gradbench/gradbench

A framework for reproducible, comparable benchmarks

🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.

LangArena: Programming Language Evaluation Suite

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

Universal components for differentiable scientific computing. 📦

Scientific machine learning (SciML) benchmarks, AI for science, and (differential) equation solvers. Covers Julia, Python (PyTorch, Jax), MATLAB, R

DiscoGrad - automatically differentiate across conditional branches in C++ programs

An autonomous agent that profiles, optimizes, and validates AI training code.

scikit-learn_bench benchmarks various implementations of machine learning algorithms across data analytics frameworks. It currently support the scikit-learn, DAAL4PY, cuML, and XGBoost frameworks for commonly used machine learning algorithms.