pytorch / pytorch/TensorRT

❓ [Question] How to save tensorrt engine ?

Open
#3,348 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question story: Documentation & Examples
Dominant language
Python
Stars
3k
Forks
410
Avg merge
3d 18h
Merged PRs (30d)
78

Description

❓ Question

I had already save torch.jit model and infer with pytorch backend successful, but I had tried find some example in project and issue, but I can not find any case, code, example, tutorial to show how to save a tensorrt engine for running by tensorrt backend, can you help me?

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.

Research direction

Review the project's existing examples and issue discussions for TensorRT engine serialization, starting from the reported TorchScript model flow that works with the PyTorch backend. Done means providing a clear, reproducible example or tutorial for saving an engine and running it with the TensorRT backend.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.