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, 23:30 UTC
[Bugfix] Remove noisy error logging during local model loading (#13458)
Isotr0py committed
Feb 18, 2025 at 19:15 UTC
29fc5772c45710bb57736cc876c52637a8691eca
1 file changed
+1
-2
vllm/transformers_utils/config.py
+1
-2
@@ -504,8 +504,7 @@ def get_sentence_transformer_tokenizer_config(model: str,
504
repo_files = list_repo_files(model,
505
revision=revision,
506
token=HF_TOKEN)
507
- except Exception as e:
508
- logger.error("Error getting repo files", e)
507
+ except Exception:
508
repo_files = []
509
510
for config_name in sentence_transformer_config_files: