An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…

A One Inch CMOS sensor (IMX283) camera board designed for Raspberry Pi

Relocate resource intensive third-party scripts off of the main thread and into a web worker. 🎉

Used for AI model generation, next-generation Blender rendering engine, texture enhancement&generation (based on ComfyUI)

Small Blender Demo files to share with people

Bring portraits to life in Real Time！onnx/tensorrt support！实时肖像驱动！

Official implementation for paper High Resolution Face Age Editing

Fast running Live Portrait with TensorRT and ONNX models

Bring portraits to life!

An open-source debugging agent in VSCode

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

ComfyUI related stuff and things

Spotlight-like client for Ollama on Windows.

PuLID native implementation for ComfyUI

Function Calling Benchmark & Testing

The homepage of OneBit model quantization framework.

[MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

Optmizier script for llama.cpp CPU execution

AutoGroq is a groundbreaking tool that revolutionizes the way users interact with Autogen™ and other AI assistants. By dynamically generating tailored teams of AI agents based on your project requi…

Intel® NPU Acceleration Library

This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.

Convenience scripts to finetune (chat-)LLaMa3 and other models for any language

OpenUI let's you describe UI using your imagination, then see it rendered live.

[NeurIPS'24] SelfCodeAlign: Self-Alignment for Code Generation

Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3.

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]