[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:
Michael
2026-02-15 04:36:47 -08:00
committed by GitHub
parent 90555a0228
commit 88010e9601
5 changed files with 68 additions and 57 deletions

View File

@@ -31,7 +31,7 @@ on:
- 'nightly-8-gpu-deepseek-v31-rocm720'
- 'nightly-8-gpu-deepseek-v32-rocm720'
- 'nightly-8-gpu-deepseek-v32-mtp-rocm720'
- 'nightly-8-gpu-kimi-k2-rocm720'
- 'nightly-8-gpu-kimi-k25-rocm720'
# MI35x ROCm 7.2 jobs
- 'nightly-test-1-gpu-mi35x-rocm720'
- 'nightly-accuracy-8-gpu-mi35x-rocm720'
@@ -42,6 +42,7 @@ on:
- 'nightly-accuracy-8-gpu-mi35x-deepseek-v32-mtp-rocm720'
- 'nightly-perf-8-gpu-mi35x-deepseek-v32-basic-rocm720'
- 'nightly-perf-8-gpu-mi35x-deepseek-v32-mtp-rocm720'
- 'nightly-8-gpu-mi35x-kimi-k25-rocm720'
workflow_call:
inputs:
ref:
@@ -82,11 +83,11 @@ jobs:
run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
- name: Nightly Unit Test ROCm 7.2 (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 ${TEST_EXIT_CODE:-0}
@@ -463,9 +464,9 @@ jobs:
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
exit ${TEST_EXIT_CODE:-0}
# 8-GPU Kimi-K2 (Accuracy + Speed) ROCm 7.2
nightly-8-gpu-kimi-k2-rocm720:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-kimi-k2-rocm720')
# 8-GPU Kimi-K2.5 (Accuracy) ROCm 7.2
nightly-8-gpu-kimi-k25-rocm720:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-kimi-k25-rocm720')
runs-on: linux-mi325-gpu-8
steps:
- name: Checkout code
@@ -483,13 +484,13 @@ jobs:
- name: Install dependencies
run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
- name: Accuracy Test ROCm 7.2 (8-GPU Kimi-K2)
- name: Accuracy Test ROCm 7.2 (8-GPU Kimi-K2.5)
timeout-minutes: 120
run: |
> github_summary.md # Clear summary file
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-kimi-k2 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-kimi-k25 --nightly --timeout-per-file 3600 --continue-on-error || TEST_EXIT_CODE=$?
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
exit ${TEST_EXIT_CODE:-0}
@@ -516,11 +517,11 @@ jobs:
bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
- name: Nightly Test MI35x ROCm 7.2 (1-GPU)
timeout-minutes: 60
timeout-minutes: 90
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
python3 run_suite.py --hw amd --suite nightly-amd-1-gpu-mi35x --nightly --timeout-per-file 600 --continue-on-error || TEST_EXIT_CODE=$?
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 ${TEST_EXIT_CODE:-0}
@@ -791,6 +792,39 @@ jobs:
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
exit ${TEST_EXIT_CODE:-0}
# MI35x 8-GPU Kimi-K2.5 (Accuracy) ROCm 7.2
nightly-8-gpu-mi35x-kimi-k25-rocm720:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-mi35x-kimi-k25-rocm720')
runs-on: linux-mi35x-gpu-8
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.ref || github.ref }}
- name: Setup docker (ROCm 7.2)
run: |
touch github_summary.md
bash scripts/ci/amd/amd_ci_start_container.sh --rocm-version rocm720
env:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
# Install tabulate for run_suite.py (missing in MI35x container)
bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
- name: Accuracy Test MI35x ROCm 7.2 (8-GPU Kimi-K2.5)
timeout-minutes: 180
run: |
> github_summary.md # Clear summary file
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-kimi-k25 --nightly --timeout-per-file 7200 --continue-on-error || TEST_EXIT_CODE=$?
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
exit ${TEST_EXIT_CODE:-0}
# MI35x 8-GPU DeepSeek-V3.2 Performance Test (MTP) ROCm 7.2
nightly-perf-8-gpu-mi35x-deepseek-v32-mtp-rocm720:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-perf-8-gpu-mi35x-deepseek-v32-mtp-rocm720')
@@ -842,7 +876,7 @@ jobs:
- nightly-8-gpu-deepseek-v31-rocm720
- nightly-8-gpu-deepseek-v32-rocm720
- nightly-8-gpu-deepseek-v32-mtp-rocm720
- nightly-8-gpu-kimi-k2-rocm720
- nightly-8-gpu-kimi-k25-rocm720
# MI35x ROCm 7.2 jobs
- nightly-test-1-gpu-mi35x-rocm720
- nightly-accuracy-8-gpu-mi35x-rocm720
@@ -853,6 +887,7 @@ jobs:
- nightly-accuracy-8-gpu-mi35x-deepseek-v32-mtp-rocm720
- nightly-perf-8-gpu-mi35x-deepseek-v32-basic-rocm720
- nightly-perf-8-gpu-mi35x-deepseek-v32-mtp-rocm720
- nightly-8-gpu-mi35x-kimi-k25-rocm720
runs-on: ubuntu-latest
steps:
- name: Check if any job failed

View File

@@ -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}