jax

Differentiable Finite Element Method with JAX

Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

Lightweight & fast OCR models for license plate text recognition.

Machine learning Guide. Learn all about Machine Learning Tools, Libraries, Frameworks, Large Language Models (LLMs), and Training Models.

Machine learning algorithms for many-body quantum systems

Physics Informed Machine Learning Tutorials (Pytorch and Jax)

Gaussian processes in JAX and Equinox.

♟️ Vectorized RL game environments in JAX

Differentiable Fluid Dynamics Package

Nonlinear optimisation (root-finding, least squares, ...) in JAX+Equinox. https://docs.kidger.site/optimistix/

Linear solvers in JAX and Equinox. https://docs.kidger.site/lineax

Solve forward and inverse problems related to partial differential equations using finite basis physics-informed neural networks (FBPINNs)

Everything you want to know about Google Cloud TPU

Felafax is building AI infra for non-NVIDIA GPUs

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.

Pax is a Jax-based machine learning framework for training large scale models. Pax allows for advanced and fully configurable experimentation and parallelization, and has demonstrated industry leading model flop utilization rates.

Zero-copy MPI communication of JAX arrays, for turbo-charged HPC applications in Python :zap:

Orbax provides common checkpointing and persistence utilities for JAX users

Keras implementation of the Yahoo Open-NSFW model

Implementation of https://srush.github.io/annotated-s4

A model predictive controller for quadruped robots based on the single rigid body model and written in python. Gradient-based (acados) or Sampling-based (jax)

XLB: Accelerated Lattice Boltzmann (XLB) for Physics-based ML