A high-throughput and memory-efficient inference and serving engine for LLMs

[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-sim…

Ring attention implementation with flash attention

The code used to train and run inference with the ColPali architecture.

The Supabase for RAG - R2R lets you build, scale, and manage user-facing Retrieval-Augmented Generation applications

Windows system utilities to maximize productivity

Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of text-embedding models and frameworks.

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Course Material for the UG Course COMP4901Y

The official Node.js / Typescript library for the OpenAI API

EAGLE: Lossless Acceleration of LLM Decoding by Feature Extrapolation

Gorilla: An API store for LLMs

[NeurIPS 2023 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

Project Page for "LISA: Reasoning Segmentation via Large Language Model"