Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
$ git clone https://github.com/NVIDIA/GenerativeAIExamples.gitA community-driven collection of RAG (Retrieval-Augmented Generation) frameworks, projects, and resources. Contribute and explore the evolving RAG ecosystem.
Enhancing Translation with RAG-Powered Large Language Models
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
High-speed Large Language Model Serving for Local Deployment
Data from GitHub · snapshot Sep 24, 2026