zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-06-24 17:31:16 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
7a34e46677
mlx/benchmarks/python/comparative
History
Awni Hannun 7a34e46677
Quantize with groups of 32 (#511) 
* allow quantize with group sizes of 32

* missing cpu dispatch

* remove print

* Fix qvm for group_size 32

---------

Co-authored-by: Angelos Katharopoulos <a_katharopoulos@apple.com>
2024-01-21 06:19:05 -08:00
..
bench_mlx.py Quantize with groups of 32 (#511) 2024-01-21 06:19:05 -08:00
bench_torch.py An initial quantized matmul implementation (#205) 2023-12-18 23:18:57 -08:00
compare.py Spelling (#342) 2024-01-01 21:08:17 -08:00
README.md awni's commit files 2023-11-29 10:30:41 -08:00

README.md

Microbenchmarks comparing MLX to PyTorch

Implement the same microbenchmarks in MLX and PyTorch to compare and make a list of the biggest possible performance improvements and/or regressions.

Run with python bench_mlx.py sum_axis --size 8x1024x128 --axis 2 --cpu for instance to measure the times it takes to sum across the 3rd axis of the above tensor on the cpu.

compare.py runs several benchmarks and compares the speed-up or lack thereof in comparison to PyTorch.

Each bench script can be run with --print-pid to print the PID and wait for a key in order to ease attaching a debugger.