[CI] Fix nightly NV jobs cancelling each other via shared concurrency groups (#24282)

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kangyan-Zhou
2026-05-02 21:53:03 -07:00
committed by GitHub
co-authored by Claude Opus 4.7
parent 76b9c8de6f
commit 266d994368
-48
View File
@@ -57,9 +57,6 @@ jobs:
nightly-test-general-1-gpu-h100: 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') 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 runs-on: 1-gpu-h100
concurrency:
group: nightly-hw-h100
cancel-in-progress: false
steps: steps:
- name: Checkout code - name: Checkout code
uses: actions/checkout@v4 uses: actions/checkout@v4
@@ -87,9 +84,6 @@ jobs:
nightly-test-kernel-1-gpu-h100: nightly-test-kernel-1-gpu-h100:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-kernel-1-gpu-h100') if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-kernel-1-gpu-h100')
runs-on: 1-gpu-h100 runs-on: 1-gpu-h100
concurrency:
group: nightly-hw-h100
cancel-in-progress: false
timeout-minutes: 60 timeout-minutes: 60
env: env:
# Full jit_kernel test grids (see sglang.jit_kernel.utils.should_run_full_tests) # Full jit_kernel test grids (see sglang.jit_kernel.utils.should_run_full_tests)
@@ -123,9 +117,6 @@ jobs:
nightly-test-kernel-8-gpu-h200: nightly-test-kernel-8-gpu-h200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-kernel-8-gpu-h200') if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-kernel-8-gpu-h200')
runs-on: 8-gpu-h200 runs-on: 8-gpu-h200
concurrency:
group: nightly-hw-h200
cancel-in-progress: false
timeout-minutes: 240 timeout-minutes: 240
env: env:
SGLANG_JIT_KERNEL_RUN_FULL_TESTS: "1" SGLANG_JIT_KERNEL_RUN_FULL_TESTS: "1"
@@ -157,9 +148,6 @@ jobs:
nightly-test-general-4-gpu-h100: nightly-test-general-4-gpu-h100:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-4-gpu-h100') if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-4-gpu-h100')
runs-on: 4-gpu-h100 runs-on: 4-gpu-h100
concurrency:
group: nightly-hw-h100
cancel-in-progress: false
steps: steps:
- name: Checkout code - name: Checkout code
uses: actions/checkout@v4 uses: actions/checkout@v4
@@ -185,9 +173,6 @@ jobs:
nightly-test-general-8-gpu-h200: nightly-test-general-8-gpu-h200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-h200') if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-h200')
runs-on: 8-gpu-h200 runs-on: 8-gpu-h200
concurrency:
group: nightly-hw-h200
cancel-in-progress: false
strategy: strategy:
fail-fast: false fail-fast: false
max-parallel: 2 max-parallel: 2
@@ -275,9 +260,6 @@ jobs:
nightly-test-general-8-gpu-h20: nightly-test-general-8-gpu-h20:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-h20') if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-h20')
runs-on: 8-gpu-h20 runs-on: 8-gpu-h20
concurrency:
group: nightly-hw-h20
cancel-in-progress: false
env: env:
SGLANG_CI_RDMA_ALL_DEVICES: "mlx5_1,mlx5_2,mlx5_3,mlx5_4" SGLANG_CI_RDMA_ALL_DEVICES: "mlx5_1,mlx5_2,mlx5_3,mlx5_4"
steps: steps:
@@ -307,9 +289,6 @@ jobs:
nightly-test-general-8-gpu-b200: nightly-test-general-8-gpu-b200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-b200') if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-general-8-gpu-b200')
runs-on: 8-gpu-b200 runs-on: 8-gpu-b200
concurrency:
group: nightly-hw-b200
cancel-in-progress: false
strategy: strategy:
fail-fast: false fail-fast: false
max-parallel: 2 max-parallel: 2
@@ -386,9 +365,6 @@ jobs:
nightly-test-text-accuracy-2-gpu-h100: 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') 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 runs-on: 2-gpu-h100
concurrency:
group: nightly-hw-h100
cancel-in-progress: false
steps: steps:
- name: Checkout code - name: Checkout code
uses: actions/checkout@v4 uses: actions/checkout@v4
@@ -414,9 +390,6 @@ jobs:
nightly-test-text-perf-2-gpu-h100: 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') 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 runs-on: 2-gpu-h100
concurrency:
group: nightly-hw-h100
cancel-in-progress: false
steps: steps:
- name: Checkout code - name: Checkout code
uses: actions/checkout@v4 uses: actions/checkout@v4
@@ -455,9 +428,6 @@ jobs:
nightly-test-vlm-accuracy-2-gpu-h100: 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') 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 runs-on: 2-gpu-h100
concurrency:
group: nightly-hw-h100
cancel-in-progress: false
steps: steps:
- name: Checkout code - name: Checkout code
uses: actions/checkout@v4 uses: actions/checkout@v4
@@ -483,9 +453,6 @@ jobs:
nightly-test-vlm-perf-2-gpu-h100: 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') 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 runs-on: 2-gpu-h100
concurrency:
group: nightly-hw-h100
cancel-in-progress: false
steps: steps:
- name: Checkout code - name: Checkout code
uses: actions/checkout@v4 uses: actions/checkout@v4
@@ -524,9 +491,6 @@ jobs:
nightly-test-multimodal-server-1-gpu: 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') 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-h100 runs-on: 1-gpu-h100
concurrency:
group: nightly-hw-h100
cancel-in-progress: false
strategy: strategy:
fail-fast: false fail-fast: false
max-parallel: 2 max-parallel: 2
@@ -585,9 +549,6 @@ jobs:
nightly-test-multimodal-server-2-gpu: 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') 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-h100 runs-on: 2-gpu-h100
concurrency:
group: nightly-hw-h100
cancel-in-progress: false
strategy: strategy:
fail-fast: false fail-fast: false
max-parallel: 2 max-parallel: 2
@@ -647,9 +608,6 @@ jobs:
nightly-test-perf-4-gpu-b200: nightly-test-perf-4-gpu-b200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-4-gpu-b200') if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-4-gpu-b200')
runs-on: 4-gpu-b200 runs-on: 4-gpu-b200
concurrency:
group: nightly-hw-b200
cancel-in-progress: false
steps: steps:
- name: Checkout code - name: Checkout code
uses: actions/checkout@v4 uses: actions/checkout@v4
@@ -675,9 +633,6 @@ jobs:
nightly-test-specialized-8-gpu-b200: nightly-test-specialized-8-gpu-b200:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-8-gpu-b200' || inputs.job_filter == 'nightly-test-specialized-8-gpu-b200') if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-perf-8-gpu-b200' || inputs.job_filter == 'nightly-test-specialized-8-gpu-b200')
runs-on: 8-gpu-b200 runs-on: 8-gpu-b200
concurrency:
group: nightly-hw-b200
cancel-in-progress: false
env: env:
RUNNER_LABELS: 8-gpu-b200 RUNNER_LABELS: 8-gpu-b200
steps: steps:
@@ -707,9 +662,6 @@ jobs:
nightly-test-diffusion-comparison: nightly-test-diffusion-comparison:
if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-diffusion-comparison') if: github.repository == 'sgl-project/sglang' && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-test-diffusion-comparison')
runs-on: 4-gpu-h100 runs-on: 4-gpu-h100
concurrency:
group: nightly-hw-h100
cancel-in-progress: false
timeout-minutes: 300 timeout-minutes: 300
steps: steps:
- name: Checkout code - name: Checkout code