lliu's repositories
dlrm
An implementation of a deep learning recommendation model (DLRM)
models
Models and examples built with TensorFlow
NVTabular
A library that sits on top of RAPIDS cuDF library providing a range of benefits for processing extremely large tabular datasets, particularly those that don't fit in GPU or CPU memory. The highlights of NVTabular’s capabilities are fast terabyte-scale data preparation and accelerated tabular data loading, all on GPU, which streamline the first step for both training and inference to any deep recommender system pipelines.
HugeCTR
HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training
sota-extractor
The SOTA extractor pipeline
AI-metrics
An open source project to document AI progress through data.