[AMD] Fix Janus-Pro crash and add Kimi-K2.5 nightly test (#18269)

This commit is contained in:
Michael
2026-02-10 22:33:13 -08:00
committed by GitHub
parent cd90346a2b
commit d84d2063d3
4 changed files with 250 additions and 10 deletions
+39 -9
View File
@@ -31,10 +31,10 @@ on:
- 'nightly-8-gpu-deepseek-v31'
- 'nightly-8-gpu-deepseek-v32'
- 'nightly-8-gpu-deepseek-v32-mtp'
- 'nightly-8-gpu-kimi-k2'
- 'nightly-8-gpu-kimi-k25'
# MI35x jobs
- 'nightly-test-1-gpu-mi35x'
- 'nightly-8-gpu-mi35x-kimi-k2'
- 'nightly-8-gpu-mi35x-kimi-k25'
- 'nightly-accuracy-8-gpu-mi35x'
- 'nightly-8-gpu-mi35x-grok1-int4'
- 'nightly-8-gpu-mi35x-grok2'
@@ -494,6 +494,36 @@ jobs:
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')
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: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Accuracy Test (8-GPU Kimi-K2.5)
timeout-minutes: 120
run: |
> github_summary.md # Clear summary file
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-kimi-k25 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
exit ${TEST_EXIT_CODE:-0}
# ============================================== MI35x Tests ==============================================
# MI35x 1-GPU tests - platform-agnostic tests that may work on CDNA4 (gfx950)
nightly-test-1-gpu-mi35x:
@@ -794,9 +824,9 @@ jobs:
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
exit ${TEST_EXIT_CODE:-0}
# MI35x 8-GPU Kimi-K2 (Accuracy)
nightly-8-gpu-mi35x-kimi-k2:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-mi35x-kimi-k2')
# MI35x 8-GPU Kimi-K2.5 (Accuracy)
nightly-8-gpu-mi35x-kimi-k25:
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-mi35x-kimi-k25')
runs-on: linux-mi35x-gpu-8
steps:
- name: Checkout code
@@ -817,13 +847,13 @@ jobs:
# Install tabulate for run_suite.py (missing in MI35x container)
bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
- name: Accuracy Test MI35x (8-GPU Kimi-K2)
- name: Accuracy Test MI35x (8-GPU Kimi-K2.5)
timeout-minutes: 180
run: |
> github_summary.md # Clear summary file
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-kimi-k2 --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-kimi-k25 --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
exit ${TEST_EXIT_CODE:-0}
@@ -878,7 +908,7 @@ jobs:
- nightly-8-gpu-deepseek-v31
- nightly-8-gpu-deepseek-v32
- nightly-8-gpu-deepseek-v32-mtp
- nightly-8-gpu-kimi-k2
- nightly-8-gpu-kimi-k25
# MI35x jobs
- nightly-test-1-gpu-mi35x
- nightly-accuracy-8-gpu-mi35x
@@ -887,7 +917,7 @@ jobs:
- nightly-8-gpu-mi35x-deepseek-r1-mxfp4
- nightly-accuracy-8-gpu-mi35x-deepseek-v32
- nightly-accuracy-8-gpu-mi35x-deepseek-v32-mtp
- nightly-8-gpu-mi35x-kimi-k2
- nightly-8-gpu-mi35x-kimi-k25
# MI35x perf jobs excluded from check - perf failures don't block CI
# - nightly-perf-8-gpu-mi35x-deepseek-v32-basic
# - nightly-perf-8-gpu-mi35x-deepseek-v32-mtp