-
Notifications
You must be signed in to change notification settings - Fork 109
[Refactor] Better tensorclass method registration #797
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
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
| Name | Max | Mean | Ops | Ops on Repo HEAD
|
Change |
|---|---|---|---|---|---|
| test_plain_set_nested | 44.1320μs | 16.7652μs | 59.6475 KOps/s | 61.4691 KOps/s | |
| test_plain_set_stack_nested | 43.0300μs | 16.5447μs | 60.4423 KOps/s | 60.6696 KOps/s | |
| test_plain_set_nested_inplace | 49.6020μs | 19.1879μs | 52.1160 KOps/s | 53.3673 KOps/s | |
| test_plain_set_stack_nested_inplace | 53.9320μs | 18.9011μs | 52.9069 KOps/s | 53.8843 KOps/s | |
| test_items | 18.3750μs | 2.5436μs | 393.1374 KOps/s | 387.3747 KOps/s | |
| test_items_nested | 1.0885ms | 0.2691ms | 3.7159 KOps/s | 3.8128 KOps/s | |
| test_items_nested_locked | 0.4015ms | 0.2701ms | 3.7019 KOps/s | 3.7738 KOps/s | |
| test_items_nested_leaf | 0.1524ms | 77.4573μs | 12.9103 KOps/s | 12.9852 KOps/s | |
| test_items_stack_nested | 0.5052ms | 0.2673ms | 3.7409 KOps/s | 3.8105 KOps/s | |
| test_items_stack_nested_leaf | 0.1529ms | 80.0698μs | 12.4891 KOps/s | 12.9384 KOps/s | |
| test_items_stack_nested_locked | 0.7963ms | 0.2741ms | 3.6482 KOps/s | 3.7968 KOps/s | |
| test_keys | 19.3660μs | 3.9001μs | 256.4022 KOps/s | 251.6913 KOps/s | |
| test_keys_nested | 0.2628ms | 0.1382ms | 7.2356 KOps/s | 7.2589 KOps/s | |
| test_keys_nested_locked | 0.6481ms | 0.1425ms | 7.0194 KOps/s | 7.0246 KOps/s | |
| test_keys_nested_leaf | 0.2043ms | 0.1174ms | 8.5185 KOps/s | 8.4624 KOps/s | |
| test_keys_stack_nested | 0.2802ms | 0.1393ms | 7.1800 KOps/s | 7.1966 KOps/s | |
| test_keys_stack_nested_leaf | 0.2336ms | 0.1177ms | 8.4943 KOps/s | 8.4763 KOps/s | |
| test_keys_stack_nested_locked | 0.2641ms | 0.1435ms | 6.9680 KOps/s | 6.9508 KOps/s | |
| test_values | 6.0138μs | 1.1483μs | 870.8308 KOps/s | 818.4541 KOps/s | |
| test_values_nested | 91.2110μs | 50.2567μs | 19.8978 KOps/s | 19.8690 KOps/s | |
| test_values_nested_locked | 0.1053ms | 50.5447μs | 19.7845 KOps/s | 19.9460 KOps/s | |
| test_values_nested_leaf | 96.2300μs | 45.5789μs | 21.9400 KOps/s | 21.9482 KOps/s | |
| test_values_stack_nested | 0.1007ms | 51.8968μs | 19.2690 KOps/s | 20.0977 KOps/s | |
| test_values_stack_nested_leaf | 95.4980μs | 45.9151μs | 21.7793 KOps/s | 21.8527 KOps/s | |
| test_values_stack_nested_locked | 95.0280μs | 51.6078μs | 19.3769 KOps/s | 19.8601 KOps/s | |
| test_membership | 15.0080μs | 1.3431μs | 744.5626 KOps/s | 744.0545 KOps/s | |
| test_membership_nested | 17.9140μs | 3.5168μs | 284.3517 KOps/s | 295.5401 KOps/s | |
| test_membership_nested_leaf | 20.8290μs | 3.5832μs | 279.0795 KOps/s | 280.0145 KOps/s | |
| test_membership_stacked_nested | 22.2520μs | 3.4892μs | 286.5987 KOps/s | 294.4006 KOps/s | |
| test_membership_stacked_nested_leaf | 22.6520μs | 3.4658μs | 288.5336 KOps/s | 293.5681 KOps/s | |
| test_membership_nested_last | 30.9180μs | 4.3162μs | 231.6862 KOps/s | 241.5682 KOps/s | |
| test_membership_nested_leaf_last | 23.8840μs | 4.3018μs | 232.4623 KOps/s | 242.9366 KOps/s | |
| test_membership_stacked_nested_last | 33.9940μs | 5.7825μs | 172.9347 KOps/s | 242.8784 KOps/s | |
| test_membership_stacked_nested_leaf_last | 23.5440μs | 5.8812μs | 170.0323 KOps/s | 243.5353 KOps/s | |
| test_nested_getleaf | 32.5110μs | 10.6537μs | 93.8638 KOps/s | 92.6227 KOps/s | |
| test_nested_get | 35.8370μs | 10.2200μs | 97.8476 KOps/s | 98.2020 KOps/s | |
| test_stacked_getleaf | 27.8720μs | 10.6434μs | 93.9547 KOps/s | 92.9409 KOps/s | |
| test_stacked_get | 20.2580μs | 10.0385μs | 99.6165 KOps/s | 98.0361 KOps/s | |
| test_nested_getitemleaf | 43.6680μs | 11.1511μs | 89.6776 KOps/s | 88.4132 KOps/s | |
| test_nested_getitem | 25.1870μs | 10.3495μs | 96.6227 KOps/s | 96.0898 KOps/s | |
| test_stacked_getitemleaf | 25.4570μs | 11.1914μs | 89.3547 KOps/s | 90.5262 KOps/s | |
| test_stacked_getitem | 33.5730μs | 10.2357μs | 97.6971 KOps/s | 98.0340 KOps/s | |
| test_lock_nested | 0.6816ms | 0.3485ms | 2.8692 KOps/s | 2.9256 KOps/s | |
| test_lock_stack_nested | 0.5328ms | 0.3138ms | 3.1864 KOps/s | 3.2275 KOps/s | |
| test_unlock_nested | 0.9293ms | 0.3573ms | 2.7987 KOps/s | 2.5726 KOps/s | |
| test_unlock_stack_nested | 0.6217ms | 0.3213ms | 3.1125 KOps/s | 3.1510 KOps/s | |
| test_flatten_speed | 0.3448ms | 96.7528μs | 10.3356 KOps/s | 10.3336 KOps/s | |
| test_unflatten_speed | 0.7057ms | 0.4078ms | 2.4524 KOps/s | 2.4795 KOps/s | |
| test_common_ops | 4.0358ms | 0.6965ms | 1.4357 KOps/s | 1.4552 KOps/s | |
| test_creation | 26.1990μs | 1.9127μs | 522.8182 KOps/s | 514.1379 KOps/s | |
| test_creation_empty | 28.5740μs | 9.8900μs | 101.1123 KOps/s | 100.7474 KOps/s | |
| test_creation_nested_1 | 49.6230μs | 12.7092μs | 78.6830 KOps/s | 79.4151 KOps/s | |
| test_creation_nested_2 | 35.7070μs | 16.0795μs | 62.1911 KOps/s | 62.2784 KOps/s | |
| test_clone | 73.6280μs | 13.4545μs | 74.3247 KOps/s | 74.9540 KOps/s | |
| test_getitem[int] | 36.2780μs | 11.4835μs | 87.0817 KOps/s | 86.8931 KOps/s | |
| test_getitem[slice_int] | 66.6050μs | 22.9630μs | 43.5483 KOps/s | 42.0833 KOps/s | |
| test_getitem[range] | 77.7660μs | 57.2976μs | 17.4527 KOps/s | 16.8295 KOps/s | |
| test_getitem[tuple] | 59.7020μs | 19.7231μs | 50.7020 KOps/s | 51.9775 KOps/s | |
| test_getitem[list] | 0.1059ms | 40.8388μs | 24.4865 KOps/s | 24.0319 KOps/s | |
| test_setitem_dim[int] | 66.7550μs | 35.6034μs | 28.0872 KOps/s | 29.7710 KOps/s | |
| test_setitem_dim[slice_int] | 0.1027ms | 62.9878μs | 15.8761 KOps/s | 16.0771 KOps/s | |
| test_setitem_dim[range] | 0.1307ms | 83.8469μs | 11.9265 KOps/s | 12.1799 KOps/s | |
| test_setitem_dim[tuple] | 0.1189ms | 50.5703μs | 19.7745 KOps/s | 20.4713 KOps/s | |
| test_setitem | 56.8670μs | 19.7756μs | 50.5674 KOps/s | 50.5479 KOps/s | |
| test_set | 49.5530μs | 19.0577μs | 52.4721 KOps/s | 50.9622 KOps/s | |
| test_set_shared | 2.6661ms | 0.1414ms | 7.0712 KOps/s | 7.1840 KOps/s | |
| test_update | 77.0340μs | 20.9307μs | 47.7768 KOps/s | 47.7072 KOps/s | |
| test_update_nested | 76.9850μs | 28.8386μs | 34.6757 KOps/s | 34.5372 KOps/s | |
| test_update__nested | 60.4130μs | 25.2887μs | 39.5433 KOps/s | 39.9791 KOps/s | |
| test_set_nested | 62.9480μs | 21.1355μs | 47.3139 KOps/s | 46.9328 KOps/s | |
| test_set_nested_new | 58.9810μs | 25.2525μs | 39.6000 KOps/s | 39.4866 KOps/s | |
| test_select | 81.7430μs | 40.3673μs | 24.7725 KOps/s | 25.0370 KOps/s | |
| test_select_nested | 0.1308ms | 60.8814μs | 16.4254 KOps/s | 16.4094 KOps/s | |
| test_exclude_nested | 0.2702ms | 0.1213ms | 8.2430 KOps/s | 8.1986 KOps/s | |
| test_empty[True] | 0.7525ms | 0.3983ms | 2.5104 KOps/s | 2.5136 KOps/s | |
| test_empty[False] | 4.1418μs | 1.1887μs | 841.2773 KOps/s | 873.5114 KOps/s | |
| test_unbind_speed | 3.4174ms | 0.2726ms | 3.6682 KOps/s | 3.8493 KOps/s | |
| test_unbind_speed_stack0 | 0.3678ms | 0.2567ms | 3.8957 KOps/s | 3.8760 KOps/s | |
| test_unbind_speed_stack1 | 62.5680ms | 0.7236ms | 1.3819 KOps/s | 1.3378 KOps/s | |
| test_split | 59.6428ms | 1.5878ms | 629.7969 Ops/s | 624.8229 Ops/s | |
| test_chunk | 56.5745ms | 1.5667ms | 638.2924 Ops/s | 659.6247 Ops/s | |
| test_creation[device0] | 3.6700ms | 85.5930μs | 11.6832 KOps/s | 12.1644 KOps/s | |
| test_creation_from_tensor | 0.1648ms | 85.2154μs | 11.7350 KOps/s | 11.9185 KOps/s | |
| test_add_one[memmap_tensor0] | 84.8690μs | 5.4706μs | 182.7959 KOps/s | 178.2763 KOps/s | |
| test_contiguous[memmap_tensor0] | 29.3250μs | 0.6565μs | 1.5233 MOps/s | 1.5695 MOps/s | |
| test_stack[memmap_tensor0] | 23.5440μs | 3.5663μs | 280.4065 KOps/s | 274.8538 KOps/s | |
| test_memmaptd_index | 0.9866ms | 0.2585ms | 3.8688 KOps/s | 3.7893 KOps/s | |
| test_memmaptd_index_astensor | 0.6891ms | 0.3320ms | 3.0125 KOps/s | 2.9676 KOps/s | |
| test_memmaptd_index_op | 1.1962ms | 0.6077ms | 1.6455 KOps/s | 1.5438 KOps/s | |
| test_serialize_model | 0.1737s | 0.1153s | 8.6701 Ops/s | 8.5117 Ops/s | |
| test_serialize_model_pickle | 0.4481s | 0.3766s | 2.6556 Ops/s | 2.6199 Ops/s | |
| test_serialize_weights | 0.1737s | 0.1102s | 9.0720 Ops/s | 8.9790 Ops/s | |
| test_serialize_weights_returnearly | 0.3214s | 0.1541s | 6.4894 Ops/s | 6.9782 Ops/s | |
| test_serialize_weights_pickle | 0.7082s | 0.4920s | 2.0323 Ops/s | 2.4031 Ops/s | |
| test_serialize_weights_filesystem | 0.1044s | 94.3392ms | 10.6000 Ops/s | 10.5014 Ops/s | |
| test_serialize_model_filesystem | 0.1021s | 93.5676ms | 10.6875 Ops/s | 9.9600 Ops/s | |
| test_reshape_pytree | 67.7870μs | 25.3941μs | 39.3793 KOps/s | 39.1986 KOps/s | |
| test_reshape_td | 90.4090μs | 34.4526μs | 29.0254 KOps/s | 29.6171 KOps/s | |
| test_view_pytree | 57.6180μs | 25.2283μs | 39.6381 KOps/s | 39.4586 KOps/s | |
| test_view_td | 69.1490μs | 38.5725μs | 25.9252 KOps/s | 26.3484 KOps/s | |
| test_unbind_pytree | 70.2910μs | 28.8350μs | 34.6801 KOps/s | 34.1596 KOps/s | |
| test_unbind_td | 0.3797ms | 38.3624μs | 26.0672 KOps/s | 26.3818 KOps/s | |
| test_split_pytree | 80.1000μs | 29.3958μs | 34.0184 KOps/s | 33.8930 KOps/s | |
| test_split_td | 0.1227ms | 40.1686μs | 24.8950 KOps/s | 24.2327 KOps/s | |
| test_add_pytree | 88.0650μs | 34.7524μs | 28.7750 KOps/s | 28.5845 KOps/s | |
| test_add_td | 0.1119ms | 55.4080μs | 18.0479 KOps/s | 19.5164 KOps/s | |
| test_distributed | 0.1962ms | 0.1007ms | 9.9277 KOps/s | 9.8344 KOps/s | |
| test_tdmodule | 46.2460μs | 16.9926μs | 58.8492 KOps/s | 56.8500 KOps/s | |
| test_tdmodule_dispatch | 65.5030μs | 33.7970μs | 29.5884 KOps/s | 28.9074 KOps/s | |
| test_tdseq | 33.5930μs | 19.7445μs | 50.6471 KOps/s | 48.6522 KOps/s | |
| test_tdseq_dispatch | 60.4830μs | 38.5603μs | 25.9334 KOps/s | 24.4876 KOps/s | |
| test_instantiation_functorch | 2.5545ms | 1.3308ms | 751.4108 Ops/s | 757.1752 Ops/s | |
| test_instantiation_td | 73.1935ms | 1.0915ms | 916.1823 Ops/s | 995.8908 Ops/s | |
| test_exec_functorch | 0.2375ms | 0.1604ms | 6.2348 KOps/s | 5.9474 KOps/s | |
| test_exec_functional_call | 0.2983ms | 0.1510ms | 6.6215 KOps/s | 6.5945 KOps/s | |
| test_exec_td | 0.2321ms | 0.1462ms | 6.8394 KOps/s | 6.7392 KOps/s | |
| test_exec_td_decorator | 0.3809ms | 0.2221ms | 4.5033 KOps/s | 4.4504 KOps/s | |
| test_vmap_mlp_speed[True-True] | 0.7749ms | 0.4880ms | 2.0490 KOps/s | 2.0670 KOps/s | |
| test_vmap_mlp_speed[True-False] | 0.7039ms | 0.4838ms | 2.0670 KOps/s | 2.0871 KOps/s | |
| test_vmap_mlp_speed[False-True] | 0.5622ms | 0.3940ms | 2.5378 KOps/s | 2.5352 KOps/s | |
| test_vmap_mlp_speed[False-False] | 0.5975ms | 0.3943ms | 2.5363 KOps/s | 2.5365 KOps/s | |
| test_vmap_mlp_speed_decorator[True-True] | 0.9593ms | 0.5523ms | 1.8106 KOps/s | 1.8164 KOps/s | |
| test_vmap_mlp_speed_decorator[True-False] | 0.9354ms | 0.5738ms | 1.7428 KOps/s | 1.8250 KOps/s | |
| test_vmap_mlp_speed_decorator[False-True] | 0.8873ms | 0.4589ms | 2.1792 KOps/s | 2.1961 KOps/s | |
| test_vmap_mlp_speed_decorator[False-False] | 0.6901ms | 0.4554ms | 2.1960 KOps/s | 2.2019 KOps/s | |
| test_to_module_speed[True] | 1.8689ms | 1.7025ms | 587.3741 Ops/s | 584.5937 Ops/s | |
| test_to_module_speed[False] | 2.5660ms | 1.6859ms | 593.1577 Ops/s | 601.0722 Ops/s | |
| test_tc_init | 52.9490μs | 26.5397μs | 37.6793 KOps/s | 37.2392 KOps/s | |
| test_tc_init_nested | 0.1120ms | 52.2427μs | 19.1414 KOps/s | 18.7000 KOps/s | |
| test_tc_first_layer_tensor | 5.1754μs | 0.7022μs | 1.4241 MOps/s | 1.4533 MOps/s | |
| test_tc_first_layer_nontensor | 1.9276μs | 0.6688μs | 1.4953 MOps/s | 1.4674 MOps/s | |
| test_tc_second_layer_tensor | 18.5950μs | 1.8091μs | 552.7517 KOps/s | 539.3521 KOps/s | |
| test_tc_second_layer_nontensor | 8.9033μs | 1.5126μs | 661.1289 KOps/s | 653.0910 KOps/s | |
| test_unbind | 86.0813ms | 5.8837ms | 169.9615 Ops/s | 163.0798 Ops/s | |
| test_full_like | 17.0749ms | 11.8955ms | 84.0651 Ops/s | 82.6947 Ops/s | |
| test_zeros_like | 6.4823ms | 5.7961ms | 172.5286 Ops/s | 164.5671 Ops/s | |
| test_ones_like | 13.4612ms | 6.2732ms | 159.4094 Ops/s | 153.3158 Ops/s | |
| test_clone | 12.8424ms | 7.8200ms | 127.8776 Ops/s | 124.0067 Ops/s | |
| test_squeeze | 59.1710μs | 14.0262μs | 71.2950 KOps/s | 71.4190 KOps/s | |
| test_unsqueeze | 0.1139ms | 59.3768μs | 16.8416 KOps/s | 14.5029 KOps/s | |
| test_split | 0.2023ms | 0.1119ms | 8.9378 KOps/s | 8.6619 KOps/s | |
| test_permute | 0.2381ms | 0.1262ms | 7.9212 KOps/s | 7.2841 KOps/s | |
| test_stack | 30.2448ms | 22.7772ms | 43.9036 Ops/s | 44.7675 Ops/s | |
| test_cat | 25.3157ms | 22.7583ms | 43.9400 Ops/s | 44.6924 Ops/s |
|
| Name | Max | Mean | Ops | Ops on Repo HEAD
|
Change |
|---|---|---|---|---|---|
| test_plain_set_nested | 0.5825ms | 13.0076μs | 76.8780 KOps/s | 76.9641 KOps/s | |
| test_plain_set_stack_nested | 32.3610μs | 13.2734μs | 75.3384 KOps/s | 76.5092 KOps/s | |
| test_plain_set_nested_inplace | 29.4600μs | 14.3970μs | 69.4590 KOps/s | 69.6289 KOps/s | |
| test_plain_set_stack_nested_inplace | 38.8910μs | 14.5948μs | 68.5176 KOps/s | 69.2705 KOps/s | |
| test_items | 19.4700μs | 4.7167μs | 212.0122 KOps/s | 210.8419 KOps/s | |
| test_items_nested | 0.3939ms | 0.3375ms | 2.9629 KOps/s | 2.9435 KOps/s | |
| test_items_nested_locked | 0.4808ms | 0.3515ms | 2.8453 KOps/s | 2.8840 KOps/s | |
| test_items_nested_leaf | 0.1110ms | 83.6290μs | 11.9576 KOps/s | 12.0547 KOps/s | |
| test_items_stack_nested | 0.3699ms | 0.3468ms | 2.8833 KOps/s | 2.8376 KOps/s | |
| test_items_stack_nested_leaf | 98.0810μs | 82.7369μs | 12.0865 KOps/s | 11.9675 KOps/s | |
| test_items_stack_nested_locked | 0.3812ms | 0.3392ms | 2.9479 KOps/s | 2.9274 KOps/s | |
| test_keys | 20.6110μs | 4.3294μs | 230.9777 KOps/s | 230.5274 KOps/s | |
| test_keys_nested | 95.2320μs | 67.4206μs | 14.8323 KOps/s | 14.9410 KOps/s | |
| test_keys_nested_locked | 2.0116ms | 72.6748μs | 13.7599 KOps/s | 13.8701 KOps/s | |
| test_keys_nested_leaf | 78.9910μs | 58.1537μs | 17.1958 KOps/s | 17.3146 KOps/s | |
| test_keys_stack_nested | 91.7610μs | 66.6144μs | 15.0118 KOps/s | 14.8760 KOps/s | |
| test_keys_stack_nested_leaf | 73.1110μs | 57.4342μs | 17.4112 KOps/s | 17.2299 KOps/s | |
| test_keys_stack_nested_locked | 88.3920μs | 71.1999μs | 14.0450 KOps/s | 13.8859 KOps/s | |
| test_values | 7.6070μs | 1.8332μs | 545.4895 KOps/s | 553.2704 KOps/s | |
| test_values_nested | 53.7510μs | 35.3119μs | 28.3190 KOps/s | 28.2085 KOps/s | |
| test_values_nested_locked | 61.0010μs | 37.5157μs | 26.6555 KOps/s | 26.8939 KOps/s | |
| test_values_nested_leaf | 47.8810μs | 31.3986μs | 31.8486 KOps/s | 31.8063 KOps/s | |
| test_values_stack_nested | 57.1610μs | 36.0311μs | 27.7538 KOps/s | 27.6346 KOps/s | |
| test_values_stack_nested_leaf | 48.2500μs | 32.1154μs | 31.1377 KOps/s | 30.6582 KOps/s | |
| test_values_stack_nested_locked | 61.2610μs | 38.0893μs | 26.2541 KOps/s | 26.3778 KOps/s | |
| test_membership | 2.7571μs | 0.7253μs | 1.3788 MOps/s | 1.3618 MOps/s | |
| test_membership_nested | 20.8700μs | 2.6002μs | 384.5879 KOps/s | 390.7616 KOps/s | |
| test_membership_nested_leaf | 21.7300μs | 2.6263μs | 380.7599 KOps/s | 391.4864 KOps/s | |
| test_membership_stacked_nested | 15.3800μs | 2.6207μs | 381.5842 KOps/s | 385.0058 KOps/s | |
| test_membership_stacked_nested_leaf | 15.0200μs | 2.6198μs | 381.7069 KOps/s | 386.1655 KOps/s | |
| test_membership_nested_last | 16.8800μs | 3.1338μs | 319.0982 KOps/s | 321.8878 KOps/s | |
| test_membership_nested_leaf_last | 26.5500μs | 3.1104μs | 321.5062 KOps/s | 321.6208 KOps/s | |
| test_membership_stacked_nested_last | 30.0110μs | 9.8385μs | 101.6416 KOps/s | 318.6476 KOps/s | |
| test_membership_stacked_nested_leaf_last | 22.8300μs | 9.8704μs | 101.3134 KOps/s | 319.7340 KOps/s | |
| test_nested_getleaf | 33.9900μs | 8.3711μs | 119.4581 KOps/s | 118.2376 KOps/s | |
| test_nested_get | 23.0800μs | 7.8631μs | 127.1764 KOps/s | 126.1773 KOps/s | |
| test_stacked_getleaf | 36.6910μs | 8.4137μs | 118.8535 KOps/s | 118.0965 KOps/s | |
| test_stacked_get | 30.1510μs | 7.9462μs | 125.8469 KOps/s | 125.3852 KOps/s | |
| test_nested_getitemleaf | 25.6910μs | 8.5305μs | 117.2263 KOps/s | 116.0903 KOps/s | |
| test_nested_getitem | 22.6000μs | 8.0177μs | 124.7242 KOps/s | 123.9708 KOps/s | |
| test_stacked_getitemleaf | 26.8700μs | 8.5550μs | 116.8901 KOps/s | 116.0661 KOps/s | |
| test_stacked_getitem | 25.4510μs | 8.0468μs | 124.2731 KOps/s | 122.1749 KOps/s | |
| test_lock_nested | 59.0151ms | 0.4160ms | 2.4041 KOps/s | 2.4094 KOps/s | |
| test_lock_stack_nested | 0.3294ms | 0.3049ms | 3.2801 KOps/s | 3.2315 KOps/s | |
| test_unlock_nested | 60.5371ms | 0.4145ms | 2.4128 KOps/s | 2.7942 KOps/s | |
| test_unlock_stack_nested | 0.3389ms | 0.3135ms | 3.1899 KOps/s | 3.1641 KOps/s | |
| test_flatten_speed | 0.1860ms | 0.1033ms | 9.6788 KOps/s | 9.8646 KOps/s | |
| test_unflatten_speed | 0.3334ms | 0.2933ms | 3.4098 KOps/s | 3.4321 KOps/s | |
| test_common_ops | 1.0754ms | 0.5854ms | 1.7082 KOps/s | 1.6860 KOps/s | |
| test_creation | 33.5710μs | 1.6420μs | 608.9989 KOps/s | 605.2293 KOps/s | |
| test_creation_empty | 24.9110μs | 9.0564μs | 110.4187 KOps/s | 111.1586 KOps/s | |
| test_creation_nested_1 | 32.1610μs | 10.8571μs | 92.1053 KOps/s | 92.3290 KOps/s | |
| test_creation_nested_2 | 28.6900μs | 12.9346μs | 77.3121 KOps/s | 76.9277 KOps/s | |
| test_clone | 85.1710μs | 11.5331μs | 86.7067 KOps/s | 85.2932 KOps/s | |
| test_getitem[int] | 25.2900μs | 10.9613μs | 91.2303 KOps/s | 89.9237 KOps/s | |
| test_getitem[slice_int] | 50.1910μs | 20.7892μs | 48.1020 KOps/s | 47.1856 KOps/s | |
| test_getitem[range] | 76.3110μs | 50.1128μs | 19.9550 KOps/s | 20.9948 KOps/s | |
| test_getitem[tuple] | 59.9510μs | 18.8582μs | 53.0274 KOps/s | 52.3171 KOps/s | |
| test_getitem[list] | 0.1350ms | 33.8991μs | 29.4993 KOps/s | 29.3417 KOps/s | |
| test_setitem_dim[int] | 50.3510μs | 30.1259μs | 33.1941 KOps/s | 33.1275 KOps/s | |
| test_setitem_dim[slice_int] | 72.9510μs | 51.1044μs | 19.5678 KOps/s | 19.7113 KOps/s | |
| test_setitem_dim[range] | 89.6210μs | 68.2906μs | 14.6433 KOps/s | 14.8306 KOps/s | |
| test_setitem_dim[tuple] | 61.8110μs | 44.5115μs | 22.4661 KOps/s | 22.7664 KOps/s | |
| test_setitem | 51.9010μs | 16.5498μs | 60.4235 KOps/s | 60.1745 KOps/s | |
| test_set | 42.3510μs | 16.1427μs | 61.9477 KOps/s | 61.6930 KOps/s | |
| test_set_shared | 1.5046ms | 96.9360μs | 10.3161 KOps/s | 10.2055 KOps/s | |
| test_update | 0.1006ms | 18.5000μs | 54.0540 KOps/s | 54.4449 KOps/s | |
| test_update_nested | 66.1610μs | 24.3275μs | 41.1057 KOps/s | 42.4524 KOps/s | |
| test_update__nested | 48.9610μs | 22.8245μs | 43.8126 KOps/s | 44.2078 KOps/s | |
| test_set_nested | 71.5710μs | 17.1034μs | 58.4680 KOps/s | 59.3113 KOps/s | |
| test_set_nested_new | 67.4710μs | 20.2817μs | 49.3056 KOps/s | 49.8916 KOps/s | |
| test_select | 67.3510μs | 31.9560μs | 31.2930 KOps/s | 30.6364 KOps/s | |
| test_select_nested | 0.8348ms | 54.5683μs | 18.3256 KOps/s | 18.2831 KOps/s | |
| test_exclude_nested | 0.1295ms | 0.1115ms | 8.9690 KOps/s | 9.1130 KOps/s | |
| test_empty[True] | 0.4216ms | 0.3553ms | 2.8148 KOps/s | 2.8679 KOps/s | |
| test_empty[False] | 3.0150μs | 0.9183μs | 1.0890 MOps/s | 1.0859 MOps/s | |
| test_to | 0.1026ms | 78.0336μs | 12.8150 KOps/s | 13.1616 KOps/s | |
| test_to_nonblocking | 91.9510μs | 61.6463μs | 16.2216 KOps/s | 16.8854 KOps/s | |
| test_unbind_speed | 1.5608ms | 0.2710ms | 3.6902 KOps/s | 3.7042 KOps/s | |
| test_unbind_speed_stack0 | 0.2924ms | 0.2715ms | 3.6829 KOps/s | 3.6705 KOps/s | |
| test_unbind_speed_stack1 | 76.0381ms | 0.8079ms | 1.2377 KOps/s | 1.2156 KOps/s | |
| test_split | 76.7739ms | 1.7076ms | 585.6132 Ops/s | 578.2267 Ops/s | |
| test_chunk | 76.6379ms | 1.7028ms | 587.2637 Ops/s | 578.1654 Ops/s | |
| test_creation[device0] | 0.1299ms | 57.9454μs | 17.2576 KOps/s | 17.2107 KOps/s | |
| test_creation_from_tensor | 0.1308ms | 55.0041μs | 18.1805 KOps/s | 18.3874 KOps/s | |
| test_add_one[memmap_tensor0] | 96.1310μs | 7.0755μs | 141.3334 KOps/s | 135.5242 KOps/s | |
| test_contiguous[memmap_tensor0] | 23.1200μs | 0.6621μs | 1.5104 MOps/s | 1.5174 MOps/s | |
| test_stack[memmap_tensor0] | 28.7000μs | 4.6646μs | 214.3803 KOps/s | 209.3450 KOps/s | |
| test_memmaptd_index | 0.5039ms | 0.2882ms | 3.4701 KOps/s | 3.4758 KOps/s | |
| test_memmaptd_index_astensor | 0.6449ms | 0.3575ms | 2.7970 KOps/s | 2.7638 KOps/s | |
| test_memmaptd_index_op | 1.0959ms | 0.6611ms | 1.5127 KOps/s | 1.4946 KOps/s | |
| test_serialize_model | 0.1871s | 0.1122s | 8.9122 Ops/s | 8.6300 Ops/s | |
| test_serialize_model_pickle | 1.3659s | 1.2376s | 0.8080 Ops/s | 0.8062 Ops/s | |
| test_serialize_weights | 0.1833s | 0.1094s | 9.1388 Ops/s | 8.7925 Ops/s | |
| test_serialize_weights_returnearly | 0.2397s | 97.3281ms | 10.2745 Ops/s | 10.1937 Ops/s | |
| test_serialize_weights_pickle | 1.3554s | 1.2485s | 0.8010 Ops/s | 0.8010 Ops/s | |
| test_reshape_pytree | 51.4620μs | 26.0867μs | 38.3337 KOps/s | 38.0298 KOps/s | |
| test_reshape_td | 77.3710μs | 30.8264μs | 32.4398 KOps/s | 32.0154 KOps/s | |
| test_view_pytree | 57.3410μs | 25.8712μs | 38.6530 KOps/s | 38.5554 KOps/s | |
| test_view_td | 62.6810μs | 35.9471μs | 27.8186 KOps/s | 27.8752 KOps/s | |
| test_unbind_pytree | 54.7510μs | 32.9106μs | 30.3853 KOps/s | 29.9151 KOps/s | |
| test_unbind_td | 0.4235ms | 41.8938μs | 23.8699 KOps/s | 23.7673 KOps/s | |
| test_split_pytree | 63.8810μs | 34.6467μs | 28.8628 KOps/s | 28.2941 KOps/s | |
| test_split_td | 0.1060ms | 39.3370μs | 25.4213 KOps/s | 25.2176 KOps/s | |
| test_add_pytree | 65.2110μs | 38.2303μs | 26.1572 KOps/s | 25.7390 KOps/s | |
| test_add_td | 72.9310μs | 49.8878μs | 20.0450 KOps/s | 19.5118 KOps/s | |
| test_distributed | 0.1966ms | 65.7800μs | 15.2022 KOps/s | 11.6034 KOps/s | |
| test_tdmodule | 84.0220μs | 15.0381μs | 66.4976 KOps/s | 66.6849 KOps/s | |
| test_tdmodule_dispatch | 46.1410μs | 29.5498μs | 33.8411 KOps/s | 34.1477 KOps/s | |
| test_tdseq | 30.9700μs | 16.9521μs | 58.9896 KOps/s | 59.2318 KOps/s | |
| test_tdseq_dispatch | 47.0400μs | 32.0111μs | 31.2391 KOps/s | 30.5462 KOps/s | |
| test_instantiation_functorch | 1.9520ms | 1.5370ms | 650.6052 Ops/s | 640.9854 Ops/s | |
| test_instantiation_td | 81.2437ms | 1.1437ms | 874.3616 Ops/s | 938.9383 Ops/s | |
| test_exec_functorch | 0.1842ms | 0.1501ms | 6.6621 KOps/s | 6.4728 KOps/s | |
| test_exec_functional_call | 0.2509ms | 0.1417ms | 7.0585 KOps/s | 6.9059 KOps/s | |
| test_exec_td | 0.1747ms | 0.1399ms | 7.1497 KOps/s | 6.9850 KOps/s | |
| test_exec_td_decorator | 0.6479ms | 0.2123ms | 4.7099 KOps/s | 4.6614 KOps/s | |
| test_vmap_mlp_speed[True-True] | 0.7497ms | 0.6035ms | 1.6570 KOps/s | 1.6582 KOps/s | |
| test_vmap_mlp_speed[True-False] | 0.6519ms | 0.5997ms | 1.6675 KOps/s | 1.6665 KOps/s | |
| test_vmap_mlp_speed[False-True] | 0.5956ms | 0.5307ms | 1.8844 KOps/s | 1.8867 KOps/s | |
| test_vmap_mlp_speed[False-False] | 0.6025ms | 0.5303ms | 1.8859 KOps/s | 1.8781 KOps/s | |
| test_vmap_mlp_speed_decorator[True-True] | 1.3533ms | 0.6707ms | 1.4909 KOps/s | 1.5144 KOps/s | |
| test_vmap_mlp_speed_decorator[True-False] | 0.7825ms | 0.6646ms | 1.5046 KOps/s | 1.5136 KOps/s | |
| test_vmap_mlp_speed_decorator[False-True] | 0.9060ms | 0.6189ms | 1.6158 KOps/s | 1.7079 KOps/s | |
| test_vmap_mlp_speed_decorator[False-False] | 0.8155ms | 0.6053ms | 1.6522 KOps/s | 1.7138 KOps/s | |
| test_vmap_transformer_speed[True-True] | 8.6987ms | 8.2470ms | 121.2557 Ops/s | 123.7995 Ops/s | |
| test_vmap_transformer_speed[True-False] | 8.8854ms | 8.2474ms | 121.2507 Ops/s | 123.4044 Ops/s | |
| test_vmap_transformer_speed[False-True] | 8.4698ms | 8.1590ms | 122.5640 Ops/s | 125.0272 Ops/s | |
| test_vmap_transformer_speed[False-False] | 8.9095ms | 8.1614ms | 122.5276 Ops/s | 125.0610 Ops/s | |
| test_vmap_transformer_speed_decorator[True-True] | 20.6840ms | 19.9415ms | 50.1467 Ops/s | 50.9500 Ops/s | |
| test_vmap_transformer_speed_decorator[True-False] | 20.4687ms | 19.9899ms | 50.0254 Ops/s | 50.8977 Ops/s | |
| test_vmap_transformer_speed_decorator[False-True] | 20.4224ms | 19.8740ms | 50.3171 Ops/s | 51.1700 Ops/s | |
| test_vmap_transformer_speed_decorator[False-False] | 20.6796ms | 19.7421ms | 50.6531 Ops/s | 51.2869 Ops/s | |
| test_to_module_speed[True] | 1.6451ms | 1.5344ms | 651.7013 Ops/s | 653.9910 Ops/s | |
| test_to_module_speed[False] | 1.6093ms | 1.5136ms | 660.6983 Ops/s | 661.2643 Ops/s | |
| test_tc_init | 0.1315ms | 25.0505μs | 39.9194 KOps/s | 39.7503 KOps/s | |
| test_tc_init_nested | 73.2810μs | 49.3279μs | 20.2725 KOps/s | 18.8358 KOps/s | |
| test_tc_first_layer_tensor | 10.6600μs | 0.4879μs | 2.0495 MOps/s | 2.7766 MOps/s | |
| test_tc_first_layer_nontensor | 2.0746μs | 0.3959μs | 2.5258 MOps/s | 2.5653 MOps/s | |
| test_tc_second_layer_tensor | 7.2542μs | 0.9765μs | 1.0241 MOps/s | 1.0263 MOps/s | |
| test_tc_second_layer_nontensor | 5.4400μs | 0.8316μs | 1.2025 MOps/s | 1.2244 MOps/s | |
| test_unbind | 95.5886ms | 6.6991ms | 149.2733 Ops/s | 128.6951 Ops/s | |
| test_full_like | 11.4492ms | 11.1531ms | 89.6608 Ops/s | 73.6863 Ops/s | |
| test_zeros_like | 8.0081ms | 7.8298ms | 127.7173 Ops/s | 126.1463 Ops/s | |
| test_ones_like | 8.8425ms | 7.8393ms | 127.5624 Ops/s | 126.4298 Ops/s | |
| test_clone | 9.7730ms | 9.4861ms | 105.4171 Ops/s | 106.2923 Ops/s | |
| test_squeeze | 60.4710μs | 11.0128μs | 90.8035 KOps/s | 88.7153 KOps/s | |
| test_unsqueeze | 0.1078ms | 52.5374μs | 19.0341 KOps/s | 15.7438 KOps/s | |
| test_split | 0.1446ms | 0.1017ms | 9.8303 KOps/s | 9.7228 KOps/s | |
| test_permute | 0.1453ms | 0.1092ms | 9.1570 KOps/s | 7.9762 KOps/s | |
| test_stack | 27.7603ms | 27.4134ms | 36.4785 Ops/s | 36.5782 Ops/s | |
| test_cat | 27.9966ms | 27.3929ms | 36.5058 Ops/s | 36.6549 Ops/s |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Labels
CLA Signed
This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
enhancement
New feature or request
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.