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 #5983] Distributed Computing: Run single large model on multiple machines #29502

New Issue
Closed
opened 2026-04-22 08:27:02 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 08:27:02 -05:00
Owner
Copy Link

Originally created by @mrmiket64 on GitHub (Jul 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5983

Hello dear Ollama team.

I'd like to request a new feature in Ollama that allows a single large model to be run across multiple machines for inference. This would enable users to take advantage of distributed computing to handle very large models that would exceed the memory capacity of a single machine.

That functionality could allow to:

  • Make more accessible to run models like llama 3.1 405b
  • Distribute the load when running several smaller models to serve a large user base

Thank you for all of your great work, it is really making a difference for me.

All the Best
Miguel

Originally created by @mrmiket64 on GitHub (Jul 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5983 Hello dear Ollama team. I'd like to request a new feature in Ollama that allows a single large model to be run across multiple machines for inference. This would enable users to take advantage of distributed computing to handle very large models that would exceed the memory capacity of a single machine. That functionality could allow to: - Make more accessible to run models like llama 3.1 405b - Distribute the load when running several smaller models to serve a large user base Thank you for all of your great work, it is really making a difference for me. All the Best Miguel
GiteaMirror added the feature request label 2026-04-22 08:27:02 -05:00
GiteaMirror commented 2026-04-22 08:27:04 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 26, 2024):

ollama use llama.cpp for inference, so that's where the distributed computing needs to be implemented. There have been attempts to do so, mainly by using the MPI framework but that work has languished recently.

<!-- gh-comment-id:2252828020 --> @rick-github commented on GitHub (Jul 26, 2024): ollama use [llama.cpp](https://github.com/ggerganov/llama.cpp) for inference, so that's where the distributed computing needs to be implemented. There have been attempts to do so, mainly by using the [MPI](https://www.geeksforgeeks.org/mpi-distributed-computing-made-easy/) framework but that work has languished recently.
GiteaMirror commented 2026-04-22 08:27:04 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 26, 2024):

Lets track this via #4643

<!-- gh-comment-id:2253284779 --> @dhiltgen commented on GitHub (Jul 26, 2024): Lets track this via #4643
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#29502
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?