minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Revert "ci: add 4-GPU mi35x runner and rebalance off the saturated 8-GPU pool" (#28751)

Browse Source
This commit is contained in:
Michael
2026-06-19 16:23:18 -07:00
committed by GitHub
parent 6b945c16f4
commit 871ed0dc0c
6 changed files with 14 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test-amd.yml
+2 -47
View File
@@ -35,7 +35,6 @@ on:
- multimodal-gen-test-1-gpu-amd
- multimodal-gen-test-2-gpu-amd
- stage-c-test-4-gpu-amd
- stage-c-test-4-gpu-amd-mi35x
- stage-c-test-large-8-gpu-amd
- stage-c-test-large-8-gpu-amd-mi35x
- stage-b-test-large-8-gpu-mi35x-disaggregation-amd
@@ -1037,50 +1036,7 @@ jobs:
fail-fast: false
matrix:
runner: [linux-mi35x-gpu-8]
part: [0]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 120
run: |
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-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 1 --timeout-per-file 3600 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
# MI35x stage-c tests that only need 4 GPUs (e.g. DeepSeek-R1-MXFP4 TP=4).
# Split off the 8-GPU mi35x suite so they no longer hold a whole 8-GPU node
# and instead run on the dedicated 4-GPU mi35x slice.
stage-c-test-4-gpu-amd-mi35x:
needs: [check-changes, call-gate, wait-for-stage-b-amd]
if: |
always() &&
(
(contains(format(',{0},', inputs.target_stage || inputs.target_stage_select), ',stage-c-test-4-gpu-amd-mi35x,')) ||
(
!(inputs.target_stage || inputs.target_stage_select) &&
((github.event_name == 'schedule') || (!failure() && !cancelled())) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi35x-gpu-4]
part: [0]
part: [0, 1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -1102,7 +1058,7 @@ jobs:
- name: Run test
timeout-minutes: 60
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-4-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 1 --timeout-per-file 3600 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
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-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
# =============================================== Disaggregation ====================================================
stage-b-test-large-8-gpu-mi35x-disaggregation-amd:
@@ -1238,7 +1194,6 @@ jobs:
stage-b-test-2-gpu-large-amd,
stage-b-test-large-8-gpu-mi35x-disaggregation-amd,
stage-c-test-4-gpu-amd,
stage-c-test-4-gpu-amd-mi35x,
stage-c-test-large-8-gpu-amd,
stage-c-test-large-8-gpu-amd-mi35x,
]