[AMD] Fix nightly 1-GPU test failures and bench_serving regression (#18761)
Co-authored-by: michaelzhang-ai <michaelzhang-ai@users.noreply.github.com>
This commit is contained in:
co-authored by
michaelzhang-ai
parent
90555a0228
commit
88010e9601
@@ -83,11 +83,11 @@ jobs:
|
||||
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
|
||||
|
||||
- name: Nightly Unit Test (1-GPU)
|
||||
timeout-minutes: 60
|
||||
timeout-minutes: 90
|
||||
run: |
|
||||
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
|
||||
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
|
||||
python3 run_suite.py --hw amd --suite nightly-amd-1-gpu --nightly --timeout-per-file 600 --continue-on-error || TEST_EXIT_CODE=$?
|
||||
python3 run_suite.py --hw amd --suite nightly-amd-1-gpu --nightly --timeout-per-file 900 --continue-on-error || TEST_EXIT_CODE=$?
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
@@ -464,36 +464,6 @@ jobs:
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
# 8-GPU Kimi-K2 (Accuracy + Speed)
|
||||
nightly-8-gpu-kimi-k2:
|
||||
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-kimi-k2')
|
||||
runs-on: linux-mi325-gpu-8
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ inputs.ref || github.ref }}
|
||||
|
||||
- name: Setup docker
|
||||
run: |
|
||||
touch github_summary.md
|
||||
bash scripts/ci/amd/amd_ci_start_container.sh
|
||||
env:
|
||||
GITHUB_WORKSPACE: ${{ github.workspace }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
|
||||
|
||||
- name: Accuracy Test (8-GPU Kimi-K2)
|
||||
timeout-minutes: 120
|
||||
run: |
|
||||
> github_summary.md # Clear summary file
|
||||
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
|
||||
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
|
||||
python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-kimi-k2 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
# 8-GPU Kimi-K2.5 (Accuracy)
|
||||
nightly-8-gpu-kimi-k25:
|
||||
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-kimi-k25')
|
||||
@@ -549,11 +519,11 @@ jobs:
|
||||
bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
|
||||
|
||||
- name: Nightly Test MI35x (1-GPU)
|
||||
timeout-minutes: 60
|
||||
timeout-minutes: 90
|
||||
run: |
|
||||
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
|
||||
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
|
||||
python3 run_suite.py --hw amd --suite nightly-amd-1-gpu-mi35x --nightly --timeout-per-file 600 --continue-on-error || TEST_EXIT_CODE=$?
|
||||
python3 run_suite.py --hw amd --suite nightly-amd-1-gpu-mi35x --nightly --timeout-per-file 900 --continue-on-error || TEST_EXIT_CODE=$?
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user