Skip to content

Address prim::TupleConstruct and also fully support returning multiple outputs #66

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
Merged
merged 6 commits into from
May 23, 2020
Merged

Address prim::TupleConstruct and also fully support returning multiple outputs #66

merged 6 commits into from
May 23, 2020

Conversation

narendasan
Copy link
Collaborator

Description

Addresses support for TorchScript programs using prim::TupleConstruct. Also fixes an issue with the ConvTranspose implementation

Closes #65

Type of change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • This change requires a documentation update

Checklist:

  • My code follows the style guidelines of this project
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas and hacks
  • I have made corresponding changes to the documentation and have regenerated the documentation (make html in docsrc)
  • I have added tests to verify my fix or my feature
  • New and existing unit tests pass locally with my changes

narendasan added 3 commits May 22, 2020 14:01
@narendasan
feat(//core/lowering): Add tuple lowering pass to remove tuples if
ce6cf75 
possible

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
@narendasan
fix(aten::_convolution): out channels was passed in incorrectly for
ee727f8 
deconv

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
@narendasan
docs: Document the tuple lowering pass
60f2d18 
Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
@narendasan narendasan added component: lowering Issues re: The lowering / preprocessing passes component: evaluators Issues re: Specific op evaluators labels May 22, 2020
@narendasan narendasan marked this pull request as draft May 22, 2020 21:11
narendasan added 3 commits May 22, 2020 20:48
@narendasan
feat(//core/compiler): Multiple outputs supported now via tuple
f9af574 
Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
@narendasan
feat(//cpp/benchmark): Increased workspace size for benchmark, may help
8171f79 
results and increase compatibility

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
@narendasan
feat(//cpp/trtorchexec): TRTorch exec now supports checking correctness
80808b7 
of multiple outputs

Signed-off-by: Naren Dasan <naren@narendasan.com>
Signed-off-by: Naren Dasan <narens@nvidia.com>
@narendasan narendasan linked an issue May 23, 2020 that may be closed by this pull request
Add Support for TupleConstruct #65
Closed
@narendasan narendasan marked this pull request as ready for review May 23, 2020 04:10
@narendasan narendasan merged commit 29a4dbf into master May 23, 2020
@narendasan narendasan deleted the prim_tupleconstruct branch July 15, 2020 00:20
frank-wei pushed a commit that referenced this pull request Jun 4, 2022
@alexbeloi
[fx][acc_ops] add acc_op mapper for torch.tensor_split (#66)
2b49f98 
Summary: Pull Request resolved: https://github.com/pytorch/fx2trt/pull/66

Reviewed By: 842974287

Differential Revision: D36126848

fbshipit-source-id: a8324bd773105be7cbdad00681cb971aa09f1822
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
component: evaluators Issues re: Specific op evaluators component: lowering Issues re: The lowering / preprocessing passes
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Add Support for TupleConstruct
1 participant
@narendasan