Skip to content

✨[Feature] Collection IO end to end support for TRT engine #1293

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

Closed
bowang007 opened this issue Aug 19, 2022 · 4 comments · Fixed by #1656
Closed

✨[Feature] Collection IO end to end support for TRT engine #1293

bowang007 opened this issue Aug 19, 2022 · 4 comments · Fixed by #1656
Assignees
Labels
component: core Issues re: The core compiler feature request New feature or request

Comments

@bowang007
Copy link
Collaborator

Is your feature request related to a problem? Please describe.

Currently Torch-TensorRT is relying on Partitioning to support Tuple/List grouped inputs, which means for some models with Tuple/List input/output, they are not supported end to end. This could also affect performance. So, we should try to implement a change where when we go to construct the inputs to the engine we on the fly group them to be in the form of the graph input so that conversion can work end to end.

@bowang007 bowang007 added the feature request New feature or request label Aug 19, 2022
@ncomly-nvidia ncomly-nvidia added the component: core Issues re: The core compiler label Aug 22, 2022
@github-actions
Copy link

This issue has not seen activity for 90 days, Remove stale label or comment or this will be closed in 10 days

@Christina-Young-NVIDIA
Copy link
Collaborator

Pending PR #1599 .

@narendasan
Copy link
Collaborator

@gs-olive Can we close this?

@gs-olive
Copy link
Collaborator

@narendasan I think we should get #1656 merged first - I can set that PR to auto-close this issue.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component: core Issues re: The core compiler feature request New feature or request
Projects
None yet
Development

Successfully merging a pull request may close this issue.

6 participants