[AMD] AMD AITER Scout Workflow (#19467)

Co-authored-by: Bingxu Chen <Bingxu.Chen@amd.com>
This commit is contained in:
YC Tseng
2026-03-02 16:10:44 +08:00
committed by GitHub
co-authored by Bingxu Chen
parent 98f47d8175
commit f2c5503542
7 changed files with 1758 additions and 148 deletions
+44 -32
View File
@@ -37,6 +37,16 @@ on:
required: false
type: string
default: ""
aiter_ref:
description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
required: false
type: string
default: ''
continue_on_error:
description: 'Continue on error (do not fail the workflow on test failures)'
required: false
type: boolean
default: true
workflow_call:
inputs:
ref:
@@ -49,6 +59,19 @@ on:
required: false
type: boolean
default: false
aiter_ref:
description: 'Override AITER commit (optional, leave empty to use Dockerfile default)'
required: false
type: string
default: ''
continue_on_error:
description: 'Continue on error (do not fail the workflow on test failures)'
required: false
type: boolean
default: true
env:
AITER_COMMIT_OVERRIDE: ${{ inputs.aiter_ref }}
concurrency:
# Include pr_head_sha in group for /rerun-stage dispatches to avoid collisions with main branch runs
@@ -146,8 +169,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 14
run: |
@@ -193,8 +215,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 20
run: |
@@ -236,12 +257,11 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run test
timeout-minutes: 10
run: |
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd --continue-on-error
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-amd ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
jit-kernel-unit-test-amd:
needs: [check-changes]
@@ -275,8 +295,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Run JIT kernel unit tests
timeout-minutes: 10
run: |
@@ -315,12 +334,11 @@ jobs:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
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-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 --timeout-per-file 1800 --continue-on-error
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 --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-small-1-gpu-amd-nondeterministic:
needs: [check-changes]
@@ -354,12 +372,11 @@ jobs:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
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-amd-nondeterministic --timeout-per-file 1800 --continue-on-error
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-nondeterministic --timeout-per-file 1800 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-small-1-gpu-amd-mi35x:
needs: [check-changes]
@@ -393,12 +410,11 @@ jobs:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
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-amd-mi35x --continue-on-error
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 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-large-1-gpu-amd:
needs: [check-changes]
@@ -433,12 +449,11 @@ jobs:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
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-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file 1800 --continue-on-error
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 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-b-test-large-2-gpu-amd:
needs: [check-changes]
@@ -473,12 +488,11 @@ jobs:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
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 --continue-on-error
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 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
multimodal-gen-test-1-gpu-amd:
needs: [check-changes]
@@ -523,7 +537,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build diffusion
bash scripts/ci/amd/amd_ci_install_dependency.sh diffusion
docker exec ci_sglang pip install amdsmi
- name: Setup kernel caches
@@ -653,7 +667,7 @@ jobs:
- name: Install dependencies
run: |
bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build diffusion
bash scripts/ci/amd/amd_ci_install_dependency.sh diffusion
docker exec ci_sglang pip install amdsmi
- name: Setup kernel caches
@@ -774,8 +788,7 @@ jobs:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- name: Test RCCL multi-GPU communication
timeout-minutes: 5
run: |
@@ -785,7 +798,7 @@ 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 3 --timeout-per-file 3600 --continue-on-error
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 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
stage-c-test-large-8-gpu-amd-mi35x:
needs: [check-changes]
@@ -820,12 +833,11 @@ jobs:
GITHUB_WORKSPACE: ${{ github.workspace }}
- name: Install dependencies
run: bash scripts/ci/amd/amd_ci_install_dependency.sh --skip-aiter-build
run: bash scripts/ci/amd/amd_ci_install_dependency.sh
- 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 1 --timeout-per-file 3600 --continue-on-error
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 ${{ inputs.continue_on_error && '--continue-on-error' || '' }}
pr-test-amd-finish:
needs: