Originally created by @yeahdongcn on GitHub (Jan 31, 2024).
Is your feature request related to a problem? Please describe.
In serving multi-models, I'd like to see the GPU metrics through UI.
Describe the solution you'd like
I have done some experiments in my repo OllamaStack, but the metrics couldn't reflect enough information, and the whole setup is somewhat complicated.
Describe alternatives you've considered
N/A
Additional context
N/A
Originally created by @yeahdongcn on GitHub (Jan 31, 2024).
**Is your feature request related to a problem? Please describe.**
In serving multi-models, I'd like to see the GPU metrics through UI.
**Describe the solution you'd like**
I have done some experiments in my repo [OllamaStack](https://github.com/yeahdongcn/OllamaStack), but the metrics couldn't reflect enough information, and the whole setup is somewhat complicated.
**Describe alternatives you've considered**
N/A
**Additional context**
N/A
Yes, as an addition to that you could also implement a total/monthly tokens used per user/of all users in the dashboard.
@jannikstdl commented on GitHub (Feb 7, 2024):
Yes, as an addition to that you could also implement a total/monthly tokens used per user/of all users in the dashboard.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @yeahdongcn on GitHub (Jan 31, 2024).
Is your feature request related to a problem? Please describe.
In serving multi-models, I'd like to see the GPU metrics through UI.
Describe the solution you'd like
I have done some experiments in my repo OllamaStack, but the metrics couldn't reflect enough information, and the whole setup is somewhat complicated.
Describe alternatives you've considered
N/A
Additional context
N/A
@jannikstdl commented on GitHub (Feb 7, 2024):
Yes, as an addition to that you could also implement a total/monthly tokens used per user/of all users in the dashboard.
@tjbck commented on GitHub (Apr 10, 2024):
Closing in favour of #1450, Let's continue our discussion there!