From f06bd210c08f6295b8b7bd765053d0188152a98c Mon Sep 17 00:00:00 2001 From: Sai Enduri Date: Tue, 15 Jul 2025 15:09:56 -0700 Subject: [PATCH] Update amd docker image. (#8045) Co-authored-by: Hubert Lu <55214931+hubertlu-tw@users.noreply.github.com> --- .github/workflows/pr-test-amd.yml | 8 ++++---- scripts/amd_ci_start_container.sh | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/.github/workflows/pr-test-amd.yml b/.github/workflows/pr-test-amd.yml index 75f2fcbd2..3ba24d979 100644 --- a/.github/workflows/pr-test-amd.yml +++ b/.github/workflows/pr-test-amd.yml @@ -223,7 +223,7 @@ jobs: fail-fast: false matrix: runner: [linux-mi300-gpu-1, linux-mi325-gpu-1] - part: [0, 1, 2, 3, 4, 5] + part: [0, 1, 2, 3, 4, 5, 6] runs-on: ${{matrix.runner}} steps: - name: Checkout code @@ -238,9 +238,9 @@ jobs: run: bash scripts/amd_ci_install_dependency.sh - name: Run test - timeout-minutes: 40 + timeout-minutes: 50 run: | - bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 6 + bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 7 unit-test-backend-2-gpu-amd: if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && @@ -293,7 +293,7 @@ jobs: - name: Run CustomAllReduce test timeout-minutes: 10 run: | - CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 bash scripts/amd_ci_exec.sh python3 -m unittest test_custom_allreduce.TestCustomAllReduce + bash scripts/amd_ci_exec.sh -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 -m unittest test_custom_allreduce.TestCustomAllReduce unit-test-sgl-kernel-amd: if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && diff --git a/scripts/amd_ci_start_container.sh b/scripts/amd_ci_start_container.sh index f7f20d57e..a6a527380 100755 --- a/scripts/amd_ci_start_container.sh +++ b/scripts/amd_ci_start_container.sh @@ -9,7 +9,7 @@ else fi # Pull the image -IMAGE="ghcr.io/saienduri/sglang:aiter-1.3" +IMAGE="rocm/sgl-dev:v0.4.9.post2-rocm630-mi30x-20250715" echo "Pulling Docker image: $IMAGE" docker pull "$IMAGE"