NVIDIA / NVIDIA/TensorRT-LLM

[AutoDeploy][Feature]: Add attention sinks support for flashinfer

Open
#8,171 1 comment 0 reactions 1 assignee View on GitHub

@nvchenghaoz is already working on this.

Since Oct 7, 2025.

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

Since the flashinfer bump up to a newer version in TRTLLM and could support the attention sinks, update the AutoDeploy flashinfer API to support the attention sinks.

Also update the tests to address the updates.

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.