[BugFix, CI] Fix GPU benchmarks

[vmoens]

No description provided.

[github-actions]

$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of CPU Benchmark Tests

Total Benchmarks: 120. Improved: $\large\color{#35bf28}16$. Worsened: $\large\color{#d91a1a}11$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	33.1620μs	17.4007μs	57.4690 KOps/s	59.1184 KOps/s	$\color{#d91a1a}-2.79\%$
test_plain_set_stack_nested	0.2043ms	0.1435ms	6.9700 KOps/s	6.9449 KOps/s	$\color{#35bf28}+0.36\%$
test_plain_set_nested_inplace	61.4540μs	19.5420μs	51.1720 KOps/s	51.8037 KOps/s	$\color{#d91a1a}-1.22\%$
test_plain_set_stack_nested_inplace	0.3318ms	0.1780ms	5.6182 KOps/s	5.6081 KOps/s	$\color{#35bf28}+0.18\%$
test_items	18.8950μs	2.4880μs	401.9256 KOps/s	408.1212 KOps/s	$\color{#d91a1a}-1.52\%$
test_items_nested	0.4379ms	0.2682ms	3.7281 KOps/s	3.6571 KOps/s	$\color{#35bf28}+1.94\%$
test_items_nested_locked	0.4506ms	0.2695ms	3.7110 KOps/s	3.6771 KOps/s	$\color{#35bf28}+0.92\%$
test_items_nested_leaf	0.5457ms	0.1673ms	5.9767 KOps/s	5.9699 KOps/s	$\color{#35bf28}+0.11\%$
test_items_stack_nested	1.4700ms	1.3231ms	755.8266 Ops/s	747.9916 Ops/s	$\color{#35bf28}+1.05\%$
test_items_stack_nested_leaf	1.9284ms	1.2087ms	827.3298 Ops/s	836.1607 Ops/s	$\color{#d91a1a}-1.06\%$
test_items_stack_nested_locked	1.0088ms	0.7734ms	1.2930 KOps/s	1.2977 KOps/s	$\color{#d91a1a}-0.36\%$
test_keys	37.2300μs	4.1909μs	238.6136 KOps/s	239.8858 KOps/s	$\color{#d91a1a}-0.53\%$
test_keys_nested	55.5088ms	0.1593ms	6.2762 KOps/s	6.4632 KOps/s	$\color{#d91a1a}-2.89\%$
test_keys_nested_locked	0.3189ms	0.1460ms	6.8472 KOps/s	6.4919 KOps/s	$\textbf{\color{#35bf28}+5.47\%}$
test_keys_nested_leaf	0.2135ms	0.1294ms	7.7307 KOps/s	7.5377 KOps/s	$\color{#35bf28}+2.56\%$
test_keys_stack_nested	1.5008ms	1.2720ms	786.1468 Ops/s	772.6035 Ops/s	$\color{#35bf28}+1.75\%$
test_keys_stack_nested_leaf	1.6517ms	1.2620ms	792.4217 Ops/s	777.8889 Ops/s	$\color{#35bf28}+1.87\%$
test_keys_stack_nested_locked	0.8915ms	0.6944ms	1.4401 KOps/s	1.4133 KOps/s	$\color{#35bf28}+1.89\%$
test_values	6.7766μs	1.1392μs	877.8436 KOps/s	851.5000 KOps/s	$\color{#35bf28}+3.09\%$
test_values_nested	92.8930μs	53.8541μs	18.5687 KOps/s	18.3720 KOps/s	$\color{#35bf28}+1.07\%$
test_values_nested_locked	0.1051ms	54.2026μs	18.4493 KOps/s	18.3374 KOps/s	$\color{#35bf28}+0.61\%$
test_values_nested_leaf	98.9240μs	48.7197μs	20.5256 KOps/s	20.7840 KOps/s	$\color{#d91a1a}-1.24\%$
test_values_stack_nested	1.2811ms	1.0546ms	948.2380 Ops/s	936.5131 Ops/s	$\color{#35bf28}+1.25\%$
test_values_stack_nested_leaf	1.2237ms	1.0348ms	966.4084 Ops/s	948.7646 Ops/s	$\color{#35bf28}+1.86\%$
test_values_stack_nested_locked	0.7484ms	0.5172ms	1.9334 KOps/s	1.9054 KOps/s	$\color{#35bf28}+1.47\%$
test_membership	15.2690μs	1.4040μs	712.2559 KOps/s	699.6134 KOps/s	$\color{#35bf28}+1.81\%$
test_membership_nested	45.8350μs	2.8800μs	347.2187 KOps/s	322.5696 KOps/s	$\textbf{\color{#35bf28}+7.64\%}$
test_membership_nested_leaf	19.7460μs	2.9073μs	343.9562 KOps/s	315.2099 KOps/s	$\textbf{\color{#35bf28}+9.12\%}$
test_membership_stacked_nested	57.0460μs	11.8387μs	84.4687 KOps/s	82.8571 KOps/s	$\color{#35bf28}+1.95\%$
test_membership_stacked_nested_leaf	35.7370μs	11.8455μs	84.4200 KOps/s	82.3453 KOps/s	$\color{#35bf28}+2.52\%$
test_membership_nested_last	44.3920μs	6.0849μs	164.3422 KOps/s	157.1372 KOps/s	$\color{#35bf28}+4.59\%$
test_membership_nested_leaf_last	43.8420μs	6.1198μs	163.4039 KOps/s	157.2650 KOps/s	$\color{#35bf28}+3.90\%$
test_membership_stacked_nested_last	0.2726ms	0.1689ms	5.9213 KOps/s	5.8885 KOps/s	$\color{#35bf28}+0.56\%$
test_membership_stacked_nested_leaf_last	0.1787ms	14.5510μs	68.7236 KOps/s	70.8581 KOps/s	$\color{#d91a1a}-3.01\%$
test_nested_getleaf	43.8110μs	10.8067μs	92.5351 KOps/s	92.9297 KOps/s	$\color{#d91a1a}-0.42\%$
test_nested_get	45.7450μs	10.1839μs	98.1938 KOps/s	98.3789 KOps/s	$\color{#d91a1a}-0.19\%$
test_stacked_getleaf	0.7038ms	0.4672ms	2.1405 KOps/s	2.1036 KOps/s	$\color{#35bf28}+1.75\%$
test_stacked_get	0.5850ms	0.4390ms	2.2779 KOps/s	2.2483 KOps/s	$\color{#35bf28}+1.31\%$
test_nested_getitemleaf	27.5410μs	10.8743μs	91.9598 KOps/s	91.8678 KOps/s	$\color{#35bf28}+0.10\%$
test_nested_getitem	48.8110μs	10.2185μs	97.8619 KOps/s	97.3062 KOps/s	$\color{#35bf28}+0.57\%$
test_stacked_getitemleaf	0.6449ms	0.4702ms	2.1267 KOps/s	2.0745 KOps/s	$\color{#35bf28}+2.51\%$
test_stacked_getitem	0.6509ms	0.4407ms	2.2693 KOps/s	2.2290 KOps/s	$\color{#35bf28}+1.81\%$
test_lock_nested	1.3721ms	0.4106ms	2.4357 KOps/s	2.2759 KOps/s	$\textbf{\color{#35bf28}+7.02\%}$
test_lock_stack_nested	85.7205ms	6.7450ms	148.2590 Ops/s	128.3678 Ops/s	$\textbf{\color{#35bf28}+15.50\%}$
test_unlock_nested	75.2142ms	0.4909ms	2.0371 KOps/s	2.1818 KOps/s	$\textbf{\color{#d91a1a}-6.63\%}$
test_unlock_stack_nested	82.5595ms	6.3325ms	157.9165 Ops/s	137.2645 Ops/s	$\textbf{\color{#35bf28}+15.05\%}$
test_flatten_speed	0.6315ms	0.3636ms	2.7505 KOps/s	2.6929 KOps/s	$\color{#35bf28}+2.14\%$
test_unflatten_speed	0.7021ms	0.4522ms	2.2116 KOps/s	2.2209 KOps/s	$\color{#d91a1a}-0.42\%$
test_common_ops	2.9020ms	0.7025ms	1.4234 KOps/s	1.3930 KOps/s	$\color{#35bf28}+2.19\%$
test_creation	19.2260μs	1.9934μs	501.6487 KOps/s	488.8750 KOps/s	$\color{#35bf28}+2.61\%$
test_creation_empty	31.1180μs	11.1392μs	89.7734 KOps/s	102.1292 KOps/s	$\textbf{\color{#d91a1a}-12.10\%}$
test_creation_nested_1	97.9920μs	14.0809μs	71.0182 KOps/s	78.3109 KOps/s	$\textbf{\color{#d91a1a}-9.31\%}$
test_creation_nested_2	47.7690μs	19.1138μs	52.3182 KOps/s	54.7666 KOps/s	$\color{#d91a1a}-4.47\%$
test_clone	0.1348ms	12.1890μs	82.0413 KOps/s	79.1777 KOps/s	$\color{#35bf28}+3.62\%$
test_getitem[int]	42.4990μs	11.6985μs	85.4808 KOps/s	81.3152 KOps/s	$\textbf{\color{#35bf28}+5.12\%}$
test_getitem[slice_int]	60.6930μs	22.7272μs	44.0002 KOps/s	40.6790 KOps/s	$\textbf{\color{#35bf28}+8.16\%}$
test_getitem[range]	83.9870μs	40.6970μs	24.5718 KOps/s	22.2015 KOps/s	$\textbf{\color{#35bf28}+10.68\%}$
test_getitem[tuple]	53.0590μs	18.7999μs	53.1919 KOps/s	50.3760 KOps/s	$\textbf{\color{#35bf28}+5.59\%}$
test_getitem[list]	0.1011ms	35.9526μs	27.8144 KOps/s	24.9452 KOps/s	$\textbf{\color{#35bf28}+11.50\%}$
test_setitem_dim[int]	67.7660μs	31.1082μs	32.1458 KOps/s	31.6479 KOps/s	$\color{#35bf28}+1.57\%$
test_setitem_dim[slice_int]	0.1015ms	56.8023μs	17.6049 KOps/s	17.3871 KOps/s	$\color{#35bf28}+1.25\%$
test_setitem_dim[range]	0.1137ms	74.6982μs	13.3872 KOps/s	11.7668 KOps/s	$\textbf{\color{#35bf28}+13.77\%}$
test_setitem_dim[tuple]	85.4290μs	46.0773μs	21.7027 KOps/s	21.0369 KOps/s	$\color{#35bf28}+3.16\%$
test_setitem	0.1523ms	19.1389μs	52.2495 KOps/s	53.9652 KOps/s	$\color{#d91a1a}-3.18\%$
test_set	0.1142ms	18.3929μs	54.3687 KOps/s	55.4491 KOps/s	$\color{#d91a1a}-1.95\%$
test_set_shared	3.2345ms	0.1370ms	7.3019 KOps/s	6.8422 KOps/s	$\textbf{\color{#35bf28}+6.72\%}$
test_update	0.1446ms	21.7032μs	46.0761 KOps/s	47.0377 KOps/s	$\color{#d91a1a}-2.04\%$
test_update_nested	0.1841ms	28.8695μs	34.6387 KOps/s	35.2382 KOps/s	$\color{#d91a1a}-1.70\%$
test_set_nested	0.1340ms	20.3465μs	49.1486 KOps/s	50.5157 KOps/s	$\color{#d91a1a}-2.71\%$
test_set_nested_new	0.2011ms	24.9036μs	40.1548 KOps/s	42.1297 KOps/s	$\color{#d91a1a}-4.69\%$
test_select	0.2098ms	49.0579μs	20.3841 KOps/s	20.4928 KOps/s	$\color{#d91a1a}-0.53\%$
test_unbind_speed	0.6291ms	0.3361ms	2.9756 KOps/s	2.9002 KOps/s	$\color{#35bf28}+2.60\%$
test_unbind_speed_stack0	78.9038ms	4.4025ms	227.1428 Ops/s	227.6393 Ops/s	$\color{#d91a1a}-0.22\%$
test_unbind_speed_stack1	2.5963μs	0.6486μs	1.5417 MOps/s	1.4873 MOps/s	$\color{#35bf28}+3.66\%$
test_split	70.5956ms	1.6798ms	595.3247 Ops/s	590.1273 Ops/s	$\color{#35bf28}+0.88\%$
test_chunk	69.0545ms	1.6434ms	608.4763 Ops/s	606.8120 Ops/s	$\color{#35bf28}+0.27\%$
test_creation[device0]	0.6034ms	0.2999ms	3.3349 KOps/s	3.3359 KOps/s	$\color{#d91a1a}-0.03\%$
test_creation_from_tensor	4.0362ms	0.3412ms	2.9309 KOps/s	3.0125 KOps/s	$\color{#d91a1a}-2.71\%$
test_add_one[memmap_tensor0]	0.4437ms	26.8323μs	37.2686 KOps/s	40.1310 KOps/s	$\textbf{\color{#d91a1a}-7.13\%}$
test_contiguous[memmap_tensor0]	28.0720μs	5.9548μs	167.9315 KOps/s	173.8288 KOps/s	$\color{#d91a1a}-3.39\%$
test_stack[memmap_tensor0]	55.2730μs	20.4794μs	48.8295 KOps/s	51.7539 KOps/s	$\textbf{\color{#d91a1a}-5.65\%}$
test_memmaptd_index	0.3149ms	0.1995ms	5.0136 KOps/s	5.0154 KOps/s	$\color{#d91a1a}-0.04\%$
test_memmaptd_index_astensor	0.6127ms	0.2583ms	3.8716 KOps/s	3.8430 KOps/s	$\color{#35bf28}+0.75\%$
test_memmaptd_index_op	0.8338ms	0.5508ms	1.8154 KOps/s	1.8966 KOps/s	$\color{#d91a1a}-4.28\%$
test_serialize_model	0.1773s	0.1122s	8.9142 Ops/s	9.0243 Ops/s	$\color{#d91a1a}-1.22\%$
test_serialize_model_pickle	0.4468s	0.3743s	2.6717 Ops/s	2.5670 Ops/s	$\color{#35bf28}+4.08\%$
test_serialize_weights	0.1669s	0.1058s	9.4511 Ops/s	9.1583 Ops/s	$\color{#35bf28}+3.20\%$
test_serialize_weights_returnearly	0.1917s	0.1301s	7.6881 Ops/s	8.2327 Ops/s	$\textbf{\color{#d91a1a}-6.61\%}$
test_serialize_weights_pickle	1.0429s	0.6191s	1.6153 Ops/s	2.4452 Ops/s	$\textbf{\color{#d91a1a}-33.94\%}$
test_serialize_weights_filesystem	0.1588s	97.8462ms	10.2201 Ops/s	10.6509 Ops/s	$\color{#d91a1a}-4.04\%$
test_serialize_model_filesystem	97.7528ms	92.7128ms	10.7860 Ops/s	9.6574 Ops/s	$\textbf{\color{#35bf28}+11.69\%}$
test_reshape_pytree	72.4170μs	22.7098μs	44.0339 KOps/s	42.2356 KOps/s	$\color{#35bf28}+4.26\%$
test_reshape_td	76.6320μs	29.7785μs	33.5812 KOps/s	33.4378 KOps/s	$\color{#35bf28}+0.43\%$
test_view_pytree	81.0080μs	22.8504μs	43.7629 KOps/s	42.9622 KOps/s	$\color{#35bf28}+1.86\%$
test_view_td	25.4770μs	4.8589μs	205.8079 KOps/s	199.7121 KOps/s	$\color{#35bf28}+3.05\%$
test_unbind_pytree	63.8090μs	26.1668μs	38.2164 KOps/s	35.9609 KOps/s	$\textbf{\color{#35bf28}+6.27\%}$
test_unbind_td	0.1260ms	53.8304μs	18.5769 KOps/s	17.3659 KOps/s	$\textbf{\color{#35bf28}+6.97\%}$
test_split_pytree	82.7340μs	26.1600μs	38.2263 KOps/s	36.9322 KOps/s	$\color{#35bf28}+3.50\%$
test_split_td	0.5785ms	42.3182μs	23.6305 KOps/s	22.8579 KOps/s	$\color{#35bf28}+3.38\%$
test_add_pytree	75.2690μs	32.1385μs	31.1153 KOps/s	30.6513 KOps/s	$\color{#35bf28}+1.51\%$
test_add_td	0.1004ms	49.3366μs	20.2689 KOps/s	21.4296 KOps/s	$\textbf{\color{#d91a1a}-5.42\%}$
test_distributed	27.1600μs	5.9601μs	167.7814 KOps/s	163.4396 KOps/s	$\color{#35bf28}+2.66\%$
test_tdmodule	0.3486ms	23.2029μs	43.0980 KOps/s	45.4925 KOps/s	$\textbf{\color{#d91a1a}-5.26\%}$
test_tdmodule_dispatch	0.1875ms	43.0371μs	23.2358 KOps/s	24.4844 KOps/s	$\textbf{\color{#d91a1a}-5.10\%}$
test_tdseq	0.1287ms	26.4491μs	37.8085 KOps/s	38.9412 KOps/s	$\color{#d91a1a}-2.91\%$
test_tdseq_dispatch	0.1366ms	46.6884μs	21.4186 KOps/s	22.0511 KOps/s	$\color{#d91a1a}-2.87\%$
test_instantiation_functorch	1.9472ms	1.2980ms	770.3986 Ops/s	764.9018 Ops/s	$\color{#35bf28}+0.72\%$
test_instantiation_td	1.6311ms	1.0057ms	994.3012 Ops/s	991.2855 Ops/s	$\color{#35bf28}+0.30\%$
test_exec_functorch	0.2887ms	0.1557ms	6.4235 KOps/s	6.2931 KOps/s	$\color{#35bf28}+2.07\%$
test_exec_functional_call	0.3714ms	0.1464ms	6.8304 KOps/s	6.8423 KOps/s	$\color{#d91a1a}-0.17\%$
test_exec_td	0.2803ms	0.1413ms	7.0749 KOps/s	6.9198 KOps/s	$\color{#35bf28}+2.24\%$
test_exec_td_decorator	0.8991ms	0.1758ms	5.6872 KOps/s	5.6753 KOps/s	$\color{#35bf28}+0.21\%$
test_vmap_mlp_speed[True-True]	1.4874ms	0.8804ms	1.1358 KOps/s	1.1069 KOps/s	$\color{#35bf28}+2.61\%$
test_vmap_mlp_speed[True-False]	0.7210ms	0.4730ms	2.1141 KOps/s	2.1380 KOps/s	$\color{#d91a1a}-1.12\%$
test_vmap_mlp_speed[False-True]	0.9439ms	0.7564ms	1.3220 KOps/s	1.2836 KOps/s	$\color{#35bf28}+2.99\%$
test_vmap_mlp_speed[False-False]	0.6310ms	0.3819ms	2.6185 KOps/s	2.5822 KOps/s	$\color{#35bf28}+1.41\%$
test_vmap_mlp_speed_decorator[True-True]	3.2742ms	1.7902ms	558.6117 Ops/s	566.5992 Ops/s	$\color{#d91a1a}-1.41\%$
test_vmap_mlp_speed_decorator[True-False]	1.0537ms	0.5294ms	1.8890 KOps/s	1.8835 KOps/s	$\color{#35bf28}+0.29\%$
test_vmap_mlp_speed_decorator[False-True]	2.2263ms	1.5150ms	660.0778 Ops/s	674.4944 Ops/s	$\color{#d91a1a}-2.14\%$
test_vmap_mlp_speed_decorator[False-False]	83.6564ms	0.4405ms	2.2699 KOps/s	2.5156 KOps/s	$\textbf{\color{#d91a1a}-9.77\%}$

[github-actions]

Result of GPU Benchmark Tests

Expand to view detailed results

Name	Max	Mean	Ops
test_plain_set_nested	29.4600μs	13.2348μs	75.5584 KOps/s
test_plain_set_stack_nested	0.1332ms	0.1171ms	8.5420 KOps/s
test_plain_set_nested_inplace	30.1600μs	14.4820μs	69.0510 KOps/s
test_plain_set_stack_nested_inplace	0.1942ms	0.1444ms	6.9228 KOps/s
test_items	21.8100μs	4.7150μs	212.0898 KOps/s
test_items_nested	0.3710ms	0.3384ms	2.9548 KOps/s
test_items_nested_locked	0.4510ms	0.3418ms	2.9261 KOps/s
test_items_nested_leaf	0.9678ms	0.2022ms	4.9467 KOps/s
test_items_stack_nested	1.3730ms	1.3200ms	757.5513 Ops/s
test_items_stack_nested_leaf	1.2506ms	1.1511ms	868.7250 Ops/s
test_items_stack_nested_locked	0.8713ms	0.8212ms	1.2178 KOps/s
test_keys	19.2800μs	4.6431μs	215.3752 KOps/s
test_keys_nested	1.9731ms	95.2435μs	10.4994 KOps/s
test_keys_nested_locked	0.1194ms	94.3764μs	10.5959 KOps/s
test_keys_nested_leaf	0.1936ms	78.6101μs	12.7210 KOps/s
test_keys_stack_nested	1.2274ms	1.1586ms	863.1235 Ops/s
test_keys_stack_nested_leaf	1.3530ms	1.1403ms	876.9580 Ops/s
test_keys_stack_nested_locked	0.7183ms	0.6448ms	1.5508 KOps/s
test_values	9.1133μs	1.8985μs	526.7364 KOps/s
test_values_nested	68.0310μs	45.5360μs	21.9607 KOps/s
test_values_nested_locked	63.0610μs	47.4557μs	21.0723 KOps/s
test_values_nested_leaf	62.7200μs	39.6052μs	25.2492 KOps/s
test_values_stack_nested	1.0121ms	0.9700ms	1.0310 KOps/s
test_values_stack_nested_leaf	1.0169ms	0.9572ms	1.0447 KOps/s
test_values_stack_nested_locked	0.5649ms	0.5049ms	1.9806 KOps/s
test_membership	14.9700μs	1.0748μs	930.3921 KOps/s
test_membership_nested	15.8500μs	2.2949μs	435.7410 KOps/s
test_membership_nested_leaf	12.4155μs	2.2023μs	454.0652 KOps/s
test_membership_stacked_nested	29.8500μs	11.0251μs	90.7025 KOps/s
test_membership_stacked_nested_leaf	31.8010μs	11.0480μs	90.5137 KOps/s
test_membership_nested_last	27.3200μs	4.7423μs	210.8684 KOps/s
test_membership_nested_leaf_last	20.4500μs	4.7445μs	210.7684 KOps/s
test_membership_stacked_nested_last	0.1629ms	0.1369ms	7.3035 KOps/s
test_membership_stacked_nested_leaf_last	34.6100μs	12.8964μs	77.5410 KOps/s
test_nested_getleaf	23.7300μs	8.5204μs	117.3653 KOps/s
test_nested_get	30.0900μs	8.0228μs	124.6443 KOps/s
test_stacked_getleaf	0.4315ms	0.3907ms	2.5595 KOps/s
test_stacked_get	0.4564ms	0.3624ms	2.7597 KOps/s
test_nested_getitemleaf	25.4100μs	8.5705μs	116.6788 KOps/s
test_nested_getitem	22.2600μs	8.0898μs	123.6122 KOps/s
test_stacked_getitemleaf	0.4480ms	0.3929ms	2.5455 KOps/s
test_stacked_getitem	0.3984ms	0.3622ms	2.7611 KOps/s
test_lock_nested	8.1174ms	0.4266ms	2.3444 KOps/s
test_lock_stack_nested	0.1075s	6.8342ms	146.3225 Ops/s
test_unlock_nested	0.8115ms	0.4142ms	2.4140 KOps/s
test_unlock_stack_nested	0.1012s	7.1586ms	139.6927 Ops/s
test_flatten_speed	82.3558ms	0.2886ms	3.4648 KOps/s
test_unflatten_speed	0.3748ms	0.3575ms	2.7971 KOps/s
test_common_ops	1.0671ms	0.5970ms	1.6749 KOps/s
test_creation	32.9310μs	1.5935μs	627.5298 KOps/s
test_creation_empty	21.3800μs	7.3310μs	136.4072 KOps/s
test_creation_nested_1	28.6900μs	9.2185μs	108.4779 KOps/s
test_creation_nested_2	33.7410μs	13.9271μs	71.8023 KOps/s
test_clone	0.1358ms	13.2226μs	75.6279 KOps/s
test_getitem[int]	38.4510μs	11.0003μs	90.9067 KOps/s
test_getitem[slice_int]	43.4210μs	21.6433μs	46.2036 KOps/s
test_getitem[range]	68.2810μs	38.8481μs	25.7413 KOps/s
test_getitem[tuple]	45.6810μs	18.8492μs	53.0527 KOps/s
test_getitem[list]	0.3602ms	34.9496μs	28.6127 KOps/s
test_setitem_dim[int]	40.5700μs	25.3027μs	39.5215 KOps/s
test_setitem_dim[slice_int]	82.2610μs	46.4252μs	21.5400 KOps/s
test_setitem_dim[range]	87.6810μs	63.2165μs	15.8187 KOps/s
test_setitem_dim[tuple]	67.2610μs	41.1281μs	24.3143 KOps/s
test_setitem	0.1360ms	17.3633μs	57.5929 KOps/s
test_set	0.1318ms	16.8902μs	59.2059 KOps/s
test_set_shared	2.7020ms	0.1047ms	9.5524 KOps/s
test_update	0.1316ms	18.8236μs	53.1249 KOps/s
test_update_nested	0.1183ms	24.8721μs	40.2057 KOps/s
test_set_nested	0.1072ms	17.7402μs	56.3692 KOps/s
test_set_nested_new	0.1074ms	21.8247μs	45.8196 KOps/s
test_select	78.4610μs	42.9427μs	23.2868 KOps/s
test_to	75.1310μs	54.4268μs	18.3733 KOps/s
test_to_nonblocking	65.2010μs	34.3985μs	29.0710 KOps/s
test_unbind_speed	0.3655ms	0.3336ms	2.9974 KOps/s
test_unbind_speed_stack0	81.8353ms	3.7952ms	263.4873 Ops/s
test_unbind_speed_stack1	3.1171μs	0.5423μs	1.8439 MOps/s
test_split	78.7775ms	1.7436ms	573.5385 Ops/s
test_chunk	1.6532ms	1.5692ms	637.2533 Ops/s
test_creation[device0]	0.3761ms	0.3080ms	3.2463 KOps/s
test_creation[device1]	0.4101ms	0.3127ms	3.1977 KOps/s
test_creation_from_tensor	0.6274ms	0.3377ms	2.9616 KOps/s
test_add_one[memmap_tensor0]	75.4410μs	24.9110μs	40.1430 KOps/s
test_add_one[memmap_tensor1]	0.2276ms	70.8505μs	14.1142 KOps/s
test_contiguous[memmap_tensor0]	25.2200μs	5.9025μs	169.4193 KOps/s
test_contiguous[memmap_tensor1]	56.1510μs	21.9970μs	45.4608 KOps/s
test_stack[memmap_tensor0]	43.4500μs	19.4589μs	51.3905 KOps/s
test_stack[memmap_tensor1]	0.1081ms	71.8150μs	13.9247 KOps/s
test_memmaptd_index	0.2782ms	0.2320ms	4.3105 KOps/s
test_memmaptd_index_astensor	0.3494ms	0.2879ms	3.4732 KOps/s
test_memmaptd_index_op	0.6529ms	0.5786ms	1.7284 KOps/s
test_serialize_model	0.1791s	0.1011s	9.8920 Ops/s
test_serialize_model_pickle	1.3488s	1.2364s	0.8088 Ops/s
test_serialize_weights	0.1758s	97.2846ms	10.2791 Ops/s
test_serialize_weights_returnearly	0.2889s	69.0289ms	14.4867 Ops/s
test_serialize_weights_pickle	1.3544s	1.2369s	0.8085 Ops/s
test_reshape_pytree	0.1645ms	24.3846μs	41.0094 KOps/s
test_reshape_td	0.1595ms	29.4939μs	33.9053 KOps/s
test_view_pytree	51.5910μs	23.5197μs	42.5176 KOps/s
test_view_td	19.4100μs	4.1489μs	241.0286 KOps/s
test_unbind_pytree	49.2300μs	28.9653μs	34.5241 KOps/s
test_unbind_td	68.5110μs	53.0792μs	18.8398 KOps/s
test_split_pytree	50.3500μs	28.2648μs	35.3797 KOps/s
test_split_td	73.9010μs	40.5842μs	24.6401 KOps/s
test_add_pytree	84.1810μs	36.1373μs	27.6722 KOps/s
test_add_td	70.3510μs	45.9516μs	21.7620 KOps/s
test_distributed	19.5210μs	5.6102μs	178.2460 KOps/s
test_tdmodule	84.5703ms	0.1017ms	9.8326 KOps/s
test_tdmodule_dispatch	0.1971ms	33.2206μs	30.1018 KOps/s
test_tdseq	35.9610μs	20.3274μs	49.1946 KOps/s
test_tdseq_dispatch	72.4310μs	36.2109μs	27.6160 KOps/s
test_instantiation_functorch	1.8969ms	1.6572ms	603.4440 Ops/s
test_instantiation_td	1.6981ms	1.1634ms	859.5383 Ops/s
test_exec_functorch	0.2124ms	0.1593ms	6.2785 KOps/s
test_exec_functional_call	0.2048ms	0.1592ms	6.2816 KOps/s
test_exec_td	0.1897ms	0.1507ms	6.6351 KOps/s
test_exec_td_decorator	0.9679ms	0.1868ms	5.3543 KOps/s
test_vmap_mlp_speed[True-True]	1.2368ms	1.1187ms	893.8669 Ops/s
test_vmap_mlp_speed[True-False]	0.7043ms	0.6626ms	1.5093 KOps/s
test_vmap_mlp_speed[False-True]	1.0800ms	1.0253ms	975.3337 Ops/s
test_vmap_mlp_speed[False-False]	0.7483ms	0.5950ms	1.6808 KOps/s
test_vmap_mlp_speed_decorator[True-True]	2.8128ms	2.0754ms	481.8294 Ops/s
test_vmap_mlp_speed_decorator[True-False]	1.0738ms	0.7091ms	1.4102 KOps/s
test_vmap_mlp_speed_decorator[False-True]	2.2992ms	1.8408ms	543.2389 Ops/s
test_vmap_mlp_speed_decorator[False-False]	0.9197ms	0.6142ms	1.6283 KOps/s
test_vmap_transformer_speed[True-True]	12.5950ms	12.4154ms	80.5450 Ops/s
test_vmap_transformer_speed[True-False]	8.4832ms	8.2384ms	121.3829 Ops/s
test_vmap_transformer_speed[False-True]	12.7062ms	12.3182ms	81.1804 Ops/s
test_vmap_transformer_speed[False-False]	8.4051ms	8.1445ms	122.7824 Ops/s
test_vmap_transformer_speed_decorator[True-True]	64.8753ms	63.7497ms	15.6863 Ops/s
test_vmap_transformer_speed_decorator[True-False]	21.4107ms	19.8152ms	50.4662 Ops/s
test_vmap_transformer_speed_decorator[False-True]	59.0935ms	58.0979ms	17.2123 Ops/s
test_vmap_transformer_speed_decorator[False-False]	21.0560ms	19.3791ms	51.6019 Ops/s