[AMD] add testcases for Qwen3 235b Instruct 2507 models (#18805)
Co-authored-by: bingxche <Bingxu.Chen@amd.com>
This commit is contained in:
mqhc2020
67
.github/workflows/nightly-test-amd-rocm720.yml
vendored
67
.github/workflows/nightly-test-amd-rocm720.yml
vendored
@@ -32,9 +32,11 @@ on:
|
||||
- 'nightly-8-gpu-deepseek-v32-rocm720'
|
||||
- 'nightly-8-gpu-deepseek-v32-mtp-rocm720'
|
||||
- 'nightly-8-gpu-kimi-k25-rocm720'
|
||||
- 'nightly-8-gpu-qwen3-235b-rocm720'
|
||||
- 'nightly-8-gpu-glm5-rocm720'
|
||||
# MI35x ROCm 7.2 jobs
|
||||
- 'nightly-test-1-gpu-mi35x-rocm720'
|
||||
- 'nightly-8-gpu-mi35x-qwen3-235b-mxfp4-rocm720'
|
||||
- 'nightly-accuracy-8-gpu-mi35x-rocm720'
|
||||
- 'nightly-8-gpu-mi35x-grok1-int4-rocm720'
|
||||
- 'nightly-8-gpu-mi35x-grok2-rocm720'
|
||||
@@ -496,6 +498,36 @@ jobs:
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
# 8-GPU Qwen3-235B (Accuracy + Performance) ROCm 7.2
|
||||
nightly-8-gpu-qwen3-235b-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-qwen3-235b-rocm720')
|
||||
runs-on: linux-mi325-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: ${{ github.workspace }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
|
||||
|
||||
- name: Accuracy Test + Performance Test ROCm 7.2 (8-GPU Qwen3)
|
||||
timeout-minutes: 120
|
||||
run: |
|
||||
> github_summary.md # Clear summary file
|
||||
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
|
||||
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
|
||||
python3 run_suite.py --hw amd --suite nightly-8-gpu-qwen3-235b --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
# 8-GPU GLM-5 (Accuracy) ROCm 7.2
|
||||
nightly-8-gpu-glm5-rocm720:
|
||||
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-glm5-rocm720')
|
||||
@@ -860,6 +892,39 @@ jobs:
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
# MI35x 8-GPU Qwen3-235B-MXFP4 (Accuracy + Performance) ROCm 7.2
|
||||
nightly-8-gpu-mi35x-qwen3-235b-mxfp4-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-qwen3-235b-mxfp4-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: ${{ github.workspace }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build --skip-test-time-deps
|
||||
# Install tabulate for run_suite.py (missing in MI35x container)
|
||||
bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
|
||||
|
||||
- name: Accuracy Test + Performance Test MI35x ROCm 7.2 (8-GPU Qwen3-235B-MXFP4)
|
||||
timeout-minutes: 120
|
||||
run: |
|
||||
> github_summary.md # Clear summary file
|
||||
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
|
||||
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
|
||||
python3 run_suite.py --hw amd --suite nightly-8-gpu-mi35x-qwen3-235b-mxfp4 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
nightly-8-gpu-mi35x-glm5-rocm720:
|
||||
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-mi35x-glm5-rocm720')
|
||||
runs-on: linux-mi35x-gpu-8
|
||||
@@ -946,6 +1011,7 @@ jobs:
|
||||
- nightly-8-gpu-deepseek-v32-rocm720
|
||||
- nightly-8-gpu-deepseek-v32-mtp-rocm720
|
||||
- nightly-8-gpu-kimi-k25-rocm720
|
||||
- nightly-8-gpu-qwen3-235b-rocm720
|
||||
- nightly-8-gpu-glm5-rocm720
|
||||
# MI35x ROCm 7.2 jobs
|
||||
- nightly-test-1-gpu-mi35x-rocm720
|
||||
@@ -958,6 +1024,7 @@ jobs:
|
||||
- nightly-perf-8-gpu-mi35x-deepseek-v32-basic-rocm720
|
||||
- nightly-perf-8-gpu-mi35x-deepseek-v32-mtp-rocm720
|
||||
- nightly-8-gpu-mi35x-kimi-k25-rocm720
|
||||
- nightly-8-gpu-mi35x-qwen3-235b-mxfp4-rocm720
|
||||
- nightly-8-gpu-mi35x-glm5-rocm720
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
|
||||
66
.github/workflows/nightly-test-amd.yml
vendored
66
.github/workflows/nightly-test-amd.yml
vendored
@@ -32,9 +32,11 @@ on:
|
||||
- 'nightly-8-gpu-deepseek-v32'
|
||||
- 'nightly-8-gpu-deepseek-v32-mtp'
|
||||
- 'nightly-8-gpu-kimi-k25'
|
||||
- 'nightly-8-gpu-qwen3-235b'
|
||||
- 'nightly-8-gpu-glm5'
|
||||
# MI35x jobs
|
||||
- 'nightly-test-1-gpu-mi35x'
|
||||
- 'nightly-8-gpu-mi35x-qwen3-235b-mxfp4'
|
||||
- 'nightly-8-gpu-mi35x-kimi-k25'
|
||||
- 'nightly-8-gpu-mi35x-glm5'
|
||||
- 'nightly-accuracy-8-gpu-mi35x'
|
||||
@@ -496,6 +498,35 @@ jobs:
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
nightly-8-gpu-qwen3-235b:
|
||||
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-qwen3-235b')
|
||||
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: ${{ github.workspace }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
|
||||
|
||||
- name: Accuracy Test + Performance Test (8-GPU Qwen3)
|
||||
timeout-minutes: 120
|
||||
run: |
|
||||
> github_summary.md # Clear summary file
|
||||
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
|
||||
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
|
||||
python3 run_suite.py --hw amd --suite nightly-8-gpu-qwen3-235b --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
nightly-8-gpu-glm5:
|
||||
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (inputs.job_filter == '' || inputs.job_filter == 'all' || inputs.job_filter == 'nightly-8-gpu-glm5')
|
||||
runs-on: linux-mi325-gpu-8
|
||||
@@ -861,6 +892,39 @@ jobs:
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
# MI35x 8-GPU Qwen3-235B-MXFP4 (Accuracy + Performance)
|
||||
nightly-8-gpu-mi35x-qwen3-235b-mxfp4:
|
||||
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-qwen3-235b-mxfp4')
|
||||
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: ${{ github.workspace }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
bash scripts/ci/amd/amd_ci_install_dependency.sh
|
||||
# Install tabulate for run_suite.py (missing in MI35x container)
|
||||
bash scripts/ci/amd/amd_ci_exec.sh pip install tabulate
|
||||
|
||||
- name: Accuracy Test + Performance Test MI35x (8-GPU Qwen3-235B-MXFP4)
|
||||
timeout-minutes: 120
|
||||
run: |
|
||||
> github_summary.md # Clear summary file
|
||||
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
|
||||
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
|
||||
python3 run_suite.py --hw amd --suite nightly-8-gpu-mi35x-qwen3-235b-mxfp4 --nightly --timeout-per-file 3600 || TEST_EXIT_CODE=$?
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
nightly-8-gpu-mi35x-glm5:
|
||||
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-glm5')
|
||||
runs-on: linux-mi35x-gpu-8
|
||||
@@ -947,6 +1011,7 @@ jobs:
|
||||
- nightly-8-gpu-deepseek-v32
|
||||
- nightly-8-gpu-deepseek-v32-mtp
|
||||
- nightly-8-gpu-kimi-k25
|
||||
- nightly-8-gpu-qwen3-235b
|
||||
- nightly-8-gpu-glm5
|
||||
# MI35x jobs
|
||||
- nightly-test-1-gpu-mi35x
|
||||
@@ -957,6 +1022,7 @@ jobs:
|
||||
- nightly-accuracy-8-gpu-mi35x-deepseek-v32
|
||||
- nightly-accuracy-8-gpu-mi35x-deepseek-v32-mtp
|
||||
- nightly-8-gpu-mi35x-kimi-k25
|
||||
- nightly-8-gpu-mi35x-qwen3-235b-mxfp4
|
||||
- nightly-8-gpu-mi35x-glm5
|
||||
# MI35x perf jobs excluded from check - perf failures don't block CI
|
||||
# - nightly-perf-8-gpu-mi35x-deepseek-v32-basic
|
||||
|
||||
Reference in New Issue
Block a user