[Feature] repeat and repeat_interleave

[vmoens]

Stack from ghstack (oldest at bottom):

• -> [Feature] repeat and repeat_interleave #1115

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}12$. Worsened: $\large\color{#d91a1a}15$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	35.5360μs	17.5288μs	57.0490 KOps/s	56.2634 KOps/s	$\color{#35bf28}+1.40\%$
test_plain_set_stack_nested	35.8870μs	17.7133μs	56.4548 KOps/s	54.8130 KOps/s	$\color{#35bf28}+3.00\%$
test_plain_set_nested_inplace	82.3020μs	19.1656μs	52.1768 KOps/s	50.8428 KOps/s	$\color{#35bf28}+2.62\%$
test_plain_set_stack_nested_inplace	83.9970μs	19.2697μs	51.8949 KOps/s	50.4051 KOps/s	$\color{#35bf28}+2.96\%$
test_items	24.7660μs	4.1210μs	242.6588 KOps/s	240.6086 KOps/s	$\color{#35bf28}+0.85\%$
test_items_nested	0.5466ms	0.3985ms	2.5096 KOps/s	2.5105 KOps/s	$\color{#d91a1a}-0.03\%$
test_items_nested_locked	0.6205ms	0.3958ms	2.5265 KOps/s	2.5153 KOps/s	$\color{#35bf28}+0.45\%$
test_items_nested_leaf	0.1189ms	71.0788μs	14.0689 KOps/s	14.0230 KOps/s	$\color{#35bf28}+0.33\%$
test_items_stack_nested	0.6365ms	0.3955ms	2.5281 KOps/s	2.4970 KOps/s	$\color{#35bf28}+1.25\%$
test_items_stack_nested_leaf	0.1285ms	74.5203μs	13.4192 KOps/s	13.4716 KOps/s	$\color{#d91a1a}-0.39\%$
test_items_stack_nested_locked	0.5179ms	0.3972ms	2.5178 KOps/s	2.4700 KOps/s	$\color{#35bf28}+1.94\%$
test_keys	28.4940μs	3.5207μs	284.0310 KOps/s	289.7957 KOps/s	$\color{#d91a1a}-1.99\%$
test_keys_nested	0.2341ms	0.1396ms	7.1625 KOps/s	7.1307 KOps/s	$\color{#35bf28}+0.45\%$
test_keys_nested_locked	0.6547ms	0.1446ms	6.9176 KOps/s	6.9608 KOps/s	$\color{#d91a1a}-0.62\%$
test_keys_nested_leaf	1.6716ms	0.1203ms	8.3131 KOps/s	8.2587 KOps/s	$\color{#35bf28}+0.66\%$
test_keys_stack_nested	0.2177ms	0.1388ms	7.2062 KOps/s	7.2742 KOps/s	$\color{#d91a1a}-0.93\%$
test_keys_stack_nested_leaf	0.1969ms	0.1197ms	8.3522 KOps/s	8.5317 KOps/s	$\color{#d91a1a}-2.10\%$
test_keys_stack_nested_locked	0.2300ms	0.1437ms	6.9578 KOps/s	7.0127 KOps/s	$\color{#d91a1a}-0.78\%$
test_values	9.3214μs	1.1018μs	907.6294 KOps/s	802.3002 KOps/s	$\textbf{\color{#35bf28}+13.13\%}$
test_values_nested	0.1089ms	55.7226μs	17.9460 KOps/s	18.1403 KOps/s	$\color{#d91a1a}-1.07\%$
test_values_nested_locked	0.1064ms	55.2496μs	18.0997 KOps/s	18.2659 KOps/s	$\color{#d91a1a}-0.91\%$
test_values_nested_leaf	0.1162ms	60.9558μs	16.4053 KOps/s	16.6647 KOps/s	$\color{#d91a1a}-1.56\%$
test_values_stack_nested	0.1188ms	56.4326μs	17.7203 KOps/s	16.5114 KOps/s	$\textbf{\color{#35bf28}+7.32\%}$
test_values_stack_nested_leaf	0.1275ms	61.0120μs	16.3902 KOps/s	16.7375 KOps/s	$\color{#d91a1a}-2.07\%$
test_values_stack_nested_locked	0.1190ms	55.8630μs	17.9009 KOps/s	17.5609 KOps/s	$\color{#35bf28}+1.94\%$
test_membership	16.4410μs	0.9073μs	1.1022 MOps/s	1.3786 MOps/s	$\textbf{\color{#d91a1a}-20.05\%}$
test_membership_nested	48.1100μs	2.9297μs	341.3301 KOps/s	344.0174 KOps/s	$\color{#d91a1a}-0.78\%$
test_membership_nested_leaf	29.1440μs	2.9558μs	338.3131 KOps/s	339.5257 KOps/s	$\color{#d91a1a}-0.36\%$
test_membership_stacked_nested	45.1340μs	2.9180μs	342.7023 KOps/s	344.2263 KOps/s	$\color{#d91a1a}-0.44\%$
test_membership_stacked_nested_leaf	24.0950μs	2.9192μs	342.5565 KOps/s	330.6699 KOps/s	$\color{#35bf28}+3.59\%$
test_membership_nested_last	28.0720μs	4.2953μs	232.8121 KOps/s	232.4949 KOps/s	$\color{#35bf28}+0.14\%$
test_membership_nested_leaf_last	54.3220μs	4.3089μs	232.0764 KOps/s	234.1053 KOps/s	$\color{#d91a1a}-0.87\%$
test_membership_stacked_nested_last	18.6750μs	4.2689μs	234.2543 KOps/s	183.2239 KOps/s	$\textbf{\color{#35bf28}+27.85\%}$
test_membership_stacked_nested_leaf_last	45.9860μs	4.3012μs	232.4952 KOps/s	184.1383 KOps/s	$\textbf{\color{#35bf28}+26.26\%}$
test_nested_getleaf	51.2880μs	10.6163μs	94.1946 KOps/s	92.8031 KOps/s	$\color{#35bf28}+1.50\%$
test_nested_get	34.3850μs	10.0920μs	99.0883 KOps/s	97.0601 KOps/s	$\color{#35bf28}+2.09\%$
test_stacked_getleaf	58.3990μs	10.7373μs	93.1332 KOps/s	93.1818 KOps/s	$\color{#d91a1a}-0.05\%$
test_stacked_get	24.0750μs	10.1580μs	98.4444 KOps/s	97.8307 KOps/s	$\color{#35bf28}+0.63\%$
test_nested_getitemleaf	48.2600μs	11.1195μs	89.9323 KOps/s	90.2013 KOps/s	$\color{#d91a1a}-0.30\%$
test_nested_getitem	39.1130μs	10.4512μs	95.6826 KOps/s	96.0114 KOps/s	$\color{#d91a1a}-0.34\%$
test_stacked_getitemleaf	39.9040μs	11.2508μs	88.8827 KOps/s	90.1872 KOps/s	$\color{#d91a1a}-1.45\%$
test_stacked_getitem	62.4470μs	10.4515μs	95.6798 KOps/s	96.8104 KOps/s	$\color{#d91a1a}-1.17\%$
test_lock_nested	1.8322ms	0.4382ms	2.2823 KOps/s	2.2734 KOps/s	$\color{#35bf28}+0.39\%$
test_lock_stack_nested	0.7874ms	0.4119ms	2.4278 KOps/s	2.4601 KOps/s	$\color{#d91a1a}-1.32\%$
test_unlock_nested	1.4167ms	0.3601ms	2.7768 KOps/s	2.7907 KOps/s	$\color{#d91a1a}-0.50\%$
test_unlock_stack_nested	0.5803ms	0.3315ms	3.0168 KOps/s	3.0920 KOps/s	$\color{#d91a1a}-2.43\%$
test_flatten_speed	0.1886ms	95.2097μs	10.5031 KOps/s	10.6481 KOps/s	$\color{#d91a1a}-1.36\%$
test_unflatten_speed	0.8834ms	0.4972ms	2.0112 KOps/s	2.0185 KOps/s	$\color{#d91a1a}-0.36\%$
test_common_ops	7.2421ms	0.7648ms	1.3076 KOps/s	1.3247 KOps/s	$\color{#d91a1a}-1.29\%$
test_creation	74.0080μs	2.0711μs	482.8312 KOps/s	475.1133 KOps/s	$\color{#35bf28}+1.62\%$
test_creation_empty	34.9850μs	10.8083μs	92.5215 KOps/s	91.7568 KOps/s	$\color{#35bf28}+0.83\%$
test_creation_nested_1	58.0180μs	13.8845μs	72.0226 KOps/s	72.5221 KOps/s	$\color{#d91a1a}-0.69\%$
test_creation_nested_2	61.6850μs	17.8737μs	55.9482 KOps/s	55.4978 KOps/s	$\color{#35bf28}+0.81\%$
test_clone	36.8590μs	13.1247μs	76.1924 KOps/s	77.1313 KOps/s	$\color{#d91a1a}-1.22\%$
test_getitem[int]	1.0360ms	12.6156μs	79.2668 KOps/s	80.6268 KOps/s	$\color{#d91a1a}-1.69\%$
test_getitem[slice_int]	0.1431ms	24.3657μs	41.0414 KOps/s	42.1659 KOps/s	$\color{#d91a1a}-2.67\%$
test_getitem[range]	0.5651ms	47.1281μs	21.2188 KOps/s	21.3939 KOps/s	$\color{#d91a1a}-0.82\%$
test_getitem[tuple]	0.1272ms	20.1070μs	49.7340 KOps/s	51.1844 KOps/s	$\color{#d91a1a}-2.83\%$
test_getitem[list]	0.4804ms	43.1691μs	23.1647 KOps/s	23.3396 KOps/s	$\color{#d91a1a}-0.75\%$
test_setitem_dim[int]	68.6580μs	25.2046μs	39.6753 KOps/s	40.9439 KOps/s	$\color{#d91a1a}-3.10\%$
test_setitem_dim[slice_int]	95.7990μs	51.3954μs	19.4570 KOps/s	19.7577 KOps/s	$\color{#d91a1a}-1.52\%$
test_setitem_dim[range]	0.1734ms	73.4462μs	13.6154 KOps/s	13.5805 KOps/s	$\color{#35bf28}+0.26\%$
test_setitem_dim[tuple]	90.4200μs	41.7349μs	23.9608 KOps/s	24.5999 KOps/s	$\color{#d91a1a}-2.60\%$
test_setitem	0.1735ms	20.0375μs	49.9065 KOps/s	50.0611 KOps/s	$\color{#d91a1a}-0.31\%$
test_set	0.2389ms	19.2031μs	52.0748 KOps/s	51.4643 KOps/s	$\color{#35bf28}+1.19\%$
test_set_shared	3.1714ms	0.1687ms	5.9269 KOps/s	5.9400 KOps/s	$\color{#d91a1a}-0.22\%$
test_update	0.2391ms	21.7433μs	45.9913 KOps/s	44.3760 KOps/s	$\color{#35bf28}+3.64\%$
test_update_nested	0.3611ms	32.2794μs	30.9795 KOps/s	31.6988 KOps/s	$\color{#d91a1a}-2.27\%$
test_update__nested	1.0820ms	32.8835μs	30.4104 KOps/s	31.1119 KOps/s	$\color{#d91a1a}-2.25\%$
test_set_nested	0.3087ms	21.5528μs	46.3977 KOps/s	46.5049 KOps/s	$\color{#d91a1a}-0.23\%$
test_set_nested_new	0.2622ms	25.4934μs	39.2258 KOps/s	38.8389 KOps/s	$\color{#35bf28}+1.00\%$
test_select	0.3351ms	41.6287μs	24.0219 KOps/s	23.7019 KOps/s	$\color{#35bf28}+1.35\%$
test_select_nested	0.1303ms	60.8925μs	16.4224 KOps/s	16.9686 KOps/s	$\color{#d91a1a}-3.22\%$
test_exclude_nested	0.1486ms	81.6344μs	12.2497 KOps/s	12.5362 KOps/s	$\color{#d91a1a}-2.28\%$
test_empty[True]	0.5586ms	0.3896ms	2.5670 KOps/s	2.6184 KOps/s	$\color{#d91a1a}-1.96\%$
test_empty[False]	12.1250μs	1.2933μs	773.2114 KOps/s	784.6014 KOps/s	$\color{#d91a1a}-1.45\%$
test_unbind_speed	0.3455ms	0.2639ms	3.7894 KOps/s	3.8210 KOps/s	$\color{#d91a1a}-0.83\%$
test_unbind_speed_stack0	0.4768ms	0.2601ms	3.8449 KOps/s	3.8903 KOps/s	$\color{#d91a1a}-1.17\%$
test_unbind_speed_stack1	0.1099s	0.7694ms	1.2998 KOps/s	1.5726 KOps/s	$\textbf{\color{#d91a1a}-17.35\%}$
test_split	1.7918ms	1.5682ms	637.6706 Ops/s	573.5148 Ops/s	$\textbf{\color{#35bf28}+11.19\%}$
test_chunk	0.1081s	1.8956ms	527.5406 Ops/s	574.5400 Ops/s	$\textbf{\color{#d91a1a}-8.18\%}$
test_consolidate_njt[False-None]	8.1608ms	7.9651ms	125.5479 Ops/s	124.2929 Ops/s	$\color{#35bf28}+1.01\%$
test_creation[device0]	0.2442ms	89.3974μs	11.1860 KOps/s	11.1141 KOps/s	$\color{#35bf28}+0.65\%$
test_creation_from_tensor	0.2223ms	93.6996μs	10.6724 KOps/s	10.5499 KOps/s	$\color{#35bf28}+1.16\%$
test_add_one[memmap_tensor0]	0.3093ms	5.0479μs	198.1005 KOps/s	211.1510 KOps/s	$\textbf{\color{#d91a1a}-6.18\%}$
test_contiguous[memmap_tensor0]	21.0190μs	0.5066μs	1.9738 MOps/s	1.9549 MOps/s	$\color{#35bf28}+0.97\%$
test_stack[memmap_tensor0]	54.8730μs	3.3730μs	296.4738 KOps/s	297.4556 KOps/s	$\color{#d91a1a}-0.33\%$
test_memmaptd_index	1.0782ms	0.2316ms	4.3184 KOps/s	4.3500 KOps/s	$\color{#d91a1a}-0.73\%$
test_memmaptd_index_astensor	0.5663ms	0.3130ms	3.1953 KOps/s	3.2473 KOps/s	$\color{#d91a1a}-1.60\%$
test_memmaptd_index_op	0.9537ms	0.5696ms	1.7555 KOps/s	1.7634 KOps/s	$\color{#d91a1a}-0.45\%$
test_serialize_model	0.1266s	0.1162s	8.6061 Ops/s	7.4291 Ops/s	$\textbf{\color{#35bf28}+15.84\%}$
test_serialize_model_pickle	0.5117s	0.4013s	2.4919 Ops/s	2.5450 Ops/s	$\color{#d91a1a}-2.09\%$
test_serialize_weights	0.1181s	0.1136s	8.8029 Ops/s	8.7251 Ops/s	$\color{#35bf28}+0.89\%$
test_serialize_weights_returnearly	0.1619s	0.1591s	6.2845 Ops/s	6.2118 Ops/s	$\color{#35bf28}+1.17\%$
test_serialize_weights_pickle	0.5448s	0.4240s	2.3585 Ops/s	2.1874 Ops/s	$\textbf{\color{#35bf28}+7.82\%}$
test_serialize_weights_filesystem	0.1521s	0.1431s	6.9892 Ops/s	6.9759 Ops/s	$\color{#35bf28}+0.19\%$
test_serialize_model_filesystem	0.1546s	0.1507s	6.6339 Ops/s	6.6829 Ops/s	$\color{#d91a1a}-0.73\%$
test_reshape_pytree	0.1175ms	27.3944μs	36.5039 KOps/s	37.0055 KOps/s	$\color{#d91a1a}-1.36\%$
test_reshape_td	74.2090μs	32.3863μs	30.8772 KOps/s	29.7503 KOps/s	$\color{#35bf28}+3.79\%$
test_view_pytree	59.1510μs	27.2516μs	36.6951 KOps/s	37.5842 KOps/s	$\color{#d91a1a}-2.37\%$
test_view_td	0.1795ms	37.2270μs	26.8622 KOps/s	27.0548 KOps/s	$\color{#d91a1a}-0.71\%$
test_unbind_pytree	71.8150μs	30.6149μs	32.6639 KOps/s	33.4334 KOps/s	$\color{#d91a1a}-2.30\%$
test_unbind_td	0.3480ms	38.4563μs	26.0036 KOps/s	25.8811 KOps/s	$\color{#35bf28}+0.47\%$
test_split_pytree	73.9590μs	30.0713μs	33.2543 KOps/s	34.5073 KOps/s	$\color{#d91a1a}-3.63\%$
test_split_td	0.4883ms	44.2980μs	22.5744 KOps/s	22.8322 KOps/s	$\color{#d91a1a}-1.13\%$
test_add_pytree	0.1057ms	37.5142μs	26.6566 KOps/s	28.3024 KOps/s	$\textbf{\color{#d91a1a}-5.82\%}$
test_add_td	0.1477ms	54.9168μs	18.2094 KOps/s	18.3352 KOps/s	$\color{#d91a1a}-0.69\%$
test_compile_add_one_nested[tensordict-compile]	0.1687ms	60.4788μs	16.5347 KOps/s	15.7665 KOps/s	$\color{#35bf28}+4.87\%$
test_compile_add_one_nested[tensordict-eager]	1.4325ms	0.1632ms	6.1276 KOps/s	6.1586 KOps/s	$\color{#d91a1a}-0.50\%$
test_compile_add_one_nested[pytree-compile]	0.1719ms	45.0677μs	22.1888 KOps/s	21.8762 KOps/s	$\color{#35bf28}+1.43\%$
test_compile_add_one_nested[pytree-eager]	0.2278ms	0.1205ms	8.3016 KOps/s	8.4668 KOps/s	$\color{#d91a1a}-1.95\%$
test_compile_copy_nested[tensordict-compile]	73.3870μs	24.8579μs	40.2287 KOps/s	38.9996 KOps/s	$\color{#35bf28}+3.15\%$
test_compile_copy_nested[tensordict-eager]	0.1079ms	53.6059μs	18.6546 KOps/s	18.7855 KOps/s	$\color{#d91a1a}-0.70\%$
test_compile_copy_nested[pytree-compile]	0.1659ms	80.2574μs	12.4599 KOps/s	12.5817 KOps/s	$\color{#d91a1a}-0.97\%$
test_compile_copy_nested[pytree-eager]	0.1422ms	69.7870μs	14.3293 KOps/s	14.5572 KOps/s	$\color{#d91a1a}-1.57\%$
test_compile_add_one_flat[tensordict-compile]	0.2526ms	0.1038ms	9.6373 KOps/s	9.5810 KOps/s	$\color{#35bf28}+0.59\%$
test_compile_add_one_flat[tensordict-eager]	0.2905ms	0.2025ms	4.9380 KOps/s	4.8935 KOps/s	$\color{#35bf28}+0.91\%$
test_compile_add_one_flat[tensorclass-compile]	0.1614ms	45.4529μs	22.0008 KOps/s	22.3854 KOps/s	$\color{#d91a1a}-1.72\%$
test_compile_add_one_flat[tensorclass-eager]	0.4586ms	60.8105μs	16.4445 KOps/s	16.0692 KOps/s	$\color{#35bf28}+2.34\%$
test_compile_add_one_flat[pytree-compile]	0.1922ms	0.1017ms	9.8336 KOps/s	9.7566 KOps/s	$\color{#35bf28}+0.79\%$
test_compile_add_one_flat[pytree-eager]	0.3102ms	0.2068ms	4.8366 KOps/s	4.9433 KOps/s	$\color{#d91a1a}-2.16\%$
test_compile_add_self_flat[tensordict-eager]	0.3151ms	0.2138ms	4.6775 KOps/s	4.7521 KOps/s	$\color{#d91a1a}-1.57\%$
test_compile_add_self_flat[tensordict-compile]	0.2232ms	0.1026ms	9.7442 KOps/s	9.6734 KOps/s	$\color{#35bf28}+0.73\%$
test_compile_add_self_flat[tensorclass-eager]	0.1377ms	53.8636μs	18.5654 KOps/s	18.5593 KOps/s	$\color{#35bf28}+0.03\%$
test_compile_add_self_flat[tensorclass-compile]	0.2110ms	46.4538μs	21.5268 KOps/s	22.1490 KOps/s	$\color{#d91a1a}-2.81\%$
test_compile_add_self_flat[pytree-eager]	0.6654ms	0.1636ms	6.1129 KOps/s	6.3245 KOps/s	$\color{#d91a1a}-3.35\%$
test_compile_add_self_flat[pytree-compile]	0.2683ms	0.1018ms	9.8261 KOps/s	9.3420 KOps/s	$\textbf{\color{#35bf28}+5.18\%}$
test_compile_copy_flat[tensordict-compile]	0.1172ms	21.6223μs	46.2486 KOps/s	47.1206 KOps/s	$\color{#d91a1a}-1.85\%$
test_compile_copy_flat[tensordict-eager]	0.1380ms	56.9885μs	17.5474 KOps/s	17.1684 KOps/s	$\color{#35bf28}+2.21\%$
test_compile_copy_flat[pytree-compile]	0.1813ms	83.9783μs	11.9078 KOps/s	12.3129 KOps/s	$\color{#d91a1a}-3.29\%$
test_compile_copy_flat[pytree-eager]	0.1443ms	73.2133μs	13.6587 KOps/s	14.4943 KOps/s	$\textbf{\color{#d91a1a}-5.76\%}$
test_compile_assign_and_add[tensordict-compile]	0.3800ms	0.2069ms	4.8332 KOps/s	4.8244 KOps/s	$\color{#35bf28}+0.18\%$
test_compile_assign_and_add[tensordict-eager]	2.4210ms	1.3117ms	762.3798 Ops/s	776.8859 Ops/s	$\color{#d91a1a}-1.87\%$
test_compile_assign_and_add[pytree-compile]	0.4413ms	0.2029ms	4.9294 KOps/s	4.8679 KOps/s	$\color{#35bf28}+1.26\%$
test_compile_assign_and_add[pytree-eager]	1.3508ms	0.7873ms	1.2701 KOps/s	1.2454 KOps/s	$\color{#35bf28}+1.99\%$
test_compile_assign_and_add_stack[compile]	0.8190ms	0.4575ms	2.1856 KOps/s	2.2049 KOps/s	$\color{#d91a1a}-0.87\%$
test_compile_assign_and_add_stack[eager]	3.5667ms	2.5946ms	385.4141 Ops/s	383.9408 Ops/s	$\color{#35bf28}+0.38\%$
test_compile_indexing[tensor-tensordict-compile]	0.1722ms	35.3030μs	28.3262 KOps/s	28.2041 KOps/s	$\color{#35bf28}+0.43\%$
test_compile_indexing[tensor-tensordict-eager]	0.5547ms	33.9512μs	29.4540 KOps/s	31.4986 KOps/s	$\textbf{\color{#d91a1a}-6.49\%}$
test_compile_indexing[tensor-tensorclass-compile]	0.1240ms	29.3529μs	34.0682 KOps/s	34.0835 KOps/s	$\color{#d91a1a}-0.04\%$
test_compile_indexing[tensor-tensorclass-eager]	70.2610μs	24.6018μs	40.6474 KOps/s	43.8956 KOps/s	$\textbf{\color{#d91a1a}-7.40\%}$
test_compile_indexing[tensor-pytree-compile]	0.1052ms	29.4367μs	33.9712 KOps/s	33.9755 KOps/s	$\color{#d91a1a}-0.01\%$
test_compile_indexing[tensor-pytree-eager]	66.4040μs	24.5611μs	40.7148 KOps/s	43.3956 KOps/s	$\textbf{\color{#d91a1a}-6.18\%}$
test_compile_indexing[slice-tensordict-compile]	0.1712ms	50.9537μs	19.6257 KOps/s	19.5095 KOps/s	$\color{#35bf28}+0.60\%$
test_compile_indexing[slice-tensordict-eager]	0.5655ms	20.2672μs	49.3408 KOps/s	50.8236 KOps/s	$\color{#d91a1a}-2.92\%$
test_compile_indexing[slice-tensorclass-compile]	0.1591ms	43.5722μs	22.9504 KOps/s	22.7692 KOps/s	$\color{#35bf28}+0.80\%$
test_compile_indexing[slice-tensorclass-eager]	80.3800μs	19.7362μs	50.6683 KOps/s	53.4774 KOps/s	$\textbf{\color{#d91a1a}-5.25\%}$
test_compile_indexing[slice-pytree-compile]	0.1487ms	44.0256μs	22.7141 KOps/s	22.2096 KOps/s	$\color{#35bf28}+2.27\%$
test_compile_indexing[slice-pytree-eager]	77.6750μs	19.9581μs	50.1050 KOps/s	53.4794 KOps/s	$\textbf{\color{#d91a1a}-6.31\%}$
test_compile_indexing[int-tensordict-compile]	0.1955ms	52.9734μs	18.8774 KOps/s	19.0529 KOps/s	$\color{#d91a1a}-0.92\%$
test_compile_indexing[int-tensordict-eager]	0.9288ms	20.0826μs	49.7943 KOps/s	51.5514 KOps/s	$\color{#d91a1a}-3.41\%$
test_compile_indexing[int-tensorclass-compile]	0.1659ms	43.8642μs	22.7976 KOps/s	22.2879 KOps/s	$\color{#35bf28}+2.29\%$
test_compile_indexing[int-tensorclass-eager]	79.0170μs	19.7196μs	50.7109 KOps/s	53.5956 KOps/s	$\textbf{\color{#d91a1a}-5.38\%}$
test_compile_indexing[int-pytree-compile]	0.1773ms	44.5472μs	22.4481 KOps/s	21.8687 KOps/s	$\color{#35bf28}+2.65\%$
test_compile_indexing[int-pytree-eager]	86.0410μs	19.7299μs	50.6844 KOps/s	52.8197 KOps/s	$\color{#d91a1a}-4.04\%$
test_mod_add[eager]	0.1158ms	33.6877μs	29.6844 KOps/s	28.2872 KOps/s	$\color{#35bf28}+4.94\%$
test_mod_add[compile]	0.2786ms	47.8537μs	20.8970 KOps/s	21.8126 KOps/s	$\color{#d91a1a}-4.20\%$
test_mod_add[compile-overhead]	0.2266ms	46.2214μs	21.6350 KOps/s	21.5690 KOps/s	$\color{#35bf28}+0.31\%$
test_mod_wrap[eager]	0.4706ms	0.2267ms	4.4113 KOps/s	4.5235 KOps/s	$\color{#d91a1a}-2.48\%$
test_mod_wrap[compile]	0.4230ms	0.2040ms	4.9018 KOps/s	4.9263 KOps/s	$\color{#d91a1a}-0.50\%$
test_mod_wrap[compile-overhead]	0.4177ms	0.2020ms	4.9513 KOps/s	4.9280 KOps/s	$\color{#35bf28}+0.47\%$
test_mod_wrap_and_backward[eager]	13.8533ms	11.2960ms	88.5272 Ops/s	84.6266 Ops/s	$\color{#35bf28}+4.61\%$
test_mod_wrap_and_backward[compile]	19.0900ms	13.5144ms	73.9950 Ops/s	86.3063 Ops/s	$\textbf{\color{#d91a1a}-14.26\%}$
test_mod_wrap_and_backward[compile-overhead]	15.4392ms	13.3919ms	74.6721 Ops/s	79.4239 Ops/s	$\textbf{\color{#d91a1a}-5.98\%}$
test_seq_add[eager]	0.2457ms	0.1098ms	9.1095 KOps/s	8.9916 KOps/s	$\color{#35bf28}+1.31\%$
test_seq_add[compile]	0.1747ms	58.3772μs	17.1300 KOps/s	16.3544 KOps/s	$\color{#35bf28}+4.74\%$
test_seq_add[compile-overhead]	0.3000ms	57.2806μs	17.4579 KOps/s	16.9330 KOps/s	$\color{#35bf28}+3.10\%$
test_seq_wrap[eager]	0.5825ms	0.4315ms	2.3175 KOps/s	2.2297 KOps/s	$\color{#35bf28}+3.94\%$
test_seq_wrap[compile]	0.3540ms	0.2211ms	4.5222 KOps/s	4.2521 KOps/s	$\textbf{\color{#35bf28}+6.35\%}$
test_seq_wrap[compile-overhead]	0.4196ms	0.2222ms	4.5011 KOps/s	4.3883 KOps/s	$\color{#35bf28}+2.57\%$
test_func_call_runtime[False-eager]	0.7417ms	0.5486ms	1.8227 KOps/s	1.8555 KOps/s	$\color{#d91a1a}-1.76\%$
test_func_call_runtime[False-compile]	0.5775ms	0.4242ms	2.3575 KOps/s	2.3769 KOps/s	$\color{#d91a1a}-0.82\%$
test_func_call_runtime[False-compile-overhead]	0.6467ms	0.4245ms	2.3555 KOps/s	2.3675 KOps/s	$\color{#d91a1a}-0.51\%$
test_func_call_runtime[True-eager]	0.9605ms	0.7616ms	1.3131 KOps/s	1.3129 KOps/s	$\color{#35bf28}+0.02\%$
test_func_call_runtime[True-compile]	0.8340ms	0.4642ms	2.1543 KOps/s	2.1709 KOps/s	$\color{#d91a1a}-0.77\%$
test_func_call_runtime[True-compile-overhead]	0.6183ms	0.4632ms	2.1588 KOps/s	2.1660 KOps/s	$\color{#d91a1a}-0.33\%$
test_func_call_cm_runtime[False-eager]	0.7159ms	0.5484ms	1.8234 KOps/s	1.8581 KOps/s	$\color{#d91a1a}-1.87\%$
test_func_call_cm_runtime[False-compile]	0.8429ms	0.4250ms	2.3527 KOps/s	2.4028 KOps/s	$\color{#d91a1a}-2.08\%$
test_func_call_cm_runtime[False-compile-overhead]	0.7881ms	0.4276ms	2.3386 KOps/s	2.4143 KOps/s	$\color{#d91a1a}-3.14\%$
test_func_call_cm_runtime[True-eager]	1.1507ms	0.8940ms	1.1186 KOps/s	1.1274 KOps/s	$\color{#d91a1a}-0.79\%$
test_func_call_cm_runtime[True-compile]	0.8898ms	0.4940ms	2.0244 KOps/s	2.0710 KOps/s	$\color{#d91a1a}-2.25\%$
test_func_call_cm_runtime[True-compile-overhead]	0.8360ms	0.4944ms	2.0228 KOps/s	2.0524 KOps/s	$\color{#d91a1a}-1.45\%$
test_vmap_func_call_cm_runtime[eager]	2.5424ms	1.9051ms	524.9205 Ops/s	530.9400 Ops/s	$\color{#d91a1a}-1.13\%$
test_vmap_func_call_cm_runtime[compile]	0.6933ms	0.5141ms	1.9451 KOps/s	1.9228 KOps/s	$\color{#35bf28}+1.16\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.6516ms	0.5155ms	1.9398 KOps/s	1.9339 KOps/s	$\color{#35bf28}+0.30\%$
test_distributed	0.2569ms	0.1248ms	8.0111 KOps/s	7.7434 KOps/s	$\color{#35bf28}+3.46\%$
test_tdmodule	0.1552ms	24.7986μs	40.3249 KOps/s	37.8917 KOps/s	$\textbf{\color{#35bf28}+6.42\%}$
test_tdmodule_dispatch	0.1367ms	46.1331μs	21.6764 KOps/s	20.5578 KOps/s	$\textbf{\color{#35bf28}+5.44\%}$
test_tdseq	54.6420μs	24.9493μs	40.0813 KOps/s	37.1229 KOps/s	$\textbf{\color{#35bf28}+7.97\%}$
test_tdseq_dispatch	0.1115ms	48.2617μs	20.7203 KOps/s	19.8199 KOps/s	$\color{#35bf28}+4.54\%$
test_instantiation_functorch	1.6488ms	1.5200ms	657.8815 Ops/s	655.7946 Ops/s	$\color{#35bf28}+0.32\%$
test_exec_functorch	0.3618ms	0.1813ms	5.5169 KOps/s	5.3819 KOps/s	$\color{#35bf28}+2.51\%$
test_exec_functional_call	0.3122ms	0.1715ms	5.8313 KOps/s	5.7841 KOps/s	$\color{#35bf28}+0.82\%$
test_exec_td_decorator	0.5571ms	0.2333ms	4.2865 KOps/s	4.2699 KOps/s	$\color{#35bf28}+0.39\%$
test_vmap_mlp_speed_decorator[True-True]	1.0920ms	0.6616ms	1.5114 KOps/s	1.4724 KOps/s	$\color{#35bf28}+2.64\%$
test_vmap_mlp_speed_decorator[True-False]	0.9489ms	0.6582ms	1.5194 KOps/s	1.5435 KOps/s	$\color{#d91a1a}-1.56\%$
test_vmap_mlp_speed_decorator[False-True]	0.8356ms	0.5290ms	1.8905 KOps/s	1.8977 KOps/s	$\color{#d91a1a}-0.38\%$
test_vmap_mlp_speed_decorator[False-False]	0.9809ms	0.5328ms	1.8770 KOps/s	1.9195 KOps/s	$\color{#d91a1a}-2.21\%$
test_to_module_speed[True]	1.4331ms	1.2909ms	774.6508 Ops/s	775.0438 Ops/s	$\color{#d91a1a}-0.05\%$
test_to_module_speed[False]	2.0077ms	1.2794ms	781.5901 Ops/s	793.8714 Ops/s	$\color{#d91a1a}-1.55\%$
test_tc_init	76.1730μs	44.8806μs	22.2814 KOps/s	21.5351 KOps/s	$\color{#35bf28}+3.47\%$
test_tc_init_nested	0.1685ms	88.7054μs	11.2733 KOps/s	10.9144 KOps/s	$\color{#35bf28}+3.29\%$
test_tc_first_layer_tensor	29.8360μs	1.5227μs	656.7425 KOps/s	663.7834 KOps/s	$\color{#d91a1a}-1.06\%$
test_tc_first_layer_nontensor	22.8030μs	4.6986μs	212.8314 KOps/s	217.7551 KOps/s	$\color{#d91a1a}-2.26\%$
test_tc_second_layer_tensor	23.6240μs	2.8250μs	353.9879 KOps/s	361.5072 KOps/s	$\color{#d91a1a}-2.08\%$
test_tc_second_layer_nontensor	39.2930μs	6.0961μs	164.0381 KOps/s	168.7694 KOps/s	$\color{#d91a1a}-2.80\%$
test_unbind	0.2346s	14.9810ms	66.7513 Ops/s	78.7751 Ops/s	$\textbf{\color{#d91a1a}-15.26\%}$
test_full_like	11.5405ms	8.0516ms	124.1983 Ops/s	125.4318 Ops/s	$\color{#d91a1a}-0.98\%$
test_zeros_like	3.9278ms	3.0814ms	324.5278 Ops/s	337.8897 Ops/s	$\color{#d91a1a}-3.95\%$
test_ones_like	3.8282ms	3.4531ms	289.5984 Ops/s	276.2951 Ops/s	$\color{#35bf28}+4.81\%$
test_clone	6.4179ms	5.5637ms	179.7372 Ops/s	184.6536 Ops/s	$\color{#d91a1a}-2.66\%$
test_squeeze	59.7820μs	11.5966μs	86.2324 KOps/s	83.9386 KOps/s	$\color{#35bf28}+2.73\%$
test_unsqueeze	0.3196ms	90.7575μs	11.0184 KOps/s	11.5336 KOps/s	$\color{#d91a1a}-4.47\%$
test_split	0.4487ms	0.1992ms	5.0211 KOps/s	5.2477 KOps/s	$\color{#d91a1a}-4.32\%$
test_permute	0.4531ms	0.2202ms	4.5406 KOps/s	4.7009 KOps/s	$\color{#d91a1a}-3.41\%$
test_stack	32.1624ms	26.1778ms	38.2003 Ops/s	38.9887 Ops/s	$\color{#d91a1a}-2.02\%$
test_cat	31.2623ms	25.9653ms	38.5129 Ops/s	38.7804 Ops/s	$\color{#d91a1a}-0.69\%$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}15$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	39.3500μs	10.4064μs	96.0946 KOps/s	94.5884 KOps/s	$\color{#35bf28}+1.59\%$
test_plain_set_stack_nested	95.2810μs	10.5013μs	95.2262 KOps/s	94.5145 KOps/s	$\color{#35bf28}+0.75\%$
test_plain_set_nested_inplace	49.9010μs	11.3239μs	88.3090 KOps/s	87.0178 KOps/s	$\color{#35bf28}+1.48\%$
test_plain_set_stack_nested_inplace	0.1105ms	11.2681μs	88.7465 KOps/s	87.7040 KOps/s	$\color{#35bf28}+1.19\%$
test_items	35.4510μs	2.8294μs	353.4309 KOps/s	338.8597 KOps/s	$\color{#35bf28}+4.30\%$
test_items_nested	0.4453ms	0.3446ms	2.9021 KOps/s	2.8846 KOps/s	$\color{#35bf28}+0.61\%$
test_items_nested_locked	0.4330ms	0.3457ms	2.8926 KOps/s	2.8712 KOps/s	$\color{#35bf28}+0.75\%$
test_items_nested_leaf	94.7310μs	57.5109μs	17.3880 KOps/s	17.4265 KOps/s	$\color{#d91a1a}-0.22\%$
test_items_stack_nested	1.1855ms	0.3475ms	2.8777 KOps/s	2.8877 KOps/s	$\color{#d91a1a}-0.35\%$
test_items_stack_nested_leaf	0.1445ms	58.7006μs	17.0356 KOps/s	16.8360 KOps/s	$\color{#35bf28}+1.19\%$
test_items_stack_nested_locked	0.4333ms	0.3483ms	2.8710 KOps/s	2.8337 KOps/s	$\color{#35bf28}+1.32\%$
test_keys	32.7810μs	3.4123μs	293.0573 KOps/s	291.4042 KOps/s	$\color{#35bf28}+0.57\%$
test_keys_nested	0.1608ms	69.4796μs	14.3927 KOps/s	14.0409 KOps/s	$\color{#35bf28}+2.51\%$
test_keys_nested_locked	0.8716ms	75.4570μs	13.2526 KOps/s	13.0874 KOps/s	$\color{#35bf28}+1.26\%$
test_keys_nested_leaf	0.1979ms	60.6043μs	16.5005 KOps/s	16.2896 KOps/s	$\color{#35bf28}+1.29\%$
test_keys_stack_nested	99.2120μs	70.8010μs	14.1241 KOps/s	13.9257 KOps/s	$\color{#35bf28}+1.42\%$
test_keys_stack_nested_leaf	91.4610μs	61.9494μs	16.1422 KOps/s	16.0378 KOps/s	$\color{#35bf28}+0.65\%$
test_keys_stack_nested_locked	0.1377ms	76.6264μs	13.0503 KOps/s	13.0023 KOps/s	$\color{#35bf28}+0.37\%$
test_values	6.8435μs	0.8423μs	1.1872 MOps/s	1.1849 MOps/s	$\color{#35bf28}+0.19\%$
test_values_nested	68.2420μs	30.9909μs	32.2675 KOps/s	32.1021 KOps/s	$\color{#35bf28}+0.52\%$
test_values_nested_locked	58.2010μs	32.7757μs	30.5104 KOps/s	30.9050 KOps/s	$\color{#d91a1a}-1.28\%$
test_values_nested_leaf	58.9610μs	33.5398μs	29.8153 KOps/s	30.1059 KOps/s	$\color{#d91a1a}-0.97\%$
test_values_stack_nested	61.9710μs	31.7716μs	31.4747 KOps/s	31.6734 KOps/s	$\color{#d91a1a}-0.63\%$
test_values_stack_nested_leaf	62.3110μs	34.3659μs	29.0986 KOps/s	29.4611 KOps/s	$\color{#d91a1a}-1.23\%$
test_values_stack_nested_locked	63.6710μs	33.4068μs	29.9340 KOps/s	30.0682 KOps/s	$\color{#d91a1a}-0.45\%$
test_membership	2.0801μs	0.5093μs	1.9635 MOps/s	1.9487 MOps/s	$\color{#35bf28}+0.76\%$
test_membership_nested	21.4855μs	1.9289μs	518.4353 KOps/s	513.7263 KOps/s	$\color{#35bf28}+0.92\%$
test_membership_nested_leaf	18.0600μs	1.9548μs	511.5658 KOps/s	511.0537 KOps/s	$\color{#35bf28}+0.10\%$
test_membership_stacked_nested	36.8110μs	2.0119μs	497.0465 KOps/s	493.2604 KOps/s	$\color{#35bf28}+0.77\%$
test_membership_stacked_nested_leaf	28.4000μs	2.0137μs	496.6094 KOps/s	493.9568 KOps/s	$\color{#35bf28}+0.54\%$
test_membership_nested_last	29.2610μs	2.9176μs	342.7424 KOps/s	343.2271 KOps/s	$\color{#d91a1a}-0.14\%$
test_membership_nested_leaf_last	31.0310μs	2.9548μs	338.4365 KOps/s	341.5729 KOps/s	$\color{#d91a1a}-0.92\%$
test_membership_stacked_nested_last	33.4800μs	2.8955μs	345.3598 KOps/s	342.6644 KOps/s	$\color{#35bf28}+0.79\%$
test_membership_stacked_nested_leaf_last	36.1500μs	2.9278μs	341.5568 KOps/s	343.8072 KOps/s	$\color{#d91a1a}-0.65\%$
test_nested_getleaf	33.7610μs	6.1572μs	162.4103 KOps/s	164.8398 KOps/s	$\color{#d91a1a}-1.47\%$
test_nested_get	35.9110μs	5.8181μs	171.8786 KOps/s	173.8255 KOps/s	$\color{#d91a1a}-1.12\%$
test_stacked_getleaf	44.3510μs	6.0689μs	164.7733 KOps/s	164.7651 KOps/s	$+0.00\%$
test_stacked_get	29.3300μs	5.7874μs	172.7905 KOps/s	173.2487 KOps/s	$\color{#d91a1a}-0.26\%$
test_nested_getitemleaf	24.8210μs	6.1537μs	162.5027 KOps/s	161.7754 KOps/s	$\color{#35bf28}+0.45\%$
test_nested_getitem	26.2400μs	5.8601μs	170.6452 KOps/s	171.5300 KOps/s	$\color{#d91a1a}-0.52\%$
test_stacked_getitemleaf	35.3200μs	6.1694μs	162.0911 KOps/s	161.8827 KOps/s	$\color{#35bf28}+0.13\%$
test_stacked_getitem	29.2500μs	5.8986μs	169.5324 KOps/s	170.6631 KOps/s	$\color{#d91a1a}-0.66\%$
test_lock_nested	0.8494ms	0.3512ms	2.8477 KOps/s	2.7440 KOps/s	$\color{#35bf28}+3.78\%$
test_lock_stack_nested	0.3572ms	0.3221ms	3.1042 KOps/s	3.0647 KOps/s	$\color{#35bf28}+1.29\%$
test_unlock_nested	0.6213ms	0.2916ms	3.4294 KOps/s	3.3522 KOps/s	$\color{#35bf28}+2.30\%$
test_unlock_stack_nested	0.2912ms	0.2630ms	3.8023 KOps/s	3.7836 KOps/s	$\color{#35bf28}+0.50\%$
test_flatten_speed	0.1028ms	74.0275μs	13.5085 KOps/s	13.5741 KOps/s	$\color{#d91a1a}-0.48\%$
test_unflatten_speed	0.4436ms	0.2989ms	3.3458 KOps/s	3.3522 KOps/s	$\color{#d91a1a}-0.19\%$
test_common_ops	1.4856ms	0.5600ms	1.7857 KOps/s	1.7358 KOps/s	$\color{#35bf28}+2.87\%$
test_creation	0.1714ms	1.4124μs	708.0320 KOps/s	693.3734 KOps/s	$\color{#35bf28}+2.11\%$
test_creation_empty	1.5072ms	6.8745μs	145.4656 KOps/s	138.2211 KOps/s	$\textbf{\color{#35bf28}+5.24\%}$
test_creation_nested_1	40.5110μs	8.4921μs	117.7562 KOps/s	112.5239 KOps/s	$\color{#35bf28}+4.65\%$
test_creation_nested_2	34.0200μs	10.8574μs	92.1029 KOps/s	88.7087 KOps/s	$\color{#35bf28}+3.83\%$
test_clone	0.1175ms	10.0306μs	99.6953 KOps/s	99.3349 KOps/s	$\color{#35bf28}+0.36\%$
test_getitem[int]	1.3018ms	10.1529μs	98.4940 KOps/s	98.2894 KOps/s	$\color{#35bf28}+0.21\%$
test_getitem[slice_int]	0.1139ms	20.0349μs	49.9130 KOps/s	50.0294 KOps/s	$\color{#d91a1a}-0.23\%$
test_getitem[range]	0.1387ms	35.6801μs	28.0269 KOps/s	26.7976 KOps/s	$\color{#35bf28}+4.59\%$
test_getitem[tuple]	0.1079ms	17.1480μs	58.3158 KOps/s	57.1867 KOps/s	$\color{#35bf28}+1.97\%$
test_getitem[list]	0.3010ms	31.3439μs	31.9042 KOps/s	30.1938 KOps/s	$\textbf{\color{#35bf28}+5.66\%}$
test_setitem_dim[int]	39.1300μs	17.5262μs	57.0574 KOps/s	55.5930 KOps/s	$\color{#35bf28}+2.63\%$
test_setitem_dim[slice_int]	67.1210μs	35.7830μs	27.9462 KOps/s	27.2566 KOps/s	$\color{#35bf28}+2.53\%$
test_setitem_dim[range]	80.6820μs	50.5796μs	19.7708 KOps/s	19.1885 KOps/s	$\color{#35bf28}+3.03\%$
test_setitem_dim[tuple]	51.6710μs	30.7183μs	32.5539 KOps/s	31.1066 KOps/s	$\color{#35bf28}+4.65\%$
test_setitem	0.1128ms	13.7193μs	72.8903 KOps/s	70.6575 KOps/s	$\color{#35bf28}+3.16\%$
test_set	0.1157ms	13.3093μs	75.1354 KOps/s	73.0027 KOps/s	$\color{#35bf28}+2.92\%$
test_set_shared	1.6141ms	0.1432ms	6.9848 KOps/s	6.9355 KOps/s	$\color{#35bf28}+0.71\%$
test_update	0.1054ms	15.4733μs	64.6273 KOps/s	61.5798 KOps/s	$\color{#35bf28}+4.95\%$
test_update_nested	1.1420ms	20.9913μs	47.6387 KOps/s	47.6665 KOps/s	$\color{#d91a1a}-0.06\%$
test_update__nested	51.7510μs	22.9860μs	43.5047 KOps/s	42.6325 KOps/s	$\color{#35bf28}+2.05\%$
test_set_nested	0.1118ms	14.1579μs	70.6321 KOps/s	67.8289 KOps/s	$\color{#35bf28}+4.13\%$
test_set_nested_new	0.1156ms	16.9726μs	58.9185 KOps/s	59.4852 KOps/s	$\color{#d91a1a}-0.95\%$
test_select	0.1240ms	27.7164μs	36.0797 KOps/s	35.4522 KOps/s	$\color{#35bf28}+1.77\%$
test_select_nested	73.7810μs	41.2351μs	24.2512 KOps/s	24.4595 KOps/s	$\color{#d91a1a}-0.85\%$
test_exclude_nested	0.1085ms	59.5616μs	16.7893 KOps/s	16.9200 KOps/s	$\color{#d91a1a}-0.77\%$
test_empty[True]	0.3224ms	0.2713ms	3.6856 KOps/s	3.7151 KOps/s	$\color{#d91a1a}-0.80\%$
test_empty[False]	3.1040μs	0.7342μs	1.3620 MOps/s	1.3622 MOps/s	$\color{#d91a1a}-0.02\%$
test_to	86.2910μs	52.6209μs	19.0039 KOps/s	17.9589 KOps/s	$\textbf{\color{#35bf28}+5.82\%}$
test_to_nonblocking	84.7210μs	44.1001μs	22.6757 KOps/s	23.2632 KOps/s	$\color{#d91a1a}-2.53\%$
test_unbind_speed	1.7086ms	0.2172ms	4.6040 KOps/s	4.3906 KOps/s	$\color{#35bf28}+4.86\%$
test_unbind_speed_stack0	0.2681ms	0.2184ms	4.5788 KOps/s	4.4698 KOps/s	$\color{#35bf28}+2.44\%$
test_unbind_speed_stack1	92.9184ms	0.6269ms	1.5952 KOps/s	1.5610 KOps/s	$\color{#35bf28}+2.19\%$
test_split	93.4650ms	1.5419ms	648.5610 Ops/s	593.6660 Ops/s	$\textbf{\color{#35bf28}+9.25\%}$
test_chunk	95.7219ms	1.6901ms	591.6719 Ops/s	637.7767 Ops/s	$\textbf{\color{#d91a1a}-7.23\%}$
test_consolidate[False-None]	3.2532ms	2.5585ms	390.8480 Ops/s	386.9618 Ops/s	$\color{#35bf28}+1.00\%$
test_consolidate[default-None]	1.6954ms	1.6132ms	619.8755 Ops/s	593.9414 Ops/s	$\color{#35bf28}+4.37\%$
test_consolidate[reduce-overhead-None]	1.8306ms	1.6724ms	597.9605 Ops/s	576.8876 Ops/s	$\color{#35bf28}+3.65\%$
test_consolidate_njt[False-None]	6.4481ms	6.2339ms	160.4124 Ops/s	151.5315 Ops/s	$\textbf{\color{#35bf28}+5.86\%}$
test_to[False-False-None]	1.8751ms	1.6677ms	599.6262 Ops/s	609.6659 Ops/s	$\color{#d91a1a}-1.65\%$
test_to[True-False-None]	1.4497ms	1.2648ms	790.6485 Ops/s	770.5512 Ops/s	$\color{#35bf28}+2.61\%$
test_to[within-False-None]	0.2934s	5.0821ms	196.7706 Ops/s	255.4697 Ops/s	$\textbf{\color{#d91a1a}-22.98\%}$
test_to[True-default-None]	5.4052ms	4.9236ms	203.1046 Ops/s	200.7955 Ops/s	$\color{#35bf28}+1.15\%$
test_to_njt[False-False-None]	7.2415ms	6.8291ms	146.4325 Ops/s	146.4517 Ops/s	$\color{#d91a1a}-0.01\%$
test_to_njt[True-False-None]	5.7216ms	5.2980ms	188.7507 Ops/s	188.1396 Ops/s	$\color{#35bf28}+0.32\%$
test_to_njt[within-False-None]	11.8188ms	11.6605ms	85.7594 Ops/s	85.2760 Ops/s	$\color{#35bf28}+0.57\%$
test_creation[device0]	0.6308ms	77.4436μs	12.9126 KOps/s	12.1831 KOps/s	$\textbf{\color{#35bf28}+5.99\%}$
test_creation_from_tensor	0.5484ms	80.8248μs	12.3724 KOps/s	12.0673 KOps/s	$\color{#35bf28}+2.53\%$
test_add_one[memmap_tensor0]	0.3294ms	6.4265μs	155.6046 KOps/s	153.2903 KOps/s	$\color{#35bf28}+1.51\%$
test_contiguous[memmap_tensor0]	2.5861μs	0.3964μs	2.5224 MOps/s	2.4735 MOps/s	$\color{#35bf28}+1.98\%$
test_stack[memmap_tensor0]	23.3900μs	4.1507μs	240.9242 KOps/s	237.8436 KOps/s	$\color{#35bf28}+1.30\%$
test_memmaptd_index	1.9614ms	0.2366ms	4.2267 KOps/s	4.0929 KOps/s	$\color{#35bf28}+3.27\%$
test_memmaptd_index_astensor	0.5580ms	0.2912ms	3.4341 KOps/s	3.2932 KOps/s	$\color{#35bf28}+4.28\%$
test_memmaptd_index_op	0.9184ms	0.5300ms	1.8869 KOps/s	1.8007 KOps/s	$\color{#35bf28}+4.79\%$
test_serialize_model	0.1317s	0.1302s	7.6777 Ops/s	7.7149 Ops/s	$\color{#d91a1a}-0.48\%$
test_serialize_model_pickle	1.3506s	1.2164s	0.8221 Ops/s	0.8239 Ops/s	$\color{#d91a1a}-0.22\%$
test_serialize_weights	0.1301s	0.1295s	7.7223 Ops/s	7.7158 Ops/s	$\color{#35bf28}+0.08\%$
test_serialize_weights_returnearly	0.3347s	54.1451ms	18.4689 Ops/s	14.9710 Ops/s	$\textbf{\color{#35bf28}+23.36\%}$
test_serialize_weights_pickle	1.4059s	1.2263s	0.8154 Ops/s	0.8203 Ops/s	$\color{#d91a1a}-0.60\%$
test_reshape_pytree	51.3210μs	21.4826μs	46.5493 KOps/s	45.4024 KOps/s	$\color{#35bf28}+2.53\%$
test_reshape_td	62.8110μs	25.5406μs	39.1533 KOps/s	39.6885 KOps/s	$\color{#d91a1a}-1.35\%$
test_view_pytree	49.1110μs	21.2452μs	47.0695 KOps/s	46.3730 KOps/s	$\color{#35bf28}+1.50\%$
test_view_td	0.1479ms	27.4798μs	36.3904 KOps/s	35.2266 KOps/s	$\color{#35bf28}+3.30\%$
test_unbind_pytree	54.6910μs	26.5376μs	37.6823 KOps/s	37.0801 KOps/s	$\color{#35bf28}+1.62\%$
test_unbind_td	0.5596ms	33.8856μs	29.5111 KOps/s	29.7848 KOps/s	$\color{#d91a1a}-0.92\%$
test_split_pytree	66.8910μs	28.8495μs	34.6626 KOps/s	34.3918 KOps/s	$\color{#35bf28}+0.79\%$
test_split_td	0.7275ms	36.7560μs	27.2065 KOps/s	27.1927 KOps/s	$\color{#35bf28}+0.05\%$
test_add_pytree	59.0410μs	32.5901μs	30.6841 KOps/s	30.3621 KOps/s	$\color{#35bf28}+1.06\%$
test_add_td	81.2510μs	41.1683μs	24.2905 KOps/s	23.5696 KOps/s	$\color{#35bf28}+3.06\%$
test_compile_add_one_nested[tensordict-compile]	0.1651ms	0.1186ms	8.4283 KOps/s	8.1983 KOps/s	$\color{#35bf28}+2.81\%$
test_compile_add_one_nested[tensordict-eager]	0.2787ms	0.1252ms	7.9886 KOps/s	8.2689 KOps/s	$\color{#d91a1a}-3.39\%$
test_compile_add_one_nested[pytree-compile]	0.1541ms	93.3693μs	10.7102 KOps/s	10.3254 KOps/s	$\color{#35bf28}+3.73\%$
test_compile_add_one_nested[pytree-eager]	0.7390ms	0.1449ms	6.8992 KOps/s	6.7628 KOps/s	$\color{#35bf28}+2.02\%$
test_compile_copy_nested[tensordict-compile]	76.3710μs	21.9723μs	45.5118 KOps/s	45.5964 KOps/s	$\color{#d91a1a}-0.19\%$
test_compile_copy_nested[tensordict-eager]	0.1035ms	26.2060μs	38.1592 KOps/s	37.3884 KOps/s	$\color{#35bf28}+2.06\%$
test_compile_copy_nested[pytree-compile]	0.3784ms	64.0971μs	15.6013 KOps/s	15.4644 KOps/s	$\color{#35bf28}+0.89\%$
test_compile_copy_nested[pytree-eager]	79.3610μs	49.3496μs	20.2636 KOps/s	20.0460 KOps/s	$\color{#35bf28}+1.09\%$
test_compile_add_one_flat[tensordict-compile]	0.1901ms	0.1374ms	7.2757 KOps/s	6.8987 KOps/s	$\textbf{\color{#35bf28}+5.47\%}$
test_compile_add_one_flat[tensordict-eager]	0.2931ms	0.2047ms	4.8844 KOps/s	4.8823 KOps/s	$\color{#35bf28}+0.04\%$
test_compile_add_one_flat[tensorclass-compile]	0.1307ms	93.8307μs	10.6575 KOps/s	9.9108 KOps/s	$\textbf{\color{#35bf28}+7.53\%}$
test_compile_add_one_flat[tensorclass-eager]	0.1033ms	51.3066μs	19.4907 KOps/s	19.7627 KOps/s	$\color{#d91a1a}-1.38\%$
test_compile_add_one_flat[pytree-compile]	0.1825ms	0.1357ms	7.3667 KOps/s	7.4584 KOps/s	$\color{#d91a1a}-1.23\%$
test_compile_add_one_flat[pytree-eager]	0.5675ms	0.4765ms	2.0987 KOps/s	2.1200 KOps/s	$\color{#d91a1a}-1.00\%$
test_compile_add_self_flat[tensordict-eager]	0.3467ms	0.2444ms	4.0909 KOps/s	4.1097 KOps/s	$\color{#d91a1a}-0.46\%$
test_compile_add_self_flat[tensordict-compile]	0.1815ms	0.1403ms	7.1272 KOps/s	7.0086 KOps/s	$\color{#35bf28}+1.69\%$
test_compile_add_self_flat[tensorclass-eager]	0.1446ms	61.5394μs	16.2497 KOps/s	16.9958 KOps/s	$\color{#d91a1a}-4.39\%$
test_compile_add_self_flat[tensorclass-compile]	0.1435ms	98.1015μs	10.1935 KOps/s	10.2069 KOps/s	$\color{#d91a1a}-0.13\%$
test_compile_add_self_flat[pytree-eager]	0.4744ms	0.4017ms	2.4897 KOps/s	2.5223 KOps/s	$\color{#d91a1a}-1.29\%$
test_compile_add_self_flat[pytree-compile]	0.1812ms	0.1324ms	7.5503 KOps/s	7.4334 KOps/s	$\color{#35bf28}+1.57\%$
test_compile_copy_flat[tensordict-compile]	53.2910μs	18.6420μs	53.6423 KOps/s	51.5969 KOps/s	$\color{#35bf28}+3.96\%$
test_compile_copy_flat[tensordict-eager]	59.9010μs	26.7312μs	37.4095 KOps/s	38.0836 KOps/s	$\color{#d91a1a}-1.77\%$
test_compile_copy_flat[pytree-compile]	0.1372ms	68.3128μs	14.6385 KOps/s	14.5893 KOps/s	$\color{#35bf28}+0.34\%$
test_compile_copy_flat[pytree-eager]	78.5420μs	50.7655μs	19.6984 KOps/s	19.7274 KOps/s	$\color{#d91a1a}-0.15\%$
test_compile_assign_and_add[tensordict-compile]	1.6353ms	0.3957ms	2.5272 KOps/s	2.1829 KOps/s	$\textbf{\color{#35bf28}+15.77\%}$
test_compile_assign_and_add[tensordict-eager]	2.7572ms	2.5710ms	388.9585 Ops/s	392.7807 Ops/s	$\color{#d91a1a}-0.97\%$
test_compile_assign_and_add[pytree-compile]	1.5990ms	0.4320ms	2.3148 KOps/s	2.2815 KOps/s	$\color{#35bf28}+1.46\%$
test_compile_assign_and_add[pytree-eager]	2.7477ms	2.5859ms	386.7129 Ops/s	386.2997 Ops/s	$\color{#35bf28}+0.11\%$
test_compile_indexing[tensor-tensordict-compile]	0.1767ms	0.1167ms	8.5698 KOps/s	8.7888 KOps/s	$\color{#d91a1a}-2.49\%$
test_compile_indexing[tensor-tensordict-eager]	0.9659ms	79.1315μs	12.6372 KOps/s	12.3754 KOps/s	$\color{#35bf28}+2.12\%$
test_compile_indexing[tensor-tensorclass-compile]	0.1890ms	0.1095ms	9.1297 KOps/s	9.4369 KOps/s	$\color{#d91a1a}-3.26\%$
test_compile_indexing[tensor-tensorclass-eager]	0.2015ms	68.3660μs	14.6272 KOps/s	15.0584 KOps/s	$\color{#d91a1a}-2.86\%$
test_compile_indexing[tensor-pytree-compile]	0.2074ms	0.1102ms	9.0780 KOps/s	9.4840 KOps/s	$\color{#d91a1a}-4.28\%$
test_compile_indexing[tensor-pytree-eager]	0.1931ms	69.0969μs	14.4724 KOps/s	15.0433 KOps/s	$\color{#d91a1a}-3.79\%$
test_compile_indexing[slice-tensordict-compile]	0.1979ms	98.8073μs	10.1207 KOps/s	10.0711 KOps/s	$\color{#35bf28}+0.49\%$
test_compile_indexing[slice-tensordict-eager]	0.1434ms	16.0004μs	62.4984 KOps/s	59.7812 KOps/s	$\color{#35bf28}+4.55\%$
test_compile_indexing[slice-tensorclass-compile]	0.2449ms	97.5114μs	10.2552 KOps/s	10.4351 KOps/s	$\color{#d91a1a}-1.72\%$
test_compile_indexing[slice-tensorclass-eager]	0.1133ms	15.2120μs	65.7374 KOps/s	64.5692 KOps/s	$\color{#35bf28}+1.81\%$
test_compile_indexing[slice-pytree-compile]	0.1997ms	96.4184μs	10.3715 KOps/s	10.3561 KOps/s	$\color{#35bf28}+0.15\%$
test_compile_indexing[slice-pytree-eager]	62.7610μs	15.0725μs	66.3458 KOps/s	60.5447 KOps/s	$\textbf{\color{#35bf28}+9.58\%}$
test_compile_indexing[int-tensordict-compile]	0.1982ms	0.1003ms	9.9665 KOps/s	9.8897 KOps/s	$\color{#35bf28}+0.78\%$
test_compile_indexing[int-tensordict-eager]	0.5882ms	15.8139μs	63.2354 KOps/s	61.6682 KOps/s	$\color{#35bf28}+2.54\%$
test_compile_indexing[int-tensorclass-compile]	0.2030ms	97.5694μs	10.2491 KOps/s	10.3443 KOps/s	$\color{#d91a1a}-0.92\%$
test_compile_indexing[int-tensorclass-eager]	0.1070ms	15.0215μs	66.5711 KOps/s	65.2490 KOps/s	$\color{#35bf28}+2.03\%$
test_compile_indexing[int-pytree-compile]	0.1883ms	97.5517μs	10.2510 KOps/s	10.3484 KOps/s	$\color{#d91a1a}-0.94\%$
test_compile_indexing[int-pytree-eager]	0.1560ms	15.0401μs	66.4890 KOps/s	65.8864 KOps/s	$\color{#35bf28}+0.91\%$
test_mod_add[eager]	0.1536ms	33.5634μs	29.7943 KOps/s	28.2223 KOps/s	$\textbf{\color{#35bf28}+5.57\%}$
test_mod_add[compile]	0.1902ms	80.4932μs	12.4234 KOps/s	12.3562 KOps/s	$\color{#35bf28}+0.54\%$
test_mod_add[compile-overhead]	0.3288ms	0.1704ms	5.8700 KOps/s	5.6683 KOps/s	$\color{#35bf28}+3.56\%$
test_mod_wrap[eager]	0.3863ms	0.2504ms	3.9936 KOps/s	3.9648 KOps/s	$\color{#35bf28}+0.73\%$
test_mod_wrap[compile]	0.3524ms	0.2759ms	3.6239 KOps/s	3.5791 KOps/s	$\color{#35bf28}+1.25\%$
test_mod_wrap[compile-overhead]	7.3057ms	3.8065ms	262.7103 Ops/s	264.0456 Ops/s	$\color{#d91a1a}-0.51\%$
test_mod_wrap_and_backward[eager]	1.6626ms	1.4096ms	709.4463 Ops/s	707.8786 Ops/s	$\color{#35bf28}+0.22\%$
test_mod_wrap_and_backward[compile]	1.3960ms	1.2213ms	818.8020 Ops/s	742.6288 Ops/s	$\textbf{\color{#35bf28}+10.26\%}$
test_mod_wrap_and_backward[compile-overhead]	1.3499ms	0.9015ms	1.1092 KOps/s	968.9545 Ops/s	$\textbf{\color{#35bf28}+14.47\%}$
test_seq_add[eager]	0.1781ms	0.1058ms	9.4493 KOps/s	9.0650 KOps/s	$\color{#35bf28}+4.24\%$
test_seq_add[compile]	0.1465ms	86.1299μs	11.6104 KOps/s	11.4117 KOps/s	$\color{#35bf28}+1.74\%$
test_seq_add[compile-overhead]	0.1655ms	0.1256ms	7.9621 KOps/s	7.8670 KOps/s	$\color{#35bf28}+1.21\%$
test_seq_wrap[eager]	0.5409ms	0.3969ms	2.5198 KOps/s	2.4596 KOps/s	$\color{#35bf28}+2.45\%$
test_seq_wrap[compile]	0.3386ms	0.2902ms	3.4460 KOps/s	3.3579 KOps/s	$\color{#35bf28}+2.62\%$
test_seq_wrap[compile-overhead]	0.2653ms	0.2183ms	4.5808 KOps/s	4.4763 KOps/s	$\color{#35bf28}+2.33\%$
test_func_call_runtime[False-eager]	0.7548ms	0.7071ms	1.4142 KOps/s	1.3849 KOps/s	$\color{#35bf28}+2.12\%$
test_func_call_runtime[False-compile]	0.9734ms	0.7707ms	1.2975 KOps/s	1.3713 KOps/s	$\textbf{\color{#d91a1a}-5.38\%}$
test_func_call_runtime[False-compile-overhead]	0.4021ms	0.3521ms	2.8399 KOps/s	2.8181 KOps/s	$\color{#35bf28}+0.77\%$
test_func_call_runtime[True-eager]	1.0039ms	0.8670ms	1.1534 KOps/s	1.1379 KOps/s	$\color{#35bf28}+1.36\%$
test_func_call_runtime[True-compile]	0.8036ms	0.7437ms	1.3446 KOps/s	1.3313 KOps/s	$\color{#35bf28}+1.00\%$
test_func_call_runtime[True-compile-overhead]	0.4331ms	0.3743ms	2.6716 KOps/s	2.6566 KOps/s	$\color{#35bf28}+0.56\%$
test_func_call_cm_runtime[False-eager]	0.7825ms	0.7035ms	1.4215 KOps/s	1.3994 KOps/s	$\color{#35bf28}+1.58\%$
test_func_call_cm_runtime[False-compile]	0.8704ms	0.7204ms	1.3881 KOps/s	1.3740 KOps/s	$\color{#35bf28}+1.03\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4229ms	0.3548ms	2.8188 KOps/s	2.8134 KOps/s	$\color{#35bf28}+0.19\%$
test_func_call_cm_runtime[True-eager]	1.0502ms	0.9593ms	1.0425 KOps/s	1.0268 KOps/s	$\color{#35bf28}+1.52\%$
test_func_call_cm_runtime[True-compile]	0.8265ms	0.7723ms	1.2948 KOps/s	1.2874 KOps/s	$\color{#35bf28}+0.57\%$
test_func_call_cm_runtime[True-compile-overhead]	0.4536ms	0.3996ms	2.5025 KOps/s	2.4824 KOps/s	$\color{#35bf28}+0.81\%$
test_vmap_func_call_cm_runtime[eager]	2.4956ms	2.0224ms	494.4703 Ops/s	490.6519 Ops/s	$\color{#35bf28}+0.78\%$
test_vmap_func_call_cm_runtime[compile]	1.0421ms	0.7830ms	1.2771 KOps/s	1.2499 KOps/s	$\color{#35bf28}+2.17\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.4643ms	0.4009ms	2.4943 KOps/s	2.4354 KOps/s	$\color{#35bf28}+2.42\%$
test_distributed	7.0640ms	0.3026ms	3.3052 KOps/s	8.5446 KOps/s	$\textbf{\color{#d91a1a}-61.32\%}$
test_tdmodule	53.5300μs	18.8369μs	53.0874 KOps/s	52.5050 KOps/s	$\color{#35bf28}+1.11\%$
test_tdmodule_dispatch	89.2710μs	33.7866μs	29.5975 KOps/s	30.2083 KOps/s	$\color{#d91a1a}-2.02\%$
test_tdseq	46.2510μs	18.8902μs	52.9374 KOps/s	54.1878 KOps/s	$\color{#d91a1a}-2.31\%$
test_tdseq_dispatch	57.9410μs	35.6941μs	28.0158 KOps/s	28.4658 KOps/s	$\color{#d91a1a}-1.58\%$
test_instantiation_functorch	1.6359ms	1.5020ms	665.7655 Ops/s	659.0167 Ops/s	$\color{#35bf28}+1.02\%$
test_exec_functorch	0.1849ms	0.1344ms	7.4398 KOps/s	7.1097 KOps/s	$\color{#35bf28}+4.64\%$
test_exec_functional_call	0.1905ms	0.1282ms	7.8030 KOps/s	7.6311 KOps/s	$\color{#35bf28}+2.25\%$
test_exec_td_decorator	0.3581ms	0.1737ms	5.7570 KOps/s	5.7073 KOps/s	$\color{#35bf28}+0.87\%$
test_vmap_mlp_speed_decorator[True-True]	0.7944ms	0.6647ms	1.5044 KOps/s	1.5070 KOps/s	$\color{#d91a1a}-0.17\%$
test_vmap_mlp_speed_decorator[True-False]	0.7674ms	0.6709ms	1.4906 KOps/s	1.5152 KOps/s	$\color{#d91a1a}-1.62\%$
test_vmap_mlp_speed_decorator[False-True]	0.7804ms	0.5874ms	1.7024 KOps/s	1.7363 KOps/s	$\color{#d91a1a}-1.95\%$
test_vmap_mlp_speed_decorator[False-False]	0.7105ms	0.5827ms	1.7162 KOps/s	1.7347 KOps/s	$\color{#d91a1a}-1.07\%$
test_vmap_transformer_speed_decorator[True-True]	19.5892ms	18.9170ms	52.8626 Ops/s	53.3361 Ops/s	$\color{#d91a1a}-0.89\%$
test_vmap_transformer_speed_decorator[True-False]	19.5821ms	18.9563ms	52.7529 Ops/s	53.3609 Ops/s	$\color{#d91a1a}-1.14\%$
test_vmap_transformer_speed_decorator[False-True]	19.5059ms	18.8324ms	53.0999 Ops/s	53.8197 Ops/s	$\color{#d91a1a}-1.34\%$
test_vmap_transformer_speed_decorator[False-False]	19.4516ms	18.8844ms	52.9538 Ops/s	53.5652 Ops/s	$\color{#d91a1a}-1.14\%$
test_to_module_speed[True]	1.0295ms	0.9202ms	1.0867 KOps/s	1.0817 KOps/s	$\color{#35bf28}+0.46\%$
test_to_module_speed[False]	1.3644ms	0.9082ms	1.1011 KOps/s	1.1138 KOps/s	$\color{#d91a1a}-1.14\%$
test_tc_init	57.4110μs	35.8501μs	27.8939 KOps/s	28.4426 KOps/s	$\color{#d91a1a}-1.93\%$
test_tc_init_nested	0.1350ms	71.3248μs	14.0204 KOps/s	14.2506 KOps/s	$\color{#d91a1a}-1.62\%$
test_tc_first_layer_tensor	4.1171μs	0.6906μs	1.4479 MOps/s	1.4367 MOps/s	$\color{#35bf28}+0.78\%$
test_tc_first_layer_nontensor	26.2710μs	2.2760μs	439.3665 KOps/s	438.6470 KOps/s	$\color{#35bf28}+0.16\%$
test_tc_second_layer_tensor	8.4250μs	1.4274μs	700.5627 KOps/s	710.9350 KOps/s	$\color{#d91a1a}-1.46\%$
test_tc_second_layer_nontensor	28.1100μs	3.0503μs	327.8391 KOps/s	334.8422 KOps/s	$\color{#d91a1a}-2.09\%$
test_unbind	0.2213s	9.8147ms	101.8883 Ops/s	155.1892 Ops/s	$\textbf{\color{#d91a1a}-34.35\%}$
test_full_like	10.8933ms	9.3992ms	106.3916 Ops/s	106.4910 Ops/s	$\color{#d91a1a}-0.09\%$
test_zeros_like	5.3218ms	4.3367ms	230.5878 Ops/s	114.2244 Ops/s	$\textbf{\color{#35bf28}+101.87\%}$
test_ones_like	9.4391ms	7.1976ms	138.9357 Ops/s	230.0173 Ops/s	$\textbf{\color{#d91a1a}-39.60\%}$
test_clone	6.7881ms	6.5047ms	153.7356 Ops/s	154.1026 Ops/s	$\color{#d91a1a}-0.24\%$
test_squeeze	57.1610μs	9.4247μs	106.1042 KOps/s	107.7323 KOps/s	$\color{#d91a1a}-1.51\%$
test_unsqueeze	0.1150ms	67.9501μs	14.7167 KOps/s	14.6533 KOps/s	$\color{#35bf28}+0.43\%$
test_split	0.3948ms	0.1498ms	6.6774 KOps/s	6.5910 KOps/s	$\color{#35bf28}+1.31\%$
test_permute	0.2347ms	0.1743ms	5.7383 KOps/s	5.8646 KOps/s	$\color{#d91a1a}-2.15\%$
test_stack	51.5033ms	50.9988ms	19.6083 Ops/s	19.7391 Ops/s	$\color{#d91a1a}-0.66\%$
test_cat	51.1761ms	50.8634ms	19.6605 Ops/s	19.7038 Ops/s	$\color{#d91a1a}-0.22\%$