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, 15:45 UTC
[Bugfix] Config got an unexpected keyword argument 'engine' (#8556)
Pastel! committed
Sep 21, 2024 at 05:00 UTC
2874bac618052a079efd837fc82cf3f3519079c7
1 file changed
-1
vllm/entrypoints/api_server.py
-1
@@ -121,7 +121,6 @@ async def run_server(args: Namespace,
121
122
shutdown_task = await serve_http(
123
app,
124
- engine=engine,
124
host=args.host,
125
port=args.port,
126
log_level=args.log_level,