NVTabular

NVTabular copied to clipboard

Makes minor adjustments to fix (some) pytest failures with RAPIDS 24.04. In local testing, the only remaining failures seem to be related to tensorflow.

rjzamora

Slow performance of Categorify operation on Triton Inference Server

1

### Description When running an NVTabular workflow with Categorify operations in Triton Inference Server, the performance is significantly slow when dealing with high cardinality data. ### Environment - Merlin Tensorflow...

rahuljantwal-8451

Bump actions/download-artifact from 2 to 4.1.7 in /.github/workflows

1

Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 2 to 4.1.7. Release notes Sourced from actions/download-artifact's releases. v4.1.7 What's Changed Update @​actions/artifact dependency by @​bethanyj28 in actions/download-artifact#325 Full Changelog: https://github.com/actions/download-artifact/compare/v4.1.6...v4.1.7 v4.1.6 What's Changed updating @actions/artifact...

dependabot[bot]

[BUG] Failed to categorical encode column during workflow fit when preprocessing criteo 1tb

1

**Describe the bug** I am following the code here (https://github.com/pytorch/torchrec/tree/main/torchrec/datasets/scripts/nvt) to preprocess criteo 1tb dataset using Nvtabular. I cannot execute the step workflow.fit, error "RuntimeError: Failed to categorical encode column...

jackzhan01

[FEA] Negative sampling for positive-only datasets

6

# Motivation Public datasets are generally provided with negative samples to make it easier to train and compare results for different algorithms. Although, the most common for industry use cases...

gabrielspmoreira

This repository has been configured to receive notifications when access to NVIDIA's self-hosted runners is within 30 days of expiration. See this [link](https://github.com/nv-gha-runners/enterprise-runner-configuration/blob/main/docs/renewing-access.md) for more information on how to renew...

nvidia-runner-mgmt[bot]

[BUG] ops.GroupBy after ops.Filter fails to group correctly, and produces unexpected NaNs

2

**Describe the bug** Applying `ops.GroupBy(...)` after `ops.Filter(...)` causes some weird behaviour. Some rows are filled with lists of `nan`s, and rows are not groupped correctly. It seems like the problem...

matib99

Hi I am running into an 130 SIGSEGV Error when trying to run my NVTabular + Transformers4Rec training script in a container using the following base image `nvcr.io/nvidia/merlin/merlin-pytorch:23.12` I believe...

imran-marwat

Dear NVTabular team, I'm following your instruction on NVTabular demo in this link: https://nvidia-merlin.github.io/NVTabular/v0.5.0/examples/advanced-ops-outbrain/03-Training-with-TF.html. However, it seems that the Outbrain's data set is no longer downloadable from Kaggle. Do you...

minhpth

Hi All, Is container support dropped at this point? The latest container from the NGC registry is from 09/05/2024. It says that the definition was updating on July 31, 2025,...

jordancaraballo