<!-- Release notes generated using configuration in .github/release.yml at master --> Today marks the 8th birthday of the deepmodeling/deepmd-kit repository! ## What's Changed ### New features * feat(pt): add compression support for se_e3_tebd by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/4992 * feat: Enhance process_systems to recursively search all paths in systems list by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5033 * feat(pt): type embedding can still be compress even if attn_layer != 0 by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5066 * feat(pt): Implement type embedding compression for se_atten by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5057 * feat(pt): Implement type embedding compression for se_e3_tebd by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5059 * feat(pt): Add support for SiLU activation function in gradient calculations by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5055 ### Bugfix * fix: bump CMake minimum version to 3.25.2 by @Copilot in https://github.com/deepmodeling/deepmd-kit/pull/5001 * fix(cmake): improve CUDA C++ standard for compatibility with gcc-14 by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/5036 * fix: optimize atom type mapping by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5043 * fix(finetune): calculate fitting stat when using random fitting in finetuning process by @Chengqian-Zhang in https://github.com/deepmodeling/deepmd-kit/pull/4928 * fix(stat): Caculate correct fitting stat when using default fparam and using share fitting. by @Chengqian-Zhang in https://github.com/deepmodeling/deepmd-kit/pull/5038 * fix: set multiprocessing start method to 'fork' in pt env (since python3.14 defaults to forkserver) by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5019 * fix(jax): fix compatibility with flax 0.12 by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/5067 * Fix: model_output_type unify name by @anyangml in https://github.com/deepmodeling/deepmd-kit/pull/5069 * fix(pd): adapting code for hardware compatibility by @HydrogenSulfate in https://github.com/deepmodeling/deepmd-kit/pull/5047 ### Enhancement * build: bump LAMMPS version to stable_22Jul2025_update2 by @Copilot in https://github.com/deepmodeling/deepmd-kit/pull/5052 * feat:support CUDA 13.0+ by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5017 * perf: accelerate data loading in training by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5023 * fix: remove hessian outdef if not necessary by @iProzd in https://github.com/deepmodeling/deepmd-kit/pull/5045 * feat: Performance Optimization: Data Loading and Statistics Acceleration by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5040 * build(deps-dev): update scikit-build-core requirement from !=0.6.0,<0.11,>=0.5 to >=0.5,!=0.6.0,<0.12 by @dependabot[bot] in https://github.com/deepmodeling/deepmd-kit/pull/5076 ### Documentation * doc:fix error in doc of se_e3_tebd by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5018 * docs: update DeepModeling email address by @njzjz-bot in https://github.com/deepmodeling/deepmd-kit/pull/5062 ### CI/CD * feat(pt/test): add unit test for the compression of se_e3_tebd by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5060 * test(common): add regression for atom type remap by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5050 * CI: stop running Horovod tests by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/5079 * build(deps): bump pypa/cibuildwheel from 3.1 to 3.2 by @dependabot[bot] in https://github.com/deepmodeling/deepmd-kit/pull/4996 * CI: Replace the macos-13 images with the macos-15-intel images by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/5002 * build(deps): bump github/codeql-action from 3 to 4 by @dependabot[bot] in https://github.com/deepmodeling/deepmd-kit/pull/5011 * build(deps): bump astral-sh/setup-uv from 6 to 7 by @dependabot[bot] in https://github.com/deepmodeling/deepmd-kit/pull/5012 * build(deps): bump actions/download-artifact from 5 to 6 by @dependabot[bot] in https://github.com/deepmodeling/deepmd-kit/pull/5025 * build(deps): bump actions/upload-artifact from 4 to 5 by @dependabot[bot] in https://github.com/deepmodeling/deepmd-kit/pull/5026 * test: add TensorFlow graph reset in teardown method for entrypoint tests and bias standard tests by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5049 * feat(test): add unit test for the compression of se_atten by @OutisLi in https://github.com/deepmodeling/deepmd-kit/pull/5058 * build(deps): bump actions/checkout from 5 to 6 by @dependabot[bot] in https://github.com/deepmodeling/deepmd-kit/pull/5063 * build(deps): bump pypa/cibuildwheel from 3.2 to 3.3 by @dependabot[bot] in https://github.com/deepmodeling/deepmd-kit/pull/5064 * chore: manage CI pinnings in pyproject.toml by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/5068 * CI: configure dependabot to bump Python deps by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/5072 * CI: pin cibuildwheel TF/PT deps to global pinnings by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/5071 * CI: free disk in package_c workflow by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/5081 * build(deps-dev): update torch requirement from ~=2.7.0 to >=2.7,<2.9 by @dependabot[bot] in https://github.com/deepmodeling/deepmd-kit/pull/5075 * build(deps-dev): update tensorflow-cpu requirement from ~=2.18.0 to >=2.18,<2.21 by @dependabot[bot] in https://github.com/deepmodeling/deepmd-kit/pull/5074 **Full Changelog**: https://github.com/deepmodeling/deepmd-kit/compare/v3.1.1...v3.1.2

<!-- Release notes generated using configuration in .github/release.yml at devel --> ## What's Changed ## Highlights ### DPA3 DPA3 is an advanced interatomic potential leveraging the message-passing architecture. Designed as a large atomic model (LAM), DPA3 is tailored to integrate and simultaneously train on datasets from various disciplines, encompassing diverse chemical and materials systems across different research domains. Its model design ensures exceptional fitting accuracy and robust generalization within and beyond the training domain. Furthermore, DPA3 maintains energy conservation and respects the physical symmetries of the potential energy surface, making it a dependable tool for a wide range of scientific applications. Refer to `examples/water/dpa3/input_torch.json` for the training script. After training, the PyTorch model can be converted to the JAX model. ### PaddlePaddle backend The PaddlePaddle backend features a similar Python interface to the PyTorch backend, ensuring compatibility and flexibility in model development. PaddlePaddle has introduced dynamic-to-static functionality and PaddlePaddle JIT compiler (CINN) in DeePMD-kit, which allow for dynamic shapes and higher-order differentiation. The dynamic-to-static functionality automatically captures the user’s dynamic graph code and converts it into a static graph. After conversion, the CINN compiler is used to optimize the computational graph, thereby enhancing the efficiency of model training and inference. In experiments with the DPA-2 model, we achieved approximately a 40% reduction in training time compared to the dynamic graph, effectively improving the model training efficiency. ### Breaking changes * breaking: enable PyTorch backend for PyPI LAMMPS by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4728 ### Other new features * feat(pt/dp): support case embedding and sharable fitting by @iProzd in https://github.com/deepmodeling/deepmd-kit/pull/4417 * feat(pt): train with energy Hessian by @1azyking in https://github.com/deepmodeling/deepmd-kit/pull/4169 * feat: add new batch size rules for large systems by @caic99 in https://github.com/deepmodeling/deepmd-kit/pull/4659 * feat: add method to access fele in pppm/dplr by @HanswithCMY in https://github.com/deepmodeling/deepmd-kit/pull/4452 * feat (tf/pt): add atomic weights to tensor loss by @ChiahsinChu in https://github.com/deepmodeling/deepmd-kit/pull/4466 * feat(pt): add `trainable` to property fitting by @ChiahsinChu in https://github.com/deepmodeling/deepmd-kit/pull/4599 * Feat(pt): Support fitting_net input statistics. by @Chengqian-Zhang in https://github.com/deepmodeling/deepmd-kit/pull/4504 * feat(jax): Hessian by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4649 * feat: add plugin mode for data modifier by @ChiahsinChu in https://github.com/deepmodeling/deepmd-kit/pull/4621 * feat(pt): add eta message for pt backend by @HydrogenSulfate in https://github.com/deepmodeling/deepmd-kit/pull/4725 * feat: add huber loss by @iProzd in https://github.com/deepmodeling/deepmd-kit/pull/4684 * feat(pt): add AdamW for pt training by @iProzd in https://github.com/deepmodeling/deepmd-kit/pull/4757 * Feat:support customized rglob by @anyangml in https://github.com/deepmodeling/deepmd-kit/pull/4763 * feat(pt/pd): add size option to dp show by @iProzd in https://github.com/deepmodeling/deepmd-kit/pull/4783 All changes in v3.0.1, v3.0.2, and v3.0.3 are included. ## Contributors * @iProzd #4417 #4655 #4419 #4609 #4633 #4647 #4675 #4684 #4730 #4757 #4754 #4756 #4760 #4778 #4781 #4783 #4792 * @pre-commit-ci #4420 #4449 #4464 #4473 #4497 #4521 #4539 #4552 #4566 #4574 #4579 #4596 #4602 #4611 #4645 #4660 #4672 #4690 #4699 #4708 #4712 #4719 #4723 #4736 #4748 #4767 #4779 #4791 * @njzjz #4482 #4483 #4484 #4507 #4619 #4410 #4438 #4442 #4446 #4459 #4485 #4479 #4508 #4534 #4531 #4542 #4550 #4553 #4557 #4561 #4565 #4570 #4575 #4547 #4582 #4613 #4624 #4558 #4638 #4636 #4640 #4649 #4668 #4680 #4720 #4728 #4738 #4692 #4700 #4704 #4702 #4717 #4724 #4726 #4729 #4735 #4753 #4774 #4765 #4776 #4775 #4766 #4780 #4786 #4794 * @Chengqian-Zhang #4471 #4504 #4639 * @HydrogenSulfate #4418 #4489 #4673 #4302 #4439 #4414 #4480 #4493 #4488 #4512 #4467 #4514 #4617 #4556 #4656 #4694 #4701 #4715 #4725 #4768 #4770 * @QuantumMisaka #4510 * @1azyking #4169 * @caic99 #4535 #4615 #4659 #4434 #4426 #4435 #4433 #4437 #4463 #4505 #4478 #4541 #4513 #4597 #4622 #4662 #4669 #4677 #4678 #4688 #4687 #4737 #4747 #4746 #4761 #4772 #4773 #4784 #4751 #4790 * @dependabot #4408 #4630 * @anyangml #4423 #4432 #4587 #4763 * @HanswithCMY #4452 * @ChiahsinChu #4466 #4538 #4599 #4621 * @RMeli #4577 * @Yi-FanLi #4581 * @wanghan-iapcm #4653 * @SumGuo-88 #4593 * @SigureMo #4664 * @njzjz-bot #4796 ## New Contributors * @HanswithCMY made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4452 * @QuantumMisaka made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4510 * @1azyking made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4169 * @RMeli made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4577 * @SumGuo-88 made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4593 * @SigureMo made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4664 **Full Changelog**: https://github.com/deepmodeling/deepmd-kit/compare/v3.0.0...v3.1.0rc0

<!-- Release notes generated using configuration in .github/release.yml at devel --> ## What's Changed ## Highlights ### DPA-3 DPA-3 is an advanced interatomic potential leveraging the message-passing architecture. Designed as a large atomic model (LAM), DPA-3 is tailored to integrate and simultaneously train on datasets from various disciplines, encompassing diverse chemical and materials systems across different research domains. Its model design ensures exceptional fitting accuracy and robust generalization within and beyond the training domain. Furthermore, DPA-3 maintains energy conservation and respects the physical symmetries of the potential energy surface, making it a dependable tool for a wide range of scientific applications. Refer to `examples/water/dpa3/input_torch.json` for the training script. After training, the PyTorch model can be converted to the JAX model. ### PaddlePaddle backend The PaddlePaddle backend features a similar Python interface to the PyTorch backend, ensuring compatibility and flexibility in model development. PaddlePaddle has introduced dynamic-to-static functionality and PaddlePaddle JIT compiler (CINN) in DeePMD-kit, which allow for dynamic shapes and higher-order differentiation. The dynamic-to-static functionality automatically captures the user’s dynamic graph code and converts it into a static graph. After conversion, the CINN compiler is used to optimize the computational graph, thereby enhancing the efficiency of model training and inference. In experiments with the DPA-2 model, we achieved approximately a 40% reduction in training time compared to the dynamic graph, effectively improving the model training efficiency. ### Breaking changes * breaking: enable PyTorch backend for PyPI LAMMPS by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4728 ### Other new features * feat(pt/dp): support case embedding and sharable fitting by @iProzd in https://github.com/deepmodeling/deepmd-kit/pull/4417 * feat(pt): train with energy Hessian by @1azyking in https://github.com/deepmodeling/deepmd-kit/pull/4169 * feat: add new batch size rules for large systems by @caic99 in https://github.com/deepmodeling/deepmd-kit/pull/4659 * feat: add method to access fele in pppm/dplr by @HanswithCMY in https://github.com/deepmodeling/deepmd-kit/pull/4452 * feat (tf/pt): add atomic weights to tensor loss by @ChiahsinChu in https://github.com/deepmodeling/deepmd-kit/pull/4466 * feat(pt): add `trainable` to property fitting by @ChiahsinChu in https://github.com/deepmodeling/deepmd-kit/pull/4599 * Feat(pt): Support fitting_net input statistics. by @Chengqian-Zhang in https://github.com/deepmodeling/deepmd-kit/pull/4504 * feat(jax): Hessian by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4649 * feat: add plugin mode for data modifier by @ChiahsinChu in https://github.com/deepmodeling/deepmd-kit/pull/4621 * feat(pt): add eta message for pt backend by @HydrogenSulfate in https://github.com/deepmodeling/deepmd-kit/pull/4725 * feat: add huber loss by @iProzd in https://github.com/deepmodeling/deepmd-kit/pull/4684 * feat(pt): add AdamW for pt training by @iProzd in https://github.com/deepmodeling/deepmd-kit/pull/4757 All changes in v3.0.1, v3.0.2, and v3.0.3 are included. ## Contributors * @iProzd #4417 #4655 #4419 #4609 #4633 #4647 #4675 #4684 #4730 #4757 #4754 #4756 #4760 #4778 * @pre-commit-ci #4420 #4449 #4464 #4473 #4497 #4521 #4539 #4552 #4566 #4574 #4579 #4596 #4602 #4611 #4645 #4660 #4672 #4690 #4699 #4708 #4712 #4719 #4723 #4736 #4748 #4767 * @njzjz #4482 #4483 #4484 #4507 #4619 #4410 #4438 #4442 #4446 #4459 #4485 #4479 #4508 #4534 #4531 #4542 #4550 #4553 #4557 #4561 #4565 #4570 #4575 #4547 #4582 #4613 #4624 #4558 #4638 #4636 #4640 #4649 #4668 #4680 #4720 #4728 #4738 #4692 #4700 #4704 #4702 #4717 #4724 #4726 #4729 #4735 #4753 #4774 #4765 #4776 #4775 #4766 * @Chengqian-Zhang #4471 #4504 #4639 * @HydrogenSulfate #4418 #4489 #4673 #4302 #4439 #4414 #4480 #4493 #4488 #4512 #4467 #4514 #4617 #4556 #4656 #4694 #4701 #4715 #4725 #4768 #4770 * @QuantumMisaka #4510 * @1azyking #4169 * @caic99 #4535 #4615 #4659 #4434 #4426 #4435 #4433 #4437 #4463 #4505 #4478 #4541 #4513 #4597 #4622 #4662 #4669 #4677 #4678 #4688 #4687 #4737 #4747 #4746 #4761 #4772 #4773 * @dependabot #4408 #4630 * @anyangml #4423 #4432 #4587 * @HanswithCMY #4452 * @ChiahsinChu #4466 #4538 #4599 #4621 * @RMeli #4577 * @Yi-FanLi #4581 * @wanghan-iapcm #4653 * @SumGuo-88 #4593 * @SigureMo #4664 ## New Contributors * @HanswithCMY made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4452 * @QuantumMisaka made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4510 * @1azyking made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4169 * @RMeli made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4577 * @SumGuo-88 made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4593 * @SigureMo made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4664 **Full Changelog**: https://github.com/deepmodeling/deepmd-kit/compare/v3.0.0...v3.1.0rc0

<!-- Release notes generated using configuration in .github/release.yml at r3.0 --> ## What's Changed ### Breaking changes - breaking(wheel): bump minimal macos version to 11.0 (#4704) ### Bugfixes - fix(tf): fix dplr Python inference (#4753) - fix: data type of nloc, nall-nloc in the input of border_op (#4653) - fix(data): Throw error when data's element is not present in `input.json/type_map` (#4639) - fix(ase): aviod duplicate stress calculation for ase calculator (#4633) - fix(pt): improve OOM detection (#4638) - fix(tf): always use float64 for the global tensor (#4735) - fix(jax): set `default_matmul_precision` to `tensorfloat32` (#4726) - fix(jax): fix NaN in sigmoid grad (#4724) - fix: fix compatibility with CMake 4.0 (#4680) ## CI/CD - fix(CI): set CMAKE_POLICY_VERSION_MINIMUM environment variable (#4692) - CI: bump PyTorch to 2.7 (#4717) - fix(tests): fix tearDownClass and release GPU memory (#4702) - fix(CI): upgrade setuptools to fix its compatibility with wheel (#4700) **Full Changelog**: https://github.com/deepmodeling/deepmd-kit/compare/v3.0.2...v3.0.3

<!-- Release notes generated using configuration in .github/release.yml at devel --> ## What's Changed ## Highlights ### DPA-3 DPA-3 is an advanced interatomic potential leveraging the message-passing architecture. Designed as a large atomic model (LAM), DPA-3 is tailored to integrate and simultaneously train on datasets from various disciplines, encompassing diverse chemical and materials systems across different research domains. Its model design ensures exceptional fitting accuracy and robust generalization within and beyond the training domain. Furthermore, DPA-3 maintains energy conservation and respects the physical symmetries of the potential energy surface, making it a dependable tool for a wide range of scientific applications. Refer to `examples/water/dpa3/input_torch.json` for the training script. After training, the PyTorch model can be converted to the JAX model. ### PaddlePaddle backends The PaddlePaddle backend features a similar Python interface to the PyTorch backend, ensuring compatibility and flexibility in model development. PaddlePaddle has introduced dynamic-to-static functionality and PaddlePaddle JIT compiler (CINN) in DeePMD-kit, which allow for dynamic shapes and higher-order differentiation. The dynamic-to-static functionality automatically captures the user’s dynamic graph code and converts it into a static graph. After conversion, the CINN compiler is used to optimize the computational graph, thereby enhancing the efficiency of model training and inference. In experiments with the DPA-2 model, we achieved approximately a 40% reduction in training time compared to the dynamic graph, effectively improving the model training efficiency. ### Other new features * feat(pt/dp): support case embedding and sharable fitting by @iProzd in https://github.com/deepmodeling/deepmd-kit/pull/4417 * feat(pt): train with energy Hessian by @1azyking in https://github.com/deepmodeling/deepmd-kit/pull/4169 * feat: add new batch size rules for large systems by @caic99 in https://github.com/deepmodeling/deepmd-kit/pull/4659 * feat: add method to access fele in pppm/dplr by @HanswithCMY in https://github.com/deepmodeling/deepmd-kit/pull/4452 * feat (tf/pt): add atomic weights to tensor loss by @ChiahsinChu in https://github.com/deepmodeling/deepmd-kit/pull/4466 * feat(pt): add `trainable` to property fitting by @ChiahsinChu in https://github.com/deepmodeling/deepmd-kit/pull/4599 * Feat(pt): Support fitting_net input statistics. by @Chengqian-Zhang in https://github.com/deepmodeling/deepmd-kit/pull/4504 * feat(jax): Hessian by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4649 * feat: add plugin mode for data modifier by @ChiahsinChu in https://github.com/deepmodeling/deepmd-kit/pull/4621 All changes in v3.0.1 and v3.0.2 are included. ## Contributors * @iProzd #4417 #4655 #4419 #4609 #4633 #4647 #4675 * @pre-commit-ci #4420 #4449 #4464 #4473 #4497 #4521 #4539 #4552 #4566 #4574 #4579 #4596 #4602 #4611 #4645 #4660 #4672 * @njzjz #4482 #4483 #4484 #4507 #4619 #4410 #4438 #4442 #4446 #4459 #4485 #4479 #4508 #4534 #4531 #4542 #4550 #4553 #4557 #4561 #4565 #4570 #4575 #4547 #4582 #4613 #4624 #4558 #4638 #4636 #4640 #4649 #4668 #4680 * @Chengqian-Zhang #4471 #4504 #4639 * @HydrogenSulfate #4418 #4489 #4673 #4302 #4439 #4414 #4480 #4493 #4488 #4512 #4467 #4514 #4617 #4556 #4656 * @QuantumMisaka #4510 * @1azyking #4169 * @caic99 #4535 #4615 #4659 #4434 #4426 #4435 #4433 #4437 #4463 #4505 #4478 #4541 #4513 #4597 #4622 #4662 #4669 #4677 #4678 * @dependabot #4408 #4630 * @anyangml #4423 #4432 #4587 * @HanswithCMY #4452 * @ChiahsinChu #4466 #4538 #4599 #4621 * @RMeli #4577 * @Yi-FanLi #4581 * @wanghan-iapcm #4653 * @SumGuo-88 #4593 * @SigureMo #4664 ## New Contributors * @HanswithCMY made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4452 * @QuantumMisaka made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4510 * @1azyking made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4169 * @RMeli made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4577 * @SumGuo-88 made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4593 * @SigureMo made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4664 **Full Changelog**: https://github.com/deepmodeling/deepmd-kit/compare/v3.0.0...v3.1.0a0

## What's Changed This patch version only contains minor features, bug fixes, enhancements, and documentation improvements. ### New features * feat(tf): support tensor fitting with hybrid descriptor by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4542 ### Enhancement * Perf: replace unnecessary `torch.split` with indexing by @caic99 in https://github.com/deepmodeling/deepmd-kit/pull/4505 * Perf: use F.linear for MLP by @caic99 in https://github.com/deepmodeling/deepmd-kit/pull/4513 * chore: improve neighbor stat log by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4561 * chore: bump pytorch to 2.6.0 by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4575 ### Bugfix * Fix: Modify docs of DPA models by @QuantumMisaka in https://github.com/deepmodeling/deepmd-kit/pull/4510 * fix(pt): fix clearing the list in set_eval_descriptor_hook by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4534 * [fix bug] load atomic_*.npy for tf tensor model by @ChiahsinChu in https://github.com/deepmodeling/deepmd-kit/pull/4538 * fix: lower `num_workers` to 4 by @caic99 in https://github.com/deepmodeling/deepmd-kit/pull/4535 * fix: fix YAML conversion by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4565 * fix(cc): remove C++ 17 usage by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4570 * Fix version in DeePMDConfigVersion.cmake by @RMeli in https://github.com/deepmodeling/deepmd-kit/pull/4577 * fix(pt): detach computed descriptor tensor to prevent OOM by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4547 * fix(pt): throw errors for GPU tensors and the CPU OP library by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4582 * use variable to store the bias of atomic polarizability by @Yi-FanLi in https://github.com/deepmodeling/deepmd-kit/pull/4581 * Fix: pt tensor loss label name by @anyangml in https://github.com/deepmodeling/deepmd-kit/pull/4587 * CI: pin jax to 0.5.0 by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4613 * fix(array-api): fix xp.where errors by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4624 ### Documentation * docs: fix the header of the scaling test table by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4507 * docs: add `sphinx.configuration` to .readthedocs.yml by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4553 * docs: add v3 paper citations by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4619 * docs: add PyTorch Profiler support details to TensorBoard documentation by @caic99 in https://github.com/deepmodeling/deepmd-kit/pull/4615 ### CI/CD * CI: switch linux_aarch64 to GitHub hosted runners by @njzjz in https://github.com/deepmodeling/deepmd-kit/pull/4557 ## New Contributors * @QuantumMisaka made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4510 * @RMeli made their first contribution in https://github.com/deepmodeling/deepmd-kit/pull/4577 **Full Changelog**: https://github.com/deepmodeling/deepmd-kit/compare/v3.0.1...v3.0.2

<!-- Release notes generated using configuration in .github/release.yml at r3.0 --> This patch version only contains bug fixes, enhancements, and documentation improvements. ## What's Changed ### Enhancements * Perf: print summary on rank 0 (deepmodeling#4434) * perf: optimize training loop (deepmodeling#4426) * chore: refactor training loop (deepmodeling#4435) * Perf: remove redundant checks on data integrity (deepmodeling#4433) * Perf: use fused Adam optimizer (deepmodeling#4463) ### Bug fixes * Fix: add model_def_script to ZBL (deepmodeling#4423) * fix: add pairtab compression (deepmodeling#4432) * fix(tf): pass type_one_side & exclude_types to DPTabulate in `se_r` (https://github.com/deepmodeling/deepmd-kit/pull/4446) * fix: print dlerror if dlopen fails (#4485) ### Documentation * chore(pt): update multitask example (#4419) * docs: update DPA-2 citation (deepmodeling#4483) * docs: update deepmd-gnn URL (deepmodeling#4482) * docs: fix a minor typo on the title of install-from-c-library.md (#4484) ### Other Changes * build(deps): bump pypa/cibuildwheel from 2.21 to 2.22 by @dependabot in https://github.com/deepmodeling/deepmd-kit/pull/4408 **Full Changelog**: https://github.com/deepmodeling/deepmd-kit/compare/v3.0.0...v3.0.1

<!-- Release notes generated using configuration in .github/release.yml at devel --> # DeePMD-kit v3: Multiple-backend Framework, DPA-2 Large Atomic Model, and Plugin Mechanisms After eight months of public tests, we are excited to present the first stable version of DeePMD-kit v3, an advanced version that enables deep potential models with TensorFlow, PyTorch, or JAX backends. Additionally, DeePMD-kit v3 introduces support for the [DPA-2 model](https://arxiv.org/abs/2312.15492), a novel architecture optimized for large atomic models. This release enhances plugin mechanisms, making integrating and developing new models easier. ## Highlights ### Multiple-backend framework: TensorFlow, PyTorch, and JAX support  DeePMD-kit v3 adds a versatile, pluggable framework providing consistent training and inference experience across multiple backends. Version 3.0.0 includes: - **TensorFlow backend**: Known for its computational efficiency with a static graph design. - **PyTorch backend**: A dynamic graph backend that simplifies model extension and development. - **DP backend**: Built with NumPy and [Array API](https://data-apis.org/array-api/), a reference backend for development without heavy deep-learning frameworks. - **JAX backend**: Based on the DP backend via Array API, a static graph backend. | Features |TensorFlow | PyTorch | JAX | DP | | ------------------------- |----------------- |------------ |------|------| |Descriptor local frame | ✅ | | | | |Descriptor se_e2_a | ✅ | ✅ | ✅ | ✅ | |Descriptor se_e2_r | ✅ | ✅ | ✅ | ✅ | |Descriptor se_e3 | ✅ | ✅ | ✅ | ✅ | |Descriptor se_e3_tebd | | ✅ | ✅ | ✅ | |Descriptor DPA1 | ✅ | ✅ | ✅ | ✅ | |Descriptor DPA2 | | ✅ | ✅ | ✅ | |Descriptor Hybrid | ✅ | ✅ | ✅ | ✅ | |Fitting energy | ✅ | ✅ | ✅ | ✅ | |Fitting dipole | ✅ | ✅ | ✅ | ✅ | |Fitting polar | ✅ | ✅ | ✅ | ✅ | |Fitting DOS | ✅ | ✅ | ✅ | ✅ | |Fitting property | | ✅ | ✅ | ✅ | | ZBL | ✅ | ✅ | ✅ | ✅ | | DPLR | ✅ | | | | | DPRc | ✅ | ✅ | ✅ | ✅ | | Spin | ✅ | ✅ | | ✅ | | Gradient calculation | ✅ | ✅ | ✅ | | | Model training | ✅ | ✅ | | | | Model compression | ✅ | ✅ | | | | Python inference | ✅ | ✅ | ✅ | ✅ | | C++ inference | ✅ | ✅ | ✅ | | Critical features of the multiple-backend framework include the ability to: - Train models using different backends with the same training data and input script, allowing backend switching based on your efficiency or convenience needs. ```sh # Training a model using the TensorFlow backend dp --tf train input.json dp --tf freeze dp --tf compress # Training a model using the PyTorch backend dp --pt train input.json dp --pt freeze dp --pt compress ``` - Convert models between backends using `dp convert-backend`, with backend-specific file extensions (e.g., `.pb` for TensorFlow and `.pth` for PyTorch). ```sh # Convert from a TensorFlow model to a PyTorch model dp convert-backend frozen_model.pb frozen_model.pth # Convert from a PyTorch model to a TensorFlow model dp convert-backend frozen_model.pth frozen_model.pb # Convert from a PyTorch model to a JAX model dp convert-backend frozen_model.pth frozen_model.savedmodel # Convert from a PyTorch model to the backend-independent DP format dp convert-backend frozen_model.pth frozen_model.dp ``` - Run inference across backends via interfaces like `dp test`, Python/C++/C interfaces, or third-party packages (e.g., dpdata, ASE, LAMMPS, AMBER, Gromacs, i-PI, CP2K, OpenMM, ABACUS, etc.). ```sh # In a LAMMPS file: # 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 # run LAMMPS with a JAX backend model pair_style deepmd frozen_model.savedmodel # Calculate model deviation using different models pair_style deepmd frozen_model.pb frozen_model.pth frozen_model.savedmodel out_file md.out out_freq 100 ``` - Add a new backend to DeePMD-kit much more quickly if you want to contribute to DeePMD-kit. ### DPA-2 model: a large atomic model as a multi-task learner The [DPA-2 model](https://arxiv.org/abs/2312.15492) offers a robust architecture for large atomic models (LAM), accurately representing diverse chemical systems for high-quality simulations. In this release, DPA-2 can be trained using the PyTorch backend, supporting both single-task (see `examples/water/dpa2`) or multi-task (see `examples/water_multi_task/pytorch_example`) training schemes. DPA-2 is available for Python/C++ inference in the JAX backend. The DPA-2 descriptor comprises `repinit` and `repformer`, as shown below.  The PyTorch backend supports training strategies for large atomic models, including: - **Parallel training**: Train large atomic models on multiple GPUs for efficiency. ```sh torchrun --nproc_per_node=4 --no-python dp --pt train input.json ``` - **Multi-task training**: For large atomic models trained across a broad range of data calculated on different DFT levels with shared descriptors. An example is given in `examples/water_multi_task/pytorch_example/input_torch.json`. - **Finetune**: Training a pre-train large atomic model on a smaller, task-specific dataset. The PyTorch backend has supported `--finetune` argument in the `dp --pt train` command line. ### Plugin mechanisms for external models In version 3.0.0, the plugin capabilities have been implemented to support the development and integration of potential energy models using TensorFlow, PyTorch, or JAX backends, leveraging DeePMD-kit's trainer, loss functions, and interfaces. A plugin example is [deepmd-gnn](https://github.com/njzjz/deepmd-gnn), which supports training the MACE and NequIP models in the DeePMD-kit with the familiar commands. ```sh dp --pt train mace.json dp --pt freeze dp --pt test -m frozen_model.pth -s ../data/ ```  ## Other new features - Descriptor se_e3_tebd. (#4066) - Fitting the property (#3867). - New training parameters: `max_ckpt_keep` (#3441), `change_bias_after_training` (#3993), and `stat_file`. - New command line interface: `dp change-bias` (#3993) and `dp show` (#3796). - Support generating JSON schema for integration with VSCode (#3849). - The latest LAMMPS version (stable_29Aug2024_update1) is supported. (#4088, #4179) ## Breaking changes - The deepmodeling conda channel is deprecated. Use the conda-forge channel instead. (#3462, #4385) - The offline package and conda packages for CUDA 11 are dropped. - Python 3.7 and 3.8 supports are dropped. (#3185, #4185) - The minimal versions of deep learning frameworks: TensorFlow 2.7, PyTorch 2.1, JAX 0.4.33, and NumPy 1.21. - 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. - Bias is removed by default from type embedding. (#3958) - The spin model is refactored, and its usage in the LAMMPS module has been changed. (#3301, #4321) - Multi-task training support is removed from the TensorFlow backend. (#3763) - The `set_prefix` key is deprecated. (#3753) - `dp test` now uses all sets for training and test. In previous versions, only the last set is used as the test set in dp test. (#3862) - 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. (#3177, #3178) - Python class `DeepTensor` (including `DeepDiople` and `DeepPolar`) now returns atomic tensor in the dimension of `natoms` instead of `nsel_atoms`. (#3390) - C++ 11 support is dropped. (#4068) For other changes, refer to **Full Changelog**: https://github.com/deepmodeling/deepmd-kit/compare/v2.2.11...v3.0.0rc0 ## Contributors The PyTorch backend was developed in the [dptech-corp/deepmd-pytorch](https://github.com/dptech-corp/deepmd-pytorch) repository, and then it was fully merged into the deepmd-kit repository in #3180. Contributors to the deepmd-pytorch repository: - @20171130 - @CaRoLZhangxy - @amcadmus - @guolinke - @iProzd - @nahso - @njzjz - @qin2xue3jian4 - @shishaochen - @zjgemi Contributors to the deepmd-kit repository: * @CaRoLZhangxy: #3162 #3287 #3337 #3375 #3379 #3434 #3436 #3612 #3613 #3614 #3656 #3657 #3740 #3780 #3917 #3919 #4209 #4237 * @Chengqian-Zhang: #3615 #3796 #3828 #3840 #3867 #3912 #4120 #4145 #4280 * @ChiahsinChu: #4246 #4248 * @Cloudac7: #4031 * @HydrogenSulfate: #4117 * @LiuGroupHNU: #3978 * @Mancn-Xu: #3567 * @Yi-FanLi: #3822 #4013 #4084 #4283 * @anyangml: #3192 #3210 #3212 #3248 #3266 #3281 #3296 #3309 #3314 #3321 #3327 #3338 #3351 #3362 #3376 #3385 #3398 #3410 #3426 #3432 #3435 #3447 #3451 #3452 #3468 #3485 #3486 #3575 #3584 #3654 #3662 #3663 #3706 #3757 #3759 #3812 #3824 #3876 #3946 #3975 #4194 #4205 #4292 #4296 #4335 #4339 #4370 #4380 * @caic99: #3465 #4165 #4401 * @chazeon: #3473 #3652 #3653 #3739 * @cherryWangY: #3877 #4227 #4297 #4298 #4299 #4300 * @dependabot: #3231 #3312 #3446 #3487 #3777 #3882 #4045 #4127 #4374 * @hztttt: #3762 * @iProzd: #3180 #3203 #3245 #3261 #3301 #3355 #3359 #3367 #3371 #3378 #3380 #3387 #3388 #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 #3957 #3958 #3967 #3971 #3976 #3992 #3993 #4006 #4007 #4015 #4066 #4089 #4138 #4139 #4148 #4162 #4222 #4223 #4224 #4225 #4243 #4244 #4321 #4323 #4324 #4344 #4353 #4354 #4372 #4375 #4394 #4395 #4440 * @iid-ccme: #4340 * @nahso: #3726 #3727 * @njzjz: #3164 #3167 #3169 #3170 #3171 #3172 #3173 #3174 #3175 #3176 #3177 #3178 #3179 #3181 #3185 #3186 #3187 #3191 #3193 #3194 #3195 #3196 #3198 #3200 #3201 #3204 #3205 #3206 #3207 #3213 #3217 #3220 #3221 #3222 #3223 #3226 #3228 #3229 #3237 #3238 #3239 #3243 #3244 #3247 #3249 #3250 #3253 #3254 #3257 #3258 #3263 #3267 #3271 #3275 #3276 #3283 #3284 #3285 #3286 #3288 #3290 #3292 #3293 #3294 #3303 #3304 #3306 #3307 #3308 #3310 #3313 #3315 #3316 #3318 #3323 #3325 #3326 #3330 #3331 #3332 #3333 #3335 #3339 #3342 #3343 #3346 #3348 #3349 #3350 #3356 #3358 #3360 #3361 #3364 #3365 #3366 #3369 #3370 #3373 #3374 #3377 #3381 #3382 #3383 #3384 #3386 #3390 #3393 #3394 #3395 #3396 #3397 #3399 #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 #3956 #3964 #3965 #3972 #3973 #3977 #3980 #3981 #3982 #3985 #3987 #3989 #3995 #3996 #4001 #4002 #4005 #4009 #4010 #4012 #4021 #4024 #4025 #4027 #4028 #4032 #4038 #4047 #4049 #4059 #4067 #4068 #4070 #4071 #4073 #4074 #4075 #4079 #4081 #4083 #4088 #4095 #4100 #4106 #4110 #4111 #4113 #4131 #4134 #4136 #4144 #4146 #4147 #4152 #4153 #4155 #4156 #4160 #4172 #4176 #4178 #4179 #4180 #4185 #4187 #4190 #4196 #4199 #4200 #4204 #4212 #4213 #4214 #4217 #4218 #4219 #4220 #4221 #4226 #4228 #4230 #4236 #4238 #4239 #4240 #4242 #4247 #4251 #4252 #4254 #4256 #4257 #4258 #4259 #4260 #4261 #4263 #4264 #4269 #4271 #4274 #4275 #4278 #4284 #4285 #4286 #4287 #4288 #4289 #4290 #4293 #4294 #4301 #4304 #4307 #4309 #4313 #4315 #4318 #4319 #4320 #4325 #4326 #4327 #4329 #4330 #4331 #4336 #4338 #4341 #4342 #4343 #4345 #4350 #4351 #4352 #4355 #4356 #4357 #4363 #4365 #4369 #4377 #4383 #4384 #4385 #4386 #4387 #4388 #4390 #4391 #4392 #4402 #4403 #4404 #4405 #4406 * @njzjz-bot: #3669 #3953 #3988 #4119 #4266 * @pre-commit-ci: #3163 #3236 #3264 #3305 #3454 #3489 #3599 #3634 #3659 #3675 #3700 #3720 #3754 #3779 #3825 #3850 #3863 #3883 #3900 #3938 #3955 #3983 #4003 #4048 #4053 #4065 #4080 #4097 #4115 #4130 #4159 #4173 #4192 #4235 #4268 #4310 #4337 #4378 * @robinzyb: #3647 * @shiruosong: #3344 #3345 * @sigbjobo: #4150 * @wanghan-iapcm: #3184 #3188 #3190 #3199 #3202 #3208 #3219 #3225 #3232 #3234 #3235 #3240 #3241 #3246 #3260 #3262 #3268 #3274 #3279 #3280 #3282 #3289 #3295 #3340 #3352 #3357 #3389 #3391 #3400 #3413 #3458 #3469 #3609 #3611 #3626 #3628 #3639 #3642 #3649 #3650 #3755 #3761 #4052 #4116 #4135 #4142 #4166 #4233 #4241 * @wangzyphysics: #3597 #4312 We also thank everyone who did tests and reported bugs in the past eight months.