Skip to content

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

Merged
narendasan merged 6 commits intomasterfrom
prim_tupleconstruct
May 23, 2020
Merged

Address prim::TupleConstruct and also fully support returning multiple outputs#66
narendasan merged 6 commits intomasterfrom
prim_tupleconstruct

Conversation

@narendasan
Copy link
Collaborator

@narendasan narendasan commented May 22, 2020

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