github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9224] Is there any method to run a model on multiple physical servers with ollama? #83698

New Issue
Closed
opened 2026-05-09 18:56:23 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-09 18:56:23 -05:00
Owner
Copy Link

Originally created by @minhvip20956 on GitHub (Feb 19, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9224

There are a lot of models with very large sizes. Is there a way to split them up and run them on multiple physical servers in a master-cluster fashion? Communicate the servers with each other via a high-speed internal network (100-200Gbps/server).
I know this is not possible yet so I am posting it here as a feature suggestion. I really hope this will be available soon as it could solve the VRAM issue with very large models (e.g. deepseek at 671b-fp16 with 1.3TB) and the computation speed could be improved with more GPUs. Also increase the redundancy when a node fails.

Originally created by @minhvip20956 on GitHub (Feb 19, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9224 There are a lot of models with very large sizes. Is there a way to split them up and run them on multiple physical servers in a master-cluster fashion? Communicate the servers with each other via a high-speed internal network (100-200Gbps/server). I know this is not possible yet so I am posting it here as a feature suggestion. I really hope this will be available soon as it could solve the VRAM issue with very large models (e.g. deepseek at 671b-fp16 with 1.3TB) and the computation speed could be improved with more GPUs. Also increase the redundancy when a node fails.
GiteaMirror added the feature request label 2026-05-09 18:56:23 -05:00
GiteaMirror commented 2026-05-09 18:56:26 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 19, 2025):

https://github.com/ollama/ollama/pull/6729

<!-- gh-comment-id:2668848038 --> @rick-github commented on GitHub (Feb 19, 2025): https://github.com/ollama/ollama/pull/6729
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#83698
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?