diff --git a/.github/workflows/pr-test-amd-rocm720.yml b/.github/workflows/pr-test-amd-rocm720.yml index 88c8320a9..7b3443a7d 100644 --- a/.github/workflows/pr-test-amd-rocm720.yml +++ b/.github/workflows/pr-test-amd-rocm720.yml @@ -310,7 +310,7 @@ jobs: run: | bash scripts/ci/amd/amd_ci_install_dependency.sh - name: Run test - timeout-minutes: 10 + timeout-minutes: 15 run: | 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 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }} @@ -559,7 +559,6 @@ jobs: ) strategy: fail-fast: false - max-parallel: 1 # Run one at a time to avoid eviction from resource exhaustion during AITER kernel JIT matrix: runner: [linux-mi325-1gpu-sglang] part: [0, 1, 2, 3] @@ -700,7 +699,6 @@ jobs: ) strategy: fail-fast: false - max-parallel: 1 # Run one at a time to avoid eviction from resource exhaustion during AITER kernel JIT matrix: runner: [linux-mi325-2gpu-sglang] part: [0, 1, 2] # 3 partitions: 2 parametrized + 1 standalone (test_disagg_server.py) diff --git a/.github/workflows/pr-test-amd.yml b/.github/workflows/pr-test-amd.yml index e596adc8f..5f442130b 100644 --- a/.github/workflows/pr-test-amd.yml +++ b/.github/workflows/pr-test-amd.yml @@ -321,7 +321,7 @@ jobs: bash scripts/ci/amd/amd_ci_install_dependency.sh - name: Run test - timeout-minutes: 10 + timeout-minutes: 15 run: | 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 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}