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, 18:15 UTC
[ci][test] fix RemoteOpenAIServer (#7838)
youkaichao committed
Aug 24, 2024 at 10:31 UTC
aab0fcdb63e322f717704e9d77199f63e036d59b
1 file changed
+1
-1
tests/utils.py
+1
-1
@@ -68,7 +68,7 @@ class RemoteOpenAIServer:
68
if not model.startswith("/"):
69
# download the model if it's not a local path
70
# to exclude the model download time from the server start time
71
- model = snapshot_download(model)
71
+ snapshot_download(model)
72
if auto_port:
73
if "-p" in cli_args or "--port" in cli_args:
74
raise ValueError("You have manually specified the port"