[AMD] Add kimi mi35x nightly test, folder organization and several stability fixes (#17895)

This commit is contained in:
Michael
2026-02-04 12:03:57 -08:00
committed by GitHub
parent 36a3e78af9
commit 6fd878b41d
34 changed files with 184 additions and 14 deletions

View File

@@ -34,6 +34,7 @@ on:
- 'nightly-8-gpu-kimi-k2'
# MI35x jobs
- 'nightly-test-1-gpu-mi35x'
- 'nightly-8-gpu-mi35x-kimi-k2'
- 'nightly-accuracy-8-gpu-mi35x'
- 'nightly-8-gpu-mi35x-grok1-int4'
- 'nightly-8-gpu-mi35x-grok2'
@@ -582,13 +583,13 @@ jobs:
bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
- name: Accuracy Test MI35x (8-GPU Grok1-INT4)
timeout-minutes: 60
timeout-minutes: 90
run: |
> github_summary.md # Clear summary file
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
-e RCCL_MSCCL_ENABLE=0 \
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-grok1-int4 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-grok1-int4 --nightly --timeout-per-file 5400 || TEST_EXIT_CODE=$?
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
exit ${TEST_EXIT_CODE:-0}
@@ -793,6 +794,39 @@ jobs:
echo "$(<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')
runs-on: linux-mi35x-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: ${{ github.workspace }}
- name: Install dependencies
run: |
bash scripts/ci/amd/amd_ci_install_dependency.sh
# Install tabulate for run_suite.py (missing in MI35x container)
bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
- name: Accuracy Test MI35x (8-GPU Kimi-K2)
timeout-minutes: 180
run: |
> github_summary.md # Clear summary file
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
python3 run_suite.py --hw amd --suite nightly-amd-accuracy-8-gpu-mi35x-kimi-k2 --nightly --timeout-per-file 7200 || TEST_EXIT_CODE=$?
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
exit ${TEST_EXIT_CODE:-0}
# MI35x 8-GPU DeepSeek-V3.2 Performance Test (MTP)
nightly-perf-8-gpu-mi35x-deepseek-v32-mtp:
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')
@@ -834,10 +868,10 @@ jobs:
# MI30x Accuracy Tests
- nightly-accuracy-2-gpu
- nightly-accuracy-2-gpu-vlm
# MI30x Performance Tests
- nightly-perf-2-gpu-text
- nightly-perf-2-gpu-vlm
- nightly-accuracy-8-gpu
# MI30x Performance Tests - excluded from check (perf failures don't block CI)
# - nightly-perf-2-gpu-text
# - nightly-perf-2-gpu-vlm
# MI30x Combined Accuracy + Performance Tests
- nightly-8-gpu-grok1-int4
- nightly-8-gpu-grok2
@@ -853,6 +887,7 @@ 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
# 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