github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9375] Update PS API to show whether a model is active or not #31880

New Issue
Open
opened 2026-04-22 12:39:31 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 12:39:31 -05:00
Owner
Copy Link

Originally created by @ankh2054 on GitHub (Feb 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9375

Hi,

Wondering if there is scope to expand ollama ps, to show whether inference is currently happening OR what the current load if on the GPU.
Currently when using ollama ps, it shows historical values. It would be great to be able to see whether a ollama server is currently busy.

Originally created by @ankh2054 on GitHub (Feb 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9375 Hi, Wondering if there is scope to expand ollama ps, to show whether inference is currently happening OR what the current load if on the GPU. Currently when using ollama ps, it shows historical values. It would be great to be able to see whether a ollama server is currently busy.
GiteaMirror added the feature request label 2026-04-22 12:39:31 -05:00
GiteaMirror commented 2026-04-22 12:39:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 26, 2025):

ollama ps doesn't show GPU load, it shows how much of the model is loaded on the GPU/CPU. If you want to monitor load, Windows has a system monitor and Linux users use nvtop.

<!-- gh-comment-id:2686155280 --> @rick-github commented on GitHub (Feb 26, 2025): `ollama ps` doesn't show GPU load, it shows how much of the model is loaded on the GPU/CPU. If you want to monitor load, Windows has a system monitor and Linux users use `nvtop`.
GiteaMirror commented 2026-04-22 12:39:34 -05:00
Author
Owner
Copy Link

@ankh2054 commented on GitHub (Feb 26, 2025):

I wasn't explaining myself correctly, I was thinking around whether a model is currently active. I think I have found a way by looking at the refCount, which I believe shows how many active requests are using the model. Need to do some testing on my end first.

will report back.

<!-- gh-comment-id:2686227666 --> @ankh2054 commented on GitHub (Feb 26, 2025): I wasn't explaining myself correctly, I was thinking around whether a model is currently active. I think I have found a way by looking at the refCount, which I believe shows how many active requests are using the model. Need to do some testing on my end first. will report back.
GiteaMirror commented 2026-04-22 12:39:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 26, 2025):

https://github.com/ollama/ollama/issues/3144

<!-- gh-comment-id:2686238308 --> @rick-github commented on GitHub (Feb 26, 2025): https://github.com/ollama/ollama/issues/3144
GiteaMirror commented 2026-04-22 12:39:35 -05:00
Author
Owner
Copy Link

@ankh2054 commented on GitHub (Feb 27, 2025):

Okay I can confirm it works, I have created a pull request. This is my first time doing a PR for Ollama, so apologies if I did something wrong.
https://github.com/ollama/ollama/pull/9392

Example shows whether a model is currently active or not.

user@unknown ~/ollama (feature/active-inference-status)> ./ollama ps
NAME              ID              SIZE      PROCESSOR    ACTIVE    UNTIL              
deepseek-r1:7b    0a8c26691023    6.0 GB    100% GPU     Yes       4 minutes from now    
user@unknown ~/ollama (feature/active-inference-status)> ./ollama ps
NAME              ID              SIZE      PROCESSOR    ACTIVE    UNTIL              
deepseek-r1:7b    0a8c26691023    6.0 GB    100% GPU     No        4 minutes from now
<!-- gh-comment-id:2687627819 --> @ankh2054 commented on GitHub (Feb 27, 2025): Okay I can confirm it works, I have created a pull request. This is my first time doing a PR for Ollama, so apologies if I did something wrong. https://github.com/ollama/ollama/pull/9392 Example shows whether a model is currently active or not. ``` user@unknown ~/ollama (feature/active-inference-status)> ./ollama ps NAME ID SIZE PROCESSOR ACTIVE UNTIL deepseek-r1:7b 0a8c26691023 6.0 GB 100% GPU Yes 4 minutes from now user@unknown ~/ollama (feature/active-inference-status)> ./ollama ps NAME ID SIZE PROCESSOR ACTIVE UNTIL deepseek-r1:7b 0a8c26691023 6.0 GB 100% GPU No 4 minutes from now ```
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#31880
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?