@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 2c9b638065
Fork 0

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