Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to implement a tensorrt plugin for "Unique" op? #3655

Closed
BobLiu20 opened this issue Feb 7, 2024 · 2 comments
Closed

How to implement a tensorrt plugin for "Unique" op? #3655

BobLiu20 opened this issue Feb 7, 2024 · 2 comments
Assignees
Labels
triaged Issue has been triaged by maintainers

Comments

@BobLiu20
Copy link

BobLiu20 commented Feb 7, 2024

I want to implement a plug-in for the operator Unique. But I don’t know how to determine its output dimension, because it cannot be determined directly based on the input (must be determined after calculation? )

nvinfer1::DataType UniquePlugin::getOutputDataType(int index, const nvinfer1::DataType* inputTypes, int nbInputs) const
    noexcept
{
    ?????????????
}

Numpy "Unuqie": https://numpy.org/doc/stable/reference/generated/numpy.unique.html

Any idea to implement it?

@BobLiu20 BobLiu20 changed the title How to implement tensorrt a plugin for "Unique" op? How to implement a tensorrt plugin for "Unique" op? Feb 7, 2024
@zerollzeng
Copy link
Collaborator

Currently we don't support data dependent plugin. @samurdhikaru for viz.

@zerollzeng zerollzeng self-assigned this Feb 8, 2024
@zerollzeng zerollzeng added the triaged Issue has been triaged by maintainers label Feb 8, 2024
@ttyio
Copy link
Collaborator

ttyio commented Apr 16, 2024

closing as duplicate with #3521, we need DDS plugin support.

@ttyio ttyio closed this as completed Apr 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
triaged Issue has been triaged by maintainers
Projects
None yet
Development

No branches or pull requests

3 participants