DORA (Dataflow-Oriented Robotic Architecture) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed dat…

The python library for real-time communication

A collection of pragmatic, real-world examples guiding you from basic to advanced use of xAI's Grok APIs.

Build datasets using natural language

A non-saturating, open-ended environment for evaluating LLMs in Factorio

No fortress, purely open ground. OpenManus is Coming.

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3.

An AI Hedge Fund Team

An Extensible Deep Learning Library

TransMLA: Multi-Head Latent Attention Is All You Need

lightweight, python based chat ui

Fully open reproduction of DeepSeek-R1

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

Code for ExploreTom

Fast low-bit matmul kernels in Triton

A library for advanced large language model reasoning

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Development repository for the Triton language and compiler

🤗 smolagents: a barebones library for agents that think in python code.

The NVIDIA RTX™ AI Toolkit is a suite of tools and SDKs for Windows developers to customize, optimize, and deploy AI models across RTX PCs and cloud.

Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

Large Reasoning Models

Fast, Flexible and Portable Structured Generation

Automate browser-based workflows with LLMs and Computer Vision

FlashInfer: Kernel Library for LLM Serving