update custom op conversions #92
Merged
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
navahgar
approved these changes
Aug 30, 2024
matthewfl
reviewed
Aug 30, 2024
| @@ -211,6 +214,118 @@ class ConvertAtenFakeQuantizePerChannelAffineOp | |||
| } | |||
| }; | |||
|
|
|||
| class ConvertAtenSortOp : public OpConversionPattern<AtenSortOp> { | |||
There was a problem hiding this comment.
Most likely the sort is coming from a top-k. I would prefer that we keep top-k instead of changing it to a sort as trt supports top-k already, and if we add sort then it just ends up getting changed back to top-k internally with additional performance penalties due to any extra ops that get added
There was a problem hiding this comment.
Good idea. We can add an internal patch here to disable the topk-->sort. I will add a new custom_op to handle the topk then.
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Outdated suggestions cannot be applied.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.
--
aten.sort--
aten.cumsum--
aten.min.dim--
aten.view(dynamic shape only)--
aten.topkTo test:
bazel test //...(in docker)