[AMD] Add MiniMax-M2.5 TP=4 nightly accuracy test for MI355X (#27126)
This commit is contained in:
@@ -82,6 +82,8 @@ on:
|
||||
- nightly-8-gpu-mi35x-glm51-rocm720
|
||||
# 8-GPU GLM-5-MXFP4 (MI35x only)
|
||||
- nightly-8-gpu-mi35x-glm5-mxfp4-rocm720
|
||||
# 4-GPU MiniMax-M2.5 (MI35x)
|
||||
- nightly-4-gpu-mi35x-minimax-m25-rocm720
|
||||
# 8-GPU MiniMax-M2.7 (MI30x only)
|
||||
- nightly-8-gpu-minimax-m27-rocm720
|
||||
# Diffusion (MI30x)
|
||||
@@ -1681,6 +1683,44 @@ jobs:
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
# ==============================================================================
|
||||
# 4-GPU MiniMax-M2.5 (MI35x)
|
||||
# ==============================================================================
|
||||
|
||||
nightly-4-gpu-mi35x-minimax-m25-rocm720:
|
||||
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (!(inputs.job_filter || inputs.job_select) || (inputs.job_filter || inputs.job_select) == 'all' || contains(format(',{0},', inputs.job_filter || inputs.job_select), ',nightly-4-gpu-mi35x-minimax-m25-rocm720,'))
|
||||
runs-on: linux-mi35x-gpu-8
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ inputs.ref || github.sha }}
|
||||
|
||||
- name: Ensure VRAM is clear
|
||||
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
|
||||
|
||||
- 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-test-time-deps
|
||||
|
||||
- name: Accuracy Test MI35x ROCm 7.2 (4-GPU MiniMax-M2.5)
|
||||
timeout-minutes: 120
|
||||
run: |
|
||||
> github_summary.md
|
||||
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
|
||||
-e SGLANG_USE_AITER=1 \
|
||||
-e SGLANG_USE_AITER_UNIFIED_ATTN=1 \
|
||||
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
|
||||
python3 run_suite.py --hw amd --suite nightly-amd-4-gpu-mi35x-minimax-m25-tp4 --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
# ==============================================================================
|
||||
# 8-GPU MiniMax-M2.7 (MI30x only)
|
||||
# ==============================================================================
|
||||
@@ -1831,6 +1871,8 @@ jobs:
|
||||
- nightly-8-gpu-mi35x-glm51-rocm720
|
||||
# 8-GPU GLM-5-MXFP4 (MI35x only)
|
||||
- nightly-8-gpu-mi35x-glm5-mxfp4-rocm720
|
||||
# 4-GPU MiniMax-M2.5 (MI35x)
|
||||
- nightly-4-gpu-mi35x-minimax-m25-rocm720
|
||||
# 8-GPU MiniMax-M2.7 (MI30x only)
|
||||
- nightly-8-gpu-minimax-m27-rocm720
|
||||
# Diffusion (MI30x)
|
||||
|
||||
@@ -79,6 +79,8 @@ on:
|
||||
- nightly-8-gpu-mi35x-glm51
|
||||
# 8-GPU GLM-5-MXFP4 (MI35x only)
|
||||
- nightly-8-gpu-mi35x-glm5-mxfp4
|
||||
# 4-GPU MiniMax-M2.5 (MI35x)
|
||||
- nightly-4-gpu-mi35x-minimax-m25
|
||||
# 8-GPU MiniMax-M2.7 (MI30x only)
|
||||
- nightly-8-gpu-minimax-m27
|
||||
# Diffusion (MI30x)
|
||||
@@ -1612,6 +1614,44 @@ jobs:
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
# ==============================================================================
|
||||
# 4-GPU MiniMax-M2.5 (MI35x)
|
||||
# ==============================================================================
|
||||
|
||||
nightly-4-gpu-mi35x-minimax-m25:
|
||||
if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && (!(inputs.job_filter || inputs.job_select) || (inputs.job_filter || inputs.job_select) == 'all' || contains(format(',{0},', inputs.job_filter || inputs.job_select), ',nightly-4-gpu-mi35x-minimax-m25,'))
|
||||
runs-on: linux-mi35x-gpu-8
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
ref: ${{ inputs.ref || github.sha }}
|
||||
|
||||
- name: Ensure VRAM is clear
|
||||
run: bash scripts/ci/amd/ensure_vram_clear.sh rocm
|
||||
|
||||
- name: Setup docker (ROCm 7.0)
|
||||
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 --skip-test-time-deps
|
||||
|
||||
- name: Accuracy Test MI35x (4-GPU MiniMax-M2.5)
|
||||
timeout-minutes: 120
|
||||
run: |
|
||||
> github_summary.md
|
||||
bash scripts/ci/amd/amd_ci_exec.sh -w /sglang-checkout/test \
|
||||
-e SGLANG_USE_AITER=1 \
|
||||
-e SGLANG_USE_AITER_UNIFIED_ATTN=1 \
|
||||
-e GITHUB_STEP_SUMMARY="/sglang-checkout/github_summary.md" \
|
||||
python3 run_suite.py --hw amd --suite nightly-amd-4-gpu-mi35x-minimax-m25-tp4 --nightly --timeout-per-file 5400 ${{ (github.event_name == 'schedule' || inputs.continue_on_error) && '--continue-on-error' || '' }} || TEST_EXIT_CODE=$?
|
||||
echo "$(<github_summary.md )" >> $GITHUB_STEP_SUMMARY || true
|
||||
exit ${TEST_EXIT_CODE:-0}
|
||||
|
||||
# ==============================================================================
|
||||
# 8-GPU MiniMax-M2.7 (MI30x only)
|
||||
# ==============================================================================
|
||||
@@ -1759,6 +1799,8 @@ jobs:
|
||||
- nightly-8-gpu-mi35x-glm51
|
||||
# 8-GPU GLM-5-MXFP4 (MI35x only)
|
||||
- nightly-8-gpu-mi35x-glm5-mxfp4
|
||||
# 4-GPU MiniMax-M2.5 (MI35x)
|
||||
- nightly-4-gpu-mi35x-minimax-m25
|
||||
# 8-GPU MiniMax-M2.7 (MI30x only)
|
||||
- nightly-8-gpu-minimax-m27
|
||||
# Diffusion (MI30x)
|
||||
|
||||
Reference in New Issue
Block a user