What's Changed

Breaking changes

• breaking: drop C 11 by @njzjz in #4068
• breaking(pt/dp): tune new sub-structures for DPA2 by @iProzd in #4089
  The default values of new options g1_out_conv and g1_out_mlp are set to True. The behaviors in previous versions are False.

New features

• feat pt : Support property fitting by @Chengqian-Zhang in #3867
• feat(pt/dp): support three-body type embedding by @iProzd in #4066
• feat: load customized OP library in the C interface by @njzjz in #4073
• feat: make dp neighbor-stat --type-map optional by @njzjz in #4049
• feat: directional nlist by @wanghan-iapcm in #4052
• feat(pt): support eval_typeebd for DeepEval by @njzjz in #4110
• feat: DeepEval.get_model_def_script and common dp show by @njzjz in #4131
• chore: support preset bias of atomic model output by @wanghan-iapcm in #4116
• feat(jax): support neural networks in #4156

Enhancement

• fix: bump LAMMPS to stable_29Aug2024 by @njzjz in #4088
• chore(pt): cleanup deadcode by @wanghan-iapcm in #4142
• chore(pt): make comm_dict for dpa2 noncompulsory when nghost is 0 by @njzjz in #4144
• Set ROCM_ROOT to ROCM_PATH when it exist by @sigbjobo in #4150
• chore(pt): move deepmd.pt.infer.deep_eval.eval_model to tests by @njzjz in #4153

Documentation

• docs: improve docs for environment variables by @njzjz in #4070
• docs: dynamically generate command outputs by @njzjz in #4071
• docs: improve error message for inconsistent type maps by @njzjz in #4074
• docs: add multiple packages to intersphinx_mapping by @njzjz in #4075
• docs: document CMake variables using Sphinx styles by @njzjz in #4079
• docs: update ipi installation command by @njzjz in #4081
• docs: fix the default value of DP_ENABLE_PYTORCH by @njzjz in #4083
• docs: fix defination of se_e3 by @njzjz in #4113
• docs: update DeepModeling URLs by @njzjz-bot in #4119
• docs(pt): examples for new dpa2 model by @iProzd in #4138

Bugfix

• fix: fix PT AutoBatchSize OOM bug and merge execute_all into base by @njzjz in #4047
• fix: replace datetime.datetime.utcnow which is deprecated by @njzjz in #4067
• fix:fix LAMMPS MPI tests with mpi4py 4.0.0 by @njzjz in #4032
• fix(pt): invalid type_map when multitask training by @Cloudac7 in #4031
• fix: manage testing models in a standard way by @njzjz in #4028
• fix(pt): fix ValueError when array byte order is not native by @njzjz in #4100
• fix(pt): convert torch.__version__ to str when serializing by @njzjz in #4106
• fix(tests): fix skip_dp by @njzjz in #4111
• [Fix] Wrap log_path with Path by @HydrogenSulfate in #4117
• fix: bugs in uts for property fit by @Chengqian-Zhang in #4120
• fix: type of the preset out bias by @wanghan-iapcm in #4135
• fix(pt): fix zero inputs for LayerNorm by @njzjz in #4134
• fix(pt/dp): share params of repinit_three_body by @iProzd in #4139
• fix(pt): move entry point from deepmd.pt.model to deepmd.pt by @njzjz in #4146
• fix: fix DPH5Path.glob for new keys by @njzjz in #4152
• fix(pt): make state_dict safe for weights_only by @iProzd in #4148
• fix(pt): fix compute_output_stats_global when atomic_output is None by @njzjz in #4155
• fix(pt ut): make separated uts deterministic by @iProzd in #4162
• fix(pt): finetuning property/dipole/polar/dos fitting with multi-dimensional data causes error by @Chengqian-Zhang in #4145

Dependency updates

• chore(deps): bump scikit-build-core to 0.9.x by @njzjz in #4038
• build(deps): bump pypa/cibuildwheel from 2.19 to 2.20 by @dependabot in #4045
• build(deps): bump pypa/cibuildwheel from 2.20 to 2.21 by @dependabot in #4127

CI/CD

• ci: add include-hidden-files to actions/upload-artifact by @njzjz in #4095
• ci: test Python 3.12 by @njzjz in #4059
• CI(codecov): do not notify until all reports are ready by @njzjz in #4136

Full Changelog: v3.0.0b3...v3.0.0b4

What's Changed

Other Changes

• fix: fix nopbc in dpdata driver by @njzjz in #4027

Full Changelog: v3.0.0b2...v3.0.0b3

What's Changed

New features

• feat: add documentation and options for multi-task arguments by @njzjz in #3989
• feat: plain text model format by @njzjz in #4025
• feat: allow model arguments to be registered outside by @njzjz in #3995
• feat: add get_model classmethod to BaseModel by @njzjz in #4002

Enhancement

• add unittest for virial and pe/atom by @Yi-FanLi in #4013

Documentation

• docs: document PYTORCH_ROOT by @njzjz in #3981
• docs: Disallow improper capitalization by @njzjz in #3982
• docs: pin sphinx-argparse to < 0.5.0 by @njzjz-bot in #3988

Bugfixes

• fix(cmake): fix set_if_higher by @njzjz in #3977
• fix(pt): ensure suffix of --init_model and --restart is .pt by @njzjz in #3980
• fix(pt): do not overwrite disp_file when restarting training by @njzjz in #3985
• fix(cc): compile select_map<int> when TensorFlow backend is off by @njzjz in #3987
• fix(pt): make 'find_' to be float in get data by @iProzd in #3992
• fix float precision problem of se_atten in line 217 (#3961) by @LiuGroupHNU in #3978
• fix: fix errors for zero atom inputs by @njzjz in #4005
• fix(pt): optimize graph memory usage by @iProzd in #4006
• fix(pt): fix lammps nlist sort with large sel by @iProzd in #3993
• fix(cc): add atomic argument to DeepPotBase::computew by @njzjz in #3996
• fix(lmp): call model deviation interface without atomic properties when they are not requested by @njzjz in #4012
• fix(c): call C interface without atomic properties when they are not requested by @njzjz in #4010
• fix(pt): fix get_dim for DescrptDPA1Compat by @iProzd in #4007
• fix(cc): fix message passing when nloc is 0 by @njzjz in #4021
• fix(pt): use user seed in DpLoaderSet by @iProzd in #4015

Code style

• style: require explicit device and dtype by @njzjz in #4001
• style: enable N804 and N805 by @njzjz in #4024

CI/CD

• ci: pin PT to 2.3.1 when using CUDA by @njzjz in #4009

Full Changelog: v3.0.0b1...v3.0.0b2

What's Changed

Breaking Changes

• breaking(pt/tf/dp): disable bias in type embedding by @iProzd in #3958
  This change may make PyTorch checkpoints generated by v3.0.0b0 cannot be used in v3.0.0b1.

New features

• feat: add plugin entry point for PT by @njzjz in #3965
• feat(tf): improve the activation setting in tebd by @iProzd in #3971

Bugfix

• fix: remove ref-names from .git_archival.txt by @njzjz-bot in #3953
• fix(dp): fix dp seed in dpa2 descriptor by @iProzd in #3957
• fix(pt): add finetune_head to argcheck by @iProzd in #3967
• fix(cmake): fix USE_PT_PYTHON_LIBS by @njzjz in #3972
• fix(cmake): set C standard according to the PyTorch version by @njzjz in #3973
• Fix: tf dipole atomic key by @anyangml in #3975
• fix(pt/tf/dp): normalize the econf by @iProzd in #3976

CI/CD

• ci(deps): bump uv to 0.2.24 by @njzjz in #3964
• style: enable B904 by @njzjz in #3956

Full Changelog: v3.0.0b0...v3.0.0b1

What's Changed

Compared to v3.0.0a0, v3.0.0b0 contains all changes in v2.2.10 and v2.2.11, as well as:

Breaking changes

• breaking: remove multi-task support in tf by @iProzd in #3763
• breaking: deprecate set_prefix by @njzjz in #3753
• breaking: use all sets for training and test by @njzjz in #3862. In previous versions, only the last set is used as the test set in dp test.
• PyTorch models trained in v3.0.0a0 cannot be used in v3.0.0b0 due to several changes. As mentioned in the release note of v3.0.0a0, we didn't promise backward compatibility for v3.0.0a0.
• The DPA-2 configurations have been changed by @iProzd in #3768. The old format in v3.0.0a0 is no longer supported.

Major new features

• Latest supported features in the PyTorch and DP backend, which are consistent with the TensorFlow backend if possible:
  • Descriptor: se_e2_a, se_e2_r, se_e3, se_atten, se_atten_v2, dpa2, hybrid;
  • Fitting: energy, dipole, polar, dos, fparam/apram support
  • Model: standard, DPRc, frozen, ZBL, Spin
  • Python inference interface
  • PyTorch only: C inference interface for energy only
  • PyTorch only: TensorBoard
• Support using the DPA-2 model in the LAMMPS by @CaRoLZhangxy in #3657. If you install the Python interface from the source, you must set the environment variable DP_ENABLE_PYTORCH=1 to build the PyTorch customized OPs.
• New command line options dp show by @Chengqian-Zhang in #3796 and dp change-bias by @iProzd in #3933.
• New training options max_ckpt_keep by @iProzd in #3441 and change_bias_after_training by @iProzd in #3933. Several training options now take effect in the PyTorch backend, such as seed by @iProzd in #3773, disp_training and time_training by @iProzd in #3775, and profiling by @njzjz in #3897.
• Performance improvement of the PyTorch backend by @njzjz in #3422, #3424, #3425 and by @iProzd in #3826
• Support generating JSON schema for integration with VSCode by @njzjz in #3849

Minor enhancements and code refactoring are listed at v3.0.0a0...v3.0.0b0.

Contributors

• @CaRoLZhangxy: #3434, #3436, #3612, #3613, #3614, #3656, #3657, #3740, #3780, #3917, #3919
• @Chengqian-Zhang: #3615, #3796, #3828, #3840, #3912
• @Mancn-Xu: #3567
• @Yi-FanLi: #3822
• @anyangml: #3398, #3410, #3426, #3432, #3435, #3447, #3451, #3452, #3468, #3485, #3486, #3575, #3584, #3654, #3662, #3663, #3706, #3757, #3759, #3812, #3824, #3876
• @caic99: #3465
• @chazeon: #3473, #3652, #3653, #3739
• @cherryWangY: #3877
• @dependabot: #3446, #3487, #3777, #3882
• @hztttt: #3762
• @iProzd: #3301, #3409, #3411, #3441, #3442, #3445, #3456, #3480, #3569, #3571, #3573, #3607, #3616, #3619, #3696, #3698, #3712, #3717, #3718, #3725, #3746, #3748, #3758, #3763, #3768, #3773, #3774, #3775, #3781, #3782, #3785, #3803, #3813, #3814, #3815, #3826, #3837, #3841, #3842, #3843, #3873, #3906, #3914, #3916, #3925, #3926, #3927, #3933, #3944, #3945
• @nahso: #3726, #3727
• @njzjz: #3393, #3402, #3403, #3404, #3405, #3415, #3418, #3419, #3421, #3422, #3423, #3424, #3425, #3431, #3437, #3438, #3443, #3444, #3449, #3450, #3453, #3461, #3462, #3464, #3484, #3519, #3570, #3572, #3574, #3580, #3581, #3583, #3600, #3601, #3605, #3610, #3617, #3618, #3620, #3621, #3624, #3625, #3631, #3632, #3633, #3636, #3651, #3658, #3671, #3676, #3682, #3685, #3686, #3687, #3688, #3694, #3695, #3701, #3709, #3711, #3714, #3715, #3716, #3721, #3737, #3753, #3767, #3776, #3784, #3787, #3792, #3793, #3794, #3798, #3800, #3801, #3810, #3811, #3816, #3820, #3829, #3832, #3834, #3835, #3836, #3838, #3845, #3846, #3849, #3851, #3855, #3856, #3857, #3861, #3862, #3870, #3872, #3874, #3875, #3878, #3880, #3888, #3889, #3890, #3891, #3893, #3894, #3895, #3896, #3897, #3918, #3921, #3922, #3930
• @njzjz-bot: #3669
• @pre-commit-ci: #3454, #3489, #3599, #3634, #3659, #3675, #3700, #3720, #3754, #3779, #3825, #3850, #3863, #3883, #3900, #3938
• @robinzyb: #3647
• @wanghan-iapcm: #3413, #3458, #3469, #3609, #3611, #3626, #3628, #3639, #3642, #3649, #3650, #3755, #3761
• @wangzyphysics: #3597

New Contributors

• @wangzyphysics made their first contribution in #3597
• @robinzyb made their first contribution in #3647
• @Mancn-Xu made their first contribution in #3567
• @njzjz-bot made their first contribution in #3669
• @cherryWangY made their first contribution in #3877

Full Changelog: v3.0.0a0...v3.0.0b0

For discussion of v3, please go to #3401

What's Changed

New feature

• feat: apply descriptor exclude_types to env mat stat by @njzjz in #3625
• feat(build): Add Git archives version files by @njzjz-bot in #3669

Enhancement

• style: enable W rules by @njzjz in #3793
• build: unpin tensorflow version on windows by @njzjz in #3721
• Add a reminder for the illegal memory error by @Yi-FanLi in #3822
• lmp: improve error message when compute/fix is not found by @njzjz in #3801

Bugfix

• tf: remove freeze warning for optional nodes by @njzjz in #3381
• fix: set rpath for protobuf by @njzjz in #3636
• fix(tf): apply exclude types to se_atten_v2 switch by @njzjz in #3651
• fix: fix git version detection in docker_package_c.sh by @njzjz in #3658
• fix(tf): fix float32 for exclude_types in se_atten_v2 by @njzjz in #3682
• Fix typo in smooth_type_embdding by @iProzd in #3698
• test: set more lossy precision requirements by @nahso in #3726
• fix: fix ipi package by @njzjz in #3835
• fix(tf): prevent fitting_attr variable scope from becoming fitting_attr_1 by @njzjz in #3930
• fix seeds in se_a and se_atten by @njzjz in #3880

Documentation

• docs: update DPA-1 reference by @njzjz in #3810
• docs: setup uv for readthedocs by @njzjz in #3685
• Clarifiy se_atten_v2 compression doc by @nahso in #3727
• docs: add document equations for se_atten_v2 by @Chengqian-Zhang in #3828

CI/CD

• CI: Accerate GitHub Actions using uv by @njzjz in #3676
• ci: bump ase to 3.23.0 by @njzjz in #3846
• ci(build): use uv for cibuildwheel by @njzjz in #3695
• chore(ci): workaround to retry error decoding response body from uv by @njzjz in #3889

Dependency updates

• build(deps): bump tar from 6.1.14 to 6.2.1 in /source/nodejs by @dependabot in #3714
• build(deps): bump pypa/cibuildwheel from 2.17 to 2.18 by @dependabot in #3777
• build(deps): bump docker/build-push-action from 5 to 6 by @dependabot in #3882

Full Changelog: v2.2.10...v2.2.11

What's Changed

New features

• Add max_ckpt_keep for trainer by @iProzd in #3441
• feat: model devi C/C API without nlist by @robinzyb in #3647

Enhancement

• Neighbor stat is 80x accelerated by @njzjz in #3275
• support checkpoint path (instead of directory) in dp freeze by @njzjz in #3254
• add fparam/aparam support for finetune by @njzjz in #3313
• chore(build): move static part of dynamic metadata to pyproject.toml by @njzjz in #3618
• test: add LAMMPS MPI tests by @njzjz in #3572
• support Python 3.12 by @njzjz in #3343

Documentation

• docs: rewrite README; deprecate manually written TOC by @njzjz in #3179
• docs: apply type_one_side=True to se_a and se_r by @njzjz in #3364
• docs: add deprecation notice for the official conda channel and more conda docs by @njzjz in #3462
• docs: Replace quick_start.ipynb with a new version. by @Mancn-Xu in #3567
• issue template: change TF version to backend version by @njzjz in #3244
• chore: remove incorrect memset TODOs by @njzjz in #3600

Bugfix

• c: change the required shape of electric field to nloc * 3 by @njzjz in #3237
• Fix LAMMPS plugin symlink path on macOS platform by @chazeon in #3473
• fix_dplr.cpp delete redundant setup by @shiruosong in #3344
• fix_dplr.cpp set atom->image when pre_force by @shiruosong in #3345
• fix: fix type hint of sel by @njzjz in #3624
• fix: make se_atten_v2 masking smooth when davg is not zero by @njzjz in #3632
• fix: do not install tf-keras for cu11 by @njzjz in #3444

CI/CD

• detect version in advance before building deepmd-kit-cu11 by @njzjz in #3172
• fix deepmd-kit-cu11 again by @njzjz in #3403
• ban print by @njzjz in #3415
• ci: add linter for markdown, yaml, CSS by @njzjz in #3574
• fix AlmaLinux GPG key error by @njzjz in #3326
• ci: reduce ASLR entropy by @njzjz in #3461

Dependency update

• bump LAMMPS to stable_2Aug2023_update3 by @njzjz in #3399
• build(deps): bump codecov/codecov-action from 3 to 4 by @dependabot in #3231
• build(deps): bump pypa/cibuildwheel from 2.16 to 2.17 by @dependabot in #3487
• pin nvidia-cudnn-cu{11,12} to <9 by @njzjz in #3610
• pin docker actions to major versions by @njzjz in #3238
• build(deps): bump the npm_and_yarn group across 1 directories with 1 update by @dependabot in #3312
• bump scikit-build-core to 0.8 by @njzjz in #3369
• build(deps): bump softprops/action-gh-release from 1 to 2 by @dependabot in #3446

New Contributors

• @shiruosong made their first contribution in #3344
• @robinzyb made their first contribution in #3647
• @Mancn-Xu made their first contribution in #3567

Full Changelog: v2.2.9...v2.2.10

DeePMD-kit v3: A multiple-backend framework for deep potentials

We are excited to announce the first alpha version of DeePMD-kit v3. DeePMD-kit v3 allows you to train and run deep potential models on top of TensorFlow or PyTorch. DeePMD-kit v3 also supports the DPA-2 model, a novel architecture for large atomic models.

Highlights

Multiple-backend framework

DeePMD-kit v3 adds a pluggable multiple-backend framework to provide consistent training and inference experiences between different backends. You can:

• Use the same training data and the input script to train a deep potential model with different backends. Switch backends based on efficiency, functionality, or convenience:

# Training a model using the TensorFlow backend
dp --tf train input.json
dp --tf freeze

# Training a mode using the PyTorch backend
dp --pt train input.json
dp --pt freeze

• Use any model to perform inference via any existing interfaces, including dp test, Python/C /C interface, and third-party packages (dpdata, ASE, LAMMPS, AMBER, Gromacs, i-PI, CP2K, OpenMM, ABACUS, etc). Take an example on LAMMPS:

# run LAMMPS with a TensorFlow backend model
pair_style deepmd frozen_model.pb
# run LAMMPS with a PyTorch backend model
pair_style deepmd frozen_model.pth
# Calculate model deviation using both models
pair_style deepmd frozen_model.pb frozen_model.pth out_file md.out out_freq 100

• Convert models between backends, using dp convert-backend, if both backends support a model:

dp convert-backend frozen_model.pb frozen_model.pth
dp convert-backend frozen_model.pth frozen_model.pb

• Add a new backend to DeePMD-kit much more quickly if you want to contribute to DeePMD-kit.

PyTorch backend: a backend designed for large atomic models and new research

We added the PyTorch backend in DeePMD-kit v3 to support the development of new models, especially for large atomic models.

DPA-2 model: Towards a universal large atomic model for molecular and material simulation

DPA-2 model is a novel architecture for Large Atomic Model (LAM) and can accurately represent a diverse range of chemical systems and materials, enabling high-quality simulations and predictions with significantly reduced efforts compared to traditional methods. The DPA-2 model is only implemented in the PyTorch backend. An example configuration is in the examples/water/dpa2 directory.

The DPA-2 descriptor includes two primary components: repinit and repformer. The detailed architecture is shown in the following figure.

Training strategies for large atomic models

The PyTorch backend has supported multiple training strategies to develop large atomic models.

Parallel training: Large atomic models have a number of hyper-parameters and complex architecture, so training a model on multiple GPUs is necessary. Benefiting from the PyTorch community ecosystem, the parallel training for the PyTorch backend can be driven by torchrun, a launcher for distributed data parallel.

torchrun --nproc_per_node=4 --no-python dp --pt train input.json

Multi-task training: Large atomic models are trained against data in a wide scope and at different DFT levels, which requires multi-task training. The PyTorch backend supports multi-task training, sharing the descriptor between different An example is given in examples/water_multi_task/pytorch_example/input_torch.json.

Finetune: Fine-tune is useful to train a pre-train large model on a smaller, task-specific dataset. The PyTorch backend has supported --finetune argument in the dp --pt train command line.

Developing new models using Python and dynamic graphs

Researchers may feel pain about the static graph and the custom C OPs from the TensorFlow backend, which sacrifices research convenience for computational performance. The PyTorch backend has a well-designed code structure written using the dynamic graph, which is currently 100% written with the Python language, making extending and debugging new deep potential models easier than the static graph.

Supporting traditional deep potential models

People may still want to use the traditional models already supported by the TensorFlow backend in the PyTorch backend and compare the same model among different backends. We almost rewrote all of the traditional models in the PyTorch backend, which are listed below:

• Features supported:
  • Descriptor: se_e2_a, se_e2_r, se_atten, hybrid;
  • Fitting: energy, dipole, polar, fparam/apram support
  • Model: standard, DPRc
  • Python inference interface
  • C inference interface for energy only
  • TensorBoard
• Features not supported yet:
  • Descriptor: se_e3, se_atten_v2, se_e2_a_mask
  • Fitting: dos
  • Model: linear_ener, DPLR, pairtab, linear_ener, frozen, pairwise_dprc, ZBL, Spin
  • Model compression
  • Python inference interface for DPLR
  • C inference interface for tensors and DPLR
  • Paralleling training using Horovod
• Features not planned:
  • Descriptor: loc_frame, se_e2_a type embedding, se_a_ebd_v2
  • NVNMD

DP backend and format: reference backend for other backends

DP is a reference backend for development that uses pure NumPy to implement models without using any heavy deep-learning frameworks. It cannot be used for training but only for Python inference. As a reference backend, it is not aimed at the best performance but only the correct results. The DP backend uses HDF5 to store model serialization data, which is backend-independent.
The DP backend and the serialization data are used in the unit test to ensure different backends have consistent results and can be converted between each other.
In the current version, the DP backend has a similar supporting status to the PyTorch backend, while DPA-1 and DPA-2 are not supported yet.

Authors

The above highlights were mainly contributed by

• Hangrui Bi (@20171130), in #3180
• Chun Cai (@caic99), in #3180
• Junhan Chang (@TablewareBox), in #3180
• Yiming Du (@nahso), in #3180
• Guolin Ke (@guolinke), in #3180
• Xinzijian Liu (@zjgemi), in #3180
• Anyang Peng (@anyangml), in #3362, #3192, #3212, #3210, #3248, #3266, #3281, #3296, #3309, #3314, #3321, #3327, #3338, #3351, #3376, #3385
• Xuejian Qin (@qin2xue3jian4), in #3180
• Han Wang (@wanghan-iapcm), in #3188, #3190, #3208, #3184, #3199, #3202, #3219, #3225, #3232, #3235, #3234, #3241, #3240, #3246, #3260, #3274, #3268, #3279, #3280, #3282, #3295, #3289, #3340, #3352, #3357, #3389, #3391, #3400
• Jinzhe Zeng (@njzjz), in #3171, #3173, #3174, #3179, #3193, #3200, #3204, #3205, #3333, #3360, #3364, #3365, #3169, #3164, #3175, #3176, #3187, #3186, #3191, #3195, #3194, #3196, #3198, #3201, #3207, #3226, #3222, #3220, #3229, #3226, #3239, #3228, #3244, #3243, #3213, #3249, #3250, #3254, #3247, #3253, #3271, #3263, #3258, #3276, #3285, #3286, #3292, #3294, #3293, #3303, #3304, #3308, #3307, #3306, #3316, #3315, #3318, #3323, #3325, #3332, #3331, #3330, #3339, #3335, #3346, #3349, #3350, #3310, #3356, #3361, #3342, #3348, #3358, #3366, #3374, #3370, #3373, #3377, #3382, #3383, #3384, #3386, #3390, #3395, #3394, #3396, #3397
• Chengqian Zhang (@Chengqian-Zhang), in #3180
• Duo Zhang (@iProzd), in #3180, #3203, #3245, #3261, #3262, #3355, #3367, #3359, #3371, #3387, #3388, #3380, #3378
• Xiangyu Zhang (@CaRoLZhangxy), in #3162, #3287, #3337, #3375, #3379

Breaking changes

• Python 3.7 support is dropped. by @njzjz in #3185
• We require all model files to have the correct filename extension for all interfaces so a corresponding backend can load them. TensorFlow model files must end with .pb extension.
• Python class DeepTensor (including DeepDiople and DeepPolar) now returns atomic tensor in the dimension of natoms instead of nsel_atoms. by @njzjz in #3390
• For developers: the Python module structure is fully refactored. The old deepmd module was moved to deepmd.tf without other API changes, and deepmd_utils was moved to deepmd without other API changes. by @njzjz in #3177, #3178

Other changes

Enhancement

• Neighbor stat for the TensorFlow backend is 80x accelerated. by @njzjz in #3275
• i-PI: remove normalize_coord by @njzjz in #3257
• LAMMPS: fix_dplr.cpp delete redundant setup and set atom->image when pre_force by @shiruosong in #3344, #3345
• Bump scikit-build-core to 0.8 by @njzjz in #3369
• Bump LAMMPS to stable_2Aug2023_update3 by @njzjz in #3399
• Add fparam/aparam support for fine-tune by @njzjz in #3313
• TF: remove freeze warning for optional nodes by @njzjz in #3381

CI/CD

• Build macos-arm64 wheel on M1 runners by @njzjz in #3206
• Other improvements and fixes to GitHub Actions by @njzjz in #3238, #3283, #3284, #3288, #3290, #3326
• Enable docstring code format by @njzjz in #3267

Bugfix

• Fix TF 2.16 compatibility by @njzjz in #3343
• Detect version in advance before building deepmd-kit-cu11 by @njzjz in #3172
• C API: change the required shape of electric field to nloc * 3 by @njzjz in #3237

New Contributors

• @anyangml made their first contribution in #3192
• @shiruosong made their first contribution in #3344

Full Changelog: https://github.com/deepmodeling/de...

What's Changed

Bugfixes

• cc: fix returning type of sel_types by @njzjz in #3181
• fix compile gromacs with precompiled C library by @njzjz in #3217
• gmx: fix include directive by @njzjz in #3221
• c: fix all memory leaks; add sanitizer checks in #3223

CI/CD

• build macos-arm64 wheel on M1 runners by @njzjz in #3206

Full Changelog: v2.2.8...v2.2.9

What's Changed

Breaking Changes

• breaking(lmp): do not apply scale factor to model deviation by @njzjz in #3036

New Features

• build neighbor list with external Python program by @njzjz in #3046
• nvnmd: init-model feature and 256 neighbors by @LiuGroupHNU in #3058
• Add pairwise tabulation as an independent model by @njzjz in #3101

Enhancement

• support compressing gelu_tf by @njzjz in #2957
• respect user defined CUDAARCHS by @njzjz in #2979
• lmp: refactor ixnode by @njzjz in #2971
• print system prob using scientific natation by @njzjz in #3008
• remove unused codes in se_a.py by @nahso in #3049
• print NaN loss when labeled data is not found by @njzjz in #3047

Documentation

• docs: add theory from v2 paper by @njzjz in #2715
• docs: configuring automatically generated release notes by @njzjz in #2975
• docs: use relative links by @njzjz in #2976
• docs: remove lammps.md by @njzjz in #2986
• docs: document horovod on Conda-Forge by @njzjz in #3001
• docs: document external neighbor list by @njzjz in #3056
• docs: update documentation for pre-compiled C library by @njzjz in #3083
• docs: update Amber interface by @njzjz in #3074
• docs: document CP2K interface by @njzjz in #3158

Build and release

• bump scikit-build-core to 0.6 by @njzjz in #2981
• bump CUDA version to 12.2 for pre-built packages by @njzjz in #2960
• add cu11 prebuilt packages by @njzjz in #3002
• bump scikit-build-core to 0.7 by @njzjz in #3038
• bump LAMMPS to stable_2Aug2023_update2 by @njzjz in #3066

Bug fixings

• fix SpecifierSet behavior with prereleases by @njzjz in #2959
• fix restarting from compressed training with type embedding by @njzjz in #2996
• Add the missing initializations for extra embedding variables by @nahso in #3005
• Fix macro issue with multiple arguments by @njzjz in #3016
• fix se_a_ebd_v2 when nloc != nall by @njzjz in #3037
• fix: invalid read and write when natom grows by @Cloudac7 in #3031
• fix GPU mapping error for Horovod finetune by @njzjz in #3048
• lmp: Register styles when using CMake by @njzjz in #3097
• fix segfault in ~Region by @njzjz in #3108
• lmp: fix evflag initialization by @njzjz in #3133
• cmake: fix setting CMAKE_HIP_FLAGS by @njzjz in #3155
• Fix max nbor size related issues by @denghuilu in #3157
• Fix possible memory leak in constructors by @njzjz in #3062
• fix memory leaks related to char* by @njzjz in #3063
• Update the path to training and validation data dir in zinc_se_a_mask.json by @dingye18 in #3068
• Fix catching by value by @njzjz in #3077
• resolve "Multiplication result converted to larger type" by @njzjz in #3149
• resolve "Multiplication result converted to larger type" by @njzjz in #3159

CI/CD

• move to ruff formatter by @njzjz in #2951
• add unit tests for LAMMPS fparam/aparam keywords by @njzjz in #2998
• fix labeler.yml with actions/labeler v5 by @njzjz in #3059
• add CodeQL checks by @njzjz in #3075

Code refactor and enhancement to prepare for upcoming v3

• rename deepmd_cli to deepmd_utils by @njzjz in #2983
• merge prob_sys_size with prob_sys_size;0:nsys:1.0 by @CaRoLZhangxy in #2963
• add utils for DP native model format by @njzjz in #3064
• rm rcut from DeepmdDataSystem by @wanghan-iapcm in #3106
• add activation_function and resnet arguments and NumPy implementation to NativeLayer by @njzjz in #3109
• NativeLayer: support None bias. by @wanghan-iapcm in #3111
• fix native layer concat bug. by @wanghan-iapcm in #3112
• model format for the embedding net by @wanghan-iapcm in #3113
• support numerical precision and env_mat by @wanghan-iapcm in #3114
• Add dp model format sea by @wanghan-iapcm in #3123
• input order of env_mat changed to be consistent with descriptor by @wanghan-iapcm in #3125
• doc string for dp model format descriptor se_e2_a by @wanghan-iapcm in #3124
• add native Networks for mutiple Network classes by @njzjz in #3117
• add definition for the output of fitting and model by @wanghan-iapcm in #3128
• cc: refactor DeepPotModelDevi, making it framework-independent by @njzjz in #3134
• fix: model check assumes call as the forward method by @wanghan-iapcm in #3136
• support fitting net by @wanghan-iapcm in #3137
• refactorize NativeLayer, interface does not rely on the platform by @wanghan-iapcm in #3138
• refactorize networks, now can be used cross platform by @wanghan-iapcm in #3141
• move utility to deepmd_utils (without modifaction) by @njzjz in #3140
• add cross-platform AutoBatchSize by @njzjz in #3143
• move deepmd.entrypoints.{doc,gui} to deepmd_utils.entrypoints.{doc,gui} by @njzjz in #3144
• cc: refactor DeepPot to support multiple backends by @njzjz in #3142
• cc: refactor DeepTensor for multiple-backend framework by @njzjz in #3151
• cc: refactor DataModifier for multiple-backend framework by @njzjz in #3148
• fix: some issue of the output def by @wanghan-iapcm in #3152
• cc: merge DeepPotBase and DeepTensor member functions by @njzjz in #3145
• move OutOfMemoryError from deepmd to deepmd_utils by @njzjz in #3153
• set dpgui entry point to deepmd_utils by @njzjz in #3161

New Contributors

• @Cloudac7 made their first contribution in #3031

Full Changelog: v2.2.7...v2.2.8