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 17, 05:30 UTC
[Minor] Fix a typo in .pt weight support (#2160)
Woosuk Kwon committed
Dec 17, 2023 at 10:12 UTC
2c9b638065ae8d69f8949e56f87990f1fcfe9255
1 file changed
+1
-1
vllm/model_executor/weight_utils.py
+1
-1
@@ -146,7 +146,7 @@ def prepare_hf_model_weights(
146
raise ValueError(f"Unknown load_format: {load_format}")
147
148
if fall_back_to_pt:
149
- allow_patterns += [".pt"]
149
+ allow_patterns += ["*.pt"]
150
151
if not is_local:
152
# Use file lock to prevent multiple processes from