[AMD] AMD CI - temporarily change to mi325 (#26443)
This commit is contained in:
@@ -63,7 +63,7 @@ on:
|
|||||||
description: 'AMD runner pool to dispatch GPU jobs to'
|
description: 'AMD runner pool to dispatch GPU jobs to'
|
||||||
required: false
|
required: false
|
||||||
type: choice
|
type: choice
|
||||||
default: mi300
|
default: mi325
|
||||||
options:
|
options:
|
||||||
- mi300
|
- mi300
|
||||||
- mi325
|
- mi325
|
||||||
@@ -180,7 +180,7 @@ jobs:
|
|||||||
|
|
||||||
# =============================================== sgl-kernel ====================================================
|
# =============================================== sgl-kernel ====================================================
|
||||||
sgl-kernel-unit-test-amd:
|
sgl-kernel-unit-test-amd:
|
||||||
name: ${{ format('sgl-kernel-unit-test-amd (linux-{0}-1gpu-sglang)', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
name: ${{ format('sgl-kernel-unit-test-amd (linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi325') }}
|
||||||
needs: [check-changes, call-gate]
|
needs: [check-changes, call-gate]
|
||||||
if: |
|
if: |
|
||||||
always() && !cancelled() &&
|
always() && !cancelled() &&
|
||||||
@@ -192,7 +192,7 @@ jobs:
|
|||||||
needs.check-changes.outputs.sgl_kernel == 'true'
|
needs.check-changes.outputs.sgl_kernel == 'true'
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
steps:
|
steps:
|
||||||
- name: Checkout code
|
- name: Checkout code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
@@ -238,7 +238,7 @@ jobs:
|
|||||||
exit $failures
|
exit $failures
|
||||||
|
|
||||||
sgl-kernel-unit-test-2-gpu-amd:
|
sgl-kernel-unit-test-2-gpu-amd:
|
||||||
name: ${{ format('sgl-kernel-unit-test-2-gpu-amd (linux-{0}-2gpu-sglang)', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
name: ${{ format('sgl-kernel-unit-test-2-gpu-amd (linux-{0}-2gpu-sglang)', inputs.runner_arch || 'mi325') }}
|
||||||
needs: [check-changes, call-gate]
|
needs: [check-changes, call-gate]
|
||||||
if: |
|
if: |
|
||||||
always() && !cancelled() &&
|
always() && !cancelled() &&
|
||||||
@@ -250,7 +250,7 @@ jobs:
|
|||||||
needs.check-changes.outputs.sgl_kernel == 'true'
|
needs.check-changes.outputs.sgl_kernel == 'true'
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
runs-on: ${{ format('linux-{0}-2gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
runs-on: ${{ format('linux-{0}-2gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
steps:
|
steps:
|
||||||
- name: Checkout code
|
- name: Checkout code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
@@ -289,7 +289,7 @@ jobs:
|
|||||||
# =============================================== primary ====================================================
|
# =============================================== primary ====================================================
|
||||||
|
|
||||||
stage-a-test-1-gpu-small-amd:
|
stage-a-test-1-gpu-small-amd:
|
||||||
name: ${{ format('stage-a-test-1-gpu-small-amd (linux-{0}-1gpu-sglang)', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
name: ${{ format('stage-a-test-1-gpu-small-amd (linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi325') }}
|
||||||
needs: [check-changes, call-gate]
|
needs: [check-changes, call-gate]
|
||||||
if: |
|
if: |
|
||||||
always() && !cancelled() &&
|
always() && !cancelled() &&
|
||||||
@@ -301,7 +301,7 @@ jobs:
|
|||||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
steps:
|
steps:
|
||||||
- name: Checkout code
|
- name: Checkout code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
@@ -326,7 +326,7 @@ jobs:
|
|||||||
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-a-test-1-gpu-small-amd ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--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-gpu-small-amd ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||||
|
|
||||||
jit-kernel-unit-test-amd:
|
jit-kernel-unit-test-amd:
|
||||||
name: ${{ format('jit-kernel-unit-test-amd (linux-{0}-1gpu-sglang)', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
name: ${{ format('jit-kernel-unit-test-amd (linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi325') }}
|
||||||
needs: [check-changes, call-gate]
|
needs: [check-changes, call-gate]
|
||||||
if: |
|
if: |
|
||||||
always() && !cancelled() &&
|
always() && !cancelled() &&
|
||||||
@@ -338,7 +338,7 @@ jobs:
|
|||||||
needs.check-changes.outputs.jit_kernel == 'true'
|
needs.check-changes.outputs.jit_kernel == 'true'
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
steps:
|
steps:
|
||||||
- name: Checkout code
|
- name: Checkout code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
@@ -389,7 +389,7 @@ jobs:
|
|||||||
max-wait-minutes: '240'
|
max-wait-minutes: '240'
|
||||||
|
|
||||||
stage-b-test-1-gpu-small-amd:
|
stage-b-test-1-gpu-small-amd:
|
||||||
name: ${{ format('stage-b-test-1-gpu-small-amd (linux-{0}-1gpu-sglang, {1})', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325'), matrix.part) }}
|
name: ${{ format('stage-b-test-1-gpu-small-amd (linux-{0}-1gpu-sglang, {1})', inputs.runner_arch || 'mi325', matrix.part) }}
|
||||||
needs: [check-changes, wait-for-stage-a-amd]
|
needs: [check-changes, wait-for-stage-a-amd]
|
||||||
if: |
|
if: |
|
||||||
always() &&
|
always() &&
|
||||||
@@ -405,7 +405,7 @@ jobs:
|
|||||||
fail-fast: false
|
fail-fast: false
|
||||||
matrix:
|
matrix:
|
||||||
part: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
|
part: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
|
||||||
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
steps:
|
steps:
|
||||||
- name: Checkout code
|
- name: Checkout code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
@@ -429,7 +429,7 @@ jobs:
|
|||||||
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 14 --timeout-per-file 2400 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--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-1-gpu-small-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 14 --timeout-per-file 2400 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||||
|
|
||||||
stage-b-test-1-gpu-small-amd-nondeterministic:
|
stage-b-test-1-gpu-small-amd-nondeterministic:
|
||||||
name: ${{ format('stage-b-test-1-gpu-small-amd-nondeterministic (linux-{0}-1gpu-sglang)', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
name: ${{ format('stage-b-test-1-gpu-small-amd-nondeterministic (linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi325') }}
|
||||||
needs: [check-changes, wait-for-stage-a-amd]
|
needs: [check-changes, wait-for-stage-a-amd]
|
||||||
if: |
|
if: |
|
||||||
always() &&
|
always() &&
|
||||||
@@ -441,7 +441,7 @@ jobs:
|
|||||||
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
((needs.check-changes.outputs.main_package == 'true') || (needs.check-changes.outputs.sgl_kernel == 'true'))
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
steps:
|
steps:
|
||||||
- name: Checkout code
|
- name: Checkout code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
@@ -504,7 +504,7 @@ jobs:
|
|||||||
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-small-amd-mi35x ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--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-1-gpu-small-amd-mi35x ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||||
|
|
||||||
stage-b-test-1-gpu-large-amd:
|
stage-b-test-1-gpu-large-amd:
|
||||||
name: ${{ format('stage-b-test-1-gpu-large-amd (linux-{0}-1gpu-sglang, {1})', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325'), matrix.part) }}
|
name: ${{ format('stage-b-test-1-gpu-large-amd (linux-{0}-1gpu-sglang, {1})', inputs.runner_arch || 'mi325', matrix.part) }}
|
||||||
needs: [check-changes, wait-for-stage-a-amd]
|
needs: [check-changes, wait-for-stage-a-amd]
|
||||||
if: |
|
if: |
|
||||||
always() &&
|
always() &&
|
||||||
@@ -520,7 +520,7 @@ jobs:
|
|||||||
fail-fast: false
|
fail-fast: false
|
||||||
matrix:
|
matrix:
|
||||||
part: [0, 1, 2]
|
part: [0, 1, 2]
|
||||||
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
runs-on: ${{ format('linux-{0}-1gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
steps:
|
steps:
|
||||||
- name: Checkout code
|
- name: Checkout code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
@@ -544,7 +544,7 @@ jobs:
|
|||||||
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-1-gpu-large-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 2700 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--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-1-gpu-large-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 2700 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||||
|
|
||||||
stage-b-test-2-gpu-large-amd:
|
stage-b-test-2-gpu-large-amd:
|
||||||
name: ${{ format('stage-b-test-2-gpu-large-amd (linux-{0}-2gpu-sglang, {1})', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325'), matrix.part) }}
|
name: ${{ format('stage-b-test-2-gpu-large-amd (linux-{0}-2gpu-sglang, {1})', inputs.runner_arch || 'mi325', matrix.part) }}
|
||||||
needs: [check-changes, wait-for-stage-a-amd]
|
needs: [check-changes, wait-for-stage-a-amd]
|
||||||
if: |
|
if: |
|
||||||
always() &&
|
always() &&
|
||||||
@@ -560,7 +560,7 @@ jobs:
|
|||||||
fail-fast: false
|
fail-fast: false
|
||||||
matrix:
|
matrix:
|
||||||
part: [0, 1]
|
part: [0, 1]
|
||||||
runs-on: ${{ format('linux-{0}-2gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
runs-on: ${{ format('linux-{0}-2gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
steps:
|
steps:
|
||||||
- name: Checkout code
|
- name: Checkout code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
@@ -889,7 +889,7 @@ jobs:
|
|||||||
max-wait-minutes: '480'
|
max-wait-minutes: '480'
|
||||||
|
|
||||||
stage-c-test-4-gpu-amd:
|
stage-c-test-4-gpu-amd:
|
||||||
name: ${{ format('stage-c-test-4-gpu-amd (linux-{0}-4gpu-sglang, {1})', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325'), matrix.part) }}
|
name: ${{ format('stage-c-test-4-gpu-amd (linux-{0}-4gpu-sglang, {1})', inputs.runner_arch || 'mi325', matrix.part) }}
|
||||||
needs: [check-changes, call-gate, wait-for-stage-b-amd]
|
needs: [check-changes, call-gate, wait-for-stage-b-amd]
|
||||||
if: |
|
if: |
|
||||||
always() &&
|
always() &&
|
||||||
@@ -905,7 +905,7 @@ jobs:
|
|||||||
fail-fast: false
|
fail-fast: false
|
||||||
matrix:
|
matrix:
|
||||||
part: [0]
|
part: [0]
|
||||||
runs-on: ${{ format('linux-{0}-4gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
runs-on: ${{ format('linux-{0}-4gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
steps:
|
steps:
|
||||||
- name: Checkout code
|
- name: Checkout code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
@@ -945,7 +945,7 @@ jobs:
|
|||||||
${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
|
||||||
|
|
||||||
stage-c-test-large-8-gpu-amd:
|
stage-c-test-large-8-gpu-amd:
|
||||||
name: ${{ format('stage-c-test-large-8-gpu-amd (linux-{0}-8gpu-sglang, {1})', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325'), matrix.part) }}
|
name: ${{ format('stage-c-test-large-8-gpu-amd (linux-{0}-8gpu-sglang, {1})', inputs.runner_arch || 'mi325', matrix.part) }}
|
||||||
needs: [check-changes, call-gate, wait-for-stage-b-amd]
|
needs: [check-changes, call-gate, wait-for-stage-b-amd]
|
||||||
if: |
|
if: |
|
||||||
always() &&
|
always() &&
|
||||||
@@ -958,12 +958,12 @@ jobs:
|
|||||||
)
|
)
|
||||||
)
|
)
|
||||||
env:
|
env:
|
||||||
RUNNER_LABELS: ${{ format('linux-{0}-8gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
RUNNER_LABELS: ${{ format('linux-{0}-8gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
strategy:
|
strategy:
|
||||||
fail-fast: false
|
fail-fast: false
|
||||||
matrix:
|
matrix:
|
||||||
part: [0, 1, 2]
|
part: [0, 1, 2]
|
||||||
runs-on: ${{ format('linux-{0}-8gpu-sglang', inputs.runner_arch || (github.event_name == 'pull_request' && 'mi300' || 'mi325')) }}
|
runs-on: ${{ format('linux-{0}-8gpu-sglang', inputs.runner_arch || 'mi325') }}
|
||||||
steps:
|
steps:
|
||||||
- name: Checkout code
|
- name: Checkout code
|
||||||
uses: actions/checkout@v4
|
uses: actions/checkout@v4
|
||||||
|
|||||||
Reference in New Issue
Block a user