AIMET is a library that provides advanced quantization and compression
A high-throughput and memory-efficient inference and serving engine
Drag & drop UI to build your customized LLM flow
Port of OpenAI's Whisper model in C/C++
C++ library for high performance inference on NVIDIA GPUs
Open source personal AI Assistant for Linux, Windows and Mac
High-performance neural network inference framework for mobile
Speech recognition module for Python
A fast image processing library with low memory needs
Self-hosted, community-driven, local OpenAI compatible API
⚡ Building applications with LLMs through composability ⚡
Models for the spaCy Natural Language Processing (NLP) library
A self-hostable CDN for databases
A simple but complete full-attention transformer
Chat with LLM like Vicuna totally in your browser with WebGPU
Telegram client, in Go. (MTProto API)
Easy-to-use deep learning framework with 3 key features
Lightning fast C++/CUDA neural network framework
Build resilient language agents as graphs
Multilingual Automatic Speech Recognition with word-level timestamps
Implementation of Imagen, Google's Text-to-Image Neural Network
Implementation of a U-net complete with efficient attention
Turns Data and AI algorithms into production-ready web applications
A library for accelerating Transformer models on NVIDIA GPUs
A Python library for audio