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, 09:30 UTC
Fix the log to correct guide user to install modelscope (#9793)
Signed-off-by: yuze.zyz <yuze.zyz@alibaba-inc.com>
tastelikefeet committed
Oct 30, 2024 at 01:36 UTC
08600ddc685558d8504eb94bbbf382230f6de386
1 file changed
+1
-1
vllm/transformers_utils/__init__.py
+1
-1
@@ -9,7 +9,7 @@ if VLLM_USE_MODELSCOPE:
9
if version.parse(modelscope.__version__) <= version.parse('1.18.0'):
10
raise ImportError(
11
'Using vLLM with ModelScope needs modelscope>=1.18.1, please '
12
- 'install by `pip install modelscope>=1.18.1`')
12
+ 'install by `pip install modelscope -U`')
13
14
from modelscope.utils.hf_util import patch_hub
15