Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature Request] add se_atten_v2 and redirect dpa1 to se_atten_v2 #3831

Closed
njzjz opened this issue May 28, 2024 · 1 comment · Fixed by #3840
Closed

[Feature Request] add se_atten_v2 and redirect dpa1 to se_atten_v2 #3831

njzjz opened this issue May 28, 2024 · 1 comment · Fixed by #3840
Assignees

Comments

@njzjz
Copy link
Member

njzjz commented May 28, 2024

Summary

  • add se_atten_v2 to PyTorch and DP
  • redirect dpa1 to se_atten_v2

Detailed Description

Per discussion.

Further Information, Files, and Links

No response

@iProzd
Copy link
Collaborator

iProzd commented May 30, 2024

Maybe no need to redirect dpa1 to se_atten_v2?
dpa1 is equivalent to se_atten from original definition, while se_atten_v2 is a special case of dpa1 to use strip structure.

@njzjz njzjz linked a pull request May 30, 2024 that will close this issue
github-merge-queue bot pushed a commit that referenced this issue Jun 6, 2024
Solve #3831 and #3139
- add `se_atten_v2` to PyTorch and DP
- add document equation for `se_attn_v2`

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Introduced a new descriptor class with enhanced configuration options
and methods for serialization and deserialization.
- Added new configurable parameters to the descriptor setup for improved
flexibility.

- **Documentation**
- Updated function documentation to reflect new arguments and usage
instructions.

- **Bug Fixes**
- Refined serialization logic to handle new parameters and class types
more accurately.
- Improved error messages for better clarity during serialization
processes.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Chenqqian Zhang <100290172+Chengqian-Zhang@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Duo <50307526+iProzd@users.noreply.github.com>
@njzjz njzjz closed this as completed Jun 6, 2024
@github-project-automation github-project-automation bot moved this from Backlog to Done in DeePMD-3.0.0 beta release Jun 6, 2024
mtaillefumier pushed a commit to mtaillefumier/deepmd-kit that referenced this issue Sep 18, 2024
Solve deepmodeling#3831 and deepmodeling#3139
- add `se_atten_v2` to PyTorch and DP
- add document equation for `se_attn_v2`

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Introduced a new descriptor class with enhanced configuration options
and methods for serialization and deserialization.
- Added new configurable parameters to the descriptor setup for improved
flexibility.

- **Documentation**
- Updated function documentation to reflect new arguments and usage
instructions.

- **Bug Fixes**
- Refined serialization logic to handle new parameters and class types
more accurately.
- Improved error messages for better clarity during serialization
processes.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: Chenqqian Zhang <100290172+Chengqian-Zhang@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Duo <50307526+iProzd@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
No open projects
Archived in project
Development

Successfully merging a pull request may close this issue.

3 participants