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, 06:00 UTC
[Bugfix] Fix modelscope token passed in (#19389)
Signed-off-by: wangli <wangli858794774@gmail.com> Signed-off-by: Jee Jee Li <pandaleefree@gmail.com> Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Li Wang committed
Jun 10, 2025 at 13:39 UTC
1efef716458ab03e0954ef2825ac71cf4f81cf9d
1 file changed
+3
-1
vllm/transformers_utils/config.py
+3
-1
@@ -143,7 +143,9 @@ def list_repo_files(
143
modelscope_list_repo_files)
144
return modelscope_list_repo_files(repo_id,
145
revision=revision,
146
- token=token)
146
+ token=os.getenv(
147
+ "MODELSCOPE_API_TOKEN",
148
+ None))
149
return hf_list_repo_files(repo_id,
150
revision=revision,
151
repo_type=repo_type,