NVIDIA-Merlin/HierarchicalKV

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.

Language: Cuda - Size: 6.09 MB - Last synced: about 23 hours ago - Pushed: about 23 hours ago - Stars: 102 - Forks: 22

NVIDIA-Merlin/dataloader

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

Language: Python - Size: 28.7 MB - Last synced: 15 days ago - Pushed: about 1 month ago - Stars: 398 - Forks: 24

NVIDIA-Merlin/NVTabular

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.

Language: Python - Size: 98.4 MB - Last synced: 15 days ago - Pushed: 19 days ago - Stars: 1,008 - Forks: 143

NVIDIA-Merlin/Transformers4Rec

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

Language: Python - Size: 213 MB - Last synced: 25 days ago - Pushed: 26 days ago - Stars: 1,033 - Forks: 142

NVIDIA-Merlin/models

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

Language: Python - Size: 113 MB - Last synced: 25 days ago - Pushed: 26 days ago - Stars: 241 - Forks: 48

NVIDIA-Merlin/Merlin

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.

Language: Python - Size: 37 MB - Last synced: 25 days ago - Pushed: 26 days ago - Stars: 687 - Forks: 110

NVIDIA-Merlin/core

Core Utilities for NVIDIA Merlin

Language: Python - Size: 223 MB - Last synced: 26 days ago - Pushed: 27 days ago - Stars: 18 - Forks: 14

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.

Language: Python - Size: 116 MB - Last synced: about 1 month ago - Pushed: about 1 month ago - Stars: 81 - Forks: 29

NVIDIA-Merlin/HugeCTR

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

Language: C++ - Size: 55.9 MB - Last synced: about 1 month ago - Pushed: about 1 month ago - Stars: 890 - Forks: 192

NVIDIA-Merlin/distributed-embeddings

distributed-embeddings is a library for building large embedding based models in Tensorflow 2.

Language: Python - Size: 1.79 MB - Last synced: 3 months ago - Pushed: 7 months ago - Stars: 41 - Forks: 10

NVIDIA-Merlin/competitions

Solutions to Recommender Systems competitions

Language: Jupyter Notebook - Size: 15.1 MB - Last synced: 7 months ago - Pushed: over 1 year ago - Stars: 188 - Forks: 42

NVIDIA-Merlin/publications

Language: Jupyter Notebook - Size: 28.6 MB - Last synced: about 1 year ago - Pushed: about 1 year ago - Stars: 59 - Forks: 10

NVIDIA-Merlin/.github

Language: Shell - Size: 49.8 KB - Last synced: 11 months ago - Pushed: 11 months ago - Stars: 0 - Forks: 0

NVIDIA-Merlin/gcp-ml-ops

MLOps pipeline for NVIDIA Merlin on GKE

Language: Python - Size: 479 KB - Last synced: about 1 year ago - Pushed: almost 3 years ago - Stars: 37 - Forks: 6

NVIDIA-Merlin/nvtabular_triton_backend

Triton Backend for NVTabular

Language: C++ - Size: 187 KB - Last synced: about 1 year ago - Pushed: about 2 years ago - Stars: 2 - Forks: 2