[Feature] _foreach_copy_ for update_

[vmoens]

Stack from ghstack (oldest at bottom):

• -> [Feature] _foreach_copy_ for update_ #1032

[github-actions]

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

Total Benchmarks: 222. Improved: $\large\color{#35bf28}19$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	64.8010μs	24.0141μs	41.6422 KOps/s	41.4010 KOps/s	$\color{#35bf28}+0.58\%$
test_plain_set_stack_nested	86.0520μs	24.2061μs	41.3119 KOps/s	41.1943 KOps/s	$\color{#35bf28}+0.29\%$
test_plain_set_nested_inplace	69.6600μs	26.6616μs	37.5071 KOps/s	37.8898 KOps/s	$\color{#d91a1a}-1.01\%$
test_plain_set_stack_nested_inplace	69.2000μs	26.5311μs	37.6916 KOps/s	38.2458 KOps/s	$\color{#d91a1a}-1.45\%$
test_items	36.6990μs	4.2327μs	236.2547 KOps/s	245.1108 KOps/s	$\color{#d91a1a}-3.61\%$
test_items_nested	0.5870ms	0.3864ms	2.5877 KOps/s	2.6480 KOps/s	$\color{#d91a1a}-2.28\%$
test_items_nested_locked	0.5795ms	0.3845ms	2.6006 KOps/s	2.6129 KOps/s	$\color{#d91a1a}-0.47\%$
test_items_nested_leaf	0.1586ms	81.6589μs	12.2461 KOps/s	12.4558 KOps/s	$\color{#d91a1a}-1.68\%$
test_items_stack_nested	0.8100ms	0.3920ms	2.5511 KOps/s	2.6110 KOps/s	$\color{#d91a1a}-2.30\%$
test_items_stack_nested_leaf	0.1730ms	83.8658μs	11.9238 KOps/s	11.9340 KOps/s	$\color{#d91a1a}-0.09\%$
test_items_stack_nested_locked	0.5512ms	0.3868ms	2.5851 KOps/s	2.5973 KOps/s	$\color{#d91a1a}-0.47\%$
test_keys	25.2770μs	3.4763μs	287.6638 KOps/s	279.4155 KOps/s	$\color{#35bf28}+2.95\%$
test_keys_nested	0.2423ms	0.1385ms	7.2189 KOps/s	7.4802 KOps/s	$\color{#d91a1a}-3.49\%$
test_keys_nested_locked	0.7327ms	0.1445ms	6.9201 KOps/s	7.1056 KOps/s	$\color{#d91a1a}-2.61\%$
test_keys_nested_leaf	0.2066ms	0.1205ms	8.2998 KOps/s	8.4928 KOps/s	$\color{#d91a1a}-2.27\%$
test_keys_stack_nested	0.2511ms	0.1343ms	7.4441 KOps/s	7.5599 KOps/s	$\color{#d91a1a}-1.53\%$
test_keys_stack_nested_leaf	0.2131ms	0.1158ms	8.6367 KOps/s	8.7217 KOps/s	$\color{#d91a1a}-0.97\%$
test_keys_stack_nested_locked	0.2598ms	0.1404ms	7.1224 KOps/s	7.2320 KOps/s	$\color{#d91a1a}-1.52\%$
test_values	6.5402μs	1.0484μs	953.8468 KOps/s	920.6233 KOps/s	$\color{#35bf28}+3.61\%$
test_values_nested	0.1599ms	92.1800μs	10.8483 KOps/s	10.5146 KOps/s	$\color{#35bf28}+3.17\%$
test_values_nested_locked	0.2068ms	92.3836μs	10.8244 KOps/s	10.5847 KOps/s	$\color{#35bf28}+2.26\%$
test_values_nested_leaf	0.1326ms	80.7621μs	12.3820 KOps/s	12.3260 KOps/s	$\color{#35bf28}+0.45\%$
test_values_stack_nested	0.1693ms	93.2887μs	10.7194 KOps/s	10.5191 KOps/s	$\color{#35bf28}+1.90\%$
test_values_stack_nested_leaf	0.1350ms	79.0742μs	12.6464 KOps/s	12.3568 KOps/s	$\color{#35bf28}+2.34\%$
test_values_stack_nested_locked	0.2074ms	93.6395μs	10.6792 KOps/s	10.5491 KOps/s	$\color{#35bf28}+1.23\%$
test_membership	16.0086μs	0.7602μs	1.3155 MOps/s	900.6911 KOps/s	$\textbf{\color{#35bf28}+46.06\%}$
test_membership_nested	0.1190ms	2.8216μs	354.4067 KOps/s	359.7426 KOps/s	$\color{#d91a1a}-1.48\%$
test_membership_nested_leaf	29.3450μs	2.7670μs	361.4071 KOps/s	347.6074 KOps/s	$\color{#35bf28}+3.97\%$
test_membership_stacked_nested	28.1420μs	2.7415μs	364.7603 KOps/s	359.7738 KOps/s	$\color{#35bf28}+1.39\%$
test_membership_stacked_nested_leaf	23.7640μs	2.7400μs	364.9631 KOps/s	353.6571 KOps/s	$\color{#35bf28}+3.20\%$
test_membership_nested_last	26.0990μs	4.2340μs	236.1852 KOps/s	238.9292 KOps/s	$\color{#d91a1a}-1.15\%$
test_membership_nested_leaf_last	33.0620μs	4.1784μs	239.3288 KOps/s	237.6224 KOps/s	$\color{#35bf28}+0.72\%$
test_membership_stacked_nested_last	45.9560μs	13.6206μs	73.4184 KOps/s	71.0024 KOps/s	$\color{#35bf28}+3.40\%$
test_membership_stacked_nested_leaf_last	39.8550μs	13.5369μs	73.8719 KOps/s	70.5443 KOps/s	$\color{#35bf28}+4.72\%$
test_nested_getleaf	0.1478ms	10.9505μs	91.3203 KOps/s	92.3273 KOps/s	$\color{#d91a1a}-1.09\%$
test_nested_get	49.5930μs	10.2804μs	97.2728 KOps/s	91.8512 KOps/s	$\textbf{\color{#35bf28}+5.90\%}$
test_stacked_getleaf	29.2050μs	10.7441μs	93.0746 KOps/s	91.9895 KOps/s	$\color{#35bf28}+1.18\%$
test_stacked_get	0.1029ms	10.2586μs	97.4795 KOps/s	97.2419 KOps/s	$\color{#35bf28}+0.24\%$
test_nested_getitemleaf	31.7600μs	11.1743μs	89.4912 KOps/s	89.6610 KOps/s	$\color{#d91a1a}-0.19\%$
test_nested_getitem	28.9050μs	10.5426μs	94.8532 KOps/s	94.4656 KOps/s	$\color{#35bf28}+0.41\%$
test_stacked_getitemleaf	45.4560μs	11.1718μs	89.5112 KOps/s	87.8583 KOps/s	$\color{#35bf28}+1.88\%$
test_stacked_getitem	34.6350μs	10.3859μs	96.2847 KOps/s	95.3498 KOps/s	$\color{#35bf28}+0.98\%$
test_lock_nested	86.3091ms	0.5913ms	1.6911 KOps/s	1.9614 KOps/s	$\textbf{\color{#d91a1a}-13.78\%}$
test_lock_stack_nested	0.7304ms	0.4583ms	2.1818 KOps/s	2.1914 KOps/s	$\color{#d91a1a}-0.44\%$
test_unlock_nested	86.4482ms	0.5112ms	1.9561 KOps/s	2.3082 KOps/s	$\textbf{\color{#d91a1a}-15.25\%}$
test_unlock_stack_nested	0.5547ms	0.3721ms	2.6874 KOps/s	2.6645 KOps/s	$\color{#35bf28}+0.86\%$
test_flatten_speed	0.1904ms	0.1008ms	9.9238 KOps/s	9.8639 KOps/s	$\color{#35bf28}+0.61\%$
test_unflatten_speed	1.0373ms	0.5172ms	1.9334 KOps/s	1.9067 KOps/s	$\color{#35bf28}+1.40\%$
test_common_ops	4.0085ms	1.1418ms	875.7719 Ops/s	833.2848 Ops/s	$\textbf{\color{#35bf28}+5.10\%}$
test_creation	23.3340μs	2.1202μs	471.6623 KOps/s	486.3882 KOps/s	$\color{#d91a1a}-3.03\%$
test_creation_empty	73.3480μs	17.8867μs	55.9076 KOps/s	58.8117 KOps/s	$\color{#d91a1a}-4.94\%$
test_creation_nested_1	55.8740μs	21.3792μs	46.7744 KOps/s	50.0850 KOps/s	$\textbf{\color{#d91a1a}-6.61\%}$
test_creation_nested_2	57.4570μs	25.4260μs	39.3298 KOps/s	41.3657 KOps/s	$\color{#d91a1a}-4.92\%$
test_clone	77.5650μs	16.9128μs	59.1269 KOps/s	56.7087 KOps/s	$\color{#35bf28}+4.26\%$
test_getitem[int]	1.0970ms	17.0284μs	58.7255 KOps/s	58.4655 KOps/s	$\color{#35bf28}+0.44\%$
test_getitem[slice_int]	0.1433ms	31.1787μs	32.0731 KOps/s	31.5664 KOps/s	$\color{#35bf28}+1.61\%$
test_getitem[range]	0.1814ms	59.5864μs	16.7823 KOps/s	16.6463 KOps/s	$\color{#35bf28}+0.82\%$
test_getitem[tuple]	0.1286ms	25.3944μs	39.3788 KOps/s	38.7449 KOps/s	$\color{#35bf28}+1.64\%$
test_getitem[list]	0.2611ms	55.4562μs	18.0323 KOps/s	18.0521 KOps/s	$\color{#d91a1a}-0.11\%$
test_setitem_dim[int]	67.3360μs	33.6503μs	29.7174 KOps/s	29.2610 KOps/s	$\color{#35bf28}+1.56\%$
test_setitem_dim[slice_int]	99.1850μs	62.4894μs	16.0027 KOps/s	15.9376 KOps/s	$\color{#35bf28}+0.41\%$
test_setitem_dim[range]	0.1538ms	85.5772μs	11.6854 KOps/s	11.3074 KOps/s	$\color{#35bf28}+3.34\%$
test_setitem_dim[tuple]	0.1060ms	50.2240μs	19.9108 KOps/s	19.5747 KOps/s	$\color{#35bf28}+1.72\%$
test_setitem	77.3150μs	30.3030μs	33.0001 KOps/s	32.5585 KOps/s	$\color{#35bf28}+1.36\%$
test_set	76.6440μs	29.6884μs	33.6831 KOps/s	33.6239 KOps/s	$\color{#35bf28}+0.18\%$
test_set_shared	2.1281ms	0.2220ms	4.5051 KOps/s	4.5083 KOps/s	$\color{#d91a1a}-0.07\%$
test_update	0.1448ms	37.6572μs	26.5554 KOps/s	26.4567 KOps/s	$\color{#35bf28}+0.37\%$
test_update_nested	0.1535ms	48.8521μs	20.4699 KOps/s	20.2523 KOps/s	$\color{#35bf28}+1.07\%$
test_update__nested	0.1128ms	42.9490μs	23.2834 KOps/s	26.5252 KOps/s	$\textbf{\color{#d91a1a}-12.22\%}$
test_set_nested	0.1261ms	32.3520μs	30.9100 KOps/s	30.3484 KOps/s	$\color{#35bf28}+1.85\%$
test_set_nested_new	0.1115ms	38.0813μs	26.2596 KOps/s	26.5214 KOps/s	$\color{#d91a1a}-0.99\%$
test_select	0.1415ms	56.1207μs	17.8187 KOps/s	18.2068 KOps/s	$\color{#d91a1a}-2.13\%$
test_select_nested	0.1212ms	58.8184μs	17.0015 KOps/s	16.7907 KOps/s	$\color{#35bf28}+1.26\%$
test_exclude_nested	0.1426ms	74.2447μs	13.4690 KOps/s	13.3682 KOps/s	$\color{#35bf28}+0.75\%$
test_empty[True]	0.6330ms	0.3531ms	2.8322 KOps/s	2.8070 KOps/s	$\color{#35bf28}+0.90\%$
test_empty[False]	9.8433μs	1.2853μs	778.0311 KOps/s	829.2650 KOps/s	$\textbf{\color{#d91a1a}-6.18\%}$
test_unbind_speed	0.6464ms	0.3019ms	3.3125 KOps/s	3.1905 KOps/s	$\color{#35bf28}+3.82\%$
test_unbind_speed_stack0	0.4936ms	0.2930ms	3.4132 KOps/s	3.4370 KOps/s	$\color{#d91a1a}-0.69\%$
test_unbind_speed_stack1	84.8765ms	0.7792ms	1.2834 KOps/s	1.3980 KOps/s	$\textbf{\color{#d91a1a}-8.20\%}$
test_split	85.1403ms	2.1471ms	465.7351 Ops/s	452.5656 Ops/s	$\color{#35bf28}+2.91\%$
test_chunk	2.2374ms	1.9974ms	500.6396 Ops/s	447.4727 Ops/s	$\textbf{\color{#35bf28}+11.88\%}$
test_creation[device0]	0.2079ms	0.1182ms	8.4632 KOps/s	8.5666 KOps/s	$\color{#d91a1a}-1.21\%$
test_creation_from_tensor	3.7967ms	0.1197ms	8.3554 KOps/s	8.4984 KOps/s	$\color{#d91a1a}-1.68\%$
test_add_one[memmap_tensor0]	0.2148ms	7.5537μs	132.3854 KOps/s	132.4761 KOps/s	$\color{#d91a1a}-0.07\%$
test_contiguous[memmap_tensor0]	16.1000μs	1.9035μs	525.3345 KOps/s	525.2369 KOps/s	$\color{#35bf28}+0.02\%$
test_stack[memmap_tensor0]	57.8380μs	5.6703μs	176.3576 KOps/s	180.6350 KOps/s	$\color{#d91a1a}-2.37\%$
test_memmaptd_index	1.1048ms	0.4202ms	2.3797 KOps/s	2.4098 KOps/s	$\color{#d91a1a}-1.25\%$
test_memmaptd_index_astensor	1.2127ms	0.5254ms	1.9032 KOps/s	1.9445 KOps/s	$\color{#d91a1a}-2.12\%$
test_memmaptd_index_op	1.4537ms	1.0516ms	950.8874 Ops/s	971.5730 Ops/s	$\color{#d91a1a}-2.13\%$
test_serialize_model	0.2028s	0.1274s	7.8475 Ops/s	8.4392 Ops/s	$\textbf{\color{#d91a1a}-7.01\%}$
test_serialize_model_pickle	0.4637s	0.3910s	2.5576 Ops/s	2.5087 Ops/s	$\color{#35bf28}+1.95\%$
test_serialize_weights	0.1210s	0.1148s	8.7088 Ops/s	7.7696 Ops/s	$\textbf{\color{#35bf28}+12.09\%}$
test_serialize_weights_returnearly	0.2553s	0.1693s	5.9064 Ops/s	6.4020 Ops/s	$\textbf{\color{#d91a1a}-7.74\%}$
test_serialize_weights_pickle	0.5466s	0.4266s	2.3440 Ops/s	2.3790 Ops/s	$\color{#d91a1a}-1.47\%$
test_serialize_weights_filesystem	0.1514s	0.1425s	7.0197 Ops/s	6.9718 Ops/s	$\color{#35bf28}+0.69\%$
test_serialize_model_filesystem	0.1552s	0.1462s	6.8410 Ops/s	6.1481 Ops/s	$\textbf{\color{#35bf28}+11.27\%}$
test_reshape_pytree	0.1144ms	38.6991μs	25.8404 KOps/s	25.2415 KOps/s	$\color{#35bf28}+2.37\%$
test_reshape_td	98.8950μs	45.5778μs	21.9405 KOps/s	20.2350 KOps/s	$\textbf{\color{#35bf28}+8.43\%}$
test_view_pytree	0.1182ms	38.9018μs	25.7058 KOps/s	25.4236 KOps/s	$\color{#35bf28}+1.11\%$
test_view_td	0.1357ms	51.3082μs	19.4901 KOps/s	17.7673 KOps/s	$\textbf{\color{#35bf28}+9.70\%}$
test_unbind_pytree	96.8910μs	36.4161μs	27.4604 KOps/s	27.0109 KOps/s	$\color{#35bf28}+1.66\%$
test_unbind_td	0.3125ms	45.6841μs	21.8894 KOps/s	21.6507 KOps/s	$\color{#35bf28}+1.10\%$
test_split_pytree	0.1159ms	38.0462μs	26.2838 KOps/s	26.0376 KOps/s	$\color{#35bf28}+0.95\%$
test_split_td	0.2141ms	58.3270μs	17.1447 KOps/s	16.7152 KOps/s	$\color{#35bf28}+2.57\%$
test_add_pytree	0.1175ms	45.4882μs	21.9837 KOps/s	20.8843 KOps/s	$\textbf{\color{#35bf28}+5.26\%}$
test_add_td	0.2285ms	87.5797μs	11.4182 KOps/s	11.3360 KOps/s	$\color{#35bf28}+0.72\%$
test_compile_add_one_nested[tensordict-compile]	0.1704ms	61.2824μs	16.3179 KOps/s	16.8975 KOps/s	$\color{#d91a1a}-3.43\%$
test_compile_add_one_nested[tensordict-eager]	0.3130ms	0.2006ms	4.9850 KOps/s	5.0989 KOps/s	$\color{#d91a1a}-2.23\%$
test_compile_add_one_nested[pytree-compile]	0.1208ms	57.5671μs	17.3710 KOps/s	17.1036 KOps/s	$\color{#35bf28}+1.56\%$
test_compile_add_one_nested[pytree-eager]	0.2717ms	0.1416ms	7.0637 KOps/s	6.9481 KOps/s	$\color{#35bf28}+1.66\%$
test_compile_copy_nested[tensordict-compile]	52.6290μs	23.7750μs	42.0609 KOps/s	41.9418 KOps/s	$\color{#35bf28}+0.28\%$
test_compile_copy_nested[tensordict-eager]	0.2034ms	75.2142μs	13.2954 KOps/s	13.3025 KOps/s	$\color{#d91a1a}-0.05\%$
test_compile_copy_nested[pytree-compile]	0.1285ms	75.1562μs	13.3056 KOps/s	13.1858 KOps/s	$\color{#35bf28}+0.91\%$
test_compile_copy_nested[pytree-eager]	0.1442ms	69.1288μs	14.4658 KOps/s	14.7060 KOps/s	$\color{#d91a1a}-1.63\%$
test_compile_add_one_flat[tensordict-compile]	0.5272ms	0.1865ms	5.3619 KOps/s	5.4316 KOps/s	$\color{#d91a1a}-1.28\%$
test_compile_add_one_flat[tensordict-eager]	0.4200ms	0.2505ms	3.9917 KOps/s	4.2161 KOps/s	$\textbf{\color{#d91a1a}-5.32\%}$
test_compile_add_one_flat[tensorclass-compile]	0.1037ms	48.9749μs	20.4186 KOps/s	20.5329 KOps/s	$\color{#d91a1a}-0.56\%$
test_compile_add_one_flat[tensorclass-eager]	0.1805ms	77.6162μs	12.8839 KOps/s	13.0675 KOps/s	$\color{#d91a1a}-1.40\%$
test_compile_add_one_flat[pytree-compile]	0.4163ms	0.1766ms	5.6626 KOps/s	5.7469 KOps/s	$\color{#d91a1a}-1.47\%$
test_compile_add_one_flat[pytree-eager]	0.5393ms	0.2891ms	3.4591 KOps/s	3.4175 KOps/s	$\color{#35bf28}+1.22\%$
test_compile_add_self_flat[tensordict-eager]	0.6239ms	0.2855ms	3.5032 KOps/s	3.6655 KOps/s	$\color{#d91a1a}-4.43\%$
test_compile_add_self_flat[tensordict-compile]	0.3388ms	0.1892ms	5.2854 KOps/s	5.4558 KOps/s	$\color{#d91a1a}-3.12\%$
test_compile_add_self_flat[tensorclass-eager]	0.1634ms	74.7994μs	13.3691 KOps/s	14.0022 KOps/s	$\color{#d91a1a}-4.52\%$
test_compile_add_self_flat[tensorclass-compile]	95.1080μs	48.8925μs	20.4530 KOps/s	20.8502 KOps/s	$\color{#d91a1a}-1.90\%$
test_compile_add_self_flat[pytree-eager]	0.4933ms	0.2316ms	4.3187 KOps/s	4.2714 KOps/s	$\color{#35bf28}+1.11\%$
test_compile_add_self_flat[pytree-compile]	0.3616ms	0.1762ms	5.6746 KOps/s	5.5778 KOps/s	$\color{#35bf28}+1.74\%$
test_compile_copy_flat[tensordict-compile]	0.2427ms	0.1131ms	8.8434 KOps/s	8.9198 KOps/s	$\color{#d91a1a}-0.86\%$
test_compile_copy_flat[tensordict-eager]	0.1797ms	79.3708μs	12.5991 KOps/s	12.8076 KOps/s	$\color{#d91a1a}-1.63\%$
test_compile_copy_flat[pytree-compile]	0.1293ms	77.2184μs	12.9503 KOps/s	12.6412 KOps/s	$\color{#35bf28}+2.45\%$
test_compile_copy_flat[pytree-eager]	0.1446ms	68.8545μs	14.5234 KOps/s	14.4263 KOps/s	$\color{#35bf28}+0.67\%$
test_compile_assign_and_add[tensordict-compile]	0.3614ms	0.1940ms	5.1555 KOps/s	5.1582 KOps/s	$\color{#d91a1a}-0.05\%$
test_compile_assign_and_add[tensordict-eager]	1.9867ms	1.7748ms	563.4515 Ops/s	576.7800 Ops/s	$\color{#d91a1a}-2.31\%$
test_compile_assign_and_add[pytree-compile]	0.2831ms	0.1905ms	5.2488 KOps/s	5.1136 KOps/s	$\color{#35bf28}+2.64\%$
test_compile_assign_and_add[pytree-eager]	1.3246ms	1.1009ms	908.3643 Ops/s	897.5386 Ops/s	$\color{#35bf28}+1.21\%$
test_compile_assign_and_add_stack[compile]	0.6961ms	0.4159ms	2.4046 KOps/s	2.3628 KOps/s	$\color{#35bf28}+1.77\%$
test_compile_assign_and_add_stack[eager]	4.3783ms	4.0770ms	245.2775 Ops/s	244.0461 Ops/s	$\color{#35bf28}+0.50\%$
test_compile_indexing[tensor-tensordict-compile]	87.4240μs	34.6774μs	28.8372 KOps/s	28.5545 KOps/s	$\color{#35bf28}+0.99\%$
test_compile_indexing[tensor-tensordict-eager]	1.0612ms	50.0508μs	19.9797 KOps/s	13.0342 KOps/s	$\textbf{\color{#35bf28}+53.29\%}$
test_compile_indexing[tensor-tensorclass-compile]	73.6080μs	30.6740μs	32.6009 KOps/s	32.0815 KOps/s	$\color{#35bf28}+1.62\%$
test_compile_indexing[tensor-tensorclass-eager]	77.5450μs	29.4581μs	33.9466 KOps/s	32.2257 KOps/s	$\textbf{\color{#35bf28}+5.34\%}$
test_compile_indexing[tensor-pytree-compile]	76.3030μs	30.8439μs	32.4213 KOps/s	32.2850 KOps/s	$\color{#35bf28}+0.42\%$
test_compile_indexing[tensor-pytree-eager]	75.6020μs	28.8057μs	34.7154 KOps/s	33.6758 KOps/s	$\color{#35bf28}+3.09\%$
test_compile_indexing[slice-tensordict-compile]	0.1800ms	75.0527μs	13.3240 KOps/s	13.1957 KOps/s	$\color{#35bf28}+0.97\%$
test_compile_indexing[slice-tensordict-eager]	0.5159ms	28.4976μs	35.0906 KOps/s	33.9905 KOps/s	$\color{#35bf28}+3.24\%$
test_compile_indexing[slice-tensorclass-compile]	0.1285ms	69.7341μs	14.3402 KOps/s	14.3352 KOps/s	$\color{#35bf28}+0.04\%$
test_compile_indexing[slice-tensorclass-eager]	84.8280μs	23.7016μs	42.1912 KOps/s	41.8430 KOps/s	$\color{#35bf28}+0.83\%$
test_compile_indexing[slice-pytree-compile]	0.1622ms	70.0913μs	14.2671 KOps/s	14.3708 KOps/s	$\color{#d91a1a}-0.72\%$
test_compile_indexing[slice-pytree-eager]	69.3000μs	23.6711μs	42.2456 KOps/s	42.3783 KOps/s	$\color{#d91a1a}-0.31\%$
test_compile_indexing[int-tensordict-compile]	0.1679ms	75.5571μs	13.2350 KOps/s	13.2502 KOps/s	$\color{#d91a1a}-0.11\%$
test_compile_indexing[int-tensordict-eager]	0.9145ms	27.9842μs	35.7344 KOps/s	34.7270 KOps/s	$\color{#35bf28}+2.90\%$
test_compile_indexing[int-tensorclass-compile]	0.1331ms	69.6435μs	14.3588 KOps/s	14.5225 KOps/s	$\color{#d91a1a}-1.13\%$
test_compile_indexing[int-tensorclass-eager]	73.0970μs	23.4779μs	42.5933 KOps/s	42.5237 KOps/s	$\color{#35bf28}+0.16\%$
test_compile_indexing[int-pytree-compile]	0.1470ms	69.9145μs	14.3032 KOps/s	14.5061 KOps/s	$\color{#d91a1a}-1.40\%$
test_compile_indexing[int-pytree-eager]	65.9930μs	23.1608μs	43.1765 KOps/s	42.5996 KOps/s	$\color{#35bf28}+1.35\%$
test_mod_add[eager]	67.8470μs	25.2217μs	39.6485 KOps/s	39.7810 KOps/s	$\color{#d91a1a}-0.33\%$
test_mod_add[compile]	0.1021ms	38.6064μs	25.9024 KOps/s	24.8600 KOps/s	$\color{#35bf28}+4.19\%$
test_mod_add[compile-overhead]	0.1076ms	38.3425μs	26.0807 KOps/s	24.6406 KOps/s	$\textbf{\color{#35bf28}+5.84\%}$
test_mod_wrap[eager]	0.3817ms	0.2101ms	4.7600 KOps/s	4.6731 KOps/s	$\color{#35bf28}+1.86\%$
test_mod_wrap[compile]	0.3444ms	0.2357ms	4.2419 KOps/s	4.2243 KOps/s	$\color{#35bf28}+0.42\%$
test_mod_wrap[compile-overhead]	0.3634ms	0.2361ms	4.2356 KOps/s	4.2528 KOps/s	$\color{#d91a1a}-0.40\%$
test_mod_wrap_and_backward[eager]	12.2604ms	10.8015ms	92.5795 Ops/s	92.7119 Ops/s	$\color{#d91a1a}-0.14\%$
test_mod_wrap_and_backward[compile]	13.3483ms	10.9598ms	91.2429 Ops/s	92.1985 Ops/s	$\color{#d91a1a}-1.04\%$
test_mod_wrap_and_backward[compile-overhead]	12.0849ms	10.9239ms	91.5422 Ops/s	90.5969 Ops/s	$\color{#35bf28}+1.04\%$
test_seq_add[eager]	0.2251ms	92.7222μs	10.7849 KOps/s	10.7248 KOps/s	$\color{#35bf28}+0.56\%$
test_seq_add[compile]	0.1300ms	64.2425μs	15.5660 KOps/s	15.0828 KOps/s	$\color{#35bf28}+3.20\%$
test_seq_add[compile-overhead]	0.1386ms	61.6596μs	16.2181 KOps/s	15.5724 KOps/s	$\color{#35bf28}+4.15\%$
test_seq_wrap[eager]	0.5623ms	0.3876ms	2.5797 KOps/s	2.5452 KOps/s	$\color{#35bf28}+1.35\%$
test_seq_wrap[compile]	1.1146ms	0.2721ms	3.6750 KOps/s	3.6233 KOps/s	$\color{#35bf28}+1.43\%$
test_seq_wrap[compile-overhead]	1.3154ms	0.2713ms	3.6859 KOps/s	3.6310 KOps/s	$\color{#35bf28}+1.51\%$
test_func_call_runtime[False-eager]	0.6616ms	0.5198ms	1.9240 KOps/s	1.8656 KOps/s	$\color{#35bf28}+3.13\%$
test_func_call_runtime[False-compile]	0.5957ms	0.5011ms	1.9955 KOps/s	1.9687 KOps/s	$\color{#35bf28}+1.36\%$
test_func_call_runtime[False-compile-overhead]	1.0513ms	0.5007ms	1.9974 KOps/s	1.9606 KOps/s	$\color{#35bf28}+1.87\%$
test_func_call_runtime[True-eager]	1.0105ms	0.7498ms	1.3337 KOps/s	1.3089 KOps/s	$\color{#35bf28}+1.89\%$
test_func_call_runtime[True-compile]	0.6245ms	0.5204ms	1.9216 KOps/s	1.9121 KOps/s	$\color{#35bf28}+0.49\%$
test_func_call_runtime[True-compile-overhead]	0.8607ms	0.5149ms	1.9420 KOps/s	1.9356 KOps/s	$\color{#35bf28}+0.33\%$
test_func_call_cm_runtime[False-eager]	0.8187ms	0.5175ms	1.9326 KOps/s	1.8602 KOps/s	$\color{#35bf28}+3.89\%$
test_func_call_cm_runtime[False-compile]	1.1132ms	0.5005ms	1.9979 KOps/s	1.9588 KOps/s	$\color{#35bf28}+1.99\%$
test_func_call_cm_runtime[False-compile-overhead]	0.6246ms	0.4999ms	2.0004 KOps/s	1.9652 KOps/s	$\color{#35bf28}+1.79\%$
test_func_call_cm_runtime[True-eager]	1.0719ms	0.8852ms	1.1297 KOps/s	1.0835 KOps/s	$\color{#35bf28}+4.27\%$
test_func_call_cm_runtime[True-compile]	1.1586ms	0.7361ms	1.3584 KOps/s	1.3100 KOps/s	$\color{#35bf28}+3.70\%$
test_func_call_cm_runtime[True-compile-overhead]	0.9540ms	0.7353ms	1.3600 KOps/s	1.3078 KOps/s	$\color{#35bf28}+3.99\%$
test_vmap_func_call_cm_runtime[eager]	2.6782ms	1.8951ms	527.6697 Ops/s	510.9624 Ops/s	$\color{#35bf28}+3.27\%$
test_vmap_func_call_cm_runtime[compile]	2.4890ms	1.9383ms	515.9029 Ops/s	501.6018 Ops/s	$\color{#35bf28}+2.85\%$
test_vmap_func_call_cm_runtime[compile-overhead]	2.5993ms	1.9551ms	511.4851 Ops/s	496.2218 Ops/s	$\color{#35bf28}+3.08\%$
test_distributed	0.2247ms	0.1269ms	7.8818 KOps/s	7.7501 KOps/s	$\color{#35bf28}+1.70\%$
test_tdmodule	40.0750μs	17.8151μs	56.1322 KOps/s	56.2238 KOps/s	$\color{#d91a1a}-0.16\%$
test_tdmodule_dispatch	68.6180μs	35.6209μs	28.0734 KOps/s	28.6859 KOps/s	$\color{#d91a1a}-2.14\%$
test_tdseq	45.4850μs	20.3813μs	49.0645 KOps/s	42.3135 KOps/s	$\textbf{\color{#35bf28}+15.95\%}$
test_tdseq_dispatch	65.7930μs	40.8584μs	24.4748 KOps/s	22.2819 KOps/s	$\textbf{\color{#35bf28}+9.84\%}$
test_instantiation_functorch	1.7738ms	1.5574ms	642.0942 Ops/s	624.2553 Ops/s	$\color{#35bf28}+2.86\%$
test_instantiation_td	1.7690ms	1.1595ms	862.4566 Ops/s	831.3938 Ops/s	$\color{#35bf28}+3.74\%$
test_exec_functorch	0.2634ms	0.1851ms	5.4034 KOps/s	5.2859 KOps/s	$\color{#35bf28}+2.22\%$
test_exec_functional_call	0.2681ms	0.1743ms	5.7379 KOps/s	5.4277 KOps/s	$\textbf{\color{#35bf28}+5.72\%}$
test_exec_td	0.3644ms	0.2050ms	4.8788 KOps/s	4.8449 KOps/s	$\color{#35bf28}+0.70\%$
test_exec_td_decorator	0.9695ms	0.2337ms	4.2782 KOps/s	4.1524 KOps/s	$\color{#35bf28}+3.03\%$
test_vmap_mlp_speed[True-True]	0.7842ms	0.6826ms	1.4650 KOps/s	1.4312 KOps/s	$\color{#35bf28}+2.36\%$
test_vmap_mlp_speed[True-False]	0.7826ms	0.6783ms	1.4743 KOps/s	1.4277 KOps/s	$\color{#35bf28}+3.26\%$
test_vmap_mlp_speed[False-True]	0.7103ms	0.5379ms	1.8591 KOps/s	1.8285 KOps/s	$\color{#35bf28}+1.67\%$
test_vmap_mlp_speed[False-False]	0.8541ms	0.5363ms	1.8646 KOps/s	1.8200 KOps/s	$\color{#35bf28}+2.45\%$
test_vmap_mlp_speed_decorator[True-True]	1.2993ms	0.6435ms	1.5541 KOps/s	1.5212 KOps/s	$\color{#35bf28}+2.16\%$
test_vmap_mlp_speed_decorator[True-False]	0.9532ms	0.6439ms	1.5530 KOps/s	1.5011 KOps/s	$\color{#35bf28}+3.46\%$
test_vmap_mlp_speed_decorator[False-True]	0.8189ms	0.5322ms	1.8788 KOps/s	1.8280 KOps/s	$\color{#35bf28}+2.78\%$
test_vmap_mlp_speed_decorator[False-False]	0.6539ms	0.5289ms	1.8908 KOps/s	1.8193 KOps/s	$\color{#35bf28}+3.93\%$
test_to_module_speed[True]	2.0388ms	1.4124ms	707.9905 Ops/s	695.2706 Ops/s	$\color{#35bf28}+1.83\%$
test_to_module_speed[False]	1.8509ms	1.3787ms	725.3073 Ops/s	722.1913 Ops/s	$\color{#35bf28}+0.43\%$
test_tc_init	0.1040ms	43.1519μs	23.1739 KOps/s	21.6386 KOps/s	$\textbf{\color{#35bf28}+7.10\%}$
test_tc_init_nested	0.1505ms	86.0397μs	11.6225 KOps/s	11.0476 KOps/s	$\textbf{\color{#35bf28}+5.20\%}$
test_tc_first_layer_tensor	18.9450μs	1.5213μs	657.3260 KOps/s	666.7584 KOps/s	$\color{#d91a1a}-1.41\%$
test_tc_first_layer_nontensor	19.1360μs	4.6175μs	216.5695 KOps/s	205.8299 KOps/s	$\textbf{\color{#35bf28}+5.22\%}$
test_tc_second_layer_tensor	23.9650μs	2.7859μs	358.9515 KOps/s	346.4804 KOps/s	$\color{#35bf28}+3.60\%$
test_tc_second_layer_nontensor	39.7440μs	5.8990μs	169.5196 KOps/s	164.3170 KOps/s	$\color{#35bf28}+3.17\%$
test_unbind	0.4728s	13.1147ms	76.2505 Ops/s	76.7507 Ops/s	$\color{#d91a1a}-0.65\%$
test_full_like	7.7997ms	7.0957ms	140.9299 Ops/s	142.1594 Ops/s	$\color{#d91a1a}-0.86\%$
test_zeros_like	5.3568ms	2.8380ms	352.3569 Ops/s	360.4499 Ops/s	$\color{#d91a1a}-2.25\%$
test_ones_like	3.4685ms	3.0574ms	327.0776 Ops/s	304.1609 Ops/s	$\textbf{\color{#35bf28}+7.53\%}$
test_clone	5.3208ms	4.7771ms	209.3338 Ops/s	202.0753 Ops/s	$\color{#35bf28}+3.59\%$
test_squeeze	64.0400μs	12.7988μs	78.1323 KOps/s	79.5954 KOps/s	$\color{#d91a1a}-1.84\%$
test_unsqueeze	0.3343ms	93.8482μs	10.6555 KOps/s	10.5460 KOps/s	$\color{#35bf28}+1.04\%$
test_split	0.3369ms	0.1955ms	5.1164 KOps/s	4.9313 KOps/s	$\color{#35bf28}+3.75\%$
test_permute	0.3586ms	0.2172ms	4.6036 KOps/s	4.4080 KOps/s	$\color{#35bf28}+4.44\%$
test_stack	29.7721ms	24.6588ms	40.5535 Ops/s	40.8199 Ops/s	$\color{#d91a1a}-0.65\%$
test_cat	28.4933ms	24.3613ms	41.0488 Ops/s	41.3429 Ops/s	$\color{#d91a1a}-0.71\%$

[github-actions]

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

Total Benchmarks: 228. Improved: $\large\color{#35bf28}13$. Worsened: $\large\color{#d91a1a}22$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	0.1380ms	16.8607μs	59.3094 KOps/s	62.8555 KOps/s	$\textbf{\color{#d91a1a}-5.64\%}$
test_plain_set_stack_nested	0.1051ms	16.7985μs	59.5293 KOps/s	62.8198 KOps/s	$\textbf{\color{#d91a1a}-5.24\%}$
test_plain_set_nested_inplace	46.2800μs	18.0193μs	55.4961 KOps/s	58.2314 KOps/s	$\color{#d91a1a}-4.70\%$
test_plain_set_stack_nested_inplace	52.3110μs	17.9786μs	55.6218 KOps/s	58.5876 KOps/s	$\textbf{\color{#d91a1a}-5.06\%}$
test_items	24.6300μs	2.8431μs	351.7293 KOps/s	345.1611 KOps/s	$\color{#35bf28}+1.90\%$
test_items_nested	0.3803ms	0.3425ms	2.9201 KOps/s	2.9395 KOps/s	$\color{#d91a1a}-0.66\%$
test_items_nested_locked	0.3711ms	0.3403ms	2.9383 KOps/s	2.9166 KOps/s	$\color{#35bf28}+0.74\%$
test_items_nested_leaf	0.1008ms	62.6453μs	15.9629 KOps/s	15.8162 KOps/s	$\color{#35bf28}+0.93\%$
test_items_stack_nested	0.3695ms	0.3381ms	2.9577 KOps/s	2.9204 KOps/s	$\color{#35bf28}+1.28\%$
test_items_stack_nested_leaf	92.1120μs	62.8094μs	15.9212 KOps/s	15.5783 KOps/s	$\color{#35bf28}+2.20\%$
test_items_stack_nested_locked	0.4305ms	0.3420ms	2.9242 KOps/s	2.8992 KOps/s	$\color{#35bf28}+0.86\%$
test_keys	32.3600μs	3.4159μs	292.7525 KOps/s	291.9812 KOps/s	$\color{#35bf28}+0.26\%$
test_keys_nested	0.1254ms	71.1575μs	14.0533 KOps/s	13.9612 KOps/s	$\color{#35bf28}+0.66\%$
test_keys_nested_locked	2.7126ms	77.2891μs	12.9384 KOps/s	12.8048 KOps/s	$\color{#35bf28}+1.04\%$
test_keys_nested_leaf	0.2393ms	61.9084μs	16.1529 KOps/s	15.9094 KOps/s	$\color{#35bf28}+1.53\%$
test_keys_stack_nested	0.2627ms	71.1475μs	14.0553 KOps/s	14.0213 KOps/s	$\color{#35bf28}+0.24\%$
test_keys_stack_nested_leaf	0.2384ms	61.2409μs	16.3290 KOps/s	15.7660 KOps/s	$\color{#35bf28}+3.57\%$
test_keys_stack_nested_locked	0.1682ms	76.5259μs	13.0675 KOps/s	12.8742 KOps/s	$\color{#35bf28}+1.50\%$
test_values	6.1152μs	0.8351μs	1.1974 MOps/s	1.1935 MOps/s	$\color{#35bf28}+0.33\%$
test_values_nested	0.1487ms	48.4619μs	20.6347 KOps/s	20.4069 KOps/s	$\color{#35bf28}+1.12\%$
test_values_nested_locked	0.1710ms	50.2338μs	19.9069 KOps/s	19.7220 KOps/s	$\color{#35bf28}+0.94\%$
test_values_nested_leaf	71.5510μs	42.6252μs	23.4603 KOps/s	23.3839 KOps/s	$\color{#35bf28}+0.33\%$
test_values_stack_nested	85.7520μs	49.0126μs	20.4029 KOps/s	19.9411 KOps/s	$\color{#35bf28}+2.32\%$
test_values_stack_nested_leaf	79.7020μs	42.8081μs	23.3601 KOps/s	22.8918 KOps/s	$\color{#35bf28}+2.05\%$
test_values_stack_nested_locked	81.3310μs	50.3905μs	19.8450 KOps/s	19.2550 KOps/s	$\color{#35bf28}+3.06\%$
test_membership	2.2626μs	0.5042μs	1.9832 MOps/s	2.0020 MOps/s	$\color{#d91a1a}-0.94\%$
test_membership_nested	19.2355μs	1.8890μs	529.3839 KOps/s	530.8155 KOps/s	$\color{#d91a1a}-0.27\%$
test_membership_nested_leaf	19.8305μs	1.8827μs	531.1591 KOps/s	541.2089 KOps/s	$\color{#d91a1a}-1.86\%$
test_membership_stacked_nested	29.0510μs	1.9604μs	510.1011 KOps/s	523.3775 KOps/s	$\color{#d91a1a}-2.54\%$
test_membership_stacked_nested_leaf	25.6000μs	1.9575μs	510.8473 KOps/s	517.3982 KOps/s	$\color{#d91a1a}-1.27\%$
test_membership_nested_last	45.4510μs	2.9868μs	334.8101 KOps/s	337.4363 KOps/s	$\color{#d91a1a}-0.78\%$
test_membership_nested_leaf_last	0.1035ms	2.9944μs	333.9550 KOps/s	334.1197 KOps/s	$\color{#d91a1a}-0.05\%$
test_membership_stacked_nested_last	37.6600μs	2.9516μs	338.7993 KOps/s	120.6990 KOps/s	$\textbf{\color{#35bf28}+180.70\%}$
test_membership_stacked_nested_leaf_last	38.3210μs	2.9642μs	337.3571 KOps/s	125.0318 KOps/s	$\textbf{\color{#35bf28}+169.82\%}$
test_nested_getleaf	0.6715ms	6.0906μs	164.1867 KOps/s	163.8605 KOps/s	$\color{#35bf28}+0.20\%$
test_nested_get	35.4510μs	5.6742μs	176.2366 KOps/s	172.9638 KOps/s	$\color{#35bf28}+1.89\%$
test_stacked_getleaf	39.9110μs	6.1494μs	162.6166 KOps/s	165.6807 KOps/s	$\color{#d91a1a}-1.85\%$
test_stacked_get	36.2700μs	5.7103μs	175.1235 KOps/s	177.8744 KOps/s	$\color{#d91a1a}-1.55\%$
test_nested_getitemleaf	30.5600μs	6.1287μs	163.1656 KOps/s	163.9230 KOps/s	$\color{#d91a1a}-0.46\%$
test_nested_getitem	33.5710μs	5.7955μs	172.5471 KOps/s	173.8654 KOps/s	$\color{#d91a1a}-0.76\%$
test_stacked_getitemleaf	28.0100μs	6.1095μs	163.6801 KOps/s	162.7440 KOps/s	$\color{#35bf28}+0.58\%$
test_stacked_getitem	27.1210μs	5.6900μs	175.7479 KOps/s	176.7920 KOps/s	$\color{#d91a1a}-0.59\%$
test_lock_nested	6.9664ms	0.4318ms	2.3157 KOps/s	2.3001 KOps/s	$\color{#35bf28}+0.68\%$
test_lock_stack_nested	0.5425ms	0.3936ms	2.5404 KOps/s	2.6166 KOps/s	$\color{#d91a1a}-2.92\%$
test_unlock_nested	0.7647ms	0.3676ms	2.7201 KOps/s	2.7200 KOps/s	$+0.01\%$
test_unlock_stack_nested	0.4655ms	0.3328ms	3.0046 KOps/s	3.1252 KOps/s	$\color{#d91a1a}-3.86\%$
test_flatten_speed	0.1711ms	75.7155μs	13.2073 KOps/s	13.0303 KOps/s	$\color{#35bf28}+1.36\%$
test_unflatten_speed	0.3666ms	0.3198ms	3.1265 KOps/s	3.0971 KOps/s	$\color{#35bf28}+0.95\%$
test_common_ops	1.5606ms	1.2657ms	790.0478 Ops/s	805.6473 Ops/s	$\color{#d91a1a}-1.94\%$
test_creation	0.1668ms	1.4921μs	670.2035 KOps/s	681.6119 KOps/s	$\color{#d91a1a}-1.67\%$
test_creation_empty	0.1905ms	15.5889μs	64.1483 KOps/s	70.8885 KOps/s	$\textbf{\color{#d91a1a}-9.51\%}$
test_creation_nested_1	0.1912ms	17.5571μs	56.9570 KOps/s	64.2117 KOps/s	$\textbf{\color{#d91a1a}-11.30\%}$
test_creation_nested_2	0.1876ms	19.8967μs	50.2597 KOps/s	55.2850 KOps/s	$\textbf{\color{#d91a1a}-9.09\%}$
test_clone	0.1863ms	29.3155μs	34.1117 KOps/s	35.1605 KOps/s	$\color{#d91a1a}-2.98\%$
test_getitem[int]	1.2979ms	16.2441μs	61.5607 KOps/s	62.9552 KOps/s	$\color{#d91a1a}-2.22\%$
test_getitem[slice_int]	0.2519ms	28.4083μs	35.2010 KOps/s	36.7439 KOps/s	$\color{#d91a1a}-4.20\%$
test_getitem[range]	0.2361ms	0.1114ms	8.9756 KOps/s	8.8708 KOps/s	$\color{#35bf28}+1.18\%$
test_getitem[tuple]	0.1205ms	23.7375μs	42.1275 KOps/s	43.1797 KOps/s	$\color{#d91a1a}-2.44\%$
test_getitem[list]	0.3228ms	0.1034ms	9.6729 KOps/s	9.9333 KOps/s	$\color{#d91a1a}-2.62\%$
test_setitem_dim[int]	0.2328ms	48.7993μs	20.4921 KOps/s	22.1245 KOps/s	$\textbf{\color{#d91a1a}-7.38\%}$
test_setitem_dim[slice_int]	92.8420μs	67.8704μs	14.7340 KOps/s	14.6808 KOps/s	$\color{#35bf28}+0.36\%$
test_setitem_dim[range]	0.3058ms	0.1302ms	7.6791 KOps/s	7.7262 KOps/s	$\color{#d91a1a}-0.61\%$
test_setitem_dim[tuple]	0.2354ms	64.8314μs	15.4246 KOps/s	16.3759 KOps/s	$\textbf{\color{#d91a1a}-5.81\%}$
test_setitem	0.1916ms	42.1623μs	23.7179 KOps/s	24.3541 KOps/s	$\color{#d91a1a}-2.61\%$
test_set	0.2174ms	42.4308μs	23.5678 KOps/s	25.1582 KOps/s	$\textbf{\color{#d91a1a}-6.32\%}$
test_set_shared	0.3582ms	56.9665μs	17.5542 KOps/s	18.6133 KOps/s	$\textbf{\color{#d91a1a}-5.69\%}$
test_update	0.2177ms	51.8390μs	19.2905 KOps/s	20.5924 KOps/s	$\textbf{\color{#d91a1a}-6.32\%}$
test_update_nested	0.2375ms	58.9109μs	16.9748 KOps/s	17.8525 KOps/s	$\color{#d91a1a}-4.92\%$
test_update__nested	0.1596ms	60.4790μs	16.5347 KOps/s	16.6089 KOps/s	$\color{#d91a1a}-0.45\%$
test_set_nested	0.1947ms	44.7508μs	22.3460 KOps/s	23.4992 KOps/s	$\color{#d91a1a}-4.91\%$
test_set_nested_new	0.1932ms	47.5848μs	21.0151 KOps/s	21.7511 KOps/s	$\color{#d91a1a}-3.38\%$
test_select	0.2062ms	60.2968μs	16.5846 KOps/s	16.7028 KOps/s	$\color{#d91a1a}-0.71\%$
test_select_nested	79.8410μs	41.5298μs	24.0791 KOps/s	24.0603 KOps/s	$\color{#35bf28}+0.08\%$
test_exclude_nested	0.1904ms	58.7596μs	17.0185 KOps/s	16.8838 KOps/s	$\color{#35bf28}+0.80\%$
test_empty[True]	0.2998ms	0.2568ms	3.8935 KOps/s	3.8054 KOps/s	$\color{#35bf28}+2.32\%$
test_empty[False]	2.7161μs	0.7518μs	1.3301 MOps/s	1.3508 MOps/s	$\color{#d91a1a}-1.53\%$
test_to	66.0220μs	26.8030μs	37.3092 KOps/s	36.8120 KOps/s	$\color{#35bf28}+1.35\%$
test_to_nonblocking	0.1104ms	26.1276μs	38.2737 KOps/s	39.1655 KOps/s	$\color{#d91a1a}-2.28\%$
test_unbind_speed	1.3421ms	0.2823ms	3.5423 KOps/s	3.5741 KOps/s	$\color{#d91a1a}-0.89\%$
test_unbind_speed_stack0	0.3523ms	0.2737ms	3.6533 KOps/s	3.6640 KOps/s	$\color{#d91a1a}-0.29\%$
test_unbind_speed_stack1	95.6271ms	0.7096ms	1.4092 KOps/s	1.4342 KOps/s	$\color{#d91a1a}-1.75\%$
test_split	99.2242ms	2.2240ms	449.6315 Ops/s	462.7561 Ops/s	$\color{#d91a1a}-2.84\%$
test_chunk	98.0074ms	2.2467ms	445.0942 Ops/s	459.7034 Ops/s	$\color{#d91a1a}-3.18\%$
test_creation[device0]	0.3406ms	0.1296ms	7.7179 KOps/s	7.8323 KOps/s	$\color{#d91a1a}-1.46\%$
test_creation_from_tensor	0.3674ms	0.1316ms	7.6000 KOps/s	7.7118 KOps/s	$\color{#d91a1a}-1.45\%$
test_add_one[memmap_tensor0]	0.2247ms	9.2188μs	108.4742 KOps/s	113.1946 KOps/s	$\color{#d91a1a}-4.17\%$
test_contiguous[memmap_tensor0]	32.1810μs	2.2602μs	442.4367 KOps/s	453.1080 KOps/s	$\color{#d91a1a}-2.36\%$
test_stack[memmap_tensor0]	37.2200μs	6.8260μs	146.4987 KOps/s	154.2896 KOps/s	$\textbf{\color{#d91a1a}-5.05\%}$
test_memmaptd_index	1.2747ms	0.4299ms	2.3259 KOps/s	2.3424 KOps/s	$\color{#d91a1a}-0.70\%$
test_memmaptd_index_astensor	0.7436ms	0.5029ms	1.9884 KOps/s	2.0170 KOps/s	$\color{#d91a1a}-1.41\%$
test_memmaptd_index_op	1.4457ms	1.0404ms	961.2068 Ops/s	976.1727 Ops/s	$\color{#d91a1a}-1.53\%$
test_serialize_model	0.1318s	0.1308s	7.6429 Ops/s	7.6096 Ops/s	$\color{#35bf28}+0.44\%$
test_serialize_model_pickle	1.3804s	1.2178s	0.8211 Ops/s	0.8235 Ops/s	$\color{#d91a1a}-0.29\%$
test_serialize_weights	0.1319s	0.1304s	7.6712 Ops/s	7.6385 Ops/s	$\color{#35bf28}+0.43\%$
test_serialize_weights_returnearly	0.2212s	56.8085ms	17.6030 Ops/s	17.5145 Ops/s	$\color{#35bf28}+0.51\%$
test_serialize_weights_pickle	1.4039s	1.2263s	0.8155 Ops/s	0.8219 Ops/s	$\color{#d91a1a}-0.78\%$
test_reshape_pytree	0.1344ms	35.9757μs	27.7966 KOps/s	27.1398 KOps/s	$\color{#35bf28}+2.42\%$
test_reshape_td	0.1326ms	42.7532μs	23.3901 KOps/s	24.4726 KOps/s	$\color{#d91a1a}-4.42\%$
test_view_pytree	0.1730ms	35.8852μs	27.8667 KOps/s	28.7004 KOps/s	$\color{#d91a1a}-2.90\%$
test_view_td	0.1828ms	46.5803μs	21.4683 KOps/s	21.5632 KOps/s	$\color{#d91a1a}-0.44\%$
test_unbind_pytree	0.1630ms	34.5515μs	28.9423 KOps/s	29.9645 KOps/s	$\color{#d91a1a}-3.41\%$
test_unbind_td	0.5469ms	42.7540μs	23.3896 KOps/s	23.5879 KOps/s	$\color{#d91a1a}-0.84\%$
test_split_pytree	0.1449ms	45.4746μs	21.9903 KOps/s	21.4216 KOps/s	$\color{#35bf28}+2.65\%$
test_split_td	97.6364ms	65.7410μs	15.2112 KOps/s	17.9208 KOps/s	$\textbf{\color{#d91a1a}-15.12\%}$
test_add_pytree	0.2110ms	57.6553μs	17.3445 KOps/s	16.2812 KOps/s	$\textbf{\color{#35bf28}+6.53\%}$
test_add_td	0.2387ms	92.2956μs	10.8347 KOps/s	10.7860 KOps/s	$\color{#35bf28}+0.45\%$
test_compile_add_one_nested[tensordict-compile]	0.3055ms	0.1613ms	6.2003 KOps/s	6.0615 KOps/s	$\color{#35bf28}+2.29\%$
test_compile_add_one_nested[tensordict-eager]	0.5730ms	0.1659ms	6.0260 KOps/s	6.0185 KOps/s	$\color{#35bf28}+0.13\%$
test_compile_add_one_nested[pytree-compile]	0.2834ms	0.1444ms	6.9269 KOps/s	6.8508 KOps/s	$\color{#35bf28}+1.11\%$
test_compile_add_one_nested[pytree-eager]	0.3478ms	0.1879ms	5.3213 KOps/s	5.4806 KOps/s	$\color{#d91a1a}-2.91\%$
test_compile_copy_nested[tensordict-compile]	0.4002ms	21.7900μs	45.8927 KOps/s	47.0499 KOps/s	$\color{#d91a1a}-2.46\%$
test_compile_copy_nested[tensordict-eager]	0.4330ms	49.0133μs	20.4026 KOps/s	20.6276 KOps/s	$\color{#d91a1a}-1.09\%$
test_compile_copy_nested[pytree-compile]	0.4458ms	65.2564μs	15.3242 KOps/s	15.5188 KOps/s	$\color{#d91a1a}-1.25\%$
test_compile_copy_nested[pytree-eager]	0.4309ms	49.9903μs	20.0039 KOps/s	20.2026 KOps/s	$\color{#d91a1a}-0.98\%$
test_compile_add_one_flat[tensordict-compile]	0.3844ms	0.3204ms	3.1210 KOps/s	3.0895 KOps/s	$\color{#35bf28}+1.02\%$
test_compile_add_one_flat[tensordict-eager]	0.6253ms	0.2348ms	4.2592 KOps/s	4.1977 KOps/s	$\color{#35bf28}+1.47\%$
test_compile_add_one_flat[tensorclass-compile]	0.6323ms	0.1279ms	7.8177 KOps/s	7.7325 KOps/s	$\color{#35bf28}+1.10\%$
test_compile_add_one_flat[tensorclass-eager]	0.4560ms	66.9081μs	14.9459 KOps/s	15.1501 KOps/s	$\color{#d91a1a}-1.35\%$
test_compile_add_one_flat[pytree-compile]	0.5242ms	0.3188ms	3.1371 KOps/s	3.1338 KOps/s	$\color{#35bf28}+0.10\%$
test_compile_add_one_flat[pytree-eager]	0.8306ms	0.6444ms	1.5517 KOps/s	1.6176 KOps/s	$\color{#d91a1a}-4.07\%$
test_compile_add_self_flat[tensordict-eager]	0.4805ms	0.2825ms	3.5394 KOps/s	3.4752 KOps/s	$\color{#35bf28}+1.85\%$
test_compile_add_self_flat[tensordict-compile]	0.5163ms	0.3232ms	3.0945 KOps/s	3.0884 KOps/s	$\color{#35bf28}+0.20\%$
test_compile_add_self_flat[tensorclass-eager]	0.4650ms	76.9646μs	12.9930 KOps/s	12.4066 KOps/s	$\color{#35bf28}+4.73\%$
test_compile_add_self_flat[tensorclass-compile]	0.2925ms	0.1296ms	7.7151 KOps/s	7.6595 KOps/s	$\color{#35bf28}+0.73\%$
test_compile_add_self_flat[pytree-eager]	0.9205ms	0.5314ms	1.8817 KOps/s	1.8892 KOps/s	$\color{#d91a1a}-0.40\%$
test_compile_add_self_flat[pytree-compile]	0.4512ms	0.3175ms	3.1498 KOps/s	3.1419 KOps/s	$\color{#35bf28}+0.25\%$
test_compile_copy_flat[tensordict-compile]	0.3971ms	20.3226μs	49.2064 KOps/s	50.0233 KOps/s	$\color{#d91a1a}-1.63\%$
test_compile_copy_flat[tensordict-eager]	0.4161ms	38.3576μs	26.0704 KOps/s	26.0238 KOps/s	$\color{#35bf28}+0.18\%$
test_compile_copy_flat[pytree-compile]	0.4501ms	69.8978μs	14.3066 KOps/s	14.2611 KOps/s	$\color{#35bf28}+0.32\%$
test_compile_copy_flat[pytree-eager]	0.4432ms	51.1713μs	19.5422 KOps/s	19.3952 KOps/s	$\color{#35bf28}+0.76\%$
test_compile_assign_and_add[tensordict-compile]	2.3603ms	0.7804ms	1.2814 KOps/s	1.1249 KOps/s	$\textbf{\color{#35bf28}+13.91\%}$
test_compile_assign_and_add[tensordict-eager]	3.5713ms	3.3048ms	302.5868 Ops/s	305.3275 Ops/s	$\color{#d91a1a}-0.90\%$
test_compile_assign_and_add[pytree-compile]	2.3075ms	0.8178ms	1.2227 KOps/s	1.1284 KOps/s	$\textbf{\color{#35bf28}+8.36\%}$
test_compile_assign_and_add[pytree-eager]	3.6486ms	3.2851ms	304.4043 Ops/s	313.8505 Ops/s	$\color{#d91a1a}-3.01\%$
test_compile_indexing[tensor-tensordict-compile]	0.2563ms	0.1097ms	9.1173 KOps/s	9.0707 KOps/s	$\color{#35bf28}+0.51\%$
test_compile_indexing[tensor-tensordict-eager]	0.2445ms	63.2661μs	15.8063 KOps/s	15.5068 KOps/s	$\color{#35bf28}+1.93\%$
test_compile_indexing[tensor-tensorclass-compile]	0.2473ms	0.1028ms	9.7254 KOps/s	9.2071 KOps/s	$\textbf{\color{#35bf28}+5.63\%}$
test_compile_indexing[tensor-tensorclass-eager]	0.4304ms	45.3924μs	22.0301 KOps/s	21.0374 KOps/s	$\color{#35bf28}+4.72\%$
test_compile_indexing[tensor-pytree-compile]	0.5020ms	0.1076ms	9.2973 KOps/s	9.1297 KOps/s	$\color{#35bf28}+1.84\%$
test_compile_indexing[tensor-pytree-eager]	0.4349ms	44.1613μs	22.6443 KOps/s	20.7719 KOps/s	$\textbf{\color{#35bf28}+9.01\%}$
test_compile_indexing[slice-tensordict-compile]	0.3099ms	0.1427ms	7.0065 KOps/s	6.8823 KOps/s	$\color{#35bf28}+1.81\%$
test_compile_indexing[slice-tensordict-eager]	0.4328ms	27.1041μs	36.8947 KOps/s	39.2764 KOps/s	$\textbf{\color{#d91a1a}-6.06\%}$
test_compile_indexing[slice-tensorclass-compile]	0.5221ms	0.1367ms	7.3129 KOps/s	7.2365 KOps/s	$\color{#35bf28}+1.06\%$
test_compile_indexing[slice-tensorclass-eager]	0.1034ms	20.9977μs	47.6243 KOps/s	48.8875 KOps/s	$\color{#d91a1a}-2.58\%$
test_compile_indexing[slice-pytree-compile]	0.5280ms	0.1324ms	7.5511 KOps/s	7.2235 KOps/s	$\color{#35bf28}+4.54\%$
test_compile_indexing[slice-pytree-eager]	0.4032ms	20.8686μs	47.9189 KOps/s	50.0768 KOps/s	$\color{#d91a1a}-4.31\%$
test_compile_indexing[int-tensordict-compile]	0.5440ms	0.1389ms	7.1991 KOps/s	6.7805 KOps/s	$\textbf{\color{#35bf28}+6.17\%}$
test_compile_indexing[int-tensordict-eager]	0.4822ms	25.0629μs	39.8996 KOps/s	38.8493 KOps/s	$\color{#35bf28}+2.70\%$
test_compile_indexing[int-tensorclass-compile]	0.5376ms	0.1325ms	7.5455 KOps/s	7.4145 KOps/s	$\color{#35bf28}+1.77\%$
test_compile_indexing[int-tensorclass-eager]	0.4043ms	20.6796μs	48.3568 KOps/s	49.3437 KOps/s	$\color{#d91a1a}-2.00\%$
test_compile_indexing[int-pytree-compile]	0.5179ms	0.1330ms	7.5171 KOps/s	7.4378 KOps/s	$\color{#35bf28}+1.07\%$
test_compile_indexing[int-pytree-eager]	0.2176ms	20.9901μs	47.6416 KOps/s	49.3632 KOps/s	$\color{#d91a1a}-3.49\%$
test_mod_add[eager]	0.4388ms	35.0630μs	28.5201 KOps/s	31.4470 KOps/s	$\textbf{\color{#d91a1a}-9.31\%}$
test_mod_add[compile]	0.2466ms	71.4545μs	13.9949 KOps/s	14.1342 KOps/s	$\color{#d91a1a}-0.99\%$
test_mod_add[compile-overhead]	0.2521ms	0.1313ms	7.6137 KOps/s	6.3716 KOps/s	$\textbf{\color{#35bf28}+19.49\%}$
test_mod_wrap[eager]	1.1751ms	0.7920ms	1.2627 KOps/s	1.2569 KOps/s	$\color{#35bf28}+0.46\%$
test_mod_wrap[compile]	1.9849ms	0.8444ms	1.1843 KOps/s	1.1696 KOps/s	$\color{#35bf28}+1.26\%$
test_mod_wrap[compile-overhead]	4.8244ms	3.0255ms	330.5258 Ops/s	328.2096 Ops/s	$\color{#35bf28}+0.71\%$
test_mod_wrap_and_backward[eager]	4.2838ms	4.0949ms	244.2084 Ops/s	238.8469 Ops/s	$\color{#35bf28}+2.24\%$
test_mod_wrap_and_backward[compile]	4.4697ms	4.0065ms	249.5938 Ops/s	244.8192 Ops/s	$\color{#35bf28}+1.95\%$
test_mod_wrap_and_backward[compile-overhead]	1.3804ms	0.9201ms	1.0868 KOps/s	992.7535 Ops/s	$\textbf{\color{#35bf28}+9.47\%}$
test_seq_add[eager]	0.3123ms	98.9533μs	10.1058 KOps/s	9.8600 KOps/s	$\color{#35bf28}+2.49\%$
test_seq_add[compile]	0.2798ms	86.1218μs	11.6115 KOps/s	12.0770 KOps/s	$\color{#d91a1a}-3.85\%$
test_seq_add[compile-overhead]	0.2640ms	0.1145ms	8.7308 KOps/s	8.3125 KOps/s	$\textbf{\color{#35bf28}+5.03\%}$
test_seq_wrap[eager]	1.0908ms	0.9450ms	1.0582 KOps/s	1.0625 KOps/s	$\color{#d91a1a}-0.41\%$
test_seq_wrap[compile]	1.0330ms	0.8573ms	1.1664 KOps/s	1.1520 KOps/s	$\color{#35bf28}+1.25\%$
test_seq_wrap[compile-overhead]	0.3467ms	0.2190ms	4.5656 KOps/s	4.3024 KOps/s	$\textbf{\color{#35bf28}+6.12\%}$
test_func_call_runtime[False-eager]	2.5971ms	2.4209ms	413.0613 Ops/s	410.4836 Ops/s	$\color{#35bf28}+0.63\%$
test_func_call_runtime[False-compile]	2.5734ms	2.4190ms	413.4008 Ops/s	409.7735 Ops/s	$\color{#35bf28}+0.89\%$
test_func_call_runtime[False-compile-overhead]	0.5031ms	0.3608ms	2.7720 KOps/s	2.7222 KOps/s	$\color{#35bf28}+1.83\%$
test_func_call_runtime[True-eager]	2.7663ms	2.5753ms	388.3069 Ops/s	386.0810 Ops/s	$\color{#35bf28}+0.58\%$
test_func_call_runtime[True-compile]	2.6160ms	2.4576ms	406.9045 Ops/s	410.0992 Ops/s	$\color{#d91a1a}-0.78\%$
test_func_call_runtime[True-compile-overhead]	0.5034ms	0.3812ms	2.6234 KOps/s	2.5886 KOps/s	$\color{#35bf28}+1.34\%$
test_func_call_cm_runtime[False-eager]	2.6604ms	2.3979ms	417.0361 Ops/s	414.7182 Ops/s	$\color{#35bf28}+0.56\%$
test_func_call_cm_runtime[False-compile]	2.6029ms	2.4275ms	411.9524 Ops/s	411.5932 Ops/s	$\color{#35bf28}+0.09\%$
test_func_call_cm_runtime[False-compile-overhead]	0.5102ms	0.3624ms	2.7595 KOps/s	2.7166 KOps/s	$\color{#35bf28}+1.58\%$
test_func_call_cm_runtime[True-eager]	2.8528ms	2.6786ms	373.3292 Ops/s	371.7620 Ops/s	$\color{#35bf28}+0.42\%$
test_func_call_cm_runtime[True-compile]	2.6980ms	2.4916ms	401.3526 Ops/s	403.7815 Ops/s	$\color{#d91a1a}-0.60\%$
test_func_call_cm_runtime[True-compile-overhead]	0.5615ms	0.4082ms	2.4496 KOps/s	2.4326 KOps/s	$\color{#35bf28}+0.70\%$
test_vmap_func_call_cm_runtime[eager]	4.2890ms	3.8410ms	260.3511 Ops/s	262.0096 Ops/s	$\color{#d91a1a}-0.63\%$
test_vmap_func_call_cm_runtime[compile]	2.6587ms	2.5122ms	398.0599 Ops/s	404.5932 Ops/s	$\color{#d91a1a}-1.61\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.5754ms	0.4074ms	2.4544 KOps/s	2.4245 KOps/s	$\color{#35bf28}+1.23\%$
test_distributed	2.2372ms	0.1720ms	5.8146 KOps/s	8.6710 KOps/s	$\textbf{\color{#d91a1a}-32.94\%}$
test_tdmodule	33.1700μs	14.5177μs	68.8815 KOps/s	71.0861 KOps/s	$\color{#d91a1a}-3.10\%$
test_tdmodule_dispatch	49.2410μs	28.7060μs	34.8359 KOps/s	37.0522 KOps/s	$\textbf{\color{#d91a1a}-5.98\%}$
test_tdseq	35.7710μs	15.6466μs	63.9117 KOps/s	67.5509 KOps/s	$\textbf{\color{#d91a1a}-5.39\%}$
test_tdseq_dispatch	56.0510μs	32.4658μs	30.8016 KOps/s	33.9684 KOps/s	$\textbf{\color{#d91a1a}-9.32\%}$
test_instantiation_functorch	2.1633ms	1.8707ms	534.5609 Ops/s	518.8702 Ops/s	$\color{#35bf28}+3.02\%$
test_instantiation_td	1.8126ms	1.1979ms	834.8202 Ops/s	818.0575 Ops/s	$\color{#35bf28}+2.05\%$
test_exec_functorch	1.1552ms	1.0178ms	982.5247 Ops/s	992.9311 Ops/s	$\color{#d91a1a}-1.05\%$
test_exec_functional_call	1.3689ms	1.0140ms	986.1937 Ops/s	982.1234 Ops/s	$\color{#35bf28}+0.41\%$
test_exec_td	1.2046ms	1.0378ms	963.5682 Ops/s	959.5270 Ops/s	$\color{#35bf28}+0.42\%$
test_exec_td_decorator	1.1993ms	1.0766ms	928.8509 Ops/s	932.2729 Ops/s	$\color{#d91a1a}-0.37\%$
test_vmap_mlp_speed[True-True]	1.4707ms	1.2803ms	781.0518 Ops/s	785.7149 Ops/s	$\color{#d91a1a}-0.59\%$
test_vmap_mlp_speed[True-False]	1.4371ms	1.2755ms	783.9837 Ops/s	789.2893 Ops/s	$\color{#d91a1a}-0.67\%$
test_vmap_mlp_speed[False-True]	1.3767ms	1.1721ms	853.1698 Ops/s	856.1587 Ops/s	$\color{#d91a1a}-0.35\%$
test_vmap_mlp_speed[False-False]	1.3732ms	1.1722ms	853.0777 Ops/s	855.9759 Ops/s	$\color{#d91a1a}-0.34\%$
test_vmap_mlp_speed_decorator[True-True]	1.8067ms	1.2564ms	795.9208 Ops/s	802.9177 Ops/s	$\color{#d91a1a}-0.87\%$
test_vmap_mlp_speed_decorator[True-False]	1.4642ms	1.2555ms	796.4653 Ops/s	802.1324 Ops/s	$\color{#d91a1a}-0.71\%$
test_vmap_mlp_speed_decorator[False-True]	1.3618ms	1.1710ms	853.9454 Ops/s	853.5334 Ops/s	$\color{#35bf28}+0.05\%$
test_vmap_mlp_speed_decorator[False-False]	1.3189ms	1.1704ms	854.4341 Ops/s	856.9635 Ops/s	$\color{#d91a1a}-0.30\%$
test_vmap_transformer_speed[True-True]	13.4793ms	13.1739ms	75.9075 Ops/s	75.3659 Ops/s	$\color{#35bf28}+0.72\%$
test_vmap_transformer_speed[True-False]	13.3967ms	13.1490ms	76.0513 Ops/s	75.6843 Ops/s	$\color{#35bf28}+0.48\%$
test_vmap_transformer_speed[False-True]	13.2303ms	13.0249ms	76.7759 Ops/s	76.4357 Ops/s	$\color{#35bf28}+0.45\%$
test_vmap_transformer_speed[False-False]	13.2962ms	13.0044ms	76.8972 Ops/s	76.4627 Ops/s	$\color{#35bf28}+0.57\%$
test_vmap_transformer_speed_decorator[True-True]	34.4341ms	34.1654ms	29.2694 Ops/s	29.3502 Ops/s	$\color{#d91a1a}-0.28\%$
test_vmap_transformer_speed_decorator[True-False]	34.4239ms	34.0867ms	29.3369 Ops/s	29.2304 Ops/s	$\color{#35bf28}+0.36\%$
test_vmap_transformer_speed_decorator[False-True]	34.7792ms	33.9491ms	29.4558 Ops/s	29.5210 Ops/s	$\color{#d91a1a}-0.22\%$
test_vmap_transformer_speed_decorator[False-False]	34.3171ms	34.0173ms	29.3968 Ops/s	29.4775 Ops/s	$\color{#d91a1a}-0.27\%$
test_to_module_speed[True]	2.0825ms	0.9988ms	1.0012 KOps/s	999.6883 Ops/s	$\color{#35bf28}+0.15\%$
test_to_module_speed[False]	1.3562ms	0.9754ms	1.0253 KOps/s	1.0212 KOps/s	$\color{#35bf28}+0.40\%$
test_tc_init	0.1492ms	35.8635μs	27.8835 KOps/s	32.2982 KOps/s	$\textbf{\color{#d91a1a}-13.67\%}$
test_tc_init_nested	0.1078ms	72.8598μs	13.7250 KOps/s	15.7862 KOps/s	$\textbf{\color{#d91a1a}-13.06\%}$
test_tc_first_layer_tensor	3.5643μs	0.6787μs	1.4733 MOps/s	1.4638 MOps/s	$\color{#35bf28}+0.65\%$
test_tc_first_layer_nontensor	31.6410μs	2.2367μs	447.0913 KOps/s	452.4715 KOps/s	$\color{#d91a1a}-1.19\%$
test_tc_second_layer_tensor	14.6080μs	1.3772μs	726.1369 KOps/s	737.4186 KOps/s	$\color{#d91a1a}-1.53\%$
test_tc_second_layer_nontensor	24.5110μs	2.9704μs	336.6556 KOps/s	340.9172 KOps/s	$\color{#d91a1a}-1.25\%$
test_unbind	0.1972s	12.2284ms	81.7770 Ops/s	92.6614 Ops/s	$\textbf{\color{#d91a1a}-11.75\%}$
test_full_like	0.8031ms	0.5756ms	1.7373 KOps/s	1.7374 KOps/s	$-0.01\%$
test_zeros_like	0.3553ms	0.1983ms	5.0431 KOps/s	5.0400 KOps/s	$\color{#35bf28}+0.06\%$
test_ones_like	0.3724ms	0.1984ms	5.0401 KOps/s	5.0464 KOps/s	$\color{#d91a1a}-0.13\%$
test_clone	0.5932ms	0.4146ms	2.4122 KOps/s	2.4131 KOps/s	$\color{#d91a1a}-0.04\%$
test_squeeze	0.1276ms	9.8779μs	101.2359 KOps/s	101.5380 KOps/s	$\color{#d91a1a}-0.30\%$
test_unsqueeze	0.2192ms	73.1197μs	13.6762 KOps/s	13.1540 KOps/s	$\color{#35bf28}+3.97\%$
test_split	0.4098ms	0.1579ms	6.3321 KOps/s	6.4060 KOps/s	$\color{#d91a1a}-1.15\%$
test_permute	0.3163ms	0.1799ms	5.5582 KOps/s	5.4742 KOps/s	$\color{#35bf28}+1.53\%$
test_stack	1.3172ms	0.8188ms	1.2213 KOps/s	1.1593 KOps/s	$\textbf{\color{#35bf28}+5.35\%}$
test_cat	1.3901ms	1.2322ms	811.5433 Ops/s	811.5973 Ops/s	$-0.01\%$