Massively Parallel Deep Reinforcement Learning. 🔥

Differentiable Rasteriser implemented in JAX. Reference: https://github.com/erwincoumans/tinyrenderer, https://github.com/ssloy/tinyrenderer/wiki; PR: https://github.com/google/brax/pull/367

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

PFRL: a PyTorch-based deep reinforcement learning library

Transparent and Efficient Financial Analysis

Versatile audio super resolution (any -> 48kHz) with AudioSR.

🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX

A JAX-based simulator for autonomous driving research.

Code for Contrastive Preference Learning (CPL)

General Purpose Audio Effect Removal

⚡ Flashbax: Accelerated Replay Buffers in JAX

Inference Combinators in JAX

Port of OpenAI's Whisper model in C/C++

A Hyperparameter Tuning Library for Keras

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

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

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

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

Instant voice cloning by MIT and MyShell. Audio foundation model.

Math OCR model that outputs LaTeX and markdown

Foundational model for human-like, expressive TTS

LAVIS - A One-stop Library for Language-Vision Intelligence

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

(Crafter + NetHack) in JAX. ICML 2024 Spotlight.

Visualize, query, and stream to train on multimodal robotics data.