MLX: NumPy like framework for Apple Silicon by Apple(ml-explore.github.io)

131 points by dagmx 2 years ago | 12 comments

Modern GPU Programming for MLSys(mlc.ai)

68 points by crowwork 4 months ago | 15 comments

How does gradient descent work?(centralflows.github.io)

292 points by jxmorris12 1 year ago | 23 comments

Understand how transformers work by demystifying the math behind them(osanseviero.github.io)

408 points by LaserPineapple 2 years ago | 94 comments

A hackerllama blog post walking through an end-to-end worked example of transformer math using small random vectors and matrices.

Algorithms for Modern Hardware(en.algorithmica.org)

273 points by throwaway2037 2 years ago | 65 comments

Optimizers need a rethink(typesanitizer.com)

132 points by ingve 2 years ago | 139 comments