github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7399] set gpu/cpu affinity per-model #51216

New Issue
Closed
opened 2026-04-28 18:56:11 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 18:56:11 -05:00
Owner
Copy Link

Originally created by @xucian on GitHub (Oct 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7399

is it possible to set the target device (gpu0, gpu1, cpu) per-model? that'd be a game-changer as we could offload smaller models to cpu while keeping bigger models on gpu
basically preventing the warmup

Originally created by @xucian on GitHub (Oct 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7399 is it possible to set the target device (gpu0, gpu1, cpu) per-model? that'd be a game-changer as we could offload smaller models to cpu while keeping bigger models on gpu basically preventing the warmup
GiteaMirror added the feature request label 2026-04-28 18:56:11 -05:00
GiteaMirror commented 2026-04-28 18:56:13 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 28, 2024):

Not currently. #3902 tracks the work on model management, but there has been little progress so far. As a limited workaround, you can force a model on to CPU by specifying num_gpu as zero, see https://github.com/ollama/ollama/issues/6950#issuecomment-2373663650 for details.

<!-- gh-comment-id:2441718772 --> @rick-github commented on GitHub (Oct 28, 2024): Not currently. #3902 tracks the work on model management, but there has been little progress so far. As a limited workaround, you can force a model on to CPU by specifying `num_gpu` as zero, see https://github.com/ollama/ollama/issues/6950#issuecomment-2373663650 for details.
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#51216
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?