Run Local LLMs on Any Device. Open-source
The Triton Inference Server provides an optimized cloud
A Pythonic framework to simplify AI service building
Trainable models and NN optimization tools
Easy-to-use Speech Toolkit including Self-Supervised Learning model
A library for accelerating Transformer models on NVIDIA GPUs
Lightweight anchor-free object detection model
Training & Implementation of chatbots leveraging GPT-like architecture