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

feat(build): Add Git archives version files #3670

Closed
wants to merge 290 commits into from
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
290 commits
Select commit Hold shift + click to select a range
677d936
fix bug of output def: the reduced virial is not defined. (#3219)
wanghan-iapcm Feb 2, 2024
412c812
gmx: fix include directive (#3221)
njzjz Feb 3, 2024
ab2c551
c: fix all memory leaks; add sanitizer checks (#3223)
njzjz Feb 4, 2024
7db1fde
Feat: numpy pairtab model (#3212)
anyangml Feb 4, 2024
cd77429
fix model doc str: add shape hint to doc string. (#3225)
wanghan-iapcm Feb 4, 2024
17f2c35
pt: rename atomic_virial to atom_virial in the model output (#3226)
njzjz Feb 5, 2024
22197f5
pt: apply global logger to pt (#3222)
njzjz Feb 5, 2024
7f5d67c
pt: apply global user set precision to pt (#3220)
njzjz Feb 5, 2024
f5bb131
fix DP_ENABLE_TENSORFLOW support (#3229)
njzjz Feb 5, 2024
18c43f6
test: better structure for the dpmodel uts (#3232)
wanghan-iapcm Feb 6, 2024
13a781f
fix: pt: energy model forward lower is not tested and has bugs. (#3235)
wanghan-iapcm Feb 6, 2024
f96e614
build(deps): bump codecov/codecov-action from 3 to 4 (#3231)
dependabot[bot] Feb 6, 2024
e281a8c
c: change the required shape of electric field to nloc * 3 (#3237)
njzjz Feb 6, 2024
37cdccf
[pre-commit.ci] pre-commit autoupdate (#3236)
pre-commit-ci[bot] Feb 6, 2024
1c8d635
pin docker actions to major versions (#3238)
njzjz Feb 6, 2024
6672a28
drop `deepmd.tf.cluster.slurm` (#3239)
njzjz Feb 6, 2024
79f98ca
test: pt: mv all model related tests to the pt/test/model folder (#3234)
wanghan-iapcm Feb 6, 2024
6c12380
add category property to OutputVariableDef (#3228)
njzjz Feb 6, 2024
07a4510
fix skipped tests (#3241)
wanghan-iapcm Feb 6, 2024
f1baf19
support separate r_differentiable and c_differentiable (#3240)
wanghan-iapcm Feb 7, 2024
a7153b1
issue template: change TF version to backend version (#3244)
njzjz Feb 7, 2024
b7f1239
Feat: add ZBL weighted DP model (#3210)
anyangml Feb 8, 2024
5ad3d96
refactor print summary (#3243)
njzjz Feb 8, 2024
cfdda1d
add hessian support in output def. (#3246)
wanghan-iapcm Feb 8, 2024
c235099
refactor DeepEval (#3213)
njzjz Feb 8, 2024
9181a02
fix: cuda tests of linear and pair atomic model (#3248)
anyangml Feb 9, 2024
9a8f712
backend-indepedent dp test (#3249)
njzjz Feb 9, 2024
d1d7881
pt: infer model type from ModelOutputDef (#3250)
njzjz Feb 9, 2024
0e2304f
breaking: pt: remove data stat from model init (#3245)
iProzd Feb 10, 2024
dc63793
tf: support checkpoint path (instead of directory) in dp freeze (#3254)
njzjz Feb 11, 2024
c131c8f
ipi: remove normalize_coord (#3257)
njzjz Feb 11, 2024
beb1b98
add `get_type_map` method to model; export model methods (#3247)
njzjz Feb 12, 2024
1bdc60d
[pre-commit.ci] pre-commit autoupdate (#3264)
pre-commit-ci[bot] Feb 13, 2024
392b9e0
pt: support loading frozen models in DeepEval (#3253)
njzjz Feb 13, 2024
6018e3c
fix bug of not passing params in model (#3260)
wanghan-iapcm Feb 13, 2024
398eb7a
enable docstring code format (#3267)
njzjz Feb 13, 2024
e41b091
breaking: pt: remove data preprocess from data stat (#3261)
iProzd Feb 13, 2024
1d23383
add neighbor stat support with NumPy and PyTorch implementation (#3271)
njzjz Feb 14, 2024
930bc1a
support TF se_e2_a serialization; add a common test fixture to compar…
njzjz Feb 14, 2024
977b430
pt: add exported methods to BaseAtomicModel (#3258)
njzjz Feb 14, 2024
25bf37a
Implement hessian autodiff calculation (#3262)
wanghan-iapcm Feb 14, 2024
097b3ab
fix bug of output dimension in pt InvarFitting (#3274)
wanghan-iapcm Feb 14, 2024
0b68097
pt: fix torchscript converage (#3276)
njzjz Feb 15, 2024
aae4850
dp: pt: rearrange folder structure of atomic_model and model. (#3268)
wanghan-iapcm Feb 15, 2024
02080db
tf: refactor neighbor stat (#3275)
njzjz Feb 15, 2024
43f17da
feat: pt: support user specified rcond for fitting stat (#3279)
wanghan-iapcm Feb 15, 2024
15f8d25
Chore: refactor InvarFitting (#3266)
anyangml Feb 16, 2024
8f91aea
feat: dp and pt: implement exclude types in descriptor se_a (#3280)
wanghan-iapcm Feb 16, 2024
f2b84ff
feat: dp and pt: implement fitting exclude types (#3282)
wanghan-iapcm Feb 17, 2024
cd1a957
improve gh actions (#3283)
njzjz Feb 17, 2024
91e7022
speed up cuda test (#3284)
njzjz Feb 17, 2024
9053caf
fix gh actions issues (#3288)
njzjz Feb 17, 2024
c55ceac
pt: refactor data stat (#3285)
njzjz Feb 18, 2024
db6c666
gh actions: fix branches ignore pattern & fix activity types (#3290)
njzjz Feb 18, 2024
6451cdb
Feat: Refactor dipole fitting pytorch (#3281)
anyangml Feb 18, 2024
5600e45
consistent energy fitting (#3286)
njzjz Feb 18, 2024
027d902
dp&pt: let DPAtomicModel fetch attributes from Fitting (#3292)
njzjz Feb 19, 2024
63bec22
pluggable backend (#3294)
njzjz Feb 19, 2024
235ff24
test the case of permuted index in different frames. (#3295)
wanghan-iapcm Feb 19, 2024
9f6ff1e
fix: replace all distinguished types by mixed types. (#3289)
wanghan-iapcm Feb 19, 2024
ab35468
pt: process frames in parallel for env mat stat (#3293)
njzjz Feb 19, 2024
ab2ed0e
pt: avoid `set_default_dtype` in tests (#3303)
njzjz Feb 20, 2024
33495d8
Feat: add polarizability fitting net (#3296)
anyangml Feb 20, 2024
fe14402
fix neighbor stat mixed_types input (#3304)
njzjz Feb 20, 2024
4b994df
[pre-commit.ci] pre-commit autoupdate (#3305)
pre-commit-ci[bot] Feb 20, 2024
f5c2f57
pt:Removed the data system implemented in PyTorch (#3287)
CaRoLZhangxy Feb 21, 2024
8b1ed14
allow both absulute and relative tolerance when testing consistency (…
njzjz Feb 21, 2024
139721f
pt: explicitly set device (#3307)
njzjz Feb 21, 2024
4956864
build(deps): bump the npm_and_yarn group across 1 directories with 1 …
dependabot[bot] Feb 21, 2024
af14ba4
Feat: add DipoleModel and PolarModel (#3309)
anyangml Feb 21, 2024
e1c0564
consistent energy model (#3306)
njzjz Feb 21, 2024
d629616
tf: add fparam/aparam support for finetune (#3313)
njzjz Feb 21, 2024
e565391
Fix: float32 bug in UTs (#3314)
anyangml Feb 22, 2024
cf21b7a
merge common subcommands in cli (#3316)
njzjz Feb 22, 2024
d7a4f72
fix AlmaLinux GPG key error (#3326)
njzjz Feb 23, 2024
94f0ad1
pt: fix se_e2_a precision cast (#3315)
njzjz Feb 23, 2024
6345207
pt: export `model_output_type` instead of `model_output_def` (#3318)
njzjz Feb 23, 2024
d949bc8
feat: convert model files between backends (#3323)
njzjz Feb 23, 2024
260ef21
Feat: add dipole consistency test (#3321)
anyangml Feb 23, 2024
543276a
Feat: add polar consistency test (#3327)
anyangml Feb 23, 2024
649fdca
store type in descriptor serialization data (#3325)
njzjz Feb 23, 2024
03ca9ab
docs: install pytorch in RTD (#3333)
njzjz Feb 24, 2024
15df69b
feat: add NumPy DeepPot (#3332)
njzjz Feb 24, 2024
91049df
store type in fitting serialization data (#3331)
njzjz Feb 24, 2024
261c802
pt: add necessary jit.export (#3337)
CaRoLZhangxy Feb 25, 2024
a3f4a67
pt: remove env.DEVICE in all `forward` functions (#3330)
njzjz Feb 26, 2024
4f70073
feat(pt/dpmodel): support type_one_side in se_e2_a (#3339)
njzjz Feb 27, 2024
3e6b507
refact: pt: mv all plugin support to base descriptor. (#3340)
wanghan-iapcm Feb 27, 2024
473cc0a
bump python to 3.12 in the test environment (#3343)
njzjz Feb 27, 2024
254afc8
fix_dplr.cpp delete redundant setup (#3344)
shiruosong Feb 27, 2024
c538d04
Feat: add se_r descriptor (#3338)
anyangml Feb 27, 2024
854d998
add BaseModel; store type in serialization (#3335)
njzjz Feb 27, 2024
b1de9e6
fix_dplr.cpp set atom->image when pre_force (#3345)
shiruosong Feb 27, 2024
004ebd6
apply PluginVariant and make_plugin_registry to classes (#3346)
njzjz Feb 28, 2024
f8ad655
add @version to serialization data (#3349)
njzjz Feb 28, 2024
fd17e2e
Fix: se_r prod_env_mat (#3351)
anyangml Feb 28, 2024
d377ccb
cc: add torch backend support for Multiple backend (#3162)
CaRoLZhangxy Feb 28, 2024
897fcc5
pt: support `--init-frz-model` (#3350)
njzjz Feb 28, 2024
16cd26c
Fix single-task training&data stat (#3355)
iProzd Feb 28, 2024
3ad57da
merge compute_output_stat (#3310)
njzjz Feb 28, 2024
2a1508d
feat(pt): support fparam/aparam in DeepEval (#3356)
njzjz Feb 28, 2024
2bee22c
fix: cast input and output types at model's interface (#3352)
wanghan-iapcm Feb 29, 2024
48c8818
pt: fix se_a type_one_side performance degradation (#3361)
njzjz Feb 29, 2024
581dea3
docs: dpmodel, model conversion (#3360)
njzjz Feb 29, 2024
17bd1ec
pt: apply argcheck to pt (#3342)
njzjz Feb 29, 2024
84d0576
docs: apply type_one_side=True to `se_a` and `se_r` (#3364)
njzjz Feb 29, 2024
d09af56
feat: update sel by statistics (#3348)
njzjz Feb 29, 2024
342b0c3
feat: support exclude atypes in atomic model (#3357)
wanghan-iapcm Feb 29, 2024
665d716
feat(pt): support fparam/aparam in C++ DeepPot (#3358)
njzjz Feb 29, 2024
ed08808
Chore: Update doc for PyTorch Energy Fitting (#3362)
anyangml Feb 29, 2024
19a4921
fix se_r consistency (#3366)
njzjz Feb 29, 2024
2511e8b
pt: Fix multitask neighbor stat (#3367)
iProzd Feb 29, 2024
fd600d7
Hybrid descriptor (#3365)
njzjz Mar 1, 2024
54efc03
bump scikit-build-core to 0.8 (#3369)
njzjz Mar 1, 2024
16c6db6
pt: refact training code (#3359)
iProzd Mar 1, 2024
54b14ef
sync descriptor alias (#3374)
njzjz Mar 1, 2024
f684be8
feat: atom_ener in energy fitting (#3370)
njzjz Mar 1, 2024
2594f09
docs: DPRc for PT, DPModel (#3373)
njzjz Mar 1, 2024
759bdcb
pt: supprot `--output` in `dp train` (#3377)
njzjz Mar 1, 2024
ee8b82b
pt: add real atoms select in c++ interface (#3375)
CaRoLZhangxy Mar 1, 2024
bdea3ce
Add trainable settings for pt (#3371)
iProzd Mar 2, 2024
92ee632
tf: remove freeze warning for optional nodes (#3381)
njzjz Mar 2, 2024
831610a
fix: prevent deepmd.tf be imported globally (#3382)
njzjz Mar 2, 2024
f4abe12
Doc: Update the developer guide for the v3 (#3376)
anyangml Mar 2, 2024
bf4b473
pt: print data summary (#3383)
njzjz Mar 2, 2024
c61ba88
pt: expand systems before training (#3384)
njzjz Mar 2, 2024
d2b18b2
Doc: Update PT Multi-task (#3387)
iProzd Mar 2, 2024
7aee42c
pt: add fparam/aparam data requirements (#3386)
njzjz Mar 2, 2024
822be1e
doc: add PyTorch parallel training content (#3379)
CaRoLZhangxy Mar 2, 2024
e918106
pt: fix params with no docstrs (#3388)
iProzd Mar 2, 2024
cbeb1d5
add mask to atomic model output when an atomic type exclusion present…
wanghan-iapcm Mar 2, 2024
59d3b12
breaking: change DeepTensor output dim from nsel_atoms to natoms (#3390)
njzjz Mar 2, 2024
8d0e3ba
pt: ban `torch.testing.assert_allclose` (#3395)
njzjz Mar 3, 2024
d4ac864
pt: Add support for dipole and polar training (#3380)
iProzd Mar 3, 2024
da014e7
Doc: Update PT tensor fitting (#3385)
anyangml Mar 3, 2024
4f933d8
ut: add null test (#3391)
wanghan-iapcm Mar 3, 2024
c31d376
Merge `change_energy_bias` and fix finetune (#3378)
iProzd Mar 3, 2024
7af9e20
bump LAMMPS to stable_2Aug2023_update3 (#3399)
njzjz Mar 3, 2024
9c508b7
allow loading either nsel or natoms atomic tensor data (#3394)
njzjz Mar 3, 2024
13a8adf
do not return g2, h2, sw in hybrid descriptors (#3396)
njzjz Mar 3, 2024
e826260
format training logging (#3397)
njzjz Mar 3, 2024
ec32340
Recovered all the skipped test for hybrid descriptor (#3400)
wanghan-iapcm Mar 3, 2024
174e908
fix github actions for release (#3402)
njzjz Mar 3, 2024
bd79dec
fix deepmd-kit-cu11 again (#3403)
njzjz Mar 4, 2024
32a86ac
pt: Fix compilation with libtorch (#3405)
njzjz Mar 4, 2024
945f1b5
set `NUM_WORKERS` to 0 in test_cuda action (#3404)
njzjz Mar 4, 2024
4454811
pt: fix multitask print_summary (#3409)
iProzd Mar 4, 2024
c8c941a
pt: fix multitask stuck on multiple-gpu (#3411)
iProzd Mar 5, 2024
c56a30d
Chore: make type_map complusory model attribute (#3410)
anyangml Mar 5, 2024
697fde9
fix bug of rcut_smth >= rcut in the test cases (#3413)
wanghan-iapcm Mar 5, 2024
268a0fc
ban print (#3415)
njzjz Mar 5, 2024
b0171ce
throw errros if rmin is no less than rmax (#3393)
njzjz Mar 5, 2024
5794a87
revert test Python to 3.11 (#3419)
njzjz Mar 6, 2024
278e6b8
convert exclude_types to sel_type (#3418)
njzjz Mar 6, 2024
d3ca9d7
pt: avoid D2H in se_e2_a (#3424)
njzjz Mar 6, 2024
fa8e645
Feat: add zbl training (#3398)
anyangml Mar 6, 2024
2d48d1f
pt: improve nlist performance (#3425)
njzjz Mar 7, 2024
09bd522
Support DPSpin for AtomicModel (#3301)
iProzd Mar 7, 2024
268591c
pt: make get_data non-blocking (#3422)
njzjz Mar 8, 2024
fefc0e6
pt: fix print_on_training when there is no validation data (#3423)
njzjz Mar 8, 2024
dabbd35
Consistent activation functions between backends (#3431)
njzjz Mar 8, 2024
66edd1f
fix errors when `dp` is executed without any subcommands (#3437)
njzjz Mar 8, 2024
d3dd604
pt: avoid torch.tensor(constant) during forward (#3421)
njzjz Mar 8, 2024
a9bcf41
clean up the init interface of pt.dataloader (#3434)
CaRoLZhangxy Mar 8, 2024
fd82f04
Add `max_ckpt_keep` for trainer (#3441)
iProzd Mar 9, 2024
a286bd4
pt: cleanup tester (#3442)
iProzd Mar 10, 2024
2ee8a3b
Feat: Add polar stat constant matrix calculation to PT (#3426)
anyangml Mar 11, 2024
804848a
fix: do not install tf-keras for cu11 (#3444)
njzjz Mar 11, 2024
b544885
pt: make jit happy with torch 2.0.0 (#3443)
njzjz Mar 11, 2024
619fd1c
Fix: ZBL null test (#3447)
anyangml Mar 11, 2024
24d02b7
pt: Add parallel implementation for LKF (#3436)
CaRoLZhangxy Mar 11, 2024
4c84514
build(deps): bump softprops/action-gh-release from 1 to 2 (#3446)
dependabot[bot] Mar 11, 2024
a88a213
refactor: split Model and AtomicModel (#3438)
njzjz Mar 11, 2024
bc35ac9
Fix: ZBL state_dict duplicated keys (#3432)
anyangml Mar 12, 2024
9bcae14
fix: remove model_def_script from AtomicModel (#3449)
njzjz Mar 12, 2024
da9b526
feat(pt): consistent "frozen" model (#3450)
njzjz Mar 12, 2024
36fdf53
chore: remove unused init_fitting_stat (#3453)
njzjz Mar 13, 2024
dda4bc6
Chore: refactor LinearAtomicModel serialize/deserialize (#3451)
anyangml Mar 13, 2024
da68686
[pre-commit.ci] pre-commit autoupdate (#3454)
pre-commit-ci[bot] Mar 13, 2024
571ddec
fix the bug of empty fitting net neuron. (#3458)
wanghan-iapcm Mar 13, 2024
487f85c
ci: reduce ASLR entropy (#3461)
njzjz Mar 14, 2024
da866a2
Fix: remove debug output in infer (#3465)
caic99 Mar 15, 2024
d61b152
fix(tf): fix DeepEval degradation for virtual types (#3464)
njzjz Mar 15, 2024
2caf92c
Feat: add DOS net (#3452)
anyangml Mar 15, 2024
80b6900
docs: add deprecation notice for the official conda channel and more …
njzjz Mar 15, 2024
39cb4d1
Chore: Move InvarFitting (#3468)
anyangml Mar 15, 2024
4b3a77b
Feat: support virtual atom (#3469)
wanghan-iapcm Mar 16, 2024
abf3477
Fix LAMMPS plugin symlink path on macOS platform (#3473)
chazeon Mar 17, 2024
eca5b30
fix(pt): Fix PairTabAtomicModel OOM error (#3484)
njzjz Mar 18, 2024
9b6042b
Fix: Invar_fitting warning msg (#3485)
anyangml Mar 18, 2024
76371ce
Clean TODOs and convert them into issues (#3519)
njzjz Mar 19, 2024
2851fb9
[pre-commit.ci] pre-commit autoupdate (#3489)
pre-commit-ci[bot] Mar 19, 2024
be95d09
build(deps): bump pypa/cibuildwheel from 2.16 to 2.17 (#3487)
dependabot[bot] Mar 19, 2024
47366f6
pt: add explicit decay_rate for lr (#3445)
iProzd Mar 20, 2024
9c861c2
pt: add index input for `use_spin` (#3456)
iProzd Mar 20, 2024
71ec631
pt: refactor loss (#3569)
iProzd Mar 20, 2024
5aa1b89
fix(pt): fix a typo in DeepEval to check do_atomic_virial (#3570)
njzjz Mar 20, 2024
b2cc0e5
pt: support multitask dp test (#3573)
iProzd Mar 21, 2024
145f501
ci: add linter for markdown, yaml, CSS (#3574)
njzjz Mar 21, 2024
fb61efb
test: add LAMMPS MPI tests (#3572)
njzjz Mar 21, 2024
e47478f
pt: support multitask finetune (#3480)
iProzd Mar 22, 2024
dc14719
pt: fix loss training when no data available (#3571)
iProzd Mar 22, 2024
a25b9a5
fix: move DeepPotential from `deepmd.tf.infer` to `deepmd.infer` (#3580)
njzjz Mar 22, 2024
a58dbc6
tf: add explict mixed_types argument to fittings (#3583)
njzjz Mar 22, 2024
48f06fe
Feat: Add DOSnet training in PT (#3486)
anyangml Mar 25, 2024
3c3e2ce
fix(tf): fix bugs in tensor training and migrate to reformat data (#3…
njzjz Mar 25, 2024
98f69e0
[pre-commit.ci] pre-commit autoupdate (#3599)
pre-commit-ci[bot] Mar 25, 2024
3c09d46
fix: natom error in calc_model_devi (#3597)
wangzyphysics Mar 26, 2024
964f02d
Fix: Pt Polar Stat keyword (#3584)
anyangml Mar 26, 2024
08b3814
feat: Support bfloat16 and ensure valid precision and activation func…
njzjz Mar 26, 2024
3b5b805
pt: fix typo in multitask finetune (#3607)
iProzd Mar 26, 2024
625e893
chore: remove incorrect memset TODOs (#3600)
njzjz Mar 26, 2024
197612a
pin nvidia-cudnn-cu{11,12} to <9 (#3610)
njzjz Mar 27, 2024
1423750
feat: Add `USE_PT_PYTHON_LIBS` CMake variable (#3605)
njzjz Mar 27, 2024
c1f22b5
rm dir source/md (#3611)
wanghan-iapcm Mar 27, 2024
f5b7aa3
fix pt bug: missing get_ntype method (#3612)
CaRoLZhangxy Mar 27, 2024
8090fa1
Fix bug in `preprocess_shared_params` when using non-zero share level…
Chengqian-Zhang Mar 27, 2024
f16d543
implement electronic configuration embedding (#3609)
wanghan-iapcm Mar 27, 2024
6da8eef
Fix fine-tuning entries bug when doing restart. (#3616)
iProzd Mar 28, 2024
571bd52
chore(build): move static part of dynamic metadata to pyproject.toml …
njzjz Mar 28, 2024
c2371cd
fix c++ interface bug (#3613)
CaRoLZhangxy Mar 28, 2024
7933c5e
pt: support list format batch size (#3614)
CaRoLZhangxy Mar 28, 2024
23f67a1
pt: use unified activation (#3619)
iProzd Mar 28, 2024
386f3b2
feat(pt): add op library (#3620)
njzjz Mar 29, 2024
cc30f27
chore: move `source/op` to `source/op/tf` (#3621)
njzjz Mar 29, 2024
d0d5a94
fix: fix type hint of sel (#3624)
njzjz Mar 30, 2024
0be9714
feat: consistent type embedding (#3617)
njzjz Mar 31, 2024
2e6ab1b
feat: auto batch size supports methods that return a dict (#3626)
wanghan-iapcm Mar 31, 2024
15e4926
fix: fix DPOSPath.save_numpy, DPH5Path.is_file, DPH5Path.is_dir (#3631)
njzjz Apr 1, 2024
8e0cc90
feat: compute output stat for a dict of labels. (#3628)
wanghan-iapcm Apr 1, 2024
cb08410
[pre-commit.ci] pre-commit autoupdate (#3634)
pre-commit-ci[bot] Apr 2, 2024
63601b0
fix(tf): make `se_atten_v2` masking smooth when davg is not zero (#3632)
njzjz Apr 2, 2024
9808898
feat(pt): allow using directories to store stat (#3633)
njzjz Apr 2, 2024
4c546d0
fix: set rpath for libtorch and protobuf (#3636)
njzjz Apr 2, 2024
073f559
refact: compute_output_stats and change_out_bias (#3639)
wanghan-iapcm Apr 3, 2024
181b631
feat: model devi C/C++ API without nlist (#3647)
robinzyb Apr 6, 2024
edb9da8
docs: Replace quick_start.ipynb with a new version. (#3567)
Mancn-Xu Apr 6, 2024
39d027e
compute output stat for atomic model (#3642)
wanghan-iapcm Apr 7, 2024
87d293a
feat: apply descriptor exclude_types to env mat stat (#3625)
njzjz Apr 7, 2024
ea98506
Fix: LinearModel Stat (#3575)
anyangml Apr 8, 2024
e71085c
Fix error for PT backend when pytorch.distributed is not available (#…
chazeon Apr 8, 2024
ff20efc
Fix: make rt library optional in tests for non-Linux platforms in CMa…
chazeon Apr 8, 2024
09fd3bb
fix(tf): apply exclude types to se_atten_v2 switch (#3651)
njzjz Apr 8, 2024
6f0bda5
test: ut for the smoothness when pair exclusion presents (#3650)
wanghan-iapcm Apr 8, 2024
2a5bbce
Fix bug: private link mpi when find_mpi is true (#3656)
CaRoLZhangxy Apr 8, 2024
6eadc29
fix: fix git version detection in docker_package_c.sh (#3658)
njzjz Apr 9, 2024
baffd39
[pre-commit.ci] pre-commit autoupdate (#3659)
pre-commit-ci[bot] Apr 9, 2024
fd2daeb
feat: support serialize and deserialize for atomic model's compute ou…
wanghan-iapcm Apr 9, 2024
a26b680
Chore: refactor atomic bias (#3654)
anyangml Apr 11, 2024
7d4a82d
feat(build): Add Git archives version files
njzjz-bot Apr 13, 2024
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
4 changes: 4 additions & 0 deletions .git_archival.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
node: $Format:%H$
node-date: $Format:%cI$
describe-name: $Format:%(describe:tags=true,match=*[0-9]*)$
ref-names: $Format:%D$
2 changes: 2 additions & 0 deletions .gitattributes
Original file line number Diff line number Diff line change
@@ -1,2 +1,4 @@
# do not show up detailed difference on GitHub
source/3rdparty/* linguist-generated=true
source/3rdparty/README.md linguist-generated=false
.git_archival.txt export-subst
6 changes: 3 additions & 3 deletions .github/ISSUE_TEMPLATE/bug-report.yml
Original file line number Diff line number Diff line change
Expand Up @@ -21,10 +21,10 @@ body:
validations:
required: true
- type: input
id: tf-version
id: backend-version
attributes:
label: TensorFlow Version
description: "The version will be printed when running DeePMD-kit."
label: Backend and its version
description: "The backend and its version will be printed when running DeePMD-kit, e.g. TensorFlow v2.15.0."
validations:
required: true
- type: dropdown
Expand Down
6 changes: 3 additions & 3 deletions .github/ISSUE_TEMPLATE/generic-issue.yml
Original file line number Diff line number Diff line change
Expand Up @@ -21,10 +21,10 @@ body:
validations:
required: true
- type: input
id: tf-version
id: backend-version
attributes:
label: TensorFlow Version
description: "The version will be printed when running DeePMD-kit."
label: Backend and its version
description: "The backend and its version will be printed when running DeePMD-kit, e.g. TensorFlow v2.15.0."
validations:
required: true
- type: textarea
Expand Down
77 changes: 38 additions & 39 deletions .github/labeler.yml
Original file line number Diff line number Diff line change
@@ -1,39 +1,38 @@
Python:
- changed-files:
- any-glob-to-any-file:
- deepmd/**/*
- deepmd_utils/**/*
- source/tests/**/*
Docs:
- changed-files:
- any-glob-to-any-file: doc/**/*
Examples:
- changed-files:
- any-glob-to-any-file: examples/**/*
Core:
- changed-files:
- any-glob-to-any-file: source/lib/**/*
CUDA:
- changed-files:
- any-glob-to-any-file: source/lib/src/gpu/**/*
ROCM:
- changed-files:
- any-glob-to-any-file: source/lib/src/gpu/**/*
OP:
- changed-files:
- any-glob-to-any-file: source/op/**/*
C++:
- changed-files:
- any-glob-to-any-file: source/api_cc/**/*
C:
- changed-files:
- any-glob-to-any-file: source/api_c/**/*
LAMMPS:
- changed-files:
- any-glob-to-any-file: source/lmp/**/*
Gromacs:
- changed-files:
- any-glob-to-any-file: source/gmx/**/*
i-Pi:
- changed-files:
- any-glob-to-any-file: source/ipi/**/*
Python:
- changed-files:
- any-glob-to-any-file:
- deepmd/**/*
- source/tests/**/*
Docs:
- changed-files:
- any-glob-to-any-file: doc/**/*
Examples:
- changed-files:
- any-glob-to-any-file: examples/**/*
Core:
- changed-files:
- any-glob-to-any-file: source/lib/**/*
CUDA:
- changed-files:
- any-glob-to-any-file: source/lib/src/gpu/**/*
ROCM:
- changed-files:
- any-glob-to-any-file: source/lib/src/gpu/**/*
OP:
- changed-files:
- any-glob-to-any-file: source/op/**/*
C++:
- changed-files:
- any-glob-to-any-file: source/api_cc/**/*
C:
- changed-files:
- any-glob-to-any-file: source/api_c/**/*
LAMMPS:
- changed-files:
- any-glob-to-any-file: source/lmp/**/*
Gromacs:
- changed-files:
- any-glob-to-any-file: source/gmx/**/*
i-Pi:
- changed-files:
- any-glob-to-any-file: source/ipi/**/*
18 changes: 16 additions & 2 deletions .github/workflows/build_cc.yml
Original file line number Diff line number Diff line change
@@ -1,6 +1,12 @@
on:
push:
branches-ignore:
- "gh-readonly-queue/**"
pull_request:
merge_group:
concurrency:
group: ${{ github.workflow }}-${{ github.ref || github.run_id }}
cancel-in-progress: true
name: Build C++
jobs:
buildcc:
Expand All @@ -27,6 +33,10 @@ jobs:
cache: 'pip'
- uses: lukka/get-cmake@latest
- run: python -m pip install tensorflow
- name: Download libtorch
run: |
wget https://download.pytorch.org/libtorch/cpu/libtorch-cxx11-abi-shared-with-deps-2.1.2%2Bcpu.zip -O libtorch.zip
unzip libtorch.zip
- run: |
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.0-1_all.deb \
&& sudo dpkg -i cuda-keyring_1.0-1_all.deb \
Expand All @@ -48,13 +58,17 @@ jobs:
&& sudo apt-get update \
&& sudo apt-get install -y rocm-dev hipcub-dev
if: matrix.variant == 'rocm'
- run: source/install/build_cc.sh
- run: |
export CMAKE_PREFIX_PATH=$GITHUB_WORKSPACE/libtorch
source/install/build_cc.sh
env:
DP_VARIANT: ${{ matrix.dp_variant }}
DOWNLOAD_TENSORFLOW: "FALSE"
CMAKE_GENERATOR: Ninja
if: matrix.variant != 'clang'
- run: source/install/build_cc.sh
- run: |
export CMAKE_PREFIX_PATH=$GITHUB_WORKSPACE/libtorch
source/install/build_cc.sh
env:
DP_VARIANT: cpu
DOWNLOAD_TENSORFLOW: "FALSE"
Expand Down
33 changes: 27 additions & 6 deletions .github/workflows/build_wheel.yml
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,16 @@ name: Build and upload to PyPI

on:
push:
branches-ignore:
- "gh-readonly-queue/**"
tags:
- "v*"
pull_request:
merge_group:

concurrency:
group: ${{ github.workflow }}-${{ github.ref || github.run_id }}
cancel-in-progress: true

jobs:
determine-arm64-runner:
Expand Down Expand Up @@ -41,12 +50,12 @@ jobs:
cuda_version: 11.8
dp_pkg_name: deepmd-kit-cu11
# macos-x86-64
- os: macos-latest
- os: macos-13
python: 311
platform_id: macosx_x86_64
dp_variant: cpu
# macos-arm64
- os: macos-latest
- os: macos-14
python: 311
platform_id: macosx_arm64
dp_variant: cpu
Expand All @@ -68,8 +77,20 @@ jobs:
- uses: docker/setup-qemu-action@v3
name: Setup QEMU
if: matrix.platform_id == 'manylinux_aarch64' && matrix.os == 'ubuntu-latest'
# detect version in advance. See #3168
- uses: actions/setup-python@v5
name: Install Python
with:
python-version: '3.11'
cache: 'pip'
if: matrix.dp_pkg_name == 'deepmd-kit-cu11'
- run: |
python -m pip install setuptools_scm
python -c "from setuptools_scm import get_version;print('SETUPTOOLS_SCM_PRETEND_VERSION='+get_version())" >> $GITHUB_ENV
rm -rf .git
if: matrix.dp_pkg_name == 'deepmd-kit-cu11'
- name: Build wheels
uses: pypa/cibuildwheel@v2.16
uses: pypa/cibuildwheel@v2.17
env:
CIBW_BUILD_VERBOSITY: 1
CIBW_ARCHS: all
Expand Down Expand Up @@ -136,20 +157,20 @@ jobs:
path: source/install/docker/dist
merge-multiple: true
- name: Log in to the Container registry
uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}

- name: Extract metadata (tags, labels) for Docker
id: meta
uses: docker/metadata-action@dbef88086f6cef02e264edb7dbf63250c17cef6c
uses: docker/metadata-action@v5
with:
images: ghcr.io/deepmodeling/deepmd-kit

- name: Build and push Docker image
uses: docker/build-push-action@4a13e500e55cf31b7a5d59a38ab2040ab0f42f56
uses: docker/build-push-action@v5
with:
context: source/install/docker
push: ${{ github.repository_owner == 'deepmodeling' && github.event_name == 'push' && github.actor != 'dependabot[bot]' }}
Expand Down
12 changes: 10 additions & 2 deletions .github/workflows/codeql.yml
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,14 @@ name: "CodeQL"

on:
push:
branches-ignore:
- "gh-readonly-queue/**"
pull_request:
schedule:
- cron: '45 2 * * 2'

concurrency:
group: ${{ github.workflow }}-${{ github.ref || github.run_id }}
cancel-in-progress: true
jobs:
analyze:
name: Analyze
Expand Down Expand Up @@ -37,6 +41,8 @@ jobs:
&& sudo apt-get update \
&& sudo apt-get -y install cuda-cudart-dev-12-2 cuda-nvcc-12-2
python -m pip install tensorflow
wget https://download.pytorch.org/libtorch/cpu/libtorch-cxx11-abi-shared-with-deps-2.1.2%2Bcpu.zip -O libtorch.zip
unzip libtorch.zip
env:
DEBIAN_FRONTEND: noninteractive
# Initializes the CodeQL tools for scanning.
Expand All @@ -46,7 +52,9 @@ jobs:
languages: ${{ matrix.language }}
queries: security-extended,security-and-quality
- name: "Run, Build Application using script"
run: source/install/build_cc.sh
run: |
export CMAKE_PREFIX_PATH=$GITHUB_WORKSPACE/libtorch
source/install/build_cc.sh
env:
DP_VARIANT: cuda
DOWNLOAD_TENSORFLOW: "FALSE"
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/labeler.yml
Original file line number Diff line number Diff line change
Expand Up @@ -11,4 +11,4 @@ jobs:
steps:
- uses: actions/labeler@v5
with:
repo-token: "${{ secrets.GITHUB_TOKEN }}"
repo-token: "${{ secrets.GITHUB_TOKEN }}"
13 changes: 11 additions & 2 deletions .github/workflows/package_c.yml
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,15 @@ name: Build C library

on:
push:
branches-ignore:
- "gh-readonly-queue/**"
tags:
- "v*"
pull_request:

merge_group:
concurrency:
group: ${{ github.workflow }}-${{ github.ref || github.run_id }}
cancel-in-progress: true
jobs:
build_c:
name: Build C library
Expand All @@ -19,6 +26,8 @@ jobs:
filename: libdeepmd_c_cu11.tar.gz
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Package C library
run: ./source/install/docker_package_c.sh
env:
Expand All @@ -35,7 +44,7 @@ jobs:
- name: Test C library
run: ./source/install/docker_test_package_c.sh
- name: Release
uses: softprops/action-gh-release@v1
uses: softprops/action-gh-release@v2
if: startsWith(github.ref, 'refs/tags/')
with:
files: ${{ matrix.filename }}
Expand Down
37 changes: 30 additions & 7 deletions .github/workflows/test_cc.yml
Original file line number Diff line number Diff line change
@@ -1,11 +1,20 @@
on:
push:
branches-ignore:
- "gh-readonly-queue/**"
pull_request:
merge_group:
concurrency:
group: ${{ github.workflow }}-${{ github.ref || github.run_id }}
cancel-in-progress: true
name: Test C++
jobs:
testcc:
name: Test C++
runs-on: ubuntu-latest
strategy:
matrix:
check_memleak: [true, false]
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
Expand All @@ -18,39 +27,53 @@ jobs:
mpi: mpich
- uses: lukka/get-cmake@latest
- run: python -m pip install tensorflow
- run: source/install/test_cc_local.sh
- name: Download libtorch
run: |
wget https://download.pytorch.org/libtorch/cpu/libtorch-cxx11-abi-shared-with-deps-2.1.2%2Bcpu.zip -O libtorch.zip
unzip libtorch.zip
# https://github.com/actions/runner-images/issues/9491
- name: Fix kernel mmap rnd bits
run: sudo sysctl vm.mmap_rnd_bits=28
if: ${{ matrix.check_memleak }}
- run: |
export CMAKE_PREFIX_PATH=$GITHUB_WORKSPACE/libtorch
source/install/test_cc_local.sh
env:
OMP_NUM_THREADS: 1
TF_INTRA_OP_PARALLELISM_THREADS: 1
TF_INTER_OP_PARALLELISM_THREADS: 1
LMP_CXX11_ABI_0: 1
CMAKE_GENERATOR: Ninja
CXXFLAGS: ${{ matrix.check_memleak && '-fsanitize=leak' || '' }}
# test lammps
# ASE issue: https://gitlab.com/ase/ase/-/merge_requests/2843
# TODO: remove ase version when ase has new release
- run: |
python -m pip install -U pip
python -m pip install -e .[cpu,test,lmp] "ase @ https://gitlab.com/ase/ase/-/archive/8c5aa5fd6448c5cfb517a014dccf2b214a9dfa8f/ase-8c5aa5fd6448c5cfb517a014dccf2b214a9dfa8f.tar.gz"
python -m pip install -e .[cpu,test,lmp] mpi4py "ase @ https://gitlab.com/ase/ase/-/archive/8c5aa5fd6448c5cfb517a014dccf2b214a9dfa8f/ase-8c5aa5fd6448c5cfb517a014dccf2b214a9dfa8f.tar.gz"
env:
DP_BUILD_TESTING: 1
if: ${{ !matrix.check_memleak }}
- run: pytest --cov=deepmd source/lmp/tests
env:
OMP_NUM_THREADS: 1
TF_INTRA_OP_PARALLELISM_THREADS: 1
TF_INTER_OP_PARALLELISM_THREADS: 1
LAMMPS_PLUGIN_PATH: ${{ github.workspace }}/dp_test/lib/deepmd_lmp
LD_LIBRARY_PATH: ${{ github.workspace }}/dp_test/lib
LD_LIBRARY_PATH: ${{ github.workspace }}/dp_test/lib:${{ github.workspace }}/libtorch/lib
if: ${{ !matrix.check_memleak }}
# test ipi
- run: pytest --cov=deepmd source/ipi/tests
env:
OMP_NUM_THREADS: 1
TF_INTRA_OP_PARALLELISM_THREADS: 1
TF_INTER_OP_PARALLELISM_THREADS: 1
PATH: ${{ github.workspace }}/dp_test/bin:$PATH
LD_LIBRARY_PATH: ${{ github.workspace }}/dp_test/lib
- uses: codecov/codecov-action@v3
with:
gcov: true
LD_LIBRARY_PATH: ${{ github.workspace }}/dp_test/lib:${{ github.workspace }}/libtorch/lib
if: ${{ !matrix.check_memleak }}
- uses: codecov/codecov-action@v4
env:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
pass:
name: Pass testing C++
needs: [testcc]
Expand Down