AI Personal Learning
and practical guidance
CyberKnife Drawing Mirror

Articles by Yang Fan

OpenPromptStudio:可视化编辑、管理图像提示词,同步自己的Notion提示词表-首席AI分享圈

OpenPromptStudio: visually edit and manage image cues, synchronize your own Notion cue lists!

General Introduction OpenPromptStudio (OPS) is an open source visual editor for AIGC prompt words, developed by Moonvy team. It is designed to simplify the process of prompt word creation and management with support for AI models such as Midjourney.OPS provides powerful prompt word management features through Notion integration, which allows users to...

TEN Agent:实时多模态智能体框架,支持与智能体无延时的语音与视频对话。-首席AI分享圈

TEN Agent: a real-time multimodal intelligent body framework that supports latency-free voice and video dialog with intelligent bodies.

Comprehensive Introduction TEN Agent is an open source, real-time, multimodal intelligences framework that integrates OpenAI Realtime API and RTC to support a variety of functions such as weather querying, web searching, visual processing, and RAG (Retrieval Augmented Generation). The framework aims to provide high-performance, low-latency audio and video interaction solutions...

Petals:分布式共享GPU运行和微调大语言模型,像BitTorrent网络一样共享GPU资源-首席AI分享圈

Petals: distributed shared GPU running and fine-tuning of large language models, sharing GPU resources like a BitTorrent network

General Introduction Petals is an open source project developed by the BigScience Workshop to run Large Language Models (LLMs) through a distributed computing approach. Users can run and fine-tune LLMs at home using consumer-grade GPUs or Google Colab, such as Llama 3.1, Mixtral, F...

Aphrodite Engine: an efficient LLM inference engine that supports multiple quantization formats and distributed inference.

Comprehensive Introduction Aphrodite Engine is the official backend engine for PygmalionAI, designed to provide an inference endpoint for PygmalionAI sites and support rapid deployment of Hugging Face compatible models. The engine utilizes vLLM's Paged Attention technology for efficient K/V management and continuous batch processing,...

llama.cpp:高效推理工具,支持多种硬件,轻松实现LLM推理-首席AI分享圈

llama.cpp: efficient inference tool, supports multiple hardware, easy to implement LLM inference

General Introduction llama.cpp is a library implemented in pure C/C++ designed to simplify the inference process for Large Language Models (LLM). It supports a wide range of hardware platforms, including Apple Silicon, NVIDIA GPUs, and AMD GPUs, and provides a variety of quantization options to increase inference speed and reduce memory usage. The project ...

en_USEnglish