Skip to content

Polish CoreML Llama Doc #5745

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

Closed
wants to merge 1 commit into from
Closed

Polish CoreML Llama Doc #5745

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
6 changes: 6 additions & 0 deletions examples/models/llama2/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -320,6 +320,8 @@ Note for Mac users: There's a known linking issue with Xcode 15.1. Refer to the

For Llama2 and stories models, pass the converted `tokenizer.bin` file instead of `tokenizer.model`.

To build for CoreML backend and validate on Mac, replace `-DEXECUTORCH_BUILD_XNNPACK=ON` with `-DEXECUTORCH_BUILD_COREML=ON`

## Step 5: Run benchmark on Android phone

**1. Build llama runner binary for Android**
Expand Down Expand Up @@ -406,6 +408,10 @@ for each backend ([CoreML](https://pytorch.org/executorch/main/build-run-coreml.

The iOS LLAMA app supports the CoreML and MPS model and the Android LLAMA app supports the QNN model. On Android, it also allow to cross compiler the llama runner binary, push to the device and run.

For CoreML, there are 2 additional optional arguments:
* `--coreml-ios`: Specify the minimum iOS version to deploy (and turn on available optimizations). E.g. `--coreml-ios 18` will turn on [in-place KV cache](https://developer.apple.com/documentation/coreml/mlstate?language=objc) and [fused scaled dot product attention kernel](https://apple.github.io/coremltools/source/coremltools.converters.mil.mil.ops.defs.html#coremltools.converters.mil.mil.ops.defs.iOS18.transformers.scaled_dot_product_attention) (the resulting model will then need at least iOS 18 to run, though)
* `--coreml-quantize`: Use [quantization tailored for CoreML](https://apple.github.io/coremltools/docs-guides/source/opt-quantization-overview.html). E.g. `--coreml-quantize b4w` will perform per-block 4-bit weight-only quantization in a way tailored for CoreML

# What is coming next?
## Quantization
- Enabling FP16 model to leverage smaller groupsize for 4-bit quantization.
Expand Down
Loading