prod_force: support multiple frames in parallel #2600
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
The previous `prod_force` did not support multiple frames in parallel, which was slow when batch size is large. Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Codecov ReportPatch coverage:
Additional details and impacted files@@ Coverage Diff @@
## devel #2600 +/- ##
==========================================
+ Coverage 76.66% 76.68% +0.02%
==========================================
Files 233 233
Lines 24177 24182 +5
Branches 1711 1695 -16
==========================================
+ Hits 18536 18545 +9
Misses 4518 4518
+ Partials 1123 1119 -4
☔ View full report in Codecov by Sentry. |
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu>
wanghan-iapcm
pushed a commit
that referenced
this pull request
Jun 12, 2023
Merged
wanghan-iapcm
pushed a commit
that referenced
this pull request
Jul 20, 2023
Add an experimental model called pairwise DPRc, which is fragment-based and integrated with QM/MM. Compression inference and training are supported. Unit tests and documentation have been added. Some features or bugfix to implement this PR have been merged in #2549, #2600, #2601, #2604, #2631, #2635, #2665, #2666, #2667, and #2679. This PR makes some changes to `model.build_descrpt` additionally: - fix errors when the suffix is not empty - fix errors when `fparam` or `aparam` are given - support model-customized `input_map` --------- Signed-off-by: Jinzhe Zeng <jinzhe.zeng@rutgers.edu> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
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.
The previous
prod_forcedid not support multiple frames in parallel, which was slow when the batch size was large.This PR adds support so that prod_force can be parallelized in the dimension of the samples.
When the batch size is about 70, the
prod_forceop is 10x faster than before on GPU cards.