[AMD][CI] Name the ROCm Image That Actually Ran in AMD Job Names (#35686)

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Bingxu Chen
2026-08-24 01:07:25 -07:00
committed by GitHub
co-authored by Cursor
parent 5c4622341f
commit 7de80e566c
9 changed files with 327 additions and 88 deletions
+16 -13
View File
@@ -226,7 +226,7 @@ jobs:
# =============================================== sgl-kernel ====================================================
sgl-kernel-unit-test-amd:
name: ${{ format('sgl-kernel-unit-test-amd (linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi300') }}
name: ${{ format('sgl-kernel-unit-test-amd (rocm700, linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi300') }}
needs: [check-changes, call-gate]
if: |
always() && !cancelled() &&
@@ -284,7 +284,7 @@ jobs:
exit $failures
sgl-kernel-unit-test-2-gpu-amd:
name: ${{ format('sgl-kernel-unit-test-2-gpu-amd (linux-{0}-2gpu-sglang)', inputs.runner_arch || 'mi300') }}
name: ${{ format('sgl-kernel-unit-test-2-gpu-amd (rocm700, linux-{0}-2gpu-sglang)', inputs.runner_arch || 'mi300') }}
needs: [check-changes, call-gate]
if: |
always() && !cancelled() &&
@@ -325,7 +325,7 @@ jobs:
# =============================================== primary ====================================================
stage-a-test-1-gpu-small-amd:
name: ${{ format('stage-a-test-1-gpu-small-amd (linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi300') }}
name: ${{ format('stage-a-test-1-gpu-small-amd (rocm700, linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi300') }}
needs: [check-changes, call-gate]
if: |
always() && !cancelled() &&
@@ -362,7 +362,7 @@ 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' || '' }}
jit-kernel-unit-test-amd:
name: ${{ format('jit-kernel-unit-test-amd (linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi300') }}
name: ${{ format('jit-kernel-unit-test-amd (rocm700, linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi300') }}
needs: [check-changes, call-gate]
if: |
always() && !cancelled() &&
@@ -399,7 +399,7 @@ jobs:
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite jit-kernel-unit-test-amd ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
jit-kernel-benchmark-test-amd:
name: ${{ format('jit-kernel-benchmark-test-amd (linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi300') }}
name: ${{ format('jit-kernel-benchmark-test-amd (rocm700, linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi300') }}
needs: [check-changes, call-gate]
if: |
always() && !cancelled() &&
@@ -462,7 +462,7 @@ jobs:
max-wait-minutes: '240'
stage-b-test-1-gpu-small-amd:
name: ${{ format('stage-b-test-1-gpu-small-amd (linux-{0}-1gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
name: ${{ format('stage-b-test-1-gpu-small-amd (rocm700, linux-{0}-1gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
needs: [check-changes, wait-for-stage-a-amd]
if: |
always() &&
@@ -502,7 +502,7 @@ 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' || '' }}
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 || 'mi300') }}
name: ${{ format('stage-b-test-1-gpu-small-amd-nondeterministic (rocm700, linux-{0}-1gpu-sglang)', inputs.runner_arch || 'mi300') }}
needs: [check-changes, wait-for-stage-a-amd]
if: |
always() &&
@@ -538,6 +538,7 @@ 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-nondeterministic --timeout-per-file 3600 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
stage-b-test-1-gpu-small-amd-mi35x:
name: ${{ format('stage-b-test-1-gpu-small-amd-mi35x (rocm700, {0})', matrix.runner) }}
needs: [check-changes, wait-for-stage-a-amd]
if: |
always() &&
@@ -577,7 +578,7 @@ 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' || '' }}
stage-b-test-1-gpu-large-amd:
name: ${{ format('stage-b-test-1-gpu-large-amd (linux-{0}-1gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
name: ${{ format('stage-b-test-1-gpu-large-amd (rocm700, linux-{0}-1gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
needs: [check-changes, wait-for-stage-a-amd]
if: |
always() &&
@@ -617,7 +618,7 @@ 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' || '' }}
stage-b-test-2-gpu-large-amd:
name: ${{ format('stage-b-test-2-gpu-large-amd (linux-{0}-2gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
name: ${{ format('stage-b-test-2-gpu-large-amd (rocm700, linux-{0}-2gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
needs: [check-changes, wait-for-stage-a-amd]
if: |
always() &&
@@ -657,7 +658,7 @@ jobs:
bash scripts/ci/amd/amd_ci_exec.sh -w "/sglang-checkout/test" python3 run_suite.py --hw amd --suite stage-b-test-2-gpu-large-amd --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 --timeout-per-file ${{ (inputs.runner_arch || 'mi300') == 'mi300' && 5400 || 2700 }} ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
multimodal-gen-test-1-gpu-amd:
name: ${{ format('multimodal-gen-test-1-gpu-amd (linux-{0}-1gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
name: ${{ format('multimodal-gen-test-1-gpu-amd (rocm700, linux-{0}-1gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
needs: [check-changes, call-gate]
if: |
always() && !cancelled() &&
@@ -805,7 +806,7 @@ jobs:
retention-days: 7
multimodal-gen-test-2-gpu-amd:
name: ${{ format('multimodal-gen-test-2-gpu-amd (linux-{0}-2gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
name: ${{ format('multimodal-gen-test-2-gpu-amd (rocm700, linux-{0}-2gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
needs: [check-changes, call-gate]
if: |
always() && !cancelled() &&
@@ -966,7 +967,7 @@ jobs:
max-wait-minutes: '480'
stage-c-test-4-gpu-amd:
name: ${{ format('stage-c-test-4-gpu-amd (linux-{0}-4gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
name: ${{ format('stage-c-test-4-gpu-amd (rocm700, linux-{0}-4gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
needs: [check-changes, call-gate, wait-for-stage-b-amd]
if: |
always() &&
@@ -1022,7 +1023,7 @@ jobs:
${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
stage-c-test-large-8-gpu-amd:
name: ${{ format('stage-c-test-large-8-gpu-amd (linux-{0}-8gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
name: ${{ format('stage-c-test-large-8-gpu-amd (rocm700, linux-{0}-8gpu-sglang, {1})', inputs.runner_arch || 'mi300', matrix.part) }}
needs: [check-changes, call-gate, wait-for-stage-b-amd]
if: |
always() &&
@@ -1070,6 +1071,7 @@ jobs:
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 4 --timeout-per-file 5400 ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }}
stage-c-test-large-8-gpu-amd-mi35x:
name: ${{ format('stage-c-test-large-8-gpu-amd-mi35x (rocm700, {0}, {1})', matrix.runner, matrix.part) }}
needs: [check-changes, call-gate, wait-for-stage-b-amd]
if: |
always() &&
@@ -1111,6 +1113,7 @@ jobs:
# =============================================== Disaggregation ====================================================
stage-b-test-large-8-gpu-mi35x-disaggregation-amd:
name: ${{ format('stage-b-test-large-8-gpu-mi35x-disaggregation-amd (rocm700, {0})', matrix.runner) }}
needs: [check-changes, wait-for-stage-a-amd]
if: |
always() &&