minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[AMD] Fix multimodal timeout issue : rocm7.2 PR Test (#23247)

Browse Source
This commit is contained in:
YC Yen-Ching Tseng
2026-04-20 18:36:08 +08:00
committed by GitHub
parent cf4b84f839
commit da62e90904
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/pr-test-amd-rocm720.yml
+2 -2
View File
@@ -667,7 +667,7 @@ jobs:
max-parallel: 1 # Run one at a time to avoid eviction from resource exhaustion during AITER kernel JIT max-parallel: 1 # Run one at a time to avoid eviction from resource exhaustion during AITER kernel JIT
matrix: matrix:
runner: [linux-mi325-2gpu-sglang] runner: [linux-mi325-2gpu-sglang]
part: [0, 1] # 2 partitions: 9 tests ÷ 2 = ~4-5 tests each part: [0, 1, 2] # 3 partitions: 2 parametrized + 1 standalone (test_disagg_server.py)
runs-on: ${{matrix.runner}} runs-on: ${{matrix.runner}}
steps: steps:
- name: Checkout code - name: Checkout code
@@ -773,7 +773,7 @@ jobs:
ci_sglang python3 sglang/multimodal_gen/test/run_suite.py \ ci_sglang python3 sglang/multimodal_gen/test/run_suite.py \
--suite 2-gpu \ --suite 2-gpu \
--partition-id ${{ matrix.part }} \ --partition-id ${{ matrix.part }} \
--total-partitions 2 --total-partitions 3
# Post-test diagnostics # Post-test diagnostics
echo "=== Post-test System Memory Status ===" echo "=== Post-test System Memory Status ==="