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 14, 05:30 UTC
[BUG] Fix file parsing for load_format runai_streamer_sharded (#26324)
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
ahao-anyscale committed
Oct 6, 2025 at 20:23 UTC
4dbdf4a2944849a540c97542c4839b87fcd2988c
1 file changed
+1
-1
vllm/model_executor/model_loader/sharded_state_loader.py
+1
-1
@@ -121,7 +121,7 @@ class ShardedStateLoader(BaseModelLoader):
121
122
filepaths = []
123
if is_s3(local_model_path):
124
- file_pattern = f"*{self.pattern.format(rank=rank, part=' * ')}"
124
+ file_pattern = f"*{self.pattern.format(rank=rank, part='*')}"
125
filepaths = s3_glob(path=local_model_path, allow_pattern=[file_pattern])
126
else:
127
filepaths = glob.glob(pattern)