github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4433] GPU layer control / prioritisation #2770

New Issue
Open
opened 2026-04-12 13:05:27 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 13:05:27 -05:00
Owner
Copy Link

Originally created by @AncientMystic on GitHub (May 14, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4433

Would it be possible to add into the configuration of ollama something similar to LM studio to control the gpu utilisation?

Also would it be possible to fine tune ollama to somehow only load certain layers to the gpu similar to unsloth?

Possibly a way to load accessed and adjacent layers maybe with configuration on how many adjacent layers/how much of the model to load at once and either offload the unused layers to ram or not load them at all and just swap out loading layers when needed instead of just loading the entire model every time

Could maybe have add it as lazy loading or something to enable the usage of larger models at higher performance

It seems to have a significant performance advantage especially on lower hardware for those of us without extreme setups if possible within ollama at least

Originally created by @AncientMystic on GitHub (May 14, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4433 Would it be possible to add into the configuration of ollama something similar to LM studio to control the gpu utilisation? Also would it be possible to fine tune ollama to somehow only load certain layers to the gpu similar to unsloth? Possibly a way to load accessed and adjacent layers maybe with configuration on how many adjacent layers/how much of the model to load at once and either offload the unused layers to ram or not load them at all and just swap out loading layers when needed instead of just loading the entire model every time Could maybe have add it as lazy loading or something to enable the usage of larger models at higher performance It seems to have a significant performance advantage especially on lower hardware for those of us without extreme setups if possible within ollama at least
GiteaMirror added the feature request label 2026-04-12 13:05:27 -05:00
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#2770
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?