Get export APIs ready for PTC #566
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
✅ Deploy Preview for resplendent-gnome-14e531 ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
facebook-github-bot
added
the
CLA Signed
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D49742989 |
angelayi
force-pushed
the
export-D49742989
branch
from
17d913f to
8a36b5d
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D49742989 |
Summary: X-link: pytorch/pytorch#110410 https://docs.google.com/document/d/1QJJEGnj2nHGPODlw38BEG3KLLCOTfdOVjPrNQbz_LM8/edit#bookmark=id.lp80wfshq130 Changes: * `torch.export` will return a functional ATen graph but not lowered to core aten decompositions (CompositeImplicitAutograd decomps still run) * `exported_program.run_decompositions(decomposition_table)` will optionally take a decomposition table, and run decompositions on the exported program, returning a new exported program. By default we will run the Core ATen decomposition table. Calling convention for Executorch stays the same: ``` pre_autograd_graph = capture_pre_autograd_graph(f, args, ...) aten_graph_no_decomps = torch.export.export(pre_autograd_graph, args, ...) # Within to_edge we decompose to core aten and then convert to edge edge_graph = exir.to_edge(aten_graph_no_decomps) ``` Reviewed By: larryliu0820, guangy10 Differential Revision: D49742989
angelayi
added a commit
to angelayi/pytorch
that referenced
this pull request
Oct 10, 2023
Summary: X-link: pytorch/executorch#566 https://docs.google.com/document/d/1QJJEGnj2nHGPODlw38BEG3KLLCOTfdOVjPrNQbz_LM8/edit#bookmark=id.lp80wfshq130 Changes: * `torch.export` will return a functional ATen graph but not lowered to core aten decompositions (CompositeImplicitAutograd decomps still run) * `exported_program.run_decompositions(decomposition_table)` will optionally take a decomposition table, and run decompositions on the exported program, returning a new exported program. By default we will run the Core ATen decomposition table. Calling convention for Executorch stays the same: ``` pre_autograd_graph = capture_pre_autograd_graph(f, args, ...) aten_graph_no_decomps = torch.export.export(pre_autograd_graph, args, ...) # Within to_edge we decompose to core aten and then convert to edge edge_graph = exir.to_edge(aten_graph_no_decomps) ``` Test Plan: CI Reviewed By: larryliu0820, guangy10 Differential Revision: D49742989
angelayi
force-pushed
the
export-D49742989
branch
from
8a36b5d to
19acbca
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D49742989 |
Contributor
|
This pull request has been merged in a4a86df. |
Contributor
|
This pull request has been reverted by 0f2bc69. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary:
https://docs.google.com/document/d/1QJJEGnj2nHGPODlw38BEG3KLLCOTfdOVjPrNQbz_LM8/edit#bookmark=id.lp80wfshq130
Changes:
torch.exportwill return a functional ATen graph w/o decompositionsexported_program.run_decompositions(decomposition_table)will optionally take a decomposition table, and run decompositions on the exported program, returning a new exported program. By default we will run the Core ATen decomposition table.Calling convention for Executorch stays the same:
Differential Revision: D49742989