NVIDIA / NVIDIA/TensorRT-LLM

[Performance]: Can Scaffolding give more information about kvcache-reuse to TensorRT-LLM?

Open
#7,080 1 comment 0 reactions 2 assignees View on GitHub

@dc3671 is already working on this.

Since Aug 22, 2025.

KV-Cache Management Performance Scaffolding
Dominant language
Python
Stars
14.7k
Forks
2.8k
Avg merge
2d 23h
Merged PRs (30d)
489

Description

Proposal to improve performance

This is a discussion.
Scaffolding can allow users to explicitly mark the relationships between different inference requests in an agent application request. Will this be helpful for the management of kvcache? If so, how should we utilize this information?

Report of performance regression

No response

Misc discussion on performance

No response

Your current environment (if you think it is necessary)

System Information:

  • OS:
  • Python version:
  • CUDA version:
  • GPU model(s):
  • Driver version:
  • TensorRT version:
  • PyTorch version:
  • TensorRT-LLM version:

Detailed output:

Paste the output of the above commands here
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.