github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1356] Concurrency and multiple calls #47222

New Issue
Closed
opened 2026-04-28 03:26:35 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-28 03:26:35 -05:00
Owner
Copy Link

Originally created by @enriquesouza on GitHub (Dec 3, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1356

Hi, I would like to know if running Ollama and making multiple calls is possible. I would love to add a server and use it for my users.

Therefore, when testing it, I saw it is waiting until a process finishes when I use the liteLLM proxy.

Is it possible?

Originally created by @enriquesouza on GitHub (Dec 3, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1356 Hi, I would like to know if running Ollama and making multiple calls is possible. I would love to add a server and use it for my users. Therefore, when testing it, I saw it is waiting until a process finishes when I use the liteLLM proxy. Is it possible?
GiteaMirror commented 2026-04-28 03:26:36 -05:00
Author
Owner
Copy Link

@austin-starks commented on GitHub (Dec 3, 2023):

Plus one. I love Ollama but I'm failing to see how I could deploy it as a cloud server.

<!-- gh-comment-id:1837311633 --> @austin-starks commented on GitHub (Dec 3, 2023): Plus one. I love Ollama but I'm failing to see how I could deploy it as a cloud server.
GiteaMirror commented 2026-04-28 03:26:36 -05:00
Author
Owner
Copy Link

@easp commented on GitHub (Dec 4, 2023):

Right now you'd need to start multiple ollama servers on different ports and put them behind a reverse proxy.

I don't have any inside knowledge, but I'd expect this to change since Llama.cpp, which Ollama uses, has added support for batched requests, which is much more efficient than load balancing among separate instances.

<!-- gh-comment-id:1839038614 --> @easp commented on GitHub (Dec 4, 2023): Right now you'd need to start multiple ollama servers on different ports and put them behind a reverse proxy. I don't have any inside knowledge, but I'd expect this to change since Llama.cpp, which Ollama uses, has added support for batched requests, which is much more efficient than load balancing among separate instances.
GiteaMirror commented 2026-04-28 03:26:36 -05:00
Author
Owner
Copy Link

@enriquesouza commented on GitHub (Dec 11, 2023):

Thanks. I used it with docker and docker swarm, and then it solved with 10 instances running, therefore it is very limited yet. I hope a new version can fix that limitation.

<!-- gh-comment-id:1850509782 --> @enriquesouza commented on GitHub (Dec 11, 2023): Thanks. I used it with docker and docker swarm, and then it solved with 10 instances running, therefore it is very limited yet. I hope a new version can fix that limitation.
GiteaMirror commented 2026-04-28 03:26:37 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 26, 2024):

Going to close this as a dupe of #358

<!-- gh-comment-id:1912843604 --> @pdevine commented on GitHub (Jan 26, 2024): Going to close this as a dupe of #358
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
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#47222
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?