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Outdated suggestions cannot be applied.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.
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.
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
[inductor] convert layout of conv weight ahead of time for inference #103642
[inductor] convert layout of conv weight ahead of time for inference #103642
Changes from all commits
3b03e06
ca24229
379fabe
53e9ed9
27b08b4
7c200c3
0122768
230405e
dd3165b
0e0d73e
bea85f7
6c3a3c6
aeb658b
d5509a3
5d8c954
92d213c
24b118b
b8c4556
File filter
Filter by extension
Conversations
Jump to
There are no files selected for viewing
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I would have thought we needed the fake_tensor_prop after, but not before. I do think we need it after or the meta's will be incorrect
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Run a FakeTensorProp before the conversion to make sure meta['val'] is properly setup. I'm worried that they may not already be setup.
But if we are sure FakeTensorProp has already been called before, we can save this call.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think we should add it again, since now the existing meta's will be incorrect, since we've changed striding