NVIDIA-Merlin / systems
Merlin Systems provides tools for combining recommendation models with other elements of production recommender systems (like feature stores, nearest neighbor search, and exploration strategies) into end-to-end recommendation pipelines that can be served with Triton Inference Server.
☆87Updated 3 months ago
Related projects: ⓘ
- Merlin Models is a collection of deep learning recommender system model reference implementations☆257Updated 4 months ago
- MLOps pipeline for NVIDIA Merlin on GKE☆41Updated 3 years ago
- Recommendations at "Reasonable Scale": joining dataOps with recSys through dbt, Merlin and Metaflow☆225Updated last year
- ☆97Updated this week
- FIL backend for the Triton Inference Server☆68Updated this week
- ☆40Updated this week
- Solutions to Recommender Systems competitions☆196Updated 2 years ago
- The deepr module provide abstractions (layers, readers, prepro, metrics, config) to help build tensorflow models on top of tf estimators☆50Updated 10 months ago
- ☆61Updated last week
- Multiple ways to model user preference in recommender systems☆13Updated 4 months ago
- Three examples of recommendation system pipelines with NVIDIA Merlin and Redis☆56Updated last year
- A library for preparing, training, and evaluating scalable deep learning hybrid recommender systems using PyTorch.☆107Updated 6 months ago
- This repository compiles prescriptive guidance and code samples for the operationalization of NVIDIA Merlin framework on Google Cloud Ver…☆34Updated 2 years ago
- A PaaS End-to-End ML Setup with Metaflow, Serverless and SageMaker.☆36Updated 3 years ago
- Official Repository for EvalRS @ CIKM 2022: a Rounded Evaluation of Recommender Systems☆68Updated 5 months ago
- Distributed XGBoost on Ray☆137Updated 2 months ago
- Multi-threaded matrix multiplication and cosine similarity calculations for dense and sparse matrices. Appropriate for calculating the K …☆73Updated 2 months ago
- SANSA - sparse EASE for millions of items☆32Updated 5 months ago
- Factorization Machines for Recommendation and Ranking Problems with Implicit Feedback Data☆170Updated last month
- A lightweight wrapper for PyTorch that provides a simple declarative API for context switching between devices, distributed modes, mixed-…☆66Updated last year
- Super Simple Similarities Service☆142Updated last year
- A deep ranking personalization framework☆131Updated last year
- The merlin dataloader lets you rapidly load tabular data for training deep leaning models with TensorFlow, PyTorch or JAX☆402Updated 5 months ago
- Behavioral "black-box" testing for recommender systems☆455Updated last year
- ClearML - Model-Serving Orchestration and Repository Solution☆137Updated last month
- Rax is a Learning-to-Rank library written in JAX.☆312Updated last week
- example how to perform distributed bayesian optimisation (autoML) using optuna on metaflow☆10Updated 2 years ago
- 🛒 Simple recommender with matrix factorization, graph, and NLP. Beating the regular collaborative filtering baseline.☆133Updated 2 months ago
- NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocess…☆749Updated last month
- ☆18Updated 5 months ago