GenAI components at micro-service level; GenAI service composer to create mega-service

Generative AI Examples is a collection of GenAI examples such as ChatQnA, Copilot, which illustrate the pipeline capabilities of the Open Platform for Enterprise AI (OPEA) project.

Supercharge Your LLM with the Fastest KV Cache Layer

Fast and memory-efficient exact attention

Hackable and optimized Transformers building blocks, supporting a composable construction.

The NVIDIA NeMo Agent toolkit is an open-source library for efficiently connecting and optimizing teams of AI agents.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many mo…

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.

A simple task management system for managing AI dev agents

Build and run AI agents using Docker Compose. A collection of ready-to-use examples for orchestrating open-source LLMs, tools, and agent runtimes.

Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

A hands-on collection of Jupyter notebooks covering key concepts, architectures, and optimizations in Large Language Models (LLMs).

The NVIDIA AIQToolkit UI streamlines interacting with AIQToolkit workflows in an easy-to-use web application.

Containerization and cloud native suite for OPEA

Supercharge Your LLM Application Evaluations 🚀

The LLM Evaluation Framework

Development repository for the Triton language and compiler

GenAI Innovations for OPEA

InstructLab Core package. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.

🚀 The fast, Pythonic way to build MCP servers and clients

Intel® AI Assistant Builder

Luigi is a Python module that helps you build complex pipelines of batch jobs. It handles dependency resolution, workflow management, visualization etc. It also comes with Hadoop support built in.

PyTorch extensions for high performance and large scale training.