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.

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

[FX] aten2trt and some pass fixes #1390

Merged
merged 1 commit into from
Oct 5, 2022
Merged

[FX] aten2trt and some pass fixes #1390

merged 1 commit into from
Oct 5, 2022

Conversation

frank-wei
Copy link
Contributor

@frank-wei frank-wei commented Oct 5, 2022 •
edited by yinghai
Loading

7ae5990ba20126da1e0a93ad0887cb1892ff48cd Janet Yang qxy11@fb.com Pass to remove for _validate_and_get_n_vectors
9faf04dc5f2698037ffec9f69ca2024b73c54086 Michael Voznesensky voz@fb.com Synchronize pytorch/torchdynamo (revision 8bbecb0@main) to pytorch/torchdynamo
710ed4460067921316c153afc23404523611f808 Ruichao Xiao xiaoruichao@fb.com [fbcode][GPU] push down parrallel split for add/mul elementwise ops
5203f38c7e0e3eed0b5c6050655c83bfd9ef5f83 Ruichao Xiao xiaoruichao@fb.com [fbcode][GPU] fuse split-linear-add as single linear
d2d202458743cdc5c482425decd919b619ac7966 Ruichao Xiao xiaoruichao@fb.com [fbcode][GPU][FIX] extend usage of fuse_parrallel_linear
aefec0f40326bbf4886f039d00322413107a5bc3 Lu Fang lufang@fb.com Enable the OSS plugin in the internal predictor
d269be2fc7d84738a642d1d53eb44e6886a28d0c Alex Beloi alexbeloi@fb.com [fx] add deferred weights (xl_weight) and tracing for xl_embedding_bag
6f233bc9c72d90a908db0548c9d2dbe853895137 Alex Beloi alexbeloi@fb.com [fx] fix out of bounds indices/offsets for embedding_bag ops with xl_weight
3ca3b21c6a85ab9a6e9de503d0f13ee713a7b67c Janet Yang qxy11@fb.com Support div, torch.norm 52955d93d25e857510ed1b765220e8e5b0b0bb08 Janet Yang qxy11@fb.com Pass to replace sum(elmtwise(X))/numel(X) w/ mean(elmtwise(X))
89c56ef76a7a329f244a013ac5ccb099cb00c3c0 Janet Yang qxy11@fb.com Support scalar clamp, fixes for nan_to_num and benchmark
afdc533da031a64e162bb08c8629ff38739e24f8 Wei Wei wwei6@fb.com [fx2trt] disable dispatch trace leaf node test 9905612fd8e6e2e79dc2f2bd1fa5b5d7fd5c98c3 Shirong Wu shirong@fb.com Add number constrain for fuse group ln d160a7a5e554d37c142e13f100bf4d8739ced232 Wei Wei wwei6@fb.com add option to remove passes c22f691e6eae1b06ecd301eb6285b32d5dc9717c Mike Iovine mikeiovine@fb.com [fx2trt] Support dict inputs in acc tracer
8c05a3c57b1f5c63108b979ef8c61411525d0b1f Mike Iovine mikeiovine@fb.com [fx2trt] Support namedtuple access in acc tracer getattr
ff2000594e3f3ff75e0074edf9c38b5609128bbd Janet Yang qxy11@fb.com Generalize remove split ops more 1580805d827eb40c941e769b0b99e7c6a3ed6f89 Wei Wei wwei6@fb.com [fx2trt] add reshape unit test d6a975462071a3747d18edcbe87a3b143b3ece88 Archie Sravankumar archishmans@fb.com Added FX tracing for log_softmax
6943ac0e322077b36a03c50c4c9065de6cd32837 Sungmin Cho sungmincho@fb.com Add replace_mutable_op lower pass
baab27b81b1275de92fdaf760a158ce951564d33 Donglin Xia doxia@fb.com Register avg_pool3d for acc_op in acc_op.py ae4c4e2c3c18d78542140fcc30e1c24f7c647ef3 Wei Wei wwei6@fb.com [aten2trt] init check-in fc94c5e110d5552349b2634662eae41f9f0b8933 Wei Wei wwei6@fb.com [ads] fix a bug in fuse_parallel_linear 87ef03338c9a25c5a610a2eb590345e8935f8d75 Wei Wei wwei6@fb.com [aten2trt] add binary ops fca64a5b09749284fc6028b510078257fd4717b1 Shirong Wu shirong@meta.com Fix dper pass 2bb168517ace7e638cffc7a241b1cbf528790b92 Mike Iovine mikeiovine@fb.com [fx2trt] Add acc normalization blocklist 8c912e085cf8722d572698286020ae1ce055023d Zhijing Li (Accelerator Enablement) tissue030@fb.com Skip unstable test_conv_add_standalone_module
b80dca9c9afa3b7d253e7806f48a890b9f83bf04 Jonathan Amazon jonamazon@fb.com [PyTorch][FX][Compiler] Add acc_op tracing support for torch.baddbmm in FX
f06174dbb190df4ea488ca99a81d4884b5ed3aa2 wwei6 wwei6@fb.com [fx2trt] compile 817c1f0b6278ce0ad04dd88d43d21e7390e3baea wwei6 wwei6@fb.com [aten2trt] init check-in 92ce42c16f34804584a7e553eddf897c9fa4f65e wwei6 wwei6@fb.com [aten2trt] binary op

Description

Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.

Fixes # (issue)

Type of change

Please delete options that are not relevant and/or add your own.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Checklist:

  • My code follows the style guidelines of this project (You can use the linters)
  • 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
  • I have added tests to verify my fix or my feature
  • New and existing unit tests pass locally with my changes
  • I have added the relevant labels to my PR in so that relevant reviewers are notified

Changes done internally at Facebook
1d31c27 
7ae5990ba20126da1e0a93ad0887cb1892ff48cd Janet Yang <qxy11@fb.com> Pass to remove for _validate_and_get_n_vectors
9faf04dc5f2698037ffec9f69ca2024b73c54086 Michael Voznesensky <voz@fb.com> Synchronize pytorch/torchdynamo (revision 8bbecb0@main) to pytorch/torchdynamo
710ed4460067921316c153afc23404523611f808 Ruichao Xiao <xiaoruichao@fb.com> [fbcode][GPU] push down parrallel split for add/mul elementwise ops
5203f38c7e0e3eed0b5c6050655c83bfd9ef5f83 Ruichao Xiao <xiaoruichao@fb.com> [fbcode][GPU] fuse split-linear-add as single linear
d2d202458743cdc5c482425decd919b619ac7966 Ruichao Xiao <xiaoruichao@fb.com> [fbcode][GPU][FIX] extend usage of fuse_parrallel_linear
aefec0f40326bbf4886f039d00322413107a5bc3 Lu Fang <lufang@fb.com> Enable the OSS plugin in the internal predictor
d269be2fc7d84738a642d1d53eb44e6886a28d0c Alex Beloi <alexbeloi@fb.com> [fx] add deferred weights (xl_weight) and tracing for xl_embedding_bag
6f233bc9c72d90a908db0548c9d2dbe853895137 Alex Beloi <alexbeloi@fb.com> [fx] fix out of bounds indices/offsets for embedding_bag ops with xl_weight
3ca3b21c6a85ab9a6e9de503d0f13ee713a7b67c Janet Yang <qxy11@fb.com> Support div, torch.norm
52955d93d25e857510ed1b765220e8e5b0b0bb08 Janet Yang <qxy11@fb.com> Pass to replace sum(elmtwise(X))/numel(X) w/ mean(elmtwise(X))
89c56ef76a7a329f244a013ac5ccb099cb00c3c0 Janet Yang <qxy11@fb.com> Support scalar clamp, fixes for nan_to_num and benchmark
48071d8da1dc66fffceb0b42ea386079f1fb9709 Wei Wei <wwei6@fb.com> [ads] bug fix in push_down_parrallel_split_ops
afdc533da031a64e162bb08c8629ff38739e24f8 Wei Wei <wwei6@fb.com> [fx2trt] disable dispatch trace leaf node test
9905612fd8e6e2e79dc2f2bd1fa5b5d7fd5c98c3 Shirong Wu <shirong@fb.com> Add number constrain for fuse group ln
d160a7a5e554d37c142e13f100bf4d8739ced232 Wei Wei <wwei6@fb.com> add option to remove passes
c22f691e6eae1b06ecd301eb6285b32d5dc9717c Mike Iovine <mikeiovine@fb.com> [fx2trt] Support dict inputs in acc tracer
8c05a3c57b1f5c63108b979ef8c61411525d0b1f Mike Iovine <mikeiovine@fb.com> [fx2trt] Support namedtuple access in acc tracer getattr
ff2000594e3f3ff75e0074edf9c38b5609128bbd Janet Yang <qxy11@fb.com> Generalize remove split ops more
1580805d827eb40c941e769b0b99e7c6a3ed6f89 Wei Wei <wwei6@fb.com> [fx2trt] add reshape unit test
d6a975462071a3747d18edcbe87a3b143b3ece88 Archie Sravankumar <archishmans@fb.com> Added FX tracing for `log_softmax`
6943ac0e322077b36a03c50c4c9065de6cd32837 Sungmin Cho <sungmincho@fb.com> Add replace_mutable_op lower pass
baab27b81b1275de92fdaf760a158ce951564d33 Donglin Xia <doxia@fb.com> Register avg_pool3d for acc_op in acc_op.py
ae4c4e2c3c18d78542140fcc30e1c24f7c647ef3 Wei Wei <wwei6@fb.com> [aten2trt] init check-in
fc94c5e110d5552349b2634662eae41f9f0b8933 Wei Wei <wwei6@fb.com> [ads] fix a bug in fuse_parallel_linear
87ef03338c9a25c5a610a2eb590345e8935f8d75 Wei Wei <wwei6@fb.com> [aten2trt] add binary ops
fca64a5b09749284fc6028b510078257fd4717b1 Shirong Wu <shirong@meta.com> Fix dper pass
2bb168517ace7e638cffc7a241b1cbf528790b92 Mike Iovine <mikeiovine@fb.com> [fx2trt] Add acc normalization blocklist
8c912e085cf8722d572698286020ae1ce055023d Zhijing Li (Accelerator Enablement) <tissue030@fb.com> Skip unstable test_conv_add_standalone_module
b80dca9c9afa3b7d253e7806f48a890b9f83bf04 Jonathan Amazon <jonamazon@fb.com> [PyTorch][FX][Compiler] Add acc_op tracing support for torch.baddbmm in FX
07751118570b74ae7523622350e13c5c82b25af3 Mike Iovine <mikeiovine@fb.com> [UMIA] Refactoring to support encoder arch scripting
34f131a5d33b2cdb9fad0449627fe1a49f4ff3b9 Nan Xiao <nanx@fb.com> [Transformer QRT] Bug fixes for inference flow
786aa2956efc8d0b13c1fb8b0bd742ac0b16dd34 Stanley Shi <s2shi@fb.com> [codemod] add oncall annotation for TARGETS files in fbcode based on cont_build information - fbcode_targets_part9142
137a3977ffeb03d0387e8a95ff2f32f3d15b3de8 Wei Wei <wwei6@meta.com> [aten2trt] resnet support
4c19a277f4b87bfbbe7f4358d97b2730e5268444 Michael Voznesensky <voz@fb.com> Synchronize pytorch/torchdynamo (revision 36c2458@main) to pytorch/torchdynamo
efe0ed169ef318054f0c7cf8c59e0486c2488f2b wwei6 <wwei6@fb.com> [not for land] disable fuse parallel pass
db7917bdf3caae49e5ca6322a3b8a92c80bbd6fd wwei6 <wwei6@fb.com> [not for land] disable fuse parallel pass
f06174dbb190df4ea488ca99a81d4884b5ed3aa2 wwei6 <wwei6@fb.com> [fx2trt] compile
817c1f0b6278ce0ad04dd88d43d21e7390e3baea wwei6 <wwei6@fb.com> [aten2trt] init check-in
92ce42c16f34804584a7e553eddf897c9fa4f65e wwei6 <wwei6@fb.com> [aten2trt] binary op
f1513322f9ac4a8fd4cf9c9d7dbe3158bd9c863d wwei6 <wwei6@fb.com> [debug]transformer_371633592
088c2fdea7331aafaaf0071911d3afaf89380fb2 wwei6 <wwei6@fb.com> [aten2trt]
043c73fb70392c8397cfb4183451bf4f19a1d79f Wei Wei <wwei6@fb.com> "(uncommitted/untracked changes)"
8de14ec733539bee5b1b1eeac91c669e490e0936 wwei6 <wwei6@fb.com> [ads] set level
github-actions[bot]
github-actions bot approved these changes Oct 5, 2022
View reviewed changes
Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code conforms to C++ style guidelines

github-actions[bot]
github-actions bot approved these changes Oct 5, 2022
View reviewed changes
Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code conforms to Python style guidelines

@frank-wei frank-wei marked this pull request as ready for review October 5, 2022 17:21
github-actions[bot]
github-actions bot approved these changes Oct 5, 2022
View reviewed changes
Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code conforms to C++ style guidelines

github-actions[bot]
github-actions bot approved these changes Oct 5, 2022
View reviewed changes
Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code conforms to Python style guidelines

yinghai
yinghai approved these changes Oct 5, 2022
View reviewed changes
Copy link

@yinghai yinghai left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please screen the commit summary next time. I did it for this time.

@frank-wei frank-wei merged commit 0daf301 into master Oct 5, 2022
@frank-wei frank-wei deleted the fb-sync-wwei6 branch October 22, 2022 00:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@yinghai yinghai yinghai approved these changes

@github-actions github-actions[bot] github-actions[bot] approved these changes

@842974287 842974287 Awaiting requested review from 842974287

@narendasan narendasan Awaiting requested review from narendasan

@wushirong wushirong Awaiting requested review from wushirong

Assignees
No one assigned
Labels
cla signed component: api [Python] Issues re: Python API component: fx fx
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@frank-wei @yinghai @facebook-github-bot