Skip to content
@NVIDIA-Merlin

NVIDIA-Merlin

Merlin is a framework providing end-to-end GPU-accelerated recommender systems, from feature engineering to deep learning training and deploying to production

Popular repositories Loading

  1. Transformers4Rec Transformers4Rec Public

    Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.

    Python 1.2k 147

  2. NVTabular NVTabular Public

    NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.

    Python 1.1k 146

  3. HugeCTR HugeCTR Public

    HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training

    C++ 979 200

  4. Merlin Merlin Public

    NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference i…

    Python 811 122

  5. dataloader dataloader Public

    The merlin dataloader lets you rapidly load tabular data for training deep leaning models with TensorFlow, PyTorch or JAX

    Python 417 26

  6. models models Public

    Merlin Models is a collection of deep learning recommender system model reference implementations

    Python 271 51

Repositories

Showing 10 of 15 repositories
  • HugeCTR Public

    HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training

    C++ 979 Apache-2.0 200 30 5 Updated Mar 19, 2025
  • publications Public
    Jupyter Notebook 61 9 1 1 Updated Mar 19, 2025
  • HierarchicalKV Public

    HierarchicalKV is a part of NVIDIA Merlin and provides hierarchical key-value storage to meet RecSys requirements. The key capability of HierarchicalKV is to store key-value feature-embeddings on high-bandwidth memory (HBM) of GPUs and in host memory. It also can be used as a generic key-value storage.

    Cuda 141 Apache-2.0 27 7 7 Updated Mar 2, 2025
  • .github Public
    Shell 0 0 0 1 Updated Feb 10, 2025
  • Merlin Public

    NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.

    Python 811 Apache-2.0 122 199 16 Updated Dec 5, 2024
  • Transformers4Rec Public

    Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.

    Python 1,161 Apache-2.0 147 90 (3 issues need help) 5 Updated Oct 8, 2024
  • NVTabular Public

    NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.

    Python 1,073 Apache-2.0 146 196 (1 issue needs help) 10 Updated Sep 3, 2024
  • nvtabular_triton_backend Public

    Triton Backend for NVTabular

    C++ 2 Apache-2.0 3 10 0 Updated Aug 9, 2024
  • core Public

    Core Utilities for NVIDIA Merlin

    Python 19 Apache-2.0 14 20 9 Updated Jul 26, 2024
  • systems Public

    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.

    Python 91 Apache-2.0 30 31 6 Updated Jun 11, 2024

Top languages

Loading…

Most used topics

Loading…