github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12885] Multiple server addresses from one host. #8539

New Issue
Open
opened 2026-04-12 21:14:48 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 21:14:48 -05:00
Owner
Copy Link

Originally created by @billbonk1235 on GitHub (Oct 31, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12885

A feature that I would have a lot of use for is a multi-person feature, I think the best way to incorporate this would make it so the user is about to have a main connection address the primary point for the resources and memory of the server. then have it so you are able to create sub connection addresses that you would be able to give to different people so that they have their own ollama client, but it uses the processing and memory power from the main connection point. This would be good because the main problem with multiple users using ollama right now is there is no way to stop parrel requests individually. I think this would be a very popular feature and would open new possibilities on growth for target audiences moving more towards companies and groups. I am currently developing an ai web application using ollama for my company that needs a ai platform offline, and i would love to talk to some of the developers just to talk about some features and possible opportunities that my company would be willing to pay for.

Originally created by @billbonk1235 on GitHub (Oct 31, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12885 A feature that I would have a lot of use for is a multi-person feature, I think the best way to incorporate this would make it so the user is about to have a main connection address the primary point for the resources and memory of the server. then have it so you are able to create sub connection addresses that you would be able to give to different people so that they have their own ollama client, but it uses the processing and memory power from the main connection point. This would be good because the main problem with multiple users using ollama right now is there is no way to stop parrel requests individually. I think this would be a very popular feature and would open new possibilities on growth for target audiences moving more towards companies and groups. I am currently developing an ai web application using ollama for my company that needs a ai platform offline, and i would love to talk to some of the developers just to talk about some features and possible opportunities that my company would be willing to pay for.
GiteaMirror added the feature request label 2026-04-12 21:14:48 -05:00
GiteaMirror commented 2026-04-12 21:14:49 -05:00
Author
Owner
Copy Link

@kitarp29 commented on GitHub (Nov 1, 2025):

Hi
I'm not one of the devs on this repo. The feature you are asking for sounds more like a middleware you can build for your own org. The CLI can currently have multiple sessions of Ollama on the same system. When it comes to API that have concurrency built into it. Please explore the variables in the docs. Also, since Ollama is a containerised application, you can have various containers running with the same volume *if you want to have a memory shared among them.

<!-- gh-comment-id:3475843069 --> @kitarp29 commented on GitHub (Nov 1, 2025): Hi I'm not one of the devs on this repo. The feature you are asking for sounds more like a middleware you can build for your own org. The CLI can currently have multiple sessions of Ollama on the same system. When it comes to API that have concurrency built into it. Please explore the variables in the docs. Also, since Ollama is a containerised application, you can have various containers running with the same volume *if you want to have a memory shared among them.
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#8539
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?