Fast, lossless LLM inference via dual-view diffusion decoding.

High-performance C++ inference engine for Diffusion Language Models (LLaDA, SEDD, MDLM)

State-of-the-art TTS model under 25MB 😻

Inference at the speed of light.

NanoGPT (124M) in 90 seconds

A minimal interface for AI Companion that runs entirely in your browser.

Tiny Llama model trained to play chess

⭐ A place to find the best components to build amazing web applications. The best of JavaScript!

CUDA on non-NVIDIA GPUs

noise_step: Training in 1.58b With No Gradient Memory

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Entropy Based Sampling and Parallel CoT Decoding

Typescript version of MarkovJunior, runs on the web with a fancy renderer

Super lightweight SVG identicon (pixelated avatar) generator

A massively parallel, high-level programming language

LLM inference in C/C++

Simple C routines for generic K-means implementations

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Path tracing renderer and utilities for three.js built on top of three-mesh-bvh.

Lenia - Mathematical Life Forms

Measure relative sizes on background image.

Create pixel art from an image

A browser extension for automating your browser by connecting blocks

Convert color bitmap images to color SVG vector images.

Resize image in browser with high quality and high speed

Deploy a no-code admin panel for any application in less than a minute. Search, create, update, and delete data entries, create custom actions, and build reports.

🚀 Free resources you may use to promote your next startup