Skip to content

Conversation

@jfix71
Copy link
Contributor

@jfix71 jfix71 commented Sep 9, 2021

Summary:

  • Any info added to the dict in node.meta["lowering_info"] will be added to the node_rep during serialization.
  • Use this to add annotations on placeholders that allow partial inputs and require padding.
  • Check for these annotations and set them in the NNPICompiledFunction as expected

Test Plan: Validated working on inline_cvr in stack. Additionally existing fx_glow end to end tests should still pass.

Differential Revision: D30824192

…g/partial to it

Summary:
- Any info added to the dict in node.meta["lowering_info"] will be added to the node_rep during serialization.
- Use this to add annotations on placeholders that allow partial inputs and require padding.
- Check for these annotations and set them in the NNPICompiledFunction as expected

Test Plan: Validated working on inline_cvr in stack. Additionally existing fx_glow end to end tests should still pass.

Differential Revision: D30824192

fbshipit-source-id: bef28b6338f40e68090e5759ac011cd56a61a994
@facebook-github-bot
Copy link
Contributor

facebook-github-bot commented Sep 9, 2021

🔗 Helpful links

💊 CI failures summary and remediations

As of commit 8af6313 (more details on the Dr. CI page):


  • 1/1 failures possibly* introduced in this PR
    • 1/1 non-scanned failure(s)

ci.pytorch.org: 1 failed


This comment was automatically generated by Dr. CI (expand for details).Follow this link to opt-out of these comments for your Pull Requests.

Please report bugs/suggestions to the (internal) Dr. CI Users group.

Click here to manually regenerate this comment.

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D30824192

jfix71 added a commit to jfix71/glow that referenced this pull request Sep 9, 2021
…g/partial to it (#64725)

Summary:
Pull Request resolved: pytorch/pytorch#64725

- Any info added to the dict in node.meta["lowering_info"] will be added to the node_rep during serialization.
- Use this to add annotations on placeholders that allow partial inputs and require padding.
- Check for these annotations and set them in the NNPICompiledFunction as expected

Differential Revision: D30824192

fbshipit-source-id: a3a3f6c0b350eb06c6481893087a1d2c25179b8c
@codecov
Copy link

codecov bot commented Sep 9, 2021

Codecov Report

Merging #64725 (8af6313) into master (d0b207e) will decrease coverage by 0.00%.
The diff coverage is 40.00%.

@@            Coverage Diff             @@
##           master   #64725      +/-   ##
==========================================
- Coverage   66.62%   66.62%   -0.01%     
==========================================
  Files         710      710              
  Lines       92433    92438       +5     
==========================================
+ Hits        61582    61583       +1     
- Misses      30851    30855       +4     

@facebook-github-bot
Copy link
Contributor

This pull request has been merged in a33fff6.

facebook-github-bot pushed a commit that referenced this pull request Sep 9, 2021
…g/partial to it (#5810)

Summary:
Pull Request resolved: pytorch/glow#5810

Pull Request resolved: #64725

- Any info added to the dict in node.meta["lowering_info"] will be added to the node_rep during serialization.
- Use this to add annotations on placeholders that allow partial inputs and require padding.
- Check for these annotations and set them in the NNPICompiledFunction as expected

Test Plan: Validated working on inline_cvr in stack. Additionally existing fx_glow end to end tests should still pass.

Reviewed By: 842974287

Differential Revision: D30824192

fbshipit-source-id: def64ef097aa35c337abb494415f7d437c6c7fa9
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants