Janus-Series: Unified Multimodal Understanding and Generation Models

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

A throughput-oriented high-performance serving framework for LLMs

Make websites accessible for AI agents

A PyTorch native library for large model training

Neural Networks: Zero to Hero

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

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

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

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Efficient Triton Kernels for LLM Training

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

FlashInfer: Kernel Library for LLM Serving

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

RAG that intelligently adapts to your use case, data, and queries

Making Long-Context LLM Inference 10x Faster and 10x Cheaper

Large Language Model Text Generation Inference

Robust Speech Recognition via Large-Scale Weak Supervision

A fully open-sourced alternative NotebookLM

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

An open-source RAG-based tool for chatting with your documents.

A 3DGS framework for omni urban scene reconstruction and simulation.

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

A modular graph-based Retrieval-Augmented Generation (RAG) system

Set of tools to assess and improve LLM security.

The Memory layer for AI Agents