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, 22:15 UTC
[Bugfix] Modify modelscope api usage in transformer_utils (#13807)
Shanshan Shen committed
Feb 25, 2025 at 16:36 UTC
2d87d7d1ac0bfa9a33a93d7f9ca7fc1389a686f7
1 file changed
+1
-2
vllm/transformers_utils/utils.py
+1
-2
@@ -29,9 +29,8 @@ def modelscope_list_repo_files(
29
) -> List[str]:
30
"""List files in a modelscope repo."""
31
from modelscope.hub.api import HubApi
32
- from modelscope.utils.hf_util import _try_login
33
- _try_login(token)
32
api = HubApi()
33
+ api.login(token)
34
# same as huggingface_hub.list_repo_files
35
files = [
36
file['Path'] for file in api.get_model_files(