pytorch / pytorch/TensorRT

📖 [Story] Implement support for serde of TRT Graph modules with torch.export serde API

Open
#2,262 0 comments 0 reactions 1 assignee View on GitHub

@peri044 is already working on this.

Since Jan 5, 2024.

Story Story: Runtime & Memory & Serialization
Dominant language
Python
Stars
3k
Forks
410
Avg merge
3d 18h
Merged PRs (30d)
78

Description

TL;DR

torch.export has serde API and now supports custom object (in our case torch.classes.tensorrt.Engine) serialization.

Goal(s)

We should be able to serialize/deserialize the output of torch-trt compilation.

Tasks

### Tasks
- [ ] https://github.com/pytorch/TensorRT/issues/2258
- [ ] https://github.com/pytorch/TensorRT/issues/2259
- [ ] https://github.com/pytorch/TensorRT/issues/2260
- [ ] https://github.com/pytorch/TensorRT/issues/2261
- [ ] https://github.com/pytorch/TensorRT/issues/2270
- [ ] https://github.com/pytorch/TensorRT/issues/2478
- [ ] https://github.com/pytorch/TensorRT/issues/2479
- [ ] https://github.com/pytorch/TensorRT/issues/2341
- [ ] https://github.com/pytorch/TensorRT/issues/2553
- [ ] https://github.com/pytorch/TensorRT/issues/2576

Additional context

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.