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 16, 20:45 UTC
[Bugfix]fix modelscope compatible issue (#6730)
liuyhwangyh committed
Jul 24, 2024 at 20:04 UTC
f4f8a9d892a357e341b90bc47a8d72ece62323d5
1 file changed
+1
-1
vllm/model_executor/model_loader/loader.py
+1
-1
@@ -161,7 +161,7 @@ class DefaultModelLoader(BaseModelLoader):
161
cache_dir=self.load_config.download_dir,
162
local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE,
163
revision=revision,
164
- ignore_patterns=self.load_config.ignore_patterns,
164
+ ignore_file_pattern=self.load_config.ignore_patterns,
165
)
166
else:
167
model_path = model