squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] Fix custom_ar support check (#7617)

Browse Source
This commit is contained in:
bnellnm 2024-08-16 22:05:49 -04:00 committed by GitHub
parent 44f26a9466
commit e680349994
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/distributed/device_communicators/custom_all_reduce.py
View File

@ -15,7 +15,7 @@ from vllm.platforms import current_platform
from vllm.utils import cuda_device_count_stateless from vllm.utils import cuda_device_count_stateless
try: try:
assert ops.is_custom_op_supported("_C_custom_ar::meta_size") ops.meta_size()
custom_ar = True custom_ar = True
except Exception: except Exception:
# For AMD GPUs and CPUs # For AMD GPUs and CPUs