github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 21:55:43 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #2366] Bump llama.cpp commit to 6b91b1e which includes Intel GPU support (iGPU, Arc, Max, Flex) #47885

New Issue
Closed
opened 2026-04-28 05:38:52 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 05:38:52 -05:00
Owner
Copy Link

Originally created by @ghost on GitHub (Feb 6, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2366

llama.cpp has added support for Intel GPUs.
commit ID: 6b91b1e0a92ac2e4e269eec6361ca53a61ced6c6

Task

  1. Bump llama.cpp commit if feasible
  2. Then update Dockerfile with with Intel GPU support for one-click deployment or as reference to bare metal deployment.

Reference for dockerfile implementation

llama.cpp guidelines on Intel GPU support via SYCL lib.

Originally created by @ghost on GitHub (Feb 6, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2366 llama.cpp has added support for Intel GPUs. commit ID: [6b91b1e0a92ac2e4e269eec6361ca53a61ced6c6](https://github.com/ggerganov/llama.cpp/commit/6b91b1e0a92ac2e4e269eec6361ca53a61ced6c6) *Task* 1. Bump llama.cpp commit if feasible 2. Then update Dockerfile with with Intel GPU support for one-click deployment or as reference to bare metal deployment. **Reference for dockerfile implementation** llama.cpp guidelines on Intel GPU support via SYCL lib. - https://github.com/ggerganov/llama.cpp/blob/master/README-sycl.md
GiteaMirror commented 2026-04-28 05:38:56 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Feb 6, 2024):

#1590

<!-- gh-comment-id:1928573693 --> @ghost commented on GitHub (Feb 6, 2024): #1590
GiteaMirror commented 2026-04-28 05:38:57 -05:00
Author
Owner
Copy Link

@ghost commented on GitHub (Feb 11, 2024):

DONE llama.cpp commit on main branch is sufficient for SYCL backend support.

  • Need to add gpu/gpu_info_xpu.h and gpu/gpu_info_xpu.c
  • llama.cpp on intel gpu system needs to compile as stated above in the README-sycl.md (Intel requirements are very dependent on system environment configuration with oneapi installation)
  • Dockerfile will test the validity of the system

The heavy lifting is done from the llama.cpp end.

I do not understand the codebase to contribute back and therefore only giving pointers.
Keeping this issue as tracing the progress only.

Please feel free to close this, if supporting at this time is not feasible or if this thread is dangling as an open issue as #1590 already highlights the Intel GPU support issue.

Cheers

<!-- gh-comment-id:1937413099 --> @ghost commented on GitHub (Feb 11, 2024): **DONE** llama.cpp commit on main branch is sufficient for SYCL backend support. - Need to add gpu/gpu_info_xpu.h and gpu/gpu_info_xpu.c - llama.cpp on intel gpu system needs to compile as stated above in the README-sycl.md (Intel requirements are very dependent on system environment configuration with oneapi installation) - Dockerfile will test the validity of the system The heavy lifting is done from the llama.cpp end. I do not understand the codebase to contribute back and therefore only giving pointers. Keeping this issue as tracing the progress only. Please feel free to close this, if supporting at this time is not feasible or if this thread is dangling as an open issue as #1590 already highlights the Intel GPU support issue. Cheers
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
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#47885
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?