{"repo":"redis-developer/redis-nvidia-recsys","free":true,"listed":false,"github":"https://github.com/redis-developer/redis-nvidia-recsys","clone":"git clone https://github.com/redis-developer/redis-nvidia-recsys.git","description":"Three examples of recommendation system pipelines with NVIDIA Merlin and Redis","language":"PureBasic","stars":74,"topics":["recommendation","recommender-system","dlrm","redis","triton","vector-database","vector-search","nvidia-merlin"],"license":"BSD-3-Clause","category":"databases-storage","readme_excerpt":"Recommendation Systems with NVIDIA Merlin and Redis 🚀 This repository holds the assets that supplement the article \" Offline to Online: Feature Storage for Real-time Recommendation Systems with NVIDIA Merlin \" written originally for the NVIDIA Developer Blog. Recommendation System Architectures We provide examples of recommendation system architectures and provide cloud deployment instructions for production usage. Each of the examples rely on Redis and the NVIDIA Merlin framework which provides a number of building blocks for creating recommendation systems. There are 3 examples within this repository 1. Offline Batch Recommendations 2. Online Recommendation Systems 3. Large-Scale Recommender Models with HugeCTR The Large-Scale expands on the second architecture for use cases that demand large scale ( 1 GPU) training or inference. Each of the examples are designed to run locally on a NVIDIA GPU enabled system with docker and docker-compose. We recommend executing all of the following on a cloud instance with an NVIDIA GPU (ideally the AWS Pytorch AMI) However, we also provide a set of terraform scripts and ansible notebooks that can deploy the infrastructure necessary to execute the examples on AWS instances. 1. Offline Batch Recommendations \"Offline\" recommendation systems use batch computing to process large quantities of data and then store them for later retrieval. The diagram above shows an example of such a system that uses a Two-Tower approach to generate recommendat","default_branch":null,"files":null,"tree":[],"storefront":"/r/redis-developer","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/redis-developer/redis-nvidia-recsys/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}