes.outputs.src == 'true'
runs-on: b200-runner
strategy:
fail-fast: false
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Install dependencies
run: |
MODE_BLACKWELL=1 bash scripts/ci_install_dependency.sh
- name: Run test
timeout-minutes: 20
run: |
cd test/srt
python3 run_suite.py --suite per-commit-8-gpu-b200 --auto-partition-id 0 --auto-partition-size 1

7
.github/workflows/vllm-dependency-test.yml vendored
View File

@@ -30,11 +30,12 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci_install_dependency.sh
pip install "vllm==0.10.0"
pip install "vllm==0.9.0"
pip install "bitsandbytes>=0.44.0"
pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu126
pip install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu126
pip install "openai==1.99.1"
- name: Run VLLM dependency tests
- name: Run vLLM dependency tests
timeout-minutes: 60
run: |
cd test/srt