auto-tuning

A technical blog post introduces a Lean4-to-TileLang tensor program superoptimizer that automatically generates optimized GPU/TPU kernels and hyperparameter scaling laws, demonstrating performance gains over torch.compile.

GEPA is an open-source tool that automatically optimizes prompt instructions using execution traces and scores, raising Claude Haiku 4.5's pass rate from 65% to 85% without requiring a model swap.