Standardized Serverless ML Inference Platform on Kubernetes

AI Powered Knowledge Graph Generator

PyTorch/XLA integration with JetStream (https://github.com/google/JetStream) for LLM inference"

Tools for merging pretrained large language models.

NVIDIA Data Center GPU Manager (DCGM) is a project for gathering telemetry and measuring the health of NVIDIA GPUs

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory…

A profiling and performance analysis tool for machine learning

Library for reading and processing ML training data.

A flexible, adaptive classification system for dynamic text classification

Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.

GenMedia Creative Studio is a Vertex AI generative media example user experience to highlight the use of Imagen, Veo and other generative media APIs on Google Cloud.

Jeo: Jax model training lib for Earth Observation

GeeFlow - generate and process large-scale geospatial datasets with Google Earth Engine.

Building blocks for rapid development of GenAI applications

Structured Outputs

JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training

DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

Set of tools to assess and improve LLM security.

An open-source tool for seamless migration from other LLMs to Llama, and for general prompt optimization.

UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities

Super-fast Structured Outputs

Python library to use Pleias-RAG models

Anthropic's Interactive Prompt Engineering Tutorial

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.

A collection of reusable, high-performance, well-documented, thorough-tested layers and models in Jax

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…