A concurrent HTTP server in order to inference using PyTorch.
If running in GPU server, it will allocate one GPU per worker(process), which is authorized by Gunicorn.
You can assign the number of worker in app.sh file (-w $num_worker)
sh app.sh
-
Notifications
You must be signed in to change notification settings - Fork 1
Gunicorn aiohttp PyTorch, A concurrent HTTP server in order to inference using PyTorch.
itsliupeng/online_http_pytorch
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Gunicorn aiohttp PyTorch, A concurrent HTTP server in order to inference using PyTorch.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published