pytorch / pytorch/TensorRT

📖 [Story] Performance improvements/gaps in Torch-TensorRT

Open
#3,627 0 comments 0 reactions 2 assignees View on GitHub

@zewenli98 is already working on this.

Since Jun 26, 2025.

Story story: Performance & Benchmarking
Dominant language
Python
Stars
3k
Forks
410
Avg merge
3d 18h
Merged PRs (30d)
78

Description

TL;DR

This story tracks all the known perf bugs and fixes for them in Torch-TensorRT compared to ONNX-TRT and TS-TRT

Goal(s)

Close the gap between ONNX-TensorRT and Torch-TensorRT. Identify the existing performance culprit during engine compilation and record them here.

Tasks

### Tasks

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.