minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 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
.github/workflows/nightly-test-nvidia.yml
+33 -33
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