perf: use einsum to calculate virial #4746
Merged
Conversation
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
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR optimizes the virial computation by replacing multiple matmul operations with a single einsum call, reducing runtime overhead especially for smaller batches and models.
- Switch PyTorch virial calc from
@ matmultotorch.einsum - Switch Paddle virial calc from
@ matmultopaddle.einsum
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| deepmd/pt/model/model/transform_output.py | Replace unsqueeze + @ matmul with torch.einsum for virial |
| deepmd/pd/model/model/transform_output.py | Replace unsqueeze + @ matmul with paddle.einsum for virial |
Comments suppressed due to low confidence (2)
deepmd/pt/model/model/transform_output.py:88
- Add a unit test to verify that the new
einsum-based virial matches the originalunsqueeze + @matmul output for various tensor shapes to ensure correctness.
extended_virial = torch.einsum("...ik,...ij->...ikj", extended_force, extended_coord)
deepmd/pd/model/model/transform_output.py:85
- [nitpick] Add a gradient consistency test to ensure the Paddle
einsumvariant produces equivalent backward results compared to the original matmul approach.
extended_virial = paddle.einsum(
Contributor
📝 Walkthrough""" WalkthroughThe changes update the computation of the Changes
Suggested labels
Suggested reviewers
📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
✨ Finishing Touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
for more information, see https://pre-commit.ci
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## devel #4746 +/- ##
==========================================
- Coverage 84.69% 84.69% -0.01%
==========================================
Files 697 697
Lines 67474 67473 -1
Branches 3540 3540
==========================================
- Hits 57147 57145 -2
+ Misses 9197 9196 -1
- Partials 1130 1132 +2 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
iProzd
approved these changes
May 20, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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.
By profiling results, using
@ matmulcreates 7 matmul to complete this operation, which are time-consuming.einsumonly requires one matmul.This optimization benefits smaller batch size and model.
Profiling results on PyTorch
Summary by CodeRabbit