ToluClassics / mlx-transformers

MLX Transformers is a library that provides model implementation in MLX. It uses a similar model interface as HuggingFace Transformers and provides a way to load and run models in Apple Silicon devices.
Apache License 2.0
47 stars 4 forks source link

added `mlx_benchmark` directory #21

Open Seun-Ajayi opened 2 months ago

Seun-Ajayi commented 2 months ago

Proposed changes

Added mlx_benchmark directory, it contains the benchmark scripts from the Repository. You can use the ffg command to run the run_benchmark.py script after moving to the mlx_benchmark directory

python run_benchmark.py --include_mps=True --include_mlx_gpu=True --include_mlx_cpu=True --include_cpu=True

The average_benchmark.md file show what each parameter represents and the mlx_README.md file contains more details on how things work.

Types of changes

What types of changes does your code introduce? Put an x in the boxes that apply