NVIDIA-Merlin / NVIDIA-Merlin/Merlin
[FEA]Transformer4rec performance enhancement - try with Triton dynamic batching
Open
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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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