Skip to content

Update llama README to reflect kleidiai is default #12865

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 28, 2025
Merged

Update llama README to reflect kleidiai is default #12865

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion examples/models/llama/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,7 @@ Please see the [Llama 3.2 model card](https://github.com/meta-llama/llama-models

### Performance

Llama 3.2 1B and 3B performance was measured on Android OnePlus 12 device. The performance measurement is expressed in terms of tokens per second using an [adb binary-based approach](#step-4-run-benchmark-on-android-phone) with prompt length of 64. It is measured with KleidiAI library. KleidiAI is not enabled by default yet. Use `-DEXECUTORCH_XNNPACK_ENABLE_KLEIDI=ON` to enable it in the build.
Llama 3.2 1B and 3B performance was measured on Android OnePlus 12 device. The performance measurement is expressed in terms of tokens per second using an [adb binary-based approach](#step-4-run-benchmark-on-android-phone) with prompt length of 64. It is measured with KleidiAI library. KleidiAI is enabled by default on the XNNPACK Backend for all ARM devices.

|Model | Decode (tokens/s) | Time-to-first-token (sec) | Prefill (tokens/s) | Model size (PTE file size in MiB) | Memory size (RSS in MiB) |
|-------|------------------:|--------------------------:| ------------------:|----------------------------------:| ------------------------:|
Expand Down
Loading