NVIDIA-Merlin / NVIDIA-Merlin/Merlin

[FEA]Transformer4rec performance enhancement - try with Triton dynamic batching

Open
#881 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
Python
Stars
907
Forks
129
PR merge metrics
No merged PRs in 30d

Description

🚀 Feature request

This is to enhance the performance of T4R with Triton dynamic batching.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names Transformer4Rec and Triton dynamic batching but provides no files, tests, entry points, or benchmark criteria. Start by locating the Transformer4Rec inference path and any Triton integration, then establish the current performance baseline; done should mean dynamic batching is implemented and its performance impact is measured.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.