NVIDIA / NVIDIA/TensorRT-LLM

[Feature]: [AutoDeploy] Enable ADP for larger batch sizes

Open
#12,783 0 comments 0 reactions 1 assignee View on GitHub

@taylor-yb-lee is already working on this.

Since Apr 6, 2026.

AutoDeploy feature request
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

🚀 The feature, motivation and pitch

Enable ADP for larger batch sizes in AutoDeploy is not performant as expected.
Applying it to DeepSeek R1, the performance gets worse significantly.
For pytorch backend, it was performing good.
To investigate whehter there is an side effect which causes ADP perf drop in AutoDeploy

Alternatives

No response

Additional context

No response

Before submitting a new issue...
  • Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.