research impl of Native Sparse Attention (2502.11089)

Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)

Enable AI models for video production in the browser

Focused on fast experimentation and simplicity

A suite of image and video neural tokenizers

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

The best OSS video generation models

NanoGPT (124M) in 3 minutes

AI Robotics tutorials for hobbyists

Fine-tuning code for SV3D

Learning Motion from Low-Rank Adaptation

Developer-friendly, embedded retrieval engine for multimodal AI. Search More; Manage Less.

LLM training in simple, raw C/CUDA

SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

EDM2 and Autoguidance -- Official PyTorch implementation

The official Meta Llama 3 GitHub site

[CVPR 2024] Official implementation of "DEADiff: An Efficient Stylization Diffusion Model with Disentangled Representations"

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

SGLang is a fast serving framework for large language models and vision language models.

Math OCR model that outputs LaTeX and markdown

Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown

GPU programming related news and material links

Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training

Modeling, training, eval, and inference code for OLMo

Chakra UI is a component system for building products with speed ⚡️

A language for constraint-guided and efficient LLM programming.

Mamba SSM architecture