feat: _do_annotate_conv_bn + _annotate_softmax #1
Conversation
This file contains 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
Dayof
changed the title
Dayof
changed the title
ShinyCode
approved these changes
Feb 15, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Motivation
Fix some torch limitations
_get_aten_graph_module_for_patternreceives this_conv_bnfn and call torchcapture_pre_autograd_graphwith it, but inside this torch function it has this following assert (torch/_export/__init__.py:147):This PR encapsulates the callable as a torch.nn.Module so that it does no raises this problem.
Add softmax quantized op
There is no softmax included in the static op in ai-edge-torch nowadays, therefore we are adding
_annotate_softmaxso that we can convert a full int8 model that included a softmax as output layer.