[Unity] Support storage reuse for dynamic shapes - #16500
Merged
Merged
Conversation
MasterJH5574
approved these changes
Feb 2, 2024
MasterJH5574
left a comment
MasterJH5574
left a comment
Contributor
There was a problem hiding this comment.
LGTM. Thank you @vinx13!
masahi
pushed a commit
to masahi/tvm
that referenced
this pull request
Feb 20, 2024
Before this PR, dynamic shapes require upper bound of variables to be provided in order to use storage planning. We can relax this requirement, for shapes with unknown bound, we can look up other tensors with the same symbolic shapes. This can be helpful for deep learning models where the layers with the same configurations are usually repeated since there are many objects with the same shapes. This PR changed the `StorageToken` to use `PrimExpr` bytes which can be integer or symbolic. For symbolic shapes, we put the tokens into a special buckets for looking up.
elvin-n
pushed a commit
to Deelvin/tvm
that referenced
this pull request
Mar 19, 2024
Before this PR, dynamic shapes require upper bound of variables to be provided in order to use storage planning. We can relax this requirement, for shapes with unknown bound, we can look up other tensors with the same symbolic shapes. This can be helpful for deep learning models where the layers with the same configurations are usually repeated since there are many objects with the same shapes. This PR changed the `StorageToken` to use `PrimExpr` bytes which can be integer or symbolic. For symbolic shapes, we put the tokens into a special buckets for looking up.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Before this PR, dynamic shapes require upper bound of variables to be provided in order to use storage planning. We can relax this requirement, for shapes with unknown bound, we can look up other tensors with the same symbolic shapes. This can be helpful for deep learning models where the layers with the same configurations are usually repeated since there are many objects with the same shapes.
This PR changed the
StorageTokento usePrimExprbytes which can be integer or symbolic. For symbolic shapes, we put the tokens into a special buckets for looking up.cc @MasterJH5574 @tqchen