canonical / canonical/llama.cpp-builds

Improve performance on arm64 builds

Open Beginner friendly
#33 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
No language data
Stars
2
Forks
4
PR merge metrics
No merged PRs in 30d

Description

`llama.cpp` can take advantage of ARM CPU microkernels (KleidiAI) and make them available, as noted [here](https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#arm-kleidiai)

For this, it seems we just need to enable the `-DGGML_CPU_KLEIDIAI=ON` flag on arm64 builds

Contributor guide

No contributing guide indexed for this repository

Research direction

Read the ARM KleidiAI section in llama.cpp's docs/build.md, then locate the arm64 build configuration in this repository. Enable -DGGML_CPU_KLEIDIAI=ON for arm64 builds and verify that the arm64 build completes with the option enabled.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
build-system, performance
Issue type
Feature
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Active
Clarity
Clearly specified
Newbie friendliness
78/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.