diff options
| author | Laurent Mazare <laurent.mazare@gmail.com> | 2023-08-05 17:25:24 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-08-05 17:25:24 +0100 |
| commit | b2788342673f76920a12e6feb6c6cc1209062193 (patch) | |
| tree | bb4ed6aca934d091b6553e128db24b851e3f3c93 /candle-examples/examples/llama | |
| parent | 0b175fcbbdbe7ca768b7beaca64ddf699f35a25b (diff) | |
| download | candle-b2788342673f76920a12e6feb6c6cc1209062193.tar.gz candle-b2788342673f76920a12e6feb6c6cc1209062193.tar.bz2 candle-b2788342673f76920a12e6feb6c6cc1209062193.zip | |
Support the Accelerate BLAS on macOS. (#325)
* Add the accelerate feature.
* Ffi tweaks.
Diffstat (limited to 'candle-examples/examples/llama')
| -rw-r--r-- | candle-examples/examples/llama/main.rs | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/candle-examples/examples/llama/main.rs b/candle-examples/examples/llama/main.rs index d0a55be1..b2c4e55a 100644 --- a/candle-examples/examples/llama/main.rs +++ b/candle-examples/examples/llama/main.rs @@ -9,6 +9,9 @@ // In order to convert the llama weights to a .npz file, run: // python examples/llama/convert_checkpoint.py ..../LLaMA/7B/consolidated.00.pth +#[cfg(feature = "accelerate")] +extern crate accelerate_src; + #[cfg(feature = "mkl")] extern crate intel_mkl_src; |