DonRL10

coding-interview-university

A complete computer science study plan to become a software engineer.

llama.cpp

LLM inference in C/C++

OpenVoice

Instant voice cloning by MyShell.

LLM101n

LLM101n: Let's build a Storyteller

llm.c

LLM training in simple, raw C/CUDA

supervision

We write your reusable computer vision tools. 💜

devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

Perplexica

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

gpt-prompt-engineer

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

01

The open-source language model computer

build-nanogpt

Video+code lecture on building nanoGPT from scratch

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

drl-zh

Deep Reinforcement Learning: Zero to Hero!

c-style

My favorite C programming practices.

ThunderKittens

Tile primitives for speedy kernels

fromthetensor

From the Tensor to Stable Diffusion, a rough outline for a 9 week course.

Triton-Puzzles

Puzzles for learning Triton

Samba

Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

AnyGPT

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

gpu-alpha

High Quality Resources on GPU Programming/Architecture

unet.cu

UNet diffusion model in pure CUDA

deep-vector-quantization

VQVAEs, GumbelSoftmaxes and friends

Awesome-GPU

Awesome resources for GPUs

quiet-star

Code for Quiet-STaR

hlb-gpt

Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wikitext-103 on a single A100 in <100 seconds. Scales to larger models with one parameter change (feature currently in alpha).

snac

Multi-Scale Neural Audio Codec (SNAC) compresses audio into discrete codes at a low bitrate

jax-diffusion-transformer

Implementation of Diffusion Transformer (DiT) in JAX

titok-pytorch

Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"

ohara

Collection of autoregressive model implementation