github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10940] Detailed info in /api/ps or other new endpoint #53716

New Issue
Closed
opened 2026-04-29 04:35:28 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 04:35:28 -05:00
Owner
Copy Link

Originally created by @ckuethe on GitHub (Jun 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10940

I'd like to propose the addition of detailed processing statistics, maybe as an addition to /api/ps or maybe a whole new endpoint, to answer the question "hey ollama, what are you doing right now?"

At this very moment, I happen to have cogito loaded, doing nothing because I haven't asked it to do anything. ollama ps says Cogito is 100% GPU, which is true but it's also not consuming any CPU, and more importantly not consuming any energy. If I tell it to go compute something, amdgpu_top or roc-smi do show that ollama runners are now using a bunch of GPU.

What I'd like to see is a way for ollama to report what's actually running, consuming compute and energy, possibly even the prompt. I'm hacking something together parse the output of rocm-smi (I assume nvidia-smi has similar outputs) to try estimate the energy consumption of running LLMs and possibly each of my queries. It seems like Ollama would be better positioned to report on resource consumption.

Thoughts?

Originally created by @ckuethe on GitHub (Jun 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10940 I'd like to propose the addition of detailed processing statistics, maybe as an addition to `/api/ps` or maybe a whole new endpoint, to answer the question "hey ollama, what are you doing right now?" At this very moment, I happen to have cogito loaded, doing nothing because I haven't asked it to do anything. `ollama ps` says Cogito is 100% GPU, which is true but it's also not consuming any CPU, and more importantly not consuming any energy. If I tell it to go compute something, `amdgpu_top` or `roc-smi` do show that ollama runners are now using a bunch of GPU. What I'd like to see is a way for ollama to report what's actually running, consuming compute and energy, possibly even the prompt. I'm hacking something together parse the output of `rocm-smi` (I assume `nvidia-smi` has similar outputs) to try estimate the energy consumption of running LLMs and possibly each of my queries. It seems like Ollama would be better positioned to report on resource consumption. Thoughts?
GiteaMirror added the feature request label 2026-04-29 04:35:28 -05:00
GiteaMirror commented 2026-04-29 04:35:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jun 1, 2025):

#3144

<!-- gh-comment-id:2927945818 --> @rick-github commented on GitHub (Jun 1, 2025): #3144
GiteaMirror commented 2026-04-29 04:35:31 -05:00
Author
Owner
Copy Link

@ckuethe commented on GitHub (Jun 1, 2025):

thanks, I'll follow that issue.

<!-- gh-comment-id:2927956523 --> @ckuethe commented on GitHub (Jun 1, 2025): thanks, I'll follow that issue.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#53716
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?