Stars
MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.
Valdi is a cross-platform UI framework that delivers native performance without sacrificing developer velocity.
A high-throughput and memory-efficient inference and serving engine for LLMs
Introduction to Machine Learning Systems
Flax is a neural network library for JAX that is designed for flexibility.
High-performance In-browser LLM Inference Engine
Minimal yet performant LLM examples in pure JAX
AI powered podcast generator, inspired by Google's NoteBookLM audio-overview and AnthusAI's Podcastic
Next generation FEniCS problem solving environment
QuadriFlow: A Scalable and Robust Method for Quadrangulation
Parkiet is a 1.6B parameter Dutch text-to-speech model (TTS)
Practical Feature-Preserving Block Decomposition for Strongly Hex-Dominant Meshing
A compact, high-performance finite element analysis engine built on JAX.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Differentiable Finite Element Method with JAX
GPU accelerated differentiable finite elements for solid mechanics with PyTorch
JAX Implementations of Descript Audio Codec and EnCodec
Whisper with disfluencies for the Dutch language
A TTS model capable of generating ultra-realistic dialogue in one pass.
Python bindings for a Rust implementation of inverse and forward kinematic solutions for six-axis industrial robots with a parallel base and spherical wrist.
Rust implementation of inverse and forward kinematic solutions for six-axis industrial robots with a parallel base and spherical wrist.
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding