Relay transform for rolling a known pattern into batch_matmul #14210
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
|
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment.
Generated by tvm-bot |
|
rasagna-quic
force-pushed
the
relay_transforms
branch
from
843a285 to
bd15fb3
Compare
rasagna-quic
force-pushed
the
relay_transforms
branch
from
ec092a7 to
3b7056b
Compare
masahi
reviewed
Mar 9, 2023
| return mod | ||
|
|
||
|
|
||
| class remove_empty_pad_callback(DFPatternCallback): |
There was a problem hiding this comment.
Sorry the class name should be CamelCase. I'll merge this, but when you send a new PR in the future, please fix them.
There was a problem hiding this comment.
Thank you @masahi for your quick review and help. I will keep the above changes in mind, when I create a new PR.
masahi
approved these changes
Mar 9, 2023
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Outdated suggestions cannot be applied.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.
This PR contains relay pattern matching to roll a pattern containing strided_slice, qnn.dense, qnn.requantize, reshape, transpose, expand_dims and concatenate operators into batch_matmul operator.
https://discuss.tvm.apache.org/t/optimizing-qat-distilbert-int8-model/14182 contains more details.
@masahi @quic-sanirudh @arangasa @jverma-quic @kparzysz-quic