NVIDIA / NVIDIA/TensorRT-LLM

[Feature]: AutoDeploy: generic constant folding

Open
#9,955 0 comments 0 reactions 1 assignee View on GitHub

@nvchenghaoz is already working on this.

Since Dec 12, 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

Let's consider using a generic graph traversal to do arbitrary constant folding. I.e. what I mean by that is that we should be able to pre-compute any subgraph that is independent of inputs and put that into a load_hook + buffer/parameter of the GraphModule and just retrieve it at runtime.

We currently have one example of this in nano3 and the A_log parameter

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.