github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5849] How to force the use of two GPUs to run a model? #65686

New Issue
Closed
opened 2026-05-03 22:14:32 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-03 22:14:32 -05:00
Owner
Copy Link

Originally created by @mizzlefeng on GitHub (Jul 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5849

I have reviewed many issues, including #4198, #4517 and so on.
I found that the explanation given is that if the graphics memory of a single GPU is sufficient to run the current model, then it will not use more GPUs. But what should I do if I force him to use two GPUs evenly? Even if I set OLLAMA_NUMPARALLEL to 2, it was ineffective and only one GPU was used in the end.

Originally created by @mizzlefeng on GitHub (Jul 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5849 I have reviewed many issues, including [#4198](https://github.com/ollama/ollama/issues/4198), [#4517](https://github.com/ollama/ollama/pull/4517) and so on. I found that the explanation given is that if the graphics memory of a single GPU is sufficient to run the current model, then it will not use more GPUs. But what should I do if I force him to use two GPUs evenly? Even if I set OLLAMA_NUMPARALLEL to 2, it was ineffective and only one GPU was used in the end.
GiteaMirror added the question label 2026-05-03 22:14:32 -05:00
GiteaMirror commented 2026-05-03 22:14:36 -05:00
Author
Owner
Copy Link

@wrapss commented on GitHub (Jul 22, 2024):

try use OLLAMA_SCHED_SPREAD=1

<!-- gh-comment-id:2243224616 --> @wrapss commented on GitHub (Jul 22, 2024): try use OLLAMA_SCHED_SPREAD=1
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 question
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#65686
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?