From 586a50cd96f8913598d06f5807bd68dd6832c46b Mon Sep 17 00:00:00 2001 From: Michael <13900043+michaelzhang-ai@users.noreply.github.com> Date: Tue, 25 Aug 2026 18:34:51 -0700 Subject: [PATCH] [AMD][CI] Restore MiniMax-M2.5 4-GPU MI35x nightly job (#36393) Co-authored-by: Cursor Agent Co-authored-by: quitenode --- .../workflows/nightly-test-amd-rocm720.yml | 48 +++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/.github/workflows/nightly-test-amd-rocm720.yml b/.github/workflows/nightly-test-amd-rocm720.yml index fbea53065..c9de4437a 100644 --- a/.github/workflows/nightly-test-amd-rocm720.yml +++ b/.github/workflows/nightly-test-amd-rocm720.yml @@ -96,6 +96,8 @@ on: - nightly-8-gpu-mi35x-glm52-fp8-rocm720 # 8-GPU GLM-5-MXFP4 (MI35x only) - nightly-8-gpu-mi35x-glm5-mxfp4-rocm720 + # 4-GPU MiniMax-M2.5 (MI35x) + - nightly-4-gpu-mi35x-minimax-m25-rocm720 # 4-GPU MiniMax-M3 MXFP8 (MI35x accuracy + performance) - nightly-4-gpu-mi35x-minimax-m3-rocm720 # 8-GPU MiniMax-M2.7 (MI30x only) @@ -2161,6 +2163,50 @@ jobs: echo "$(> $GITHUB_STEP_SUMMARY || true exit ${TEST_EXIT_CODE:-0} + # ============================================================================== + # 4-GPU MiniMax-M2.5 (MI35x) + # ============================================================================== + + nightly-4-gpu-mi35x-minimax-m25-rocm720: + name: ${{ format('nightly-4-gpu-mi35x-minimax-m25 ({0}, linux-mi35x-gpu-8)', matrix.rocm_version) }} + strategy: + fail-fast: false + matrix: + rocm_version: ${{ fromJson(inputs.rocm_version && inputs.rocm_version != 'all' && format('["{0}"]', inputs.rocm_version) || '["rocm724", "rocm720"]') }} + if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (!(inputs.job_filter || inputs.job_select) || (inputs.job_filter || inputs.job_select) == 'all' || contains(format(',{0},', inputs.job_filter || inputs.job_select), ',nightly-4-gpu-mi35x-minimax-m25-rocm720,')) + runs-on: linux-mi35x-gpu-8 + steps: + - name: Checkout code + uses: actions/checkout@v4 + with: + ref: ${{ inputs.ref || github.sha }} + + - name: Ensure VRAM is clear + run: bash scripts/ci/amd/ensure_vram_clear.sh rocm + + - name: Setup docker (${{ matrix.rocm_version }}) + run: | + touch github_summary.md + bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version ${{ matrix.rocm_version }} + env: + GITHUB_WORKSPACE: ${{ github.workspace }} + ENABLE_CACHE_HOST: "1" + + - name: Install dependencies + run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-test-time-deps + + - name: Accuracy Test MI35x ROCm 7.2 (4-GPU MiniMax-M2.5) + timeout-minutes: 120 + run: | + > github_summary.md + bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \ + -e SGLANG_USE_AITER=1 \ + -e SGLANG_USE_AITER_UNIFIED_ATTN=1 \ + -e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \ + python3 run_suite.py --hw amd --suite nightly-amd-4-gpu-mi35x-minimax-m25-tp4 --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$? + echo "$(> $GITHUB_STEP_SUMMARY || true + exit ${TEST_EXIT_CODE:-0} + # ============================================================================== # 4-GPU MiniMax-M3 MXFP8 (MI35x accuracy + performance) # ============================================================================== @@ -2383,6 +2429,8 @@ jobs: - nightly-8-gpu-mi35x-glm52-fp8-rocm720 # 8-GPU GLM-5-MXFP4 (MI35x only) - nightly-8-gpu-mi35x-glm5-mxfp4-rocm720 + # 4-GPU MiniMax-M2.5 (MI35x) + - nightly-4-gpu-mi35x-minimax-m25-rocm720 # 4-GPU MiniMax-M3 MXFP8 (MI35x accuracy + performance) - nightly-4-gpu-mi35x-minimax-m3-rocm720 # 8-GPU MiniMax-M2.7 (MI30x only)