From 8022505705eb7dc6239ab0bbdb7c1a0ce8682d40 Mon Sep 17 00:00:00 2001 From: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com> Date: Thu, 10 Sep 2026 17:41:15 +0800 Subject: [PATCH] Revert "[CI] Temporarily disable GB300 tests" (#38842) --- .github/workflows/nightly-test-nvidia.yml | 32 +++++++++++----------- .github/workflows/pr-test.yml | 32 +++++++++++----------- .github/workflows/release-whl-deepgemm.yml | 6 ++-- 3 files changed, 35 insertions(+), 35 deletions(-) diff --git a/.github/workflows/nightly-test-nvidia.yml b/.github/workflows/nightly-test-nvidia.yml index d4424ca49..a3e4e2c52 100644 --- a/.github/workflows/nightly-test-nvidia.yml +++ b/.github/workflows/nightly-test-nvidia.yml @@ -139,20 +139,20 @@ jobs: scheduled: true secrets: inherit - # nightly-4-gpu-gb300: - # needs: check-changes - # if: github.repository == 'sgl-project/sglang' && (inputs.runner_filter == '' || inputs.runner_filter == 'all' || inputs.runner_filter == '4-gpu-gb300') - # uses: ./.github/workflows/_pr-test-stage.yml - # with: - # self_name: nightly-test-4-gpu-gb300 - # runner_config: 4-gpu-gb300 - # check_changes: ${{ toJson(needs.check-changes.outputs) }} - # caller_inputs: ${{ toJson(inputs) }} - # partitions: ${{ needs.check-changes.outputs.partitions }} - # run_timeout_minutes: '360' - # job_timeout_minutes: '420' - # scheduled: true - # secrets: inherit + nightly-4-gpu-gb300: + needs: check-changes + if: github.repository == 'sgl-project/sglang' && (inputs.runner_filter == '' || inputs.runner_filter == 'all' || inputs.runner_filter == '4-gpu-gb300') + uses: ./.github/workflows/_pr-test-stage.yml + with: + self_name: nightly-test-4-gpu-gb300 + runner_config: 4-gpu-gb300 + check_changes: ${{ toJson(needs.check-changes.outputs) }} + caller_inputs: ${{ toJson(inputs) }} + partitions: ${{ needs.check-changes.outputs.partitions }} + run_timeout_minutes: '360' + job_timeout_minutes: '420' + scheduled: true + secrets: inherit nightly-8-gpu-h200: needs: check-changes @@ -265,7 +265,7 @@ jobs: - nightly-2-gpu-large - nightly-4-gpu-h100 - nightly-4-gpu-b200 - # - nightly-4-gpu-gb300 + - nightly-4-gpu-gb300 - nightly-8-gpu-h200 - nightly-8-gpu-b200 runs-on: ubuntu-latest @@ -312,7 +312,7 @@ jobs: - nightly-2-gpu-large - nightly-4-gpu-h100 - nightly-4-gpu-b200 - # - nightly-4-gpu-gb300 + - nightly-4-gpu-gb300 - nightly-8-gpu-h200 - nightly-8-gpu-b200 - nightly-test-diffusion diff --git a/.github/workflows/pr-test.yml b/.github/workflows/pr-test.yml index 7c4d110b3..e0c7f1220 100644 --- a/.github/workflows/pr-test.yml +++ b/.github/workflows/pr-test.yml @@ -474,21 +474,21 @@ jobs: rust_ext_artifact: ${{ needs.rust-ext-build.outputs.artifact_name }} secrets: inherit - # base-c-test-4-gpu-gb300: - # needs: [check-changes, call-gate, wait-for-base-b, sgl-kernel-build-wheels, rust-ext-build-aarch64] - # if: ${{ !failure() && !cancelled() }} - # uses: ./.github/workflows/_pr-test-stage.yml - # with: - # self_name: base-c-test-4-gpu-gb300 - # runner_config: 4-gpu-gb300 - # check_changes: ${{ toJson(needs.check-changes.outputs) }} - # caller_inputs: ${{ toJson(inputs) }} - # partitions: ${{ needs.check-changes.outputs.partitions }} - # run_timeout_minutes: '30' - # timeout_per_file: '1800' - # # The one aarch64 stage, so it takes the aarch64 build, not rust-ext-build's. - # rust_ext_artifact: ${{ needs.rust-ext-build-aarch64.outputs.artifact_name }} - # secrets: inherit + base-c-test-4-gpu-gb300: + needs: [check-changes, call-gate, wait-for-base-b, sgl-kernel-build-wheels, rust-ext-build-aarch64] + if: ${{ !failure() && !cancelled() }} + uses: ./.github/workflows/_pr-test-stage.yml + with: + self_name: base-c-test-4-gpu-gb300 + runner_config: 4-gpu-gb300 + check_changes: ${{ toJson(needs.check-changes.outputs) }} + caller_inputs: ${{ toJson(inputs) }} + partitions: ${{ needs.check-changes.outputs.partitions }} + run_timeout_minutes: '30' + timeout_per_file: '1800' + # The one aarch64 stage, so it takes the aarch64 build, not rust-ext-build's. + rust_ext_artifact: ${{ needs.rust-ext-build-aarch64.outputs.artifact_name }} + secrets: inherit base-c-test-8-gpu-b300: needs: [check-changes, call-gate, wait-for-base-b, sgl-kernel-build-wheels, rust-ext-build] @@ -537,7 +537,7 @@ jobs: base-c-test-8-gpu-h20, base-c-test-8-gpu-h200, base-c-test-4-gpu-b200, - # base-c-test-4-gpu-gb300, + base-c-test-4-gpu-gb300, base-c-test-8-gpu-b300, ] if: always() diff --git a/.github/workflows/release-whl-deepgemm.yml b/.github/workflows/release-whl-deepgemm.yml index b0863d625..b321bc946 100644 --- a/.github/workflows/release-whl-deepgemm.yml +++ b/.github/workflows/release-whl-deepgemm.yml @@ -194,9 +194,9 @@ jobs: # - arch_label: sm120 # runner: 1-gpu-5090 # wheel_arch: x86_64 - # - arch_label: sm100-aarch64 - # runner: 4-gpu-gb300 - # wheel_arch: aarch64 + - arch_label: sm100-aarch64 + runner: 4-gpu-gb300 + wheel_arch: aarch64 runs-on: ${{ matrix.runner }} timeout-minutes: 120 steps: