xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 08:04:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

[UX] Put CUDA attention backend selection log into one line (#29337)

Browse Source 
Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin 2025-11-25 09:46:18 -05:00 committed by GitHub
parent 794029f012
commit dbc3d9991a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/platforms/cuda.py
View File

@ -407,9 +407,6 @@ class CudaPlatformBase(Platform):
# We have found some valid backends. Select the one with the
# highest priority.
logger.info(
"Valid backends: %s", [b[0].name for b in valid_backends_priorities]
)
sorted_indices = sorted(
range(len(valid_backends_priorities)),
key=lambda i: valid_backends_priorities[i][1],
@ -417,8 +414,9 @@ class CudaPlatformBase(Platform):
selected_index = sorted_indices[0]
selected_backend = valid_backends_priorities[selected_index][0]
logger.info(
"Using %s backend.",
"Using %s attention backend out of potential backends: %s",
selected_backend.name,
[b[0].name for b in valid_backends_priorities],
)
return selected_backend.get_path()