Add model validation for all GPU runners to prevent cache corruption (#13171)
Co-authored-by: Kangyan Zhou <zky314343421@gmail.com>
This commit is contained in:
co-authored by
Kangyan Zhou
parent
85b8c5c4cd
commit
9bd511a582
@@ -202,6 +202,8 @@ jobs:
|
||||
needs: [check-changes, sgl-kernel-build-wheels]
|
||||
if: needs.check-changes.outputs.sgl_kernel == 'true'
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 1-gpu-runner
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
@@ -231,6 +233,8 @@ jobs:
|
||||
needs: [check-changes, sgl-kernel-build-wheels]
|
||||
if: needs.check-changes.outputs.sgl_kernel == 'true'
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 1-gpu-runner
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
@@ -262,6 +266,7 @@ jobs:
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
CI: true
|
||||
RUNNER_LABELS: 1-gpu-runner
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
@@ -350,6 +355,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 1-gpu-runner
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
@@ -377,6 +384,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 1-gpu-runner
|
||||
strategy:
|
||||
fail-fast: false
|
||||
max-parallel: 5
|
||||
@@ -409,6 +418,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 2-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 2-gpu-runner
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
@@ -440,6 +451,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 4-gpu-h100
|
||||
env:
|
||||
RUNNER_LABELS: 4-gpu-h100
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
@@ -506,6 +519,7 @@ jobs:
|
||||
runs-on: 8-gpu-h20
|
||||
env:
|
||||
SGLANG_CI_RDMA_ALL_DEVICES: "mlx5_1,mlx5_2,mlx5_3,mlx5_4"
|
||||
RUNNER_LABELS: 8-gpu-h20
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
@@ -537,6 +551,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 1-gpu-runner
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
@@ -596,6 +612,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 1-gpu-runner
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
@@ -647,6 +665,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 1-gpu-runner
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
@@ -680,6 +700,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 2-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 2-gpu-runner
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
@@ -737,6 +759,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 1-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 1-gpu-runner
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
@@ -767,6 +791,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 2-gpu-runner
|
||||
env:
|
||||
RUNNER_LABELS: 2-gpu-runner
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
@@ -797,6 +823,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 4-gpu-h100
|
||||
env:
|
||||
RUNNER_LABELS: 4-gpu-h100
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
@@ -853,6 +881,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 4-gpu-b200
|
||||
env:
|
||||
RUNNER_LABELS: 4-gpu-b200
|
||||
strategy:
|
||||
fail-fast: false
|
||||
steps:
|
||||
@@ -882,6 +912,8 @@ jobs:
|
||||
if: always() && !failure() && !cancelled() &&
|
||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||
runs-on: 4-gpu-gb200
|
||||
env:
|
||||
RUNNER_LABELS: 4-gpu-gb200
|
||||
strategy:
|
||||
fail-fast: false
|
||||
steps:
|
||||
|
||||
Reference in New Issue
Block a user