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 #7022] Can we have a native integrated gpu support ? #30212

New Issue
Closed
opened 2026-04-22 09:44:23 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 09:44:23 -05:00
Owner
Copy Link

Originally created by @user7z on GitHub (Sep 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7022

Its would be great to have ollama native support for igpus , for laptop use , it well free the cpu threads for other tasks , the igpu is that little device that we dont make use of it , despite performance , one wouls have his cpu for other tasks , llm-cpp & oneapi is not the solution in my opinion , specially for igpus

Originally created by @user7z on GitHub (Sep 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7022 Its would be great to have ollama native support for igpus , for laptop use , it well free the cpu threads for other tasks , the igpu is that little device that we dont make use of it , despite performance , one wouls have his cpu for other tasks , llm-cpp & oneapi is not the solution in my opinion , specially for igpus
GiteaMirror added the feature request label 2026-04-22 09:44:23 -05:00
GiteaMirror commented 2026-04-22 09:44:26 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Sep 28, 2024):

You didn't mention which brand of iGPU you're looking for support, but since you mentioned oneapi, I'll assume Intel. We're tracking Intel iGPU support via #3113 although #2033 might be relevant as well.

<!-- gh-comment-id:2381014363 --> @dhiltgen commented on GitHub (Sep 28, 2024): You didn't mention which brand of iGPU you're looking for support, but since you mentioned oneapi, I'll assume Intel. We're tracking Intel iGPU support via #3113 although #2033 might be relevant as well.
GiteaMirror commented 2026-04-22 09:44:26 -05:00
Author
Owner
Copy Link

@user7z commented on GitHub (Sep 29, 2024):

@dhiltgen it boils down to ipex-llm , thats why i said "natively" , because ipex-llm dont seem to be it , lack of compatibility is the primarlly reason , even with what suround it , from a technical perspective what would be needed to add a native igpu support , i think ipex-llm is just a temproary solution

<!-- gh-comment-id:2381044224 --> @user7z commented on GitHub (Sep 29, 2024): @dhiltgen it boils down to ipex-llm , thats why i said "natively" , because ipex-llm dont seem to be it , lack of compatibility is the primarlly reason , even with what suround it , from a technical perspective what would be needed to add a native igpu support , i think ipex-llm is just a temproary solution
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#30212
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?