A curated collection of awesome Strudel resources including tracks (popular song covers and remixes), tutorials, and repositories

llama3 implementation one matrix multiplication at a time

Puzzles for learning Triton

An unofficial pytorch implementation of BakedSDF

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

PartyKit Cursor Party fork for interconnected.org

TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.

Solve puzzles. Learn CUDA.

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Distribute and run LLMs with a single file.

Browse the web with GPT-4V and Vimium

Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.

A coding agent for open models like Kimi K3

[ICCV 2023] Text2Tex: Text-driven Texture Synthesis via Diffusion Models

Official Implementation for "TEXTure: Text-Guided Texturing of 3D Shapes"

A computer science textbook

A high-throughput and memory-efficient inference and serving engine for LLMs

You like pytorch? You like micrograd? You love tinygrad! ❤️

Corne keyboard, a split keyboard with 3x6 column staggered keys and 3 thumb keys.

Let's make sand talk

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable…

A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft

A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation (NeurIPS 2023 Spotlight)

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

A unified framework for 3D content generation.

Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.