Skip to content

Develop/omni #252

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.

Sign up for GitHub

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

Jump to bottom
Merged
YutackPark merged 62 commits into from
Dec 13, 2025
Merged

Develop/omni #252

YutackPark merged 62 commits into from
Dec 13, 2025

Conversation

@YutackPark
Copy link
Member

@YutackPark YutackPark commented Nov 13, 2025

#249

Release after merge

YutackPark and others added 30 commits May 8, 2025 16:23
@YutackPark
flash init
eff5640
@YutackPark
flash init
08c50d4
@YutackPark
Merge branch 'main' into flash
620a1ec
@YutackPark
wip
5cd9747
@YutackPark
flashTP
ed6bf8a
@YutackPark
chore
7cb36aa
@YutackPark
Feats: flashTP support in LAMMPS
20bc409
@YutackPark
Merge branch 'main' into flash
df60dff
@YutackPark
chore
9fde421
@pre-commit-ci
[pre-commit.ci] auto fixes from pre-commit.com hooks
16b84fe 
for more information, see https://pre-commit.ci
@YutackPark
fix: lammps parallel + flashTP
2ce7ab6
@YutackPark
Merge branch 'main' into flash
eeb3c59
@YutackPark
chore
1bf207d
@YutackPark
bugfix
5969e42
@YutackPark
fix
198e015
@YutackPark
chore: better err msg
fe226d1
@YutackPark
feats: cueq latest + fused scatter
5dc1925
@pre-commit-ci
[pre-commit.ci] auto fixes from pre-commit.com hooks
0f63a32 
for more information, see https://pre-commit.ci
@YutackPark
bugifx
679abfe
@YutackPark
bugfix
35d95a7
@YutackPark
Merge branch 'flash' of github.com:MDIL-SNU/SevenNet into flash
ff13087
@YutackPark
bugfix
bb68b90
@YutackPark
activate calc backend with envvar + remove debug print
7fd05e3
@pre-commit-ci
[pre-commit.ci] auto fixes from pre-commit.com hooks
ca46d55 
for more information, see https://pre-commit.ci
@lee2tae
[WIP] Wrapper for mliap
3ac1aad
@lee2tae
add: mliap entry point
ac1cc87
@lee2tae
Merge branch 'flash' into develop/mliap_tmp
2aa9f5f
@lee2tae
[WIP] modality + Cueq
b281725
@alphalm4
initial commit w ghost exchange
e62c16c
@alphalm4
changelog
4f29869
@YutackPark
Copy link
Member Author

YutackPark commented Nov 17, 2025 •
edited
Loading

@lee2tae @alphalm4
I think the new lammps_mliap module could be more simple and can be integrated to sevennet without creating the new modules (folders).

  • Please integrate sevenn/integrations/lammps_mliap/create_lmp_mliap_file to sevenn/main/sevenn_get_model.py.

  • We can simplify the class name into "SevenNetMLIAPWrapper, and the file name into mliap_wrapper.py`. The term ML-IAP already imply it is about LAMMPS interface.

    SevenNet/sevenn/integrations/lammps_mliap/lmp_mliap_wrapper.py

    Line 24 in fc725f2

    class SevenNetLAMMPSMLIAPWrapper(MLIAPUnified):

  • Please move sevenn/integrations/lammps_mliap/lmp_mliap_wrapper.py to the top level. sevenn/~~.py.

  • As we can find from this PR: Add init files for integrations and lammps_mliap #255 , new dependency lammps is introduced but pyproject.toml is not changed. There are two choices, make the lammps dependency mandatory or optional. I'm not familiar with lammps as a python package but if it is simple enough and does not break anything, we could choose the option 1.

@alphalm4
Copy link
Contributor

alphalm4 commented Nov 17, 2025

integration working in my fork

alphalm4 and others added 18 commits November 17, 2025 12:53
@alphalm4
add r2scan-d3 param and readme update
fbbafbd
@alphalm4
update readme
c624c25
@alphalm4
incorperate mliap into sevenn_get_model and add dependencies
57f70e7
@alphalm4
recover pair_e3gnn deploy compatibiility via DummyExchange, change mo…
b3d8d8c 
…dule name (LAMMPSMLIAP -> MLIAP)
@alphalm4
refactor mliap parts
a429af8
@alphalm4
clean, set TP accel=False in calculator.py
e8fd171
@alphalm4
re
126ae29
@YutackPark
chore: lint
5770a19
@YutackPark
refactor
7f44a9d
@YutackPark
rename filename + refactor get_model.py
9a2ca64
@YutackPark
mliap.py
08b7c41
@YutackPark
Merge pull request #257 from alphalm4/develop/omni
a733895 
Update MLIAP-related parts and D3 parts
@lee2tae
ML-IAP pytest code
89e9a00
@lee2tae
small bug fix in torch.as_tensor()
4cc35d7
@lee2tae
bugfix + clean
4c650b9
@YutackPark
Merge pull request #258 from lee2tae/develop/omni
f845565 
ML-IAP pytest code
@YutackPark
chore: add TF32 CUBLAS warning
8bb23d3
@pre-commit-ci
[pre-commit.ci] auto fixes from pre-commit.com hooks
cdf0f5d 
for more information, see https://pre-commit.ci
@YutackPark YutackPark merged commit a167fd9 into main Dec 13, 2025
1 of 2 checks passed
@YutackPark YutackPark deleted the develop/omni branch December 13, 2025 10:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@alphalm4 alphalm4 Awaiting requested review from alphalm4

@Jaesun0912 Jaesun0912 Awaiting requested review from Jaesun0912

@greendragon920 greendragon920 Awaiting requested review from greendragon920

@lee2tae lee2tae Awaiting requested review from lee2tae

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@YutackPark @alphalm4 @lee2tae @Jaesun0912