A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 13:30 UTC
[Bugfix] Fix f-string for Python 3.9-3.11 (#16962)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Apr 22, 2025 at 12:45 UTC
d6da9322c84feb83884a177e8a445986b88b7223
1 file changed
+1
-1
vllm/model_executor/model_loader/loader.py
+1
-1
@@ -703,7 +703,7 @@ class ShardedStateLoader(BaseModelLoader):
703
704
filepaths = []
705
if is_s3(local_model_path):
706
- file_pattern = f"*{self.pattern.format(rank=rank, part=" * ")}"
706
+ file_pattern = f"*{self.pattern.format(rank=rank, part=' * ')}"
707
filepaths = s3_glob(path=local_model_path,
708
allow_pattern=[file_pattern])
709
else: