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 #10560] GPU unused #53463

New Issue
Closed
opened 2026-04-29 03:17:06 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-29 03:17:06 -05:00
Owner
Copy Link

Originally created by @HendyTurtle on GitHub (May 4, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10560

Originally created by @HendyTurtle on GitHub (May 4, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10560
GiteaMirror added the bug label 2026-04-29 03:17:06 -05:00
GiteaMirror commented 2026-04-29 03:17:11 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 4, 2025):

ollama currently supports a subset of the available hardware acceleration platforms. See here for NPU support request and here for Arc.

<!-- gh-comment-id:2849190597 --> @rick-github commented on GitHub (May 4, 2025): ollama currently supports a [subset](https://github.com/ollama/ollama/blob/main/docs/gpu.md) of the available hardware acceleration platforms. See [here](https://github.com/ollama/ollama/issues/5186) for NPU support request and [here](https://github.com/ollama/ollama/issues/1590) for Arc.
GiteaMirror commented 2026-04-29 03:17:11 -05:00
Author
Owner
Copy Link

@chnxq commented on GitHub (May 4, 2025):

Hi @rick-github I have an attempt to use the latest version of Ollama to support Intel GPU. Currently, there are still some issues with the Moe model of QWen3 and it is being debugged. For Gema, DeepSeek, and Qwen2.5, they can be supported. I used the SYCL to modify Ollama to detect the memory size of the GPU. It is also hoped that it can be merged into the version of Ollama. https://github.com/chnxq/ollama .On the branch chnxq/add-oneapi, env var ref .bat file.

<!-- gh-comment-id:2849297233 --> @chnxq commented on GitHub (May 4, 2025): Hi @rick-github I have an attempt to use the latest version of Ollama to support Intel GPU. Currently, there are still some issues with the Moe model of QWen3 and it is being debugged. For Gema, DeepSeek, and Qwen2.5, they can be supported. I used the SYCL to modify Ollama to detect the memory size of the GPU. It is also hoped that it can be merged into the version of Ollama. https://github.com/chnxq/ollama .On the branch chnxq/add-oneapi, env var ref .bat file.
GiteaMirror commented 2026-04-29 03:17:12 -05:00
Author
Owner
Copy Link

@wbste commented on GitHub (May 5, 2025):

Hi @rick-github I have an attempt to use the latest version of Ollama to support Intel GPU. Currently, there are still some issues with the Moe model of QWen3 and it is being debugged. For Gema, DeepSeek, and Qwen2.5, they can be supported. I used the SYCL to modify Ollama to detect the memory size of the GPU. It is also hoped that it can be merged into the version of Ollama. https://github.com/chnxq/ollama .On the branch chnxq/add-oneapi, env var ref .bat file.

This would be so awesome! Intel's ipex version always lags behind. I'd love integration into ollama itself!

<!-- gh-comment-id:2849753379 --> @wbste commented on GitHub (May 5, 2025): > Hi [@rick-github](https://github.com/rick-github) I have an attempt to use the latest version of Ollama to support Intel GPU. Currently, there are still some issues with the Moe model of QWen3 and it is being debugged. For Gema, DeepSeek, and Qwen2.5, they can be supported. I used the SYCL to modify Ollama to detect the memory size of the GPU. It is also hoped that it can be merged into the version of Ollama. https://github.com/chnxq/ollama .On the branch chnxq/add-oneapi, env var ref .bat file. This would be so awesome! Intel's ipex version always lags behind. I'd love integration into ollama itself!
GiteaMirror commented 2026-04-29 03:17:13 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 16, 2025):

#10322

<!-- gh-comment-id:2886469501 --> @rick-github commented on GitHub (May 16, 2025): #10322
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 bug
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#53463
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?