Fix potential memory fault issue and ncclSystemError in CI test (#8681)
Co-authored-by: wunhuang <wunhuang@amd.com>
This commit is contained in:
2
.github/workflows/pr-test-amd.yml
vendored
2
.github/workflows/pr-test-amd.yml
vendored
@@ -291,7 +291,7 @@ jobs:
|
||||
bash scripts/amd_ci_exec.sh python3 run_suite.py --suite per-commit-8-gpu-amd --timeout-per-file 3600
|
||||
|
||||
- name: Run CustomAllReduce test
|
||||
timeout-minutes: 10
|
||||
timeout-minutes: 20
|
||||
run: |
|
||||
bash scripts/amd_ci_exec.sh -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python3 -m unittest test_custom_allreduce.TestCustomAllReduce
|
||||
|
||||
|
||||
Reference in New Issue
Block a user