A minimal implementation of DeepMind's Genie world model

A nearly complete collection of prefix sum algorithms implemented in CUDA, D3D12, Unity and WGPU. Theoretically portable to all wave/warp/subgroup sizes.

Blazing 💥 fast terminal-ui for git written in rust 🦀

Nano vLLM

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

SoTA open-source TTS

A retro game engine for Python

Next Generation Visual Programming System

A TTS model capable of generating ultra-realistic dialogue in one pass.

Horizontal scaling for PostgreSQL with automatic sharding.

https://hf.co/hexgrad/Kokoro-82M

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation

TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

A Python framework for accelerated simulation, data generation and spatial computing.

Generate Diffuse Textures on Meshes directly in Blender 3D with Stable Diffusion.

Interface for OuteTTS models.

Efficient optimizers

An email and SMTP testing tool with API for developers

🤖 Compile docs into text files for LLMs

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

Document to Markdown OCR library with Llama 3.2 vision

Texting Robots: Common Crawl `robots.txt` Test

A 3D printer slicing algorithm that lets you print 90° overhangs without support material.

A light-weight Arduino hardware package for ATtiny13

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

PyTorch code and models for the DINOv2 self-supervised learning method.