Model Optimization Python Packages

onnx-ir

Efficient in-memory representation for ONNX, in Python

mlbuild

Performance CI/CD for on-device ML models — catch inference regressions before they ship

sk-autod

Auto-diagnose deep learning training pathologies: overfitting, unstable LR, exploding gradients, noisy training, and early stopping issues.

floppy-tracker

A hardware-agnostic profiler for tracking the FLOPs and BOPs of Machine and Deep Learning algorithms.

layer-scan

Automated LLM layer duplication config scanner

mlflow-assist

A comprehensive toolkit for ML and LLM development

floppy-lib

A hardware-agnostic profiler for tracking the FLOPs and BOPs of Machine and Deep Learning algorithms.