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.
This project helps data scientists and machine learning engineers deploy recommendation models into live, production-ready systems. It takes trained recommendation models and related data processing steps, then packages them into an optimized pipeline for real-time serving. The output is a high-performance recommendation engine ready to integrate into applications like e-commerce sites or content platforms.
No commits in the last 6 months.
Use this if you need to combine various components of a recommendation system, like feature lookups, candidate generation, and ranking models, into a single, efficient serving pipeline.
Not ideal if you are only training recommendation models and do not need to deploy them for real-time inference in a production environment.
Stars
94
Forks
31
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIA-Merlin/systems"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PennyLaneAI/pennylane
PennyLane is an open-source quantum software platform for quantum computing, quantum machine...
qiskit-community/qiskit-machine-learning
An open-source library built on Qiskit for quantum machine learning tasks at scale on quantum...
netket/netket
Machine learning algorithms for many-body quantum systems
tencent-quantum-lab/tensorcircuit
Tensor network based quantum software framework for the NISQ era
mit-han-lab/torchquantum
A PyTorch-based framework for Quantum Classical Simulation, Quantum Machine Learning, Quantum...