Cross Entropy Python Packages

mlx-train-perf

Fused, logit-free linear-cross-entropy loss, RAM-fit planner, and benchmark harness for MLX fine-tuning on Apple Silicon

balanced-loss

Easy to use class balanced cross entropy and focal loss implementation for Pytorch

optimal

A python metaheuristic optimization library. Currently supports Genetic Algorithms, Gravitational Search, Cross Entropy, and PBIL.

orogram

A library for working with 1D piecewise linear probability density functions.

orda-kernel

ORDA: Triton kernels for logit-level knowledge distillation loss.

optimiser

Generic implementations of numerical optimization methods. As of now, only cross-entropy method is here.