github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4069] Support to build llama.cpp with Intel oneMKL #64563

New Issue
Closed
opened 2026-05-03 18:08:21 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-03 18:08:21 -05:00
Owner
Copy Link

Originally created by @MarkWard0110 on GitHub (May 1, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4069

What would be required to build with Intel oneMKL?

It seems this is how avx_vnni instruction set is made available for Intel processors that do not support AVX512. The Intel Core i9 14900k does not support AVX512.

It also references Intel's publication Optimizing and Running LLaMA2 on Intel CPU

There is also this AVX2 is dimwitted compared to AVX512. How do different builds affect how models perform on Intel CPU?

What if llama.cpp build configuration + quantized models is a double down on poorly performing models?

Originally created by @MarkWard0110 on GitHub (May 1, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4069 What would be required to build with [Intel oneMKL](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#intel-onemkl)? It seems this is how `avx_vnni` instruction set is made available for Intel processors that do not support AVX512. The Intel Core i9 14900k does not support AVX512. It also references Intel's publication [Optimizing and Running LLaMA2 on Intel CPU](https://www.intel.com/content/www/us/en/content-details/791610/optimizing-and-running-llama2-on-intel-cpu.html) There is also this [AVX2 is dimwitted compared to AVX512](https://github.com/google/gemma.cpp/issues/23). How do different builds affect how models perform on Intel CPU? What if `llama.cpp` build configuration + quantized models is a double down on poorly performing models?
GiteaMirror added the intelfeature request labels 2026-05-03 18:08:21 -05:00
GiteaMirror commented 2026-05-03 18:08:25 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 25, 2024):

Intel GPU support is being tracked via #1590

AVX512 (and friends) is tracked via #2205

<!-- gh-comment-id:2250978698 --> @dhiltgen commented on GitHub (Jul 25, 2024): Intel GPU support is being tracked via #1590 AVX512 (and friends) is tracked via #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 feature request intel
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#64563
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?