[AMD] CI - enable deepseekv3.2 on MI325-8gpu and merge perf/accuracy test suites into stage-b suites (#17633)

Co-authored-by: Bingxu Chen <Bingxu.Chen@amd.com>
This commit is contained in:
YC Tseng
2026-01-28 10:54:36 +08:00
committed by GitHub
parent 1c4616a034
commit 52bca42870
9 changed files with 91 additions and 233 deletions

View File

@@ -315,12 +315,12 @@ jobs:
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-amd-mi35x
stage-b-test-large-2-gpu-amd:
stage-b-test-large-1-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-large-2-gpu-amd') ||
(inputs.target_stage == 'stage-b-test-large-1-gpu-amd') ||
(
!inputs.target_stage &&
(!failure() && !cancelled()) &&
@@ -330,7 +330,8 @@ jobs:
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-2]
runner: [linux-mi325-gpu-1]
part: [0, 1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -352,7 +353,47 @@ jobs:
- name: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-amd
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800
stage-b-test-large-2-gpu-amd:
needs: [check-changes, stage-a-test-1-amd]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-large-2-gpu-amd') ||
(
!inputs.target_stage &&
(!failure() && !cancelled()) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-2]
part: [0, 1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: 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: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800
multimodal-gen-test-1-gpu-amd:
needs: [check-changes]
@@ -611,7 +652,7 @@ jobs:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-8]
part: [0, 1]
part: [0, 1, 2]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -639,7 +680,7 @@ jobs:
- name: Run test
timeout-minutes: 60
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 3600
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 3600
stage-c-test-large-8-gpu-amd-mi35x:
needs: [check-changes, call-gate, stage-b-test-small-1-gpu-amd, stage-b-test-large-2-gpu-amd]
@@ -657,7 +698,7 @@ jobs:
fail-fast: false
matrix:
runner: [linux-mi35x-gpu-8]
part: [0, 1, 2]
part: [0]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
@@ -679,203 +720,7 @@ jobs:
- name: Run test
timeout-minutes: 60
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 3600
stage-b-test-small-1-gpu-performance-amd:
needs: [check-changes, call-gate, stage-a-test-1-amd]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-small-1-gpu-performance-amd') ||
(
!inputs.target_stage &&
(!failure() && !cancelled()) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: 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: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-performance-amd --timeout-per-file 1200
stage-b-test-large-1-gpu-performance-amd:
needs: [check-changes, call-gate, stage-a-test-1-amd]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-large-1-gpu-performance-amd') ||
(
!inputs.target_stage &&
(!failure() && !cancelled()) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-1]
part: [0, 1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: 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: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-1-gpu-performance-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1200
stage-b-test-large-2-gpu-performance-amd:
needs: [check-changes, call-gate, stage-a-test-1-amd]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-large-2-gpu-performance-amd') ||
(
!inputs.target_stage &&
(!failure() && !cancelled()) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-2]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: 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: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-performance-amd --timeout-per-file 1200
stage-b-test-small-1-gpu-accuracy-amd:
needs: [check-changes, stage-a-test-1-amd]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-small-1-gpu-accuracy-amd') ||
(
!inputs.target_stage &&
(!failure() && !cancelled()) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-1]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: 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: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" -e SGLANG_USE_AITER=0 python3 run_suite.py --hw amd --suite stage-b-test-small-1-gpu-accuracy-amd --timeout-per-file 1800
stage-b-test-large-2-gpu-accuracy-amd:
needs: [check-changes, stage-a-test-1-amd]
if: |
always() &&
(
(inputs.target_stage == 'stage-b-test-large-2-gpu-accuracy-amd') ||
(
!inputs.target_stage &&
(!failure() && !cancelled()) &&
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
)
)
strategy:
fail-fast: false
matrix:
runner: [linux-mi325-gpu-2]
runs-on: ${{matrix.runner}}
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
ref: ${{ inputs.pr_head_sha || inputs.ref || github.sha }}
- name: Ensure VRAM is clear
run: bash scripts/ensure_vram_clear.sh rocm
- name: Start CI container
run: 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: Run test
timeout-minutes: 30
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" -e SGLANG_USE_AITER_AR=0 -e SGLANG_USE_AITER=0 -e HF_HUB_ENABLE_HF_TRANSFER=0 python3 run_suite.py --hw amd --suite stage-b-test-large-2-gpu-accuracy-amd --timeout-per-file 1800
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-c-test-large-8-gpu-amd-mi35x --auto-partition-id ${{ matrix.part }} --auto-partition-size 1 --timeout-per-file 3600
pr-test-amd-finish:
needs:
@@ -891,12 +736,8 @@ jobs:
stage-a-test-1-amd,
stage-b-test-small-1-gpu-amd,
stage-b-test-small-1-gpu-amd-mi35x,
stage-b-test-large-1-gpu-amd,
stage-b-test-large-2-gpu-amd,
stage-b-test-small-1-gpu-performance-amd,
stage-b-test-large-1-gpu-performance-amd,
stage-b-test-large-2-gpu-performance-amd,
stage-b-test-small-1-gpu-accuracy-amd,
stage-b-test-large-2-gpu-accuracy-amd,
stage-c-test-large-8-gpu-amd,
stage-c-test-large-8-gpu-amd-mi35x,
]