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

ci: unify PR test suite naming (#21187)

Browse Source
This commit is contained in:
Lianmin Zheng
2026-03-23 00:18:45 -07:00
committed by GitHub
parent 3d312643b9
commit 814202704b
283 changed files with 554 additions and 554 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
.github/workflows/pr-test-amd-rocm720.yml vendored
View File

@@ -35,13 +35,13 @@ on:
- ''
- sgl-kernel-unit-test-amd
- sgl-kernel-unit-test-2-gpu-amd
- stage-a-test-small-1-gpu-amd
- stage-a-test-1-gpu-small-amd
- jit-kernel-unit-test-amd
- stage-b-test-small-1-gpu-amd
- stage-b-test-small-1-gpu-amd-nondeterministic
- stage-b-test-small-1-gpu-amd-mi35x
- stage-b-test-large-1-gpu-amd
- stage-b-test-large-2-gpu-amd
- stage-b-test-1-gpu-small-amd
- stage-b-test-1-gpu-small-amd-nondeterministic
- stage-b-test-1-gpu-small-amd-mi35x
- stage-b-test-1-gpu-large-amd
- stage-b-test-2-gpu-large-amd
- multimodal-gen-test-1-gpu-amd
- multimodal-gen-test-2-gpu-amd
- stage-c-test-large-8-gpu-amd
@@ -246,12 +246,12 @@ jobs:
# =============================================== primary ====================================================
stage-a-test-small-1-gpu-amd:
stage-a-test-1-gpu-small-amd:
needs: [check-changes]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-a-test-small-1-gpu-amd,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-a-test-1-gpu-small-amd,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -283,7 +283,7 @@ jobs:
- name: Run test
timeout-minutes: 10
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-small-1-gpu-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-gpu-small-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
jit-kernel-unit-test-amd:
needs: [check-changes]
@@ -323,12 +323,12 @@ jobs:
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout" python3 -m pytest -q python/sglang/jit_kernel/tests/test_store_cache.py
stage-b-test-small-1-gpu-amd:
stage-b-test-1-gpu-small-amd:
needs: [check-changes]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-small-1-gpu-amd,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -360,14 +360,14 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 14 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 14 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-small-1-gpu-amd-nondeterministic:
stage-b-test-1-gpu-small-amd-nondeterministic:
needs: [check-changes]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-small-1-gpu-amd-nondeterministic,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd-nondeterministic,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -398,14 +398,14 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-nondeterministic --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd-nondeterministic --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-small-1-gpu-amd-mi35x:
stage-b-test-1-gpu-small-amd-mi35x:
needs: [check-changes]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-small-1-gpu-amd-mi35x,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd-mi35x,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -436,14 +436,14 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-mi35x ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd-mi35x ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-large-1-gpu-amd:
stage-b-test-1-gpu-large-amd:
needs: [check-changes]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-large-1-gpu-amd,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-large-amd,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -475,14 +475,14 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-large-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-large-2-gpu-amd:
stage-b-test-2-gpu-large-amd:
needs: [check-changes]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-large-2-gpu-amd,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-2-gpu-large-amd,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -514,7 +514,7 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-2-gpu-large-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
multimodal-gen-test-1-gpu-amd:
needs: [check-changes]
@@ -984,13 +984,13 @@ jobs:
multimodal-gen-test-1-gpu-amd,
multimodal-gen-test-2-gpu-amd,
stage-a-test-small-1-gpu-amd,
stage-a-test-1-gpu-small-amd,
jit-kernel-unit-test-amd,
stage-b-test-small-1-gpu-amd,
stage-b-test-small-1-gpu-amd-nondeterministic,
stage-b-test-small-1-gpu-amd-mi35x,
stage-b-test-large-1-gpu-amd,
stage-b-test-large-2-gpu-amd,
stage-b-test-1-gpu-small-amd,
stage-b-test-1-gpu-small-amd-nondeterministic,
stage-b-test-1-gpu-small-amd-mi35x,
stage-b-test-1-gpu-large-amd,
stage-b-test-2-gpu-large-amd,
stage-b-test-large-8-gpu-35x-disaggregation-amd,
stage-c-test-large-8-gpu-amd,
stage-c-test-large-8-gpu-amd-mi35x,

76
.github/workflows/pr-test-amd.yml vendored
View File

@@ -33,13 +33,13 @@ on:
- ''
- sgl-kernel-unit-test-amd
- sgl-kernel-unit-test-2-gpu-amd
- stage-a-test-small-1-gpu-amd
- stage-a-test-1-gpu-small-amd
- jit-kernel-unit-test-amd
- stage-b-test-small-1-gpu-amd
- stage-b-test-small-1-gpu-amd-nondeterministic
- stage-b-test-small-1-gpu-amd-mi35x
- stage-b-test-large-1-gpu-amd
- stage-b-test-large-2-gpu-amd
- stage-b-test-1-gpu-small-amd
- stage-b-test-1-gpu-small-amd-nondeterministic
- stage-b-test-1-gpu-small-amd-mi35x
- stage-b-test-1-gpu-large-amd
- stage-b-test-2-gpu-large-amd
- multimodal-gen-test-1-gpu-amd
- multimodal-gen-test-2-gpu-amd
- stage-c-test-large-8-gpu-amd
@@ -246,12 +246,12 @@ jobs:
# =============================================== primary ====================================================
stage-a-test-small-1-gpu-amd:
stage-a-test-1-gpu-small-amd:
needs: [check-changes]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-a-test-small-1-gpu-amd,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-a-test-1-gpu-small-amd,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -284,7 +284,7 @@ jobs:
- name: Run test
timeout-minutes: 10
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-small-1-gpu-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-gpu-small-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
jit-kernel-unit-test-amd:
needs: [check-changes]
@@ -325,12 +325,12 @@ jobs:
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout" python3 -m pytest -q python/sglang/jit_kernel/tests/test_store_cache.py
stage-b-test-small-1-gpu-amd:
needs: [check-changes, stage-a-test-small-1-gpu-amd]
stage-b-test-1-gpu-small-amd:
needs: [check-changes, stage-a-test-1-gpu-small-amd]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-small-1-gpu-amd,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -363,14 +363,14 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 14 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 14 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-small-1-gpu-amd-nondeterministic:
needs: [check-changes, stage-a-test-small-1-gpu-amd]
stage-b-test-1-gpu-small-amd-nondeterministic:
needs: [check-changes, stage-a-test-1-gpu-small-amd]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-small-1-gpu-amd-nondeterministic,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd-nondeterministic,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -402,14 +402,14 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-nondeterministic --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd-nondeterministic --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-small-1-gpu-amd-mi35x:
needs: [check-changes, stage-a-test-small-1-gpu-amd]
stage-b-test-1-gpu-small-amd-mi35x:
needs: [check-changes, stage-a-test-1-gpu-small-amd]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-small-1-gpu-amd-mi35x,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-small-amd-mi35x,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -441,14 +441,14 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-mi35x ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd-mi35x ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-large-1-gpu-amd:
needs: [check-changes, stage-a-test-small-1-gpu-amd]
stage-b-test-1-gpu-large-amd:
needs: [check-changes, stage-a-test-1-gpu-small-amd]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-large-1-gpu-amd,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-1-gpu-large-amd,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -481,14 +481,14 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-large-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-large-2-gpu-amd:
needs: [check-changes, stage-a-test-small-1-gpu-amd]
stage-b-test-2-gpu-large-amd:
needs: [check-changes, stage-a-test-1-gpu-small-amd]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-large-2-gpu-amd,')) ||
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-b-test-2-gpu-large-amd,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
(!failure() && !cancelled()) &&
@@ -521,7 +521,7 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-2-gpu-large-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
multimodal-gen-test-1-gpu-amd:
needs: [check-changes]
@@ -779,7 +779,7 @@ jobs:
stage-c-test-large-8-gpu-amd:
needs: [check-changes, call-gate, stage-b-test-small-1-gpu-amd, stage-b-test-large-2-gpu-amd]
needs: [check-changes, call-gate, stage-b-test-1-gpu-small-amd, stage-b-test-2-gpu-large-amd]
if: |
always() &&
(
@@ -827,7 +827,7 @@ jobs:
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 3600 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-c-test-large-8-gpu-amd-mi35x:
needs: [check-changes, call-gate, stage-b-test-small-1-gpu-amd, stage-b-test-large-2-gpu-amd]
needs: [check-changes, call-gate, stage-b-test-1-gpu-small-amd, stage-b-test-2-gpu-large-amd]
if: |
always() &&
(
@@ -868,7 +868,7 @@ jobs:
# =============================================== Disaggregation ====================================================
stage-b-test-large-8-gpu-35x-disaggregation-amd:
needs: [check-changes, stage-a-test-small-1-gpu-amd]
needs: [check-changes, stage-a-test-1-gpu-small-amd]
if: |
always() &&
(
@@ -989,13 +989,13 @@ jobs:
multimodal-gen-test-1-gpu-amd,
multimodal-gen-test-2-gpu-amd,
stage-a-test-small-1-gpu-amd,
stage-a-test-1-gpu-small-amd,
jit-kernel-unit-test-amd,
stage-b-test-small-1-gpu-amd,
stage-b-test-small-1-gpu-amd-nondeterministic,
stage-b-test-small-1-gpu-amd-mi35x,
stage-b-test-large-1-gpu-amd,
stage-b-test-large-2-gpu-amd,
stage-b-test-1-gpu-small-amd,
stage-b-test-1-gpu-small-amd-nondeterministic,
stage-b-test-1-gpu-small-amd-mi35x,
stage-b-test-1-gpu-large-amd,
stage-b-test-2-gpu-large-amd,
stage-b-test-large-8-gpu-35x-disaggregation-amd,
stage-c-test-large-8-gpu-amd,
stage-c-test-large-8-gpu-amd-mi35x,

56
.github/workflows/pr-test.yml vendored
View File

@@ -345,7 +345,7 @@ jobs:
id: wait
with:
stage-name: stage-a
jobs: '["stage-a-test-small-1-gpu", "stage-a-cpu-only"]'
jobs: '["stage-a-test-1-gpu-small", "stage-a-test-cpu"]'
max-wait-minutes: '240'
wait-for-stage-b:
@@ -377,9 +377,9 @@ jobs:
stage-name: stage-b
jobs: |
[
{"prefix": "stage-b-test-small-1-gpu", "expected_count": 8},
{"prefix": "stage-b-test-large-1-gpu", "expected_count": 14},
{"prefix": "stage-b-test-large-2-gpu", "expected_count": 4},
{"prefix": "stage-b-test-1-gpu-small", "expected_count": 8},
{"prefix": "stage-b-test-1-gpu-large", "expected_count": 14},
{"prefix": "stage-b-test-2-gpu-large", "expected_count": 4},
{"prefix": "stage-b-test-4-gpu-b200", "expected_count": 1}
]
max-wait-minutes: '480'
@@ -833,12 +833,12 @@ jobs:
# =============================================== primary ====================================================
# Runs on 5090 (32GB, SM120)
stage-a-test-small-1-gpu:
stage-a-test-1-gpu-small:
needs: [check-changes, call-gate, sgl-kernel-build-wheels]
if: |
always() &&
(
(inputs.target_stage == 'stage-a-test-small-1-gpu') ||
(inputs.target_stage == 'stage-a-test-1-gpu-small') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -876,17 +876,17 @@ jobs:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test/
python3 run_suite.py --hw cuda --suite stage-a-test-small-1-gpu $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-a-test-1-gpu-small $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
stage-a-cpu-only:
stage-a-test-cpu:
needs: [check-changes, call-gate]
if: |
always() &&
(
(inputs.target_stage == 'stage-a-cpu-only') ||
(inputs.target_stage == 'stage-a-test-cpu') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -932,15 +932,15 @@ jobs:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test/
python3 run_suite.py --hw cpu --suite stage-a-cpu-only $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cpu --suite stage-a-test-cpu $CONTINUE_ON_ERROR_FLAG
# Runs on 5090 (32GB, SM120)
stage-b-test-small-1-gpu:
stage-b-test-1-gpu-small:
needs: [check-changes, call-gate, wait-for-stage-a, sgl-kernel-build-wheels]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-small-1-gpu') ||
(inputs.target_stage == 'stage-b-test-1-gpu-small') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -988,7 +988,7 @@ jobs:
run: |
source /etc/profile.d/sglang-ci.sh
cd test/
python3 run_suite.py --hw cuda --suite stage-b-test-small-1-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 8 $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-b-test-1-gpu-small --auto-partition-id ${{ matrix.partition }} --auto-partition-size 8 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
@@ -996,12 +996,12 @@ jobs:
artifact-suffix: ${{ matrix.partition }}
# Runs on H100 (80GB, SM90) - tests that don't pass on 5090 (FA3, FP8, high VRAM, etc.)
stage-b-test-large-1-gpu:
stage-b-test-1-gpu-large:
needs: [check-changes, call-gate, wait-for-stage-a, sgl-kernel-build-wheels]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-large-1-gpu') ||
(inputs.target_stage == 'stage-b-test-1-gpu-large') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -1044,19 +1044,19 @@ jobs:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test/
python3 run_suite.py --hw cuda --suite stage-b-test-large-1-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 14 --timeout-per-file 1800 $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-b-test-1-gpu-large --auto-partition-id ${{ matrix.partition }} --auto-partition-size 14 --timeout-per-file 1800 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
with:
artifact-suffix: ${{ matrix.partition }}
stage-b-test-large-2-gpu:
stage-b-test-2-gpu-large:
needs: [check-changes, call-gate, wait-for-stage-a, sgl-kernel-build-wheels]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-large-2-gpu') ||
(inputs.target_stage == 'stage-b-test-2-gpu-large') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -1101,7 +1101,7 @@ jobs:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test/
python3 run_suite.py --hw cuda --suite stage-b-test-large-2-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 4 $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-b-test-2-gpu-large --auto-partition-id ${{ matrix.partition }} --auto-partition-size 4 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
@@ -1502,12 +1502,12 @@ jobs:
with:
artifact-suffix: ${{ matrix.part }}
stage-c-test-deepep-4-gpu:
stage-c-test-deepep-4-gpu-h100:
needs: [check-changes, call-gate, wait-for-stage-b]
if: |
always() &&
(
(inputs.target_stage == 'stage-c-test-deepep-4-gpu') ||
(inputs.target_stage == 'stage-c-test-deepep-4-gpu-h100') ||
(
!inputs.target_stage &&
((github.event_name == 'schedule' || inputs.test_parallel_dispatch == true) || (!failure() && !cancelled())) &&
@@ -1557,7 +1557,7 @@ jobs:
CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
run: |
cd test
python3 run_suite.py --hw cuda --suite stage-c-test-deepep-4-gpu $CONTINUE_ON_ERROR_FLAG
python3 run_suite.py --hw cuda --suite stage-c-test-deepep-4-gpu-h100 $CONTINUE_ON_ERROR_FLAG
- uses: ./.github/actions/upload-cuda-coredumps
if: always()
@@ -1753,16 +1753,16 @@ jobs:
multimodal-gen-test-1-gpu,
multimodal-gen-test-2-gpu,
stage-a-test-small-1-gpu,
stage-a-cpu-only,
stage-b-test-small-1-gpu,
stage-b-test-large-1-gpu,
stage-b-test-large-2-gpu,
stage-a-test-1-gpu-small,
stage-a-test-cpu,
stage-b-test-1-gpu-small,
stage-b-test-1-gpu-large,
stage-b-test-2-gpu-large,
stage-b-test-4-gpu-b200,
stage-c-test-4-gpu-h100,
stage-c-test-8-gpu-h20,
stage-c-test-8-gpu-h200,
stage-c-test-deepep-4-gpu,
stage-c-test-deepep-4-gpu-h100,
stage-c-test-deepep-8-gpu-h200,
stage-c-test-4-gpu-b200,
# stage-c-test-4-gpu-gb200, # Temporarily disabled — no GB200 runner