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 #6904] Option to know number of running request in ollama #30128

New Issue
Closed
opened 2026-04-22 09:36:06 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 09:36:06 -05:00
Owner
Copy Link

Originally created by @Jegatheesh001 on GitHub (Sep 21, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6904

Option to know number of running request in ollama

Originally created by @Jegatheesh001 on GitHub (Sep 21, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6904 Option to know number of running request in ollama
GiteaMirror added the feature request label 2026-04-22 09:36:06 -05:00
GiteaMirror commented 2026-04-22 09:36:07 -05:00
Author
Owner
Copy Link

@byarbrough commented on GitHub (Sep 21, 2024):

@Jegatheesh001 please provide more detail on why you want this information. What problem are you trying to solve and how do you envision accessing "the number of requests running?"

<!-- gh-comment-id:2365361617 --> @byarbrough commented on GitHub (Sep 21, 2024): @Jegatheesh001 please provide more detail on why you want this information. What problem are you trying to solve and how do you envision accessing "the number of requests running?"
GiteaMirror commented 2026-04-22 09:36:08 -05:00
Author
Owner
Copy Link

@Gomez12 commented on GitHub (Sep 22, 2024):

For me I have wondered about this as well.
I have ollama setup so that it should run 8 in parallel, I have a client-program setup so that it does 8 parallel requests.

But the client also does things to the responses which also takes time, although the llm takes most of the time I am still left wondering if Ollama is really answering 8 requests, or only 6 because there are always 2 client-threads doing other things...

And with 1 client I could collect the info from the client but this becomes more complicated if you have multiple clients etc.

Basically I would like to know how efficient I am using the llm.

<!-- gh-comment-id:2366463298 --> @Gomez12 commented on GitHub (Sep 22, 2024): For me I have wondered about this as well. I have ollama setup so that it should run 8 in parallel, I have a client-program setup so that it does 8 parallel requests. But the client also does things to the responses which also takes time, although the llm takes most of the time I am still left wondering if Ollama is really answering 8 requests, or only 6 because there are always 2 client-threads doing other things... And with 1 client I could collect the info from the client but this becomes more complicated if you have multiple clients etc. Basically I would like to know how efficient I am using the llm.
GiteaMirror commented 2026-04-22 09:36:08 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Sep 25, 2024):

I believe that this is the same idea as in #2004

Assuming so, let's track it there and add any additional information.

<!-- gh-comment-id:2372621106 --> @jessegross commented on GitHub (Sep 25, 2024): I believe that this is the same idea as in #2004 Assuming so, let's track it there and add any additional information.
GiteaMirror commented 2026-04-22 09:36:09 -05:00
Author
Owner
Copy Link

@Quadav commented on GitHub (Sep 16, 2025):

I believe that this is the same idea as in #2004

Assuming so, let's track it there and add any additional information.

I believe that these are 2 different things - amount of requests in concurrency that are running now, and the amount of requests that are waiting in the queue

<!-- gh-comment-id:3298039689 --> @Quadav commented on GitHub (Sep 16, 2025): > I believe that this is the same idea as in [#2004](https://github.com/ollama/ollama/issues/2004) > > Assuming so, let's track it there and add any additional information. I believe that these are 2 different things - amount of requests in concurrency that are running now, and the amount of requests that are waiting in the queue
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#30128
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?