Skip to content

↔ [Converter] Add support for aten.matmul in the FX aten path #1709

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.

Sign up for GitHub

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

Jump to bottom
Closed
gs-olive opened this issue Mar 2, 2023 · 1 comment · Fixed by #1770
Closed

↔ [Converter] Add support for aten.matmul in the FX aten path #1709

gs-olive opened this issue Mar 2, 2023 · 1 comment · Fixed by #1770
Assignees
@apbose
Labels
feature request New feature or request No Activity

Comments

@gs-olive
Copy link
Collaborator

gs-olive commented Mar 2, 2023 •
edited
Loading

aten.matmul

  • Function Schema: torch.ops.aten.matmul: ((torch.float32, torch.float32), {})

  • Original PyTorch API: torch.matmul

  • Relevant TensorRT Documentation: IMatrixMultiplyLayer

Add support for matmul as an aten converter.
@gs-olive gs-olive added the feature request New feature or request label Mar 2, 2023
@apbose apbose mentioned this issue Mar 24, 2023
Merged
@github-actions
Copy link

github-actions bot commented Jun 5, 2023

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

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@apbose apbose

Labels
feature request New feature or request No Activity
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

fx2trt converters aten::slice,aten::select and aten::matmul pytorch/TensorRT
2 participants
@apbose @gs-olive