JAX in JavaScript – ML library for the web, running on WebGPU & Wasm

Puffing up reinforcement learning

A debugging and profiling tool that can trace and visualize python code execution

Nintendo Switch Teleoperation and ACT autonomy on ALOHA for Bigym benchmark tasks

Nano vLLM

make pokemon music

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

Background coding agent and real-time web interface

Hierarchical Reasoning Model Official Release

llama3 implementation one matrix multiplication at a time

A Datacenter Scale Distributed Inference Serving Framework

Minimalistic 4D-parallelism distributed training framework for education purpose

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

Wan: Open and Advanced Large-Scale Video Generative Models

A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.

FlashMLA: Efficient Multi-head Latent Attention Kernels

A zero-dependency ML framework in C with a modern Python API for full control over execution and memory.

A Lightweight Recommendation System

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Minecraft AI with LLMs+Mineflayer

Virtual Machine for the Web

A language model programming library.

LlamaIndex is the leading document agent and OCR platform

Hunt down social media accounts by username across social networks

Efficient Triton Kernels for LLM Training

Instant is the best backend for AI-coded apps. You get auth, permissions, storage, presence, and streams — everything you need to ship apps your users will love.