chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

ci: rename 1/2-gpu-runner labels to 1/2-gpu-h100 (#21008)

Browse Source
This commit is contained in:
Lianmin Zheng
2026-03-20 06:04:15 -07:00
committed by GitHub
parent 104b10f70a
commit 2d7a262ca3
11 changed files with 57 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/ci-coverage-overview.yml vendored
View File

@@ -71,7 +71,7 @@ jobs:
unit-test-coverage:
name: Unit Test Code Coverage
if: github.event_name != 'pull_request'
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
timeout-minutes: 30
steps:
- name: Checkout code

4
.github/workflows/diffusion-ci-gt-gen.yml vendored
View File

@@ -25,7 +25,7 @@ permissions:
jobs:
multimodal-diffusion-gen-1gpu:
if: github.repository == 'sgl-project/sglang'
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
strategy:
matrix:
part: [0, 1]
@@ -59,7 +59,7 @@ jobs:
multimodal-diffusion-gen-2gpu:
if: github.repository == 'sgl-project/sglang'
runs-on: 2-gpu-runner
runs-on: 2-gpu-h100
strategy:
matrix:
part: [0, 1]

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

@@ -28,7 +28,7 @@ jobs:
run-all-notebooks:
needs: [call-gate]
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
if: github.event_name != 'pull_request' || needs.call-gate.result == 'success'
steps:
- name: Checkout code

66
.github/workflows/nightly-test-nvidia.yml vendored
View File

@@ -12,15 +12,15 @@ on:
default: 'all'
options:
- 'all'
- 'nightly-test-general-1-gpu-runner'
- 'nightly-test-general-1-gpu-h100'
- 'nightly-test-general-4-gpu-h100'
- 'nightly-test-general-8-gpu-h200'
- 'nightly-test-general-8-gpu-h20'
- 'nightly-test-general-8-gpu-b200'
- 'nightly-test-text-accuracy-2-gpu-runner'
- 'nightly-test-text-perf-2-gpu-runner'
- 'nightly-test-vlm-accuracy-2-gpu-runner'
- 'nightly-test-vlm-perf-2-gpu-runner'
- 'nightly-test-text-accuracy-2-gpu-h100'
- 'nightly-test-text-perf-2-gpu-h100'
- 'nightly-test-vlm-accuracy-2-gpu-h100'
- 'nightly-test-vlm-perf-2-gpu-h100'
- 'nightly-test-multimodal-server-1-gpu'
- 'nightly-test-multimodal-server-2-gpu'
- 'nightly-test-perf-4-gpu-b200'
@@ -50,9 +50,9 @@ env:
jobs:
# General tests - 1 GPU
nightly-test-general-1-gpu-runner:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-1-gpu-runner')
runs-on: 1-gpu-runner
nightly-test-general-1-gpu-h100:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-1-gpu-h100')
runs-on: 1-gpu-h100
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -280,9 +280,9 @@ jobs:
artifact-suffix: ${{ matrix.partition }}
# Text model accuracy tests
nightly-test-text-accuracy-2-gpu-runner:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-text-accuracy-2-gpu-runner')
runs-on: 2-gpu-runner
nightly-test-text-accuracy-2-gpu-h100:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-text-accuracy-2-gpu-h100')
runs-on: 2-gpu-h100
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -303,9 +303,9 @@ jobs:
if: always()
# Text model performance tests
nightly-test-text-perf-2-gpu-runner:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-text-perf-2-gpu-runner')
runs-on: 2-gpu-runner
nightly-test-text-perf-2-gpu-h100:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-text-perf-2-gpu-h100')
runs-on: 2-gpu-h100
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -321,7 +321,7 @@ jobs:
env:
TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
GPU_CONFIG: "2-gpu-runner"
GPU_CONFIG: "2-gpu-h100"
run: |
cd test
rm -rf performance_profiles_text_models/
@@ -339,9 +339,9 @@ jobs:
if: always()
# VLM accuracy tests
nightly-test-vlm-accuracy-2-gpu-runner:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-vlm-accuracy-2-gpu-runner')
runs-on: 2-gpu-runner
nightly-test-vlm-accuracy-2-gpu-h100:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-vlm-accuracy-2-gpu-h100')
runs-on: 2-gpu-h100
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -362,9 +362,9 @@ jobs:
if: always()
# VLM performance tests
nightly-test-vlm-perf-2-gpu-runner:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-vlm-perf-2-gpu-runner')
runs-on: 2-gpu-runner
nightly-test-vlm-perf-2-gpu-h100:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-vlm-perf-2-gpu-h100')
runs-on: 2-gpu-h100
steps:
- name: Checkout code
uses: actions/checkout@v4
@@ -380,7 +380,7 @@ jobs:
env:
TRACE_BASE_URL: https://raw.githubusercontent.com/sglang-bot/sglang-ci-data/main/traces/${{ github.run_id }}
PERFETTO_RELAY_URL: ${{ vars.PERFETTO_RELAY_URL }}
GPU_CONFIG: "2-gpu-runner"
GPU_CONFIG: "2-gpu-h100"
run: |
cd test
rm -rf performance_profiles_vlms/
@@ -400,7 +400,7 @@ jobs:
# diffusion performance tests
nightly-test-multimodal-server-1-gpu:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-multimodal-server-1-gpu')
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
strategy:
fail-fast: false
max-parallel: 5
@@ -421,7 +421,7 @@ jobs:
env:
SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
GITHUB_RUN_ID: ${{ github.run_id }}
GPU_CONFIG: "1-gpu-runner"
GPU_CONFIG: "1-gpu-h100"
timeout-minutes: 60
run: |
@@ -435,7 +435,7 @@ jobs:
if: always()
run: |
python3 scripts/ci/utils/save_diffusion_metrics.py \
--gpu-config 1-gpu-runner \
--gpu-config 1-gpu-h100 \
--run-id ${{ github.run_id }} \
--output python/diffusion-metrics-1gpu-partition-${{ matrix.part }}.json \
--results-json python/diffusion-results.json
@@ -456,7 +456,7 @@ jobs:
nightly-test-multimodal-server-2-gpu:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-multimodal-server-2-gpu')
runs-on: 2-gpu-runner
runs-on: 2-gpu-h100
strategy:
fail-fast: false
max-parallel: 5
@@ -477,7 +477,7 @@ jobs:
env:
SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
GITHUB_RUN_ID: ${{ github.run_id }}
GPU_CONFIG: "2-gpu-runner"
GPU_CONFIG: "2-gpu-h100"
timeout-minutes: 60
run: |
@@ -491,7 +491,7 @@ jobs:
if: always()
run: |
python3 scripts/ci/utils/save_diffusion_metrics.py \
--gpu-config 2-gpu-runner \
--gpu-config 2-gpu-h100 \
--run-id ${{ github.run_id }} \
--output python/diffusion-metrics-2gpu-partition-${{ matrix.part }}.json \
--results-json python/diffusion-results.json
@@ -608,15 +608,15 @@ jobs:
check-all-jobs:
if: github.repository == 'sgl-project/sglang' && always()
needs:
- nightly-test-general-1-gpu-runner
- nightly-test-general-1-gpu-h100
- nightly-test-general-4-gpu-h100
- nightly-test-general-8-gpu-h200
- nightly-test-general-8-gpu-h20
- nightly-test-general-8-gpu-b200
- nightly-test-text-accuracy-2-gpu-runner
- nightly-test-text-perf-2-gpu-runner
- nightly-test-vlm-accuracy-2-gpu-runner
- nightly-test-vlm-perf-2-gpu-runner
- nightly-test-text-accuracy-2-gpu-h100
- nightly-test-text-perf-2-gpu-h100
- nightly-test-vlm-accuracy-2-gpu-h100
- nightly-test-vlm-perf-2-gpu-h100
- nightly-test-multimodal-server-1-gpu
- nightly-test-multimodal-server-2-gpu
- nightly-test-perf-4-gpu-b200

22
.github/workflows/pr-test.yml vendored
View File

@@ -493,7 +493,7 @@ jobs:
inputs.test_parallel_dispatch != true &&
!inputs.target_stage &&
needs.check-changes.outputs.sgl_kernel == 'true'
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
timeout-minutes: 240
steps:
- uses: actions/checkout@v4
@@ -531,7 +531,7 @@ jobs:
inputs.test_parallel_dispatch != true &&
!inputs.target_stage &&
needs.check-changes.outputs.sgl_kernel == 'true'
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
timeout-minutes: 240
steps:
- uses: actions/checkout@v4
@@ -569,7 +569,7 @@ jobs:
inputs.test_parallel_dispatch != true &&
!inputs.target_stage &&
needs.check-changes.outputs.sgl_kernel == 'true'
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
timeout-minutes: 240
env:
CI: true
@@ -692,7 +692,7 @@ jobs:
inputs.test_parallel_dispatch != true &&
!inputs.target_stage &&
needs.check-changes.outputs.jit_kernel == 'true'
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
timeout-minutes: 240
steps:
- uses: actions/checkout@v4
@@ -715,7 +715,7 @@ jobs:
if: |
github.event_name == 'schedule' &&
needs.check-changes.outputs.jit_kernel == 'true'
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
timeout-minutes: 240
env:
SGLANG_JIT_KERNEL_RUN_FULL_TESTS: "1"
@@ -743,7 +743,7 @@ jobs:
inputs.test_parallel_dispatch != true &&
!inputs.target_stage &&
needs.check-changes.outputs.jit_kernel == 'true'
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
timeout-minutes: 240
env:
CI: true
@@ -945,7 +945,7 @@ jobs:
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
timeout-minutes: 240
strategy:
fail-fast: false
@@ -996,7 +996,7 @@ jobs:
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
runs-on: 2-gpu-runner
runs-on: 2-gpu-h100
timeout-minutes: 240
strategy:
fail-fast: false
@@ -1101,7 +1101,7 @@ jobs:
needs.check-changes.outputs.multimodal_gen == 'true'
)
)
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
timeout-minutes: 240
strategy:
fail-fast: false
@@ -1155,7 +1155,7 @@ jobs:
needs.check-changes.outputs.multimodal_gen == 'true'
)
)
runs-on: 2-gpu-runner
runs-on: 2-gpu-h100
timeout-minutes: 240
strategy:
fail-fast: false
@@ -1210,7 +1210,7 @@ jobs:
needs.check-changes.outputs.multimodal_gen == 'true'
)
)
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
timeout-minutes: 120
steps:
- name: Checkout code

2
.github/workflows/release-docs.yml vendored
View File

@@ -21,7 +21,7 @@ env:
jobs:
execute-and-deploy:
runs-on: 1-gpu-runner
runs-on: 1-gpu-h100
if: github.repository == 'sgl-project/sglang'
steps:
- name: Checkout code

4
.github/workflows/rerun-ut.yml vendored
View File

@@ -13,9 +13,9 @@ on:
required: true
type: choice
options:
- 1-gpu-runner
- 1-gpu-h100
- 1-gpu-5090
- 2-gpu-runner
- 2-gpu-h100
- 4-gpu-h100
- 4-gpu-a10
- 4-gpu-b200

2
docs/developer_guide/setup_github_runner.md
View File

@@ -31,7 +31,7 @@ Then follow https://github.com/sgl-project/sglang/settings/actions/runners/new?a
**Notes**
- Do not need to specify the runner group
- Give it a name (e.g., `test-sgl-gpu-0`) and some labels (e.g., `1-gpu-runner`). The labels can be edited later in Github Settings.
- Give it a name (e.g., `test-sgl-gpu-0`) and some labels (e.g., `1-gpu-h100`). The labels can be edited later in Github Settings.
- Do not need to change the work folder.
### Step 3: Run the runner by `run.sh`

4
scripts/ci/utils/save_diffusion_metrics.py
View File

@@ -6,7 +6,7 @@ with metadata for the performance dashboard.
Usage:
python3 scripts/ci/utils/save_diffusion_metrics.py \
--gpu-config 1-gpu-runner \
--gpu-config 1-gpu-h100 \
--run-id 12345678 \
--output test/diffusion-metrics-1gpu.json \
--results-json test/diffusion-results.json
@@ -129,7 +129,7 @@ def main():
parser.add_argument(
"--gpu-config",
required=True,
help="GPU configuration (e.g., 1-gpu-runner, 2-gpu-runner)",
help="GPU configuration (e.g., 1-gpu-h100, 2-gpu-h100)",
)
parser.add_argument(
"--run-id",

4
scripts/ci/utils/slash_command_handler.py
View File

@@ -416,8 +416,8 @@ CUDA_SUITE_TO_RUNNER = {
"stage-a-test-small-1-gpu": "1-gpu-5090",
"stage-a-cpu-only": "ubuntu-latest",
"stage-b-test-small-1-gpu": "1-gpu-5090",
"stage-b-test-large-1-gpu": "1-gpu-runner",
"stage-b-test-large-2-gpu": "2-gpu-runner",
"stage-b-test-large-1-gpu": "1-gpu-h100",
"stage-b-test-large-2-gpu": "2-gpu-h100",
"stage-b-test-4-gpu-b200": "4-gpu-b200",
"stage-c-test-4-gpu-h100": "4-gpu-h100",
"stage-c-test-8-gpu-h200": "8-gpu-h200",

2
test/README.md
View File

@@ -75,7 +75,7 @@ When adding 1-GPU tests, choose the appropriate suite based on hardware compatib
| `stage-a-test-small-1-gpu` | `1-gpu-5090` | RTX 5090 (32GB, SM120) | Stage A per-commit smoke on 5090 (CUDA) |
| `stage-a-test-small-1-gpu-amd` | AMD CI runners | ROCm | Stage A per-commit smoke (AMD) |
| `stage-b-test-small-1-gpu` | `1-gpu-5090` | RTX 5090 (32GB, SM120) | 5090-compatible tests (preferred) |
| `stage-b-test-large-1-gpu` | `1-gpu-runner` | H100 (80GB, SM90) | Large models or 5090-incompatible tests |
| `stage-b-test-large-1-gpu` | `1-gpu-h100` | H100 (80GB, SM90) | Large models or 5090-incompatible tests |
**Use `stage-b-test-small-1-gpu` (5090) whenever possible** - this is the preferred suite for most 1-GPU tests.