You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
userandpass
changed the title
How to solve the problem of automatically reloading the model on the card if it is called after a certain period of time
How can we make model calls faster
May 17, 2024
After I added the "keep_alive": "24h" parameter, after a while I executed the nvidia-smi command, there was no ollama on the card, so I needed to call the interface to display it
What is the issue?
I used docker to load multiple ollama images and distribute them using nginx, which was much slower than calling the deployed model directly
OS
Linux
GPU
Nvidia
CPU
No response
Ollama version
0.1.34
The text was updated successfully, but these errors were encountered: