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, 03:00 UTC
[Bugfix] Ensure download_weights_from_hf(..) inside loader is using the revision parameter (#4217)
alexm-nm committed
Apr 22, 2024 at 12:10 UTC
15436806912d7ad9371c8bcf6a46857590c107d2
1 file changed
+1
-1
vllm/model_executor/model_loader/loader.py
+1
-1
@@ -172,7 +172,7 @@ class DefaultModelLoader(BaseModelLoader):
172
if not is_local:
173
hf_folder = download_weights_from_hf(model_name_or_path,
174
self.load_config.download_dir,
175
- allow_patterns)
175
+ allow_patterns, revision)
176
else:
177
hf_folder = model_name_or_path
178