[AMD CI] Add 2-GPU sgl-kernel Tests (#17555)

Co-authored-by: YC Tseng <yctseng@amd.com>
This commit is contained in:
Bingxu Chen
2026-01-23 13:48:52 +08:00
committed by GitHub
parent c0b5a180fe
commit 50a2e4345a
3 changed files with 64 additions and 2 deletions

View File

@@ -152,6 +152,47 @@ jobs:
docker exec -w /sglang-checkout/sgl-kernel/tests/sgl_diffusion ci_sglang python3 -m pytest test_timestep_embedding.py
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_moe_topk_sigmoid.py
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_torch_defaults_reset.py
sgl-kernel-unit-test-2-gpu-amd:
needs: [check-changes]
if: |
always() &&
(
(inputs.target_stage == 'sgl-kernel-unit-test-2-gpu-amd') ||
(
!inputs.target_stage &&
needs.check-changes.outputs.sgl_kernel == 'true'
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-2]
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/ensure_vram_clear.sh rocm
- name: Start CI container
run: bash scripts/ci/amd_ci_start_container.sh
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/ci/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 20
run: |
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_amd_deterministic_custom_allreduce.py
docker exec -w /sglang-checkout/sgl-kernel/tests ci_sglang python3 -m pytest test_amd_nccl_allreduce_determinism.py
# =============================================== primary ====================================================
stage-a-test-1-amd:
@@ -842,6 +883,7 @@ jobs:
check-changes,
sgl-kernel-unit-test-amd,
sgl-kernel-unit-test-2-gpu-amd,
multimodal-gen-test-1-gpu-amd,
multimodal-gen-test-2-gpu-amd,