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 #2451] [FEATURE] Add support for Intel Xeon (Sapphire and Emerald Rapids) accelerators and AI features such as AMX and AVX 512. #63471

New Issue
Closed
opened 2026-05-03 13:39:08 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-03 13:39:08 -05:00
Owner
Copy Link

Originally created by @scouzi1966 on GitHub (Feb 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2451

Originally assigned to: @dhiltgen on GitHub.

Note that Intel is trying to demystify AVX512 with a AVX 10 standard. But they are the same.

AVX512
https://www.intel.com/content/www/us/en/architecture-and-technology/avx-512-overview.html

AMX
https://www.intel.com/content/www/us/en/products/docs/accelerator-engines/advanced-matrix-extensions/overview.html

AVX512 is also being fully implemented by AMD

Originally created by @scouzi1966 on GitHub (Feb 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2451 Originally assigned to: @dhiltgen on GitHub. Note that Intel is trying to demystify AVX512 with a AVX 10 standard. But they are the same. AVX512 https://www.intel.com/content/www/us/en/architecture-and-technology/avx-512-overview.html AMX https://www.intel.com/content/www/us/en/products/docs/accelerator-engines/advanced-matrix-extensions/overview.html AVX512 is also being fully implemented by AMD
GiteaMirror commented 2026-05-03 13:39:11 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Feb 18, 2024):

cc @dhiltgen

<!-- gh-comment-id:1950999403 --> @pdevine commented on GitHub (Feb 18, 2024): cc @dhiltgen
GiteaMirror commented 2026-05-03 13:39:12 -05:00
Author
Owner
Copy Link

@scouzi1966 commented on GitHub (Feb 19, 2024):

I've since analyzed the code base more closely and realize that this probably belongs more with llama.cpp project which would eventually make it's way here. There seems to be Intel involvement here as well.

https://github.com/intel/neural-speed.

You can close this request if you want from my point of view.

<!-- gh-comment-id:1953070811 --> @scouzi1966 commented on GitHub (Feb 19, 2024): I've since analyzed the code base more closely and realize that this probably belongs more with llama.cpp project which would eventually make it's way here. There seems to be Intel involvement here as well. https://github.com/intel/neural-speed. You can close this request if you want from my point of view.
GiteaMirror commented 2026-05-03 13:39:14 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Feb 19, 2024):

This might wind up being a dup of #2205

<!-- gh-comment-id:1953118810 --> @dhiltgen commented on GitHub (Feb 19, 2024): This might wind up being a dup of #2205
GiteaMirror commented 2026-05-03 13:39:17 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 11, 2024):

Closing for https://github.com/ollama/ollama/issues/2205

<!-- gh-comment-id:2105410230 --> @jmorganca commented on GitHub (May 11, 2024): Closing for https://github.com/ollama/ollama/issues/2205
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#63471
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?