[BugFix] Enforce zip(..., strict=True) in TDModules

[vmoens]

Stack from ghstack (oldest at bottom):

• -> [BugFix] Enforce zip(..., strict=True) in TDModules #1212
• [BugFix] Fix get for nestedkeys with default in tensorclass #1211

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}11$. Worsened: $\large\color{#d91a1a}14$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	53.8510μs	20.9333μs	47.7708 KOps/s	48.8313 KOps/s	$\color{#d91a1a}-2.17\%$
test_plain_set_stack_nested	61.3460μs	20.9120μs	47.8195 KOps/s	47.9966 KOps/s	$\color{#d91a1a}-0.37\%$
test_plain_set_nested_inplace	63.5600μs	22.8847μs	43.6973 KOps/s	44.2429 KOps/s	$\color{#d91a1a}-1.23\%$
test_plain_set_stack_nested_inplace	82.7360μs	22.6770μs	44.0976 KOps/s	44.3642 KOps/s	$\color{#d91a1a}-0.60\%$
test_items	25.6590μs	4.1841μs	239.0013 KOps/s	241.5190 KOps/s	$\color{#d91a1a}-1.04\%$
test_items_nested	0.7118ms	0.4054ms	2.4666 KOps/s	2.4477 KOps/s	$\color{#35bf28}+0.77\%$
test_items_nested_locked	0.7387ms	0.4060ms	2.4629 KOps/s	2.4739 KOps/s	$\color{#d91a1a}-0.45\%$
test_items_nested_leaf	0.1485ms	75.8872μs	13.1774 KOps/s	13.1239 KOps/s	$\color{#35bf28}+0.41\%$
test_items_stack_nested	0.4864ms	0.4058ms	2.4640 KOps/s	2.4636 KOps/s	$\color{#35bf28}+0.02\%$
test_items_stack_nested_leaf	0.1560ms	79.2404μs	12.6198 KOps/s	12.7124 KOps/s	$\color{#d91a1a}-0.73\%$
test_items_stack_nested_locked	0.6822ms	0.4071ms	2.4561 KOps/s	2.4613 KOps/s	$\color{#d91a1a}-0.21\%$
test_keys	21.2800μs	3.5294μs	283.3375 KOps/s	283.1453 KOps/s	$\color{#35bf28}+0.07\%$
test_keys_nested	0.2690ms	0.1672ms	5.9798 KOps/s	6.1610 KOps/s	$\color{#d91a1a}-2.94\%$
test_keys_nested_locked	1.9072ms	0.1741ms	5.7446 KOps/s	5.9314 KOps/s	$\color{#d91a1a}-3.15\%$
test_keys_nested_leaf	0.2274ms	0.1456ms	6.8689 KOps/s	7.0387 KOps/s	$\color{#d91a1a}-2.41\%$
test_keys_stack_nested	0.2947ms	0.1670ms	5.9875 KOps/s	6.0909 KOps/s	$\color{#d91a1a}-1.70\%$
test_keys_stack_nested_leaf	0.2323ms	0.1439ms	6.9502 KOps/s	7.0401 KOps/s	$\color{#d91a1a}-1.28\%$
test_keys_stack_nested_locked	0.2855ms	0.1706ms	5.8614 KOps/s	5.9043 KOps/s	$\color{#d91a1a}-0.73\%$
test_values	15.3190μs	1.1575μs	863.9030 KOps/s	872.0078 KOps/s	$\color{#d91a1a}-0.93\%$
test_values_nested	0.1213ms	61.6542μs	16.2195 KOps/s	16.2724 KOps/s	$\color{#d91a1a}-0.32\%$
test_values_nested_locked	0.1289ms	61.3872μs	16.2900 KOps/s	16.2611 KOps/s	$\color{#35bf28}+0.18\%$
test_values_nested_leaf	0.1218ms	70.3469μs	14.2153 KOps/s	14.1677 KOps/s	$\color{#35bf28}+0.34\%$
test_values_stack_nested	0.1183ms	63.0287μs	15.8658 KOps/s	15.9617 KOps/s	$\color{#d91a1a}-0.60\%$
test_values_stack_nested_leaf	0.2328ms	71.4859μs	13.9888 KOps/s	13.9865 KOps/s	$\color{#35bf28}+0.02\%$
test_values_stack_nested_locked	0.1229ms	62.9709μs	15.8803 KOps/s	15.9690 KOps/s	$\color{#d91a1a}-0.56\%$
test_membership	25.1770μs	0.8660μs	1.1547 MOps/s	1.3768 MOps/s	$\textbf{\color{#d91a1a}-16.13\%}$
test_membership_nested	33.0220μs	2.8957μs	345.3392 KOps/s	347.0686 KOps/s	$\color{#d91a1a}-0.50\%$
test_membership_nested_leaf	34.5650μs	2.8716μs	348.2412 KOps/s	346.9198 KOps/s	$\color{#35bf28}+0.38\%$
test_membership_stacked_nested	38.0920μs	2.8169μs	354.9990 KOps/s	349.0537 KOps/s	$\color{#35bf28}+1.70\%$
test_membership_stacked_nested_leaf	48.1610μs	2.9008μs	344.7304 KOps/s	348.4254 KOps/s	$\color{#d91a1a}-1.06\%$
test_membership_nested_last	26.6500μs	4.3579μs	229.4696 KOps/s	231.1831 KOps/s	$\color{#d91a1a}-0.74\%$
test_membership_nested_leaf_last	57.6390μs	4.3565μs	229.5432 KOps/s	229.8804 KOps/s	$\color{#d91a1a}-0.15\%$
test_membership_stacked_nested_last	29.3650μs	4.3552μs	229.6085 KOps/s	229.9304 KOps/s	$\color{#d91a1a}-0.14\%$
test_membership_stacked_nested_leaf_last	61.6160μs	4.3629μs	229.2054 KOps/s	230.4563 KOps/s	$\color{#d91a1a}-0.54\%$
test_nested_getleaf	40.5270μs	10.4759μs	95.4571 KOps/s	95.1955 KOps/s	$\color{#35bf28}+0.27\%$
test_nested_get	67.3470μs	9.9124μs	100.8836 KOps/s	99.9722 KOps/s	$\color{#35bf28}+0.91\%$
test_stacked_getleaf	66.0540μs	10.3629μs	96.4982 KOps/s	95.7661 KOps/s	$\color{#35bf28}+0.76\%$
test_stacked_get	38.8830μs	9.8691μs	101.3262 KOps/s	100.9439 KOps/s	$\color{#35bf28}+0.38\%$
test_nested_getitemleaf	55.8750μs	11.0136μs	90.7969 KOps/s	89.9908 KOps/s	$\color{#35bf28}+0.90\%$
test_nested_getitem	49.8440μs	10.4363μs	95.8190 KOps/s	92.6213 KOps/s	$\color{#35bf28}+3.45\%$
test_stacked_getitemleaf	62.5880μs	10.9967μs	90.9365 KOps/s	91.2508 KOps/s	$\color{#d91a1a}-0.34\%$
test_stacked_getitem	63.3190μs	10.3946μs	96.2042 KOps/s	93.6108 KOps/s	$\color{#35bf28}+2.77\%$
test_lock_nested	0.6783ms	0.4096ms	2.4413 KOps/s	2.4065 KOps/s	$\color{#35bf28}+1.45\%$
test_lock_stack_nested	0.6887ms	0.4222ms	2.3684 KOps/s	2.3460 KOps/s	$\color{#35bf28}+0.96\%$
test_unlock_nested	0.6728ms	0.3397ms	2.9436 KOps/s	2.9634 KOps/s	$\color{#d91a1a}-0.67\%$
test_unlock_stack_nested	0.5406ms	0.3404ms	2.9374 KOps/s	2.8962 KOps/s	$\color{#35bf28}+1.42\%$
test_flatten_speed	0.1765ms	99.9619μs	10.0038 KOps/s	9.8214 KOps/s	$\color{#35bf28}+1.86\%$
test_unflatten_speed	0.8664ms	0.5208ms	1.9202 KOps/s	1.9482 KOps/s	$\color{#d91a1a}-1.44\%$
test_common_ops	1.0025ms	0.7951ms	1.2576 KOps/s	1.1953 KOps/s	$\textbf{\color{#35bf28}+5.21\%}$
test_creation	28.5030μs	2.5292μs	395.3797 KOps/s	403.1710 KOps/s	$\color{#d91a1a}-1.93\%$
test_creation_empty	42.0800μs	12.6250μs	79.2081 KOps/s	79.6598 KOps/s	$\color{#d91a1a}-0.57\%$
test_creation_nested_1	56.0760μs	15.6422μs	63.9295 KOps/s	64.4009 KOps/s	$\color{#d91a1a}-0.73\%$
test_creation_nested_2	60.7840μs	20.0226μs	49.9435 KOps/s	49.8003 KOps/s	$\color{#35bf28}+0.29\%$
test_clone	72.5370μs	13.5071μs	74.0349 KOps/s	72.7797 KOps/s	$\color{#35bf28}+1.72\%$
test_getitem[int]	0.9021ms	13.1814μs	75.8643 KOps/s	77.4506 KOps/s	$\color{#d91a1a}-2.05\%$
test_getitem[slice_int]	0.1342ms	24.6628μs	40.5470 KOps/s	42.2446 KOps/s	$\color{#d91a1a}-4.02\%$
test_getitem[range]	0.2034ms	51.4173μs	19.4487 KOps/s	20.2203 KOps/s	$\color{#d91a1a}-3.82\%$
test_getitem[tuple]	0.1256ms	20.4786μs	48.8314 KOps/s	49.8936 KOps/s	$\color{#d91a1a}-2.13\%$
test_getitem[list]	0.2372ms	46.5333μs	21.4900 KOps/s	21.8014 KOps/s	$\color{#d91a1a}-1.43\%$
test_setitem_dim[int]	60.9840μs	25.5355μs	39.1612 KOps/s	38.1613 KOps/s	$\color{#35bf28}+2.62\%$
test_setitem_dim[slice_int]	93.4660μs	50.6914μs	19.7272 KOps/s	19.7017 KOps/s	$\color{#35bf28}+0.13\%$
test_setitem_dim[range]	0.1457ms	76.9308μs	12.9987 KOps/s	12.8228 KOps/s	$\color{#35bf28}+1.37\%$
test_setitem_dim[tuple]	81.3530μs	40.6284μs	24.6133 KOps/s	24.3621 KOps/s	$\color{#35bf28}+1.03\%$
test_setitem	93.3360μs	21.0497μs	47.5067 KOps/s	46.3305 KOps/s	$\color{#35bf28}+2.54\%$
test_set	78.7590μs	20.4248μs	48.9600 KOps/s	47.7451 KOps/s	$\color{#35bf28}+2.54\%$
test_set_shared	4.7504ms	0.1798ms	5.5613 KOps/s	5.5043 KOps/s	$\color{#35bf28}+1.04\%$
test_update	0.1391ms	24.0032μs	41.6612 KOps/s	40.7271 KOps/s	$\color{#35bf28}+2.29\%$
test_update_nested	81.7640μs	33.8460μs	29.5456 KOps/s	28.5525 KOps/s	$\color{#35bf28}+3.48\%$
test_update__nested	1.2035ms	34.0907μs	29.3335 KOps/s	28.9386 KOps/s	$\color{#35bf28}+1.36\%$
test_set_nested	57.0070μs	22.4566μs	44.5303 KOps/s	43.0396 KOps/s	$\color{#35bf28}+3.46\%$
test_set_nested_new	0.1110ms	27.4585μs	36.4185 KOps/s	36.2649 KOps/s	$\color{#35bf28}+0.42\%$
test_select	0.1279ms	43.6623μs	22.9031 KOps/s	22.7704 KOps/s	$\color{#35bf28}+0.58\%$
test_select_nested	0.1090ms	62.7543μs	15.9352 KOps/s	15.9754 KOps/s	$\color{#d91a1a}-0.25\%$
test_exclude_nested	0.1707ms	80.9927μs	12.3468 KOps/s	12.4551 KOps/s	$\color{#d91a1a}-0.87\%$
test_empty[True]	0.5387ms	0.4100ms	2.4393 KOps/s	2.4835 KOps/s	$\color{#d91a1a}-1.78\%$
test_empty[False]	7.1032μs	1.3858μs	721.6239 KOps/s	725.1353 KOps/s	$\color{#d91a1a}-0.48\%$
test_unbind_speed	0.3359ms	0.2686ms	3.7223 KOps/s	3.6569 KOps/s	$\color{#35bf28}+1.79\%$
test_unbind_speed_stack0	0.5897ms	0.2658ms	3.7619 KOps/s	3.7168 KOps/s	$\color{#35bf28}+1.21\%$
test_unbind_speed_stack1	99.0742ms	0.7221ms	1.3848 KOps/s	1.2542 KOps/s	$\textbf{\color{#35bf28}+10.41\%}$
test_split	0.1101s	1.8031ms	554.6113 Ops/s	564.4595 Ops/s	$\color{#d91a1a}-1.74\%$
test_chunk	98.9448ms	1.7748ms	563.4366 Ops/s	620.0436 Ops/s	$\textbf{\color{#d91a1a}-9.13\%}$
test_consolidate_njt[False-None]	8.5912ms	8.2694ms	120.9277 Ops/s	108.6097 Ops/s	$\textbf{\color{#35bf28}+11.34\%}$
test_creation[device0]	3.8462ms	93.4718μs	10.6984 KOps/s	10.9346 KOps/s	$\color{#d91a1a}-2.16\%$
test_creation_from_tensor	0.2739ms	93.9709μs	10.6416 KOps/s	10.4711 KOps/s	$\color{#35bf28}+1.63\%$
test_add_one[memmap_tensor0]	84.0880μs	4.8029μs	208.2089 KOps/s	188.0603 KOps/s	$\textbf{\color{#35bf28}+10.71\%}$
test_contiguous[memmap_tensor0]	13.7970μs	0.5307μs	1.8843 MOps/s	1.9527 MOps/s	$\color{#d91a1a}-3.50\%$
test_stack[memmap_tensor0]	26.9910μs	3.5658μs	280.4446 KOps/s	286.1820 KOps/s	$\color{#d91a1a}-2.00\%$
test_memmaptd_index	1.3119ms	0.2336ms	4.2808 KOps/s	4.3205 KOps/s	$\color{#d91a1a}-0.92\%$
test_memmaptd_index_astensor	0.5952ms	0.3187ms	3.1380 KOps/s	3.1470 KOps/s	$\color{#d91a1a}-0.29\%$
test_memmaptd_index_op	0.8199ms	0.5925ms	1.6878 KOps/s	1.6540 KOps/s	$\color{#35bf28}+2.05\%$
test_serialize_model	0.2215s	0.1306s	7.6569 Ops/s	8.7886 Ops/s	$\textbf{\color{#d91a1a}-12.88\%}$
test_serialize_model_pickle	0.4927s	0.4050s	2.4692 Ops/s	2.5398 Ops/s	$\color{#d91a1a}-2.78\%$
test_serialize_weights	0.1348s	0.1158s	8.6350 Ops/s	8.7871 Ops/s	$\color{#d91a1a}-1.73\%$
test_serialize_weights_returnearly	0.1730s	0.1610s	6.2094 Ops/s	6.3814 Ops/s	$\color{#d91a1a}-2.70\%$
test_serialize_weights_pickle	0.6200s	0.4604s	2.1719 Ops/s	1.1990 Ops/s	$\textbf{\color{#35bf28}+81.14\%}$
test_serialize_weights_filesystem	0.2521s	0.1595s	6.2694 Ops/s	7.0644 Ops/s	$\textbf{\color{#d91a1a}-11.25\%}$
test_serialize_model_filesystem	0.1633s	0.1481s	6.7538 Ops/s	7.1508 Ops/s	$\textbf{\color{#d91a1a}-5.55\%}$
test_reshape_pytree	76.5840μs	26.0512μs	38.3860 KOps/s	36.8780 KOps/s	$\color{#35bf28}+4.09\%$
test_reshape_td	96.2120μs	32.5220μs	30.7484 KOps/s	31.4936 KOps/s	$\color{#d91a1a}-2.37\%$
test_view_pytree	76.2640μs	26.1785μs	38.1993 KOps/s	38.9949 KOps/s	$\color{#d91a1a}-2.04\%$
test_view_td	87.3950μs	38.7048μs	25.8366 KOps/s	26.9321 KOps/s	$\color{#d91a1a}-4.07\%$
test_unbind_pytree	79.7310μs	29.4873μs	33.9129 KOps/s	33.6184 KOps/s	$\color{#35bf28}+0.88\%$
test_unbind_td	0.3483ms	39.7408μs	25.1631 KOps/s	24.8447 KOps/s	$\color{#35bf28}+1.28\%$
test_split_pytree	93.6760μs	29.0556μs	34.4168 KOps/s	34.1243 KOps/s	$\color{#35bf28}+0.86\%$
test_split_td	0.5653ms	47.2305μs	21.1727 KOps/s	21.9025 KOps/s	$\color{#d91a1a}-3.33\%$
test_add_pytree	0.1505ms	35.2973μs	28.3308 KOps/s	27.9936 KOps/s	$\color{#35bf28}+1.20\%$
test_add_td	0.1678ms	57.7832μs	17.3061 KOps/s	17.1213 KOps/s	$\color{#35bf28}+1.08\%$
test_compile_add_one_nested[tensordict-compile]	0.1373ms	67.0936μs	14.9046 KOps/s	14.9539 KOps/s	$\color{#d91a1a}-0.33\%$
test_compile_add_one_nested[tensordict-eager]	0.3276ms	0.1739ms	5.7489 KOps/s	5.7902 KOps/s	$\color{#d91a1a}-0.71\%$
test_compile_add_one_nested[pytree-compile]	0.1166ms	46.1948μs	21.6475 KOps/s	21.9751 KOps/s	$\color{#d91a1a}-1.49\%$
test_compile_add_one_nested[pytree-eager]	0.1921ms	0.1178ms	8.4892 KOps/s	8.2839 KOps/s	$\color{#35bf28}+2.48\%$
test_compile_copy_nested[tensordict-compile]	82.2450μs	28.4278μs	35.1769 KOps/s	36.0621 KOps/s	$\color{#d91a1a}-2.45\%$
test_compile_copy_nested[tensordict-eager]	0.1202ms	58.5064μs	17.0921 KOps/s	16.7634 KOps/s	$\color{#35bf28}+1.96\%$
test_compile_copy_nested[pytree-compile]	0.2116ms	80.5937μs	12.4079 KOps/s	12.4629 KOps/s	$\color{#d91a1a}-0.44\%$
test_compile_copy_nested[pytree-eager]	0.1281ms	65.6102μs	15.2415 KOps/s	14.9595 KOps/s	$\color{#35bf28}+1.89\%$
test_compile_add_one_flat[tensordict-compile]	0.1756ms	0.1073ms	9.3164 KOps/s	9.4471 KOps/s	$\color{#d91a1a}-1.38\%$
test_compile_add_one_flat[tensordict-eager]	0.4261ms	0.2176ms	4.5949 KOps/s	4.6396 KOps/s	$\color{#d91a1a}-0.96\%$
test_compile_add_one_flat[tensorclass-compile]	98.3350μs	47.5691μs	21.0221 KOps/s	21.3904 KOps/s	$\color{#d91a1a}-1.72\%$
test_compile_add_one_flat[tensorclass-eager]	0.1599ms	68.0141μs	14.7028 KOps/s	14.3670 KOps/s	$\color{#35bf28}+2.34\%$
test_compile_add_one_flat[pytree-compile]	0.1804ms	0.1007ms	9.9336 KOps/s	10.0587 KOps/s	$\color{#d91a1a}-1.24\%$
test_compile_add_one_flat[pytree-eager]	0.6507ms	0.2077ms	4.8143 KOps/s	4.9497 KOps/s	$\color{#d91a1a}-2.74\%$
test_compile_add_self_flat[tensordict-eager]	0.6117ms	0.2381ms	4.1995 KOps/s	4.3321 KOps/s	$\color{#d91a1a}-3.06\%$
test_compile_add_self_flat[tensordict-compile]	0.2320ms	0.1129ms	8.8577 KOps/s	9.2897 KOps/s	$\color{#d91a1a}-4.65\%$
test_compile_add_self_flat[tensorclass-eager]	1.3172ms	65.3268μs	15.3077 KOps/s	16.2233 KOps/s	$\textbf{\color{#d91a1a}-5.64\%}$
test_compile_add_self_flat[tensorclass-compile]	0.2041ms	48.7979μs	20.4927 KOps/s	20.7380 KOps/s	$\color{#d91a1a}-1.18\%$
test_compile_add_self_flat[pytree-eager]	0.2588ms	0.1569ms	6.3725 KOps/s	6.3055 KOps/s	$\color{#35bf28}+1.06\%$
test_compile_add_self_flat[pytree-compile]	0.2073ms	0.1003ms	9.9675 KOps/s	9.8228 KOps/s	$\color{#35bf28}+1.47\%$
test_compile_copy_flat[tensordict-compile]	65.7840μs	21.8805μs	45.7027 KOps/s	46.7537 KOps/s	$\color{#d91a1a}-2.25\%$
test_compile_copy_flat[tensordict-eager]	0.1269ms	67.4151μs	14.8335 KOps/s	14.7558 KOps/s	$\color{#35bf28}+0.53\%$
test_compile_copy_flat[pytree-compile]	0.1766ms	80.7527μs	12.3835 KOps/s	12.3812 KOps/s	$\color{#35bf28}+0.02\%$
test_compile_copy_flat[pytree-eager]	0.1352ms	67.1688μs	14.8879 KOps/s	14.8435 KOps/s	$\color{#35bf28}+0.30\%$
test_compile_assign_and_add[tensordict-compile]	0.4222ms	0.2161ms	4.6280 KOps/s	4.6191 KOps/s	$\color{#35bf28}+0.19\%$
test_compile_assign_and_add[tensordict-eager]	1.5656ms	1.3639ms	733.2098 Ops/s	720.1438 Ops/s	$\color{#35bf28}+1.81\%$
test_compile_assign_and_add[pytree-compile]	0.2871ms	0.2111ms	4.7368 KOps/s	4.7165 KOps/s	$\color{#35bf28}+0.43\%$
test_compile_assign_and_add[pytree-eager]	1.4329ms	0.8264ms	1.2100 KOps/s	1.2105 KOps/s	$\color{#d91a1a}-0.04\%$
test_compile_assign_and_add_stack[compile]	0.8332ms	0.4622ms	2.1637 KOps/s	2.2108 KOps/s	$\color{#d91a1a}-2.13\%$
test_compile_assign_and_add_stack[eager]	3.0513ms	2.7492ms	363.7424 Ops/s	354.1209 Ops/s	$\color{#35bf28}+2.72\%$
test_compile_indexing[tensor-tensordict-compile]	0.1539ms	41.2943μs	24.2164 KOps/s	26.1915 KOps/s	$\textbf{\color{#d91a1a}-7.54\%}$
test_compile_indexing[tensor-tensordict-eager]	0.8489ms	34.2752μs	29.1756 KOps/s	30.0706 KOps/s	$\color{#d91a1a}-2.98\%$
test_compile_indexing[tensor-tensorclass-compile]	76.3340μs	31.4911μs	31.7551 KOps/s	33.0660 KOps/s	$\color{#d91a1a}-3.96\%$
test_compile_indexing[tensor-tensorclass-eager]	0.1073ms	23.1135μs	43.2648 KOps/s	42.9805 KOps/s	$\color{#35bf28}+0.66\%$
test_compile_indexing[tensor-pytree-compile]	0.1201ms	33.8721μs	29.5228 KOps/s	32.9896 KOps/s	$\textbf{\color{#d91a1a}-10.51\%}$
test_compile_indexing[tensor-pytree-eager]	63.6300μs	23.7498μs	42.1056 KOps/s	43.5451 KOps/s	$\color{#d91a1a}-3.31\%$
test_compile_indexing[slice-tensordict-compile]	0.1384ms	56.0952μs	17.8268 KOps/s	19.2118 KOps/s	$\textbf{\color{#d91a1a}-7.21\%}$
test_compile_indexing[slice-tensordict-eager]	0.3335ms	20.2612μs	49.3555 KOps/s	50.0626 KOps/s	$\color{#d91a1a}-1.41\%$
test_compile_indexing[slice-tensorclass-compile]	0.1482ms	47.0439μs	21.2567 KOps/s	22.1005 KOps/s	$\color{#d91a1a}-3.82\%$
test_compile_indexing[slice-tensorclass-eager]	84.9100μs	18.2739μs	54.7228 KOps/s	53.4045 KOps/s	$\color{#35bf28}+2.47\%$
test_compile_indexing[slice-pytree-compile]	0.1228ms	47.6665μs	20.9791 KOps/s	21.6090 KOps/s	$\color{#d91a1a}-2.92\%$
test_compile_indexing[slice-pytree-eager]	96.7720μs	18.3789μs	54.4103 KOps/s	52.9444 KOps/s	$\color{#35bf28}+2.77\%$
test_compile_indexing[int-tensordict-compile]	0.1403ms	58.0675μs	17.2213 KOps/s	18.7016 KOps/s	$\textbf{\color{#d91a1a}-7.92\%}$
test_compile_indexing[int-tensordict-eager]	1.0833ms	20.2742μs	49.3237 KOps/s	49.8746 KOps/s	$\color{#d91a1a}-1.10\%$
test_compile_indexing[int-tensorclass-compile]	0.1067ms	47.6662μs	20.9792 KOps/s	21.6362 KOps/s	$\color{#d91a1a}-3.04\%$
test_compile_indexing[int-tensorclass-eager]	85.1800μs	18.4072μs	54.3266 KOps/s	53.8348 KOps/s	$\color{#35bf28}+0.91\%$
test_compile_indexing[int-pytree-compile]	0.1316ms	47.7922μs	20.9239 KOps/s	21.6709 KOps/s	$\color{#d91a1a}-3.45\%$
test_compile_indexing[int-pytree-eager]	95.4930μs	18.3285μs	54.5598 KOps/s	54.3258 KOps/s	$\color{#35bf28}+0.43\%$
test_mod_add[eager]	89.2280μs	36.3004μs	27.5479 KOps/s	28.1124 KOps/s	$\color{#d91a1a}-2.01\%$
test_mod_add[compile]	0.1419ms	65.7761μs	15.2031 KOps/s	15.2074 KOps/s	$\color{#d91a1a}-0.03\%$
test_mod_add[compile-overhead]	0.1411ms	65.3984μs	15.2909 KOps/s	15.4762 KOps/s	$\color{#d91a1a}-1.20\%$
test_mod_wrap[eager]	0.3423ms	0.2171ms	4.6058 KOps/s	4.3678 KOps/s	$\textbf{\color{#35bf28}+5.45\%}$
test_mod_wrap[compile]	2.2420ms	0.2276ms	4.3935 KOps/s	4.2958 KOps/s	$\color{#35bf28}+2.27\%$
test_mod_wrap[compile-overhead]	0.4413ms	0.2250ms	4.4444 KOps/s	4.4386 KOps/s	$\color{#35bf28}+0.13\%$
test_mod_wrap_and_backward[eager]	18.8012ms	12.7906ms	78.1824 Ops/s	91.9392 Ops/s	$\textbf{\color{#d91a1a}-14.96\%}$
test_mod_wrap_and_backward[compile]	14.9818ms	12.7216ms	78.6067 Ops/s	84.8104 Ops/s	$\textbf{\color{#d91a1a}-7.31\%}$
test_mod_wrap_and_backward[compile-overhead]	14.1621ms	11.7918ms	84.8045 Ops/s	85.2968 Ops/s	$\color{#d91a1a}-0.58\%$
test_seq_add[eager]	0.2160ms	0.1162ms	8.6083 KOps/s	8.5391 KOps/s	$\color{#35bf28}+0.81\%$
test_seq_add[compile]	0.1388ms	77.3195μs	12.9334 KOps/s	12.9313 KOps/s	$\color{#35bf28}+0.02\%$
test_seq_add[compile-overhead]	0.1582ms	75.9377μs	13.1687 KOps/s	13.1198 KOps/s	$\color{#35bf28}+0.37\%$
test_seq_wrap[eager]	0.8461ms	0.4486ms	2.2292 KOps/s	2.1941 KOps/s	$\color{#35bf28}+1.60\%$
test_seq_wrap[compile]	0.7049ms	0.2489ms	4.0177 KOps/s	4.0773 KOps/s	$\color{#d91a1a}-1.46\%$
test_seq_wrap[compile-overhead]	0.4520ms	0.2436ms	4.1058 KOps/s	4.0830 KOps/s	$\color{#35bf28}+0.56\%$
test_func_call_runtime[False-eager]	0.8135ms	0.5354ms	1.8677 KOps/s	1.8316 KOps/s	$\color{#35bf28}+1.97\%$
test_func_call_runtime[False-compile]	0.6263ms	0.4426ms	2.2593 KOps/s	2.2325 KOps/s	$\color{#35bf28}+1.20\%$
test_func_call_runtime[False-compile-overhead]	0.9726ms	0.4457ms	2.2437 KOps/s	2.2564 KOps/s	$\color{#d91a1a}-0.56\%$
test_func_call_runtime[True-eager]	0.9293ms	0.7488ms	1.3355 KOps/s	1.3248 KOps/s	$\color{#35bf28}+0.80\%$
test_func_call_runtime[True-compile]	0.6321ms	0.4609ms	2.1697 KOps/s	2.1537 KOps/s	$\color{#35bf28}+0.74\%$
test_func_call_runtime[True-compile-overhead]	0.5728ms	0.4598ms	2.1750 KOps/s	2.1390 KOps/s	$\color{#35bf28}+1.68\%$
test_func_call_cm_runtime[False-eager]	0.7540ms	0.5255ms	1.9028 KOps/s	1.8229 KOps/s	$\color{#35bf28}+4.38\%$
test_func_call_cm_runtime[False-compile]	0.7869ms	0.4379ms	2.2835 KOps/s	2.2494 KOps/s	$\color{#35bf28}+1.52\%$
test_func_call_cm_runtime[False-compile-overhead]	0.6398ms	0.4351ms	2.2983 KOps/s	2.2525 KOps/s	$\color{#35bf28}+2.03\%$
test_func_call_cm_runtime[True-eager]	1.0288ms	0.8861ms	1.1285 KOps/s	1.1084 KOps/s	$\color{#35bf28}+1.82\%$
test_func_call_cm_runtime[True-compile]	0.9106ms	0.7785ms	1.2845 KOps/s	1.2446 KOps/s	$\color{#35bf28}+3.21\%$
test_func_call_cm_runtime[True-compile-overhead]	1.2147ms	0.7886ms	1.2680 KOps/s	1.2300 KOps/s	$\color{#35bf28}+3.09\%$
test_vmap_func_call_cm_runtime[eager]	2.5536ms	1.8827ms	531.1438 Ops/s	515.6853 Ops/s	$\color{#35bf28}+3.00\%$
test_vmap_func_call_cm_runtime[compile]	1.0696ms	0.5374ms	1.8609 KOps/s	1.8529 KOps/s	$\color{#35bf28}+0.44\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.6632ms	0.5330ms	1.8760 KOps/s	1.8317 KOps/s	$\color{#35bf28}+2.42\%$
test_distributed	0.2673ms	0.1226ms	8.1574 KOps/s	8.0289 KOps/s	$\color{#35bf28}+1.60\%$
test_tdmodule	64.3410μs	26.5737μs	37.6312 KOps/s	37.0008 KOps/s	$\color{#35bf28}+1.70\%$
test_tdmodule_dispatch	82.1150μs	52.0278μs	19.2205 KOps/s	20.5672 KOps/s	$\textbf{\color{#d91a1a}-6.55\%}$
test_tdseq	57.9590μs	28.0351μs	35.6695 KOps/s	33.4545 KOps/s	$\textbf{\color{#35bf28}+6.62\%}$
test_tdseq_dispatch	93.6660μs	53.4957μs	18.6931 KOps/s	18.1775 KOps/s	$\color{#35bf28}+2.84\%$
test_instantiation_functorch	1.7068ms	1.5039ms	664.9552 Ops/s	659.7755 Ops/s	$\color{#35bf28}+0.79\%$
test_exec_functorch	0.3221ms	0.1749ms	5.7187 KOps/s	5.4823 KOps/s	$\color{#35bf28}+4.31\%$
test_exec_functional_call	0.3348ms	0.1721ms	5.8108 KOps/s	5.8058 KOps/s	$\color{#35bf28}+0.09\%$
test_exec_td_decorator	0.4393ms	0.2238ms	4.4681 KOps/s	4.1551 KOps/s	$\textbf{\color{#35bf28}+7.53\%}$
test_vmap_mlp_speed_decorator[True-True]	1.1282ms	0.6551ms	1.5265 KOps/s	1.5386 KOps/s	$\color{#d91a1a}-0.79\%$
test_vmap_mlp_speed_decorator[True-False]	0.8923ms	0.6506ms	1.5370 KOps/s	1.5269 KOps/s	$\color{#35bf28}+0.66\%$
test_vmap_mlp_speed_decorator[False-True]	0.6959ms	0.5236ms	1.9098 KOps/s	1.8960 KOps/s	$\color{#35bf28}+0.73\%$
test_vmap_mlp_speed_decorator[False-False]	0.7074ms	0.5218ms	1.9166 KOps/s	1.8928 KOps/s	$\color{#35bf28}+1.26\%$
test_to_module_speed[True]	2.1640ms	1.3214ms	756.7916 Ops/s	763.7252 Ops/s	$\color{#d91a1a}-0.91\%$
test_to_module_speed[False]	2.0853ms	1.2926ms	773.6502 Ops/s	780.3354 Ops/s	$\color{#d91a1a}-0.86\%$
test_tc_init	79.0590μs	48.0857μs	20.7962 KOps/s	21.3406 KOps/s	$\color{#d91a1a}-2.55\%$
test_tc_init_nested	0.2205ms	96.3495μs	10.3789 KOps/s	10.7309 KOps/s	$\color{#d91a1a}-3.28\%$
test_tc_first_layer_tensor	36.5990μs	1.5377μs	650.3174 KOps/s	654.4991 KOps/s	$\color{#d91a1a}-0.64\%$
test_tc_first_layer_nontensor	22.9630μs	4.7213μs	211.8080 KOps/s	217.5134 KOps/s	$\color{#d91a1a}-2.62\%$
test_tc_second_layer_tensor	41.2880μs	2.9135μs	343.2344 KOps/s	357.2334 KOps/s	$\color{#d91a1a}-3.92\%$
test_tc_second_layer_nontensor	23.7150μs	6.0594μs	165.0332 KOps/s	170.0315 KOps/s	$\color{#d91a1a}-2.94\%$
test_unbind	0.2149s	14.3637ms	69.6201 Ops/s	77.0477 Ops/s	$\textbf{\color{#d91a1a}-9.64\%}$
test_full_like	8.4826ms	6.8251ms	146.5188 Ops/s	132.1244 Ops/s	$\textbf{\color{#35bf28}+10.89\%}$
test_zeros_like	4.3857ms	2.6421ms	378.4804 Ops/s	358.5789 Ops/s	$\textbf{\color{#35bf28}+5.55\%}$
test_ones_like	3.6462ms	3.0646ms	326.3055 Ops/s	302.5821 Ops/s	$\textbf{\color{#35bf28}+7.84\%}$
test_clone	5.1253ms	4.7593ms	210.1164 Ops/s	206.3418 Ops/s	$\color{#35bf28}+1.83\%$
test_squeeze	60.8610μs	12.3737μs	80.8168 KOps/s	82.6143 KOps/s	$\color{#d91a1a}-2.18\%$
test_unsqueeze	0.1595ms	92.1464μs	10.8523 KOps/s	11.1909 KOps/s	$\color{#d91a1a}-3.03\%$
test_split	0.4704ms	0.1944ms	5.1433 KOps/s	5.2014 KOps/s	$\color{#d91a1a}-1.12\%$
test_permute	0.3387ms	0.1996ms	5.0110 KOps/s	5.0555 KOps/s	$\color{#d91a1a}-0.88\%$
test_stack	31.4467ms	23.5888ms	42.3929 Ops/s	41.7058 Ops/s	$\color{#35bf28}+1.65\%$
test_cat	25.6654ms	23.2408ms	43.0278 Ops/s	41.4973 Ops/s	$\color{#35bf28}+3.69\%$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}51$. Worsened: $\large\color{#d91a1a}12$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	34.9410μs	11.3443μs	88.1499 KOps/s	73.7386 KOps/s	$\textbf{\color{#35bf28}+19.54\%}$
test_plain_set_stack_nested	43.8610μs	11.4233μs	87.5403 KOps/s	74.9246 KOps/s	$\textbf{\color{#35bf28}+16.84\%}$
test_plain_set_nested_inplace	46.5000μs	12.4216μs	80.5047 KOps/s	69.0263 KOps/s	$\textbf{\color{#35bf28}+16.63\%}$
test_plain_set_stack_nested_inplace	42.5310μs	12.5029μs	79.9816 KOps/s	67.5499 KOps/s	$\textbf{\color{#35bf28}+18.40\%}$
test_items	22.4100μs	2.9901μs	334.4325 KOps/s	344.3494 KOps/s	$\color{#d91a1a}-2.88\%$
test_items_nested	0.4153ms	0.3706ms	2.6981 KOps/s	2.7268 KOps/s	$\color{#d91a1a}-1.05\%$
test_items_nested_locked	0.3993ms	0.3734ms	2.6782 KOps/s	2.7441 KOps/s	$\color{#d91a1a}-2.40\%$
test_items_nested_leaf	84.0810μs	59.4042μs	16.8338 KOps/s	16.9621 KOps/s	$\color{#d91a1a}-0.76\%$
test_items_stack_nested	2.8936ms	0.3757ms	2.6619 KOps/s	2.7378 KOps/s	$\color{#d91a1a}-2.77\%$
test_items_stack_nested_leaf	97.0210μs	60.7154μs	16.4703 KOps/s	16.8073 KOps/s	$\color{#d91a1a}-2.01\%$
test_items_stack_nested_locked	0.4131ms	0.3702ms	2.7013 KOps/s	2.7323 KOps/s	$\color{#d91a1a}-1.13\%$
test_keys	23.0500μs	3.4592μs	289.0828 KOps/s	288.8354 KOps/s	$\color{#35bf28}+0.09\%$
test_keys_nested	0.1218ms	89.1283μs	11.2198 KOps/s	11.2892 KOps/s	$\color{#d91a1a}-0.61\%$
test_keys_nested_locked	0.7250ms	95.5117μs	10.4699 KOps/s	10.5866 KOps/s	$\color{#d91a1a}-1.10\%$
test_keys_nested_leaf	0.1129ms	80.0278μs	12.4957 KOps/s	12.6091 KOps/s	$\color{#d91a1a}-0.90\%$
test_keys_stack_nested	0.1197ms	89.6451μs	11.1551 KOps/s	11.2581 KOps/s	$\color{#d91a1a}-0.92\%$
test_keys_stack_nested_leaf	0.1188ms	81.4310μs	12.2803 KOps/s	12.5847 KOps/s	$\color{#d91a1a}-2.42\%$
test_keys_stack_nested_locked	0.1470ms	96.1369μs	10.4018 KOps/s	10.5030 KOps/s	$\color{#d91a1a}-0.96\%$
test_values	6.8733μs	0.8520μs	1.1737 MOps/s	1.1739 MOps/s	$\color{#d91a1a}-0.01\%$
test_values_nested	85.4410μs	37.9435μs	26.3550 KOps/s	26.7502 KOps/s	$\color{#d91a1a}-1.48\%$
test_values_nested_locked	90.1110μs	39.3472μs	25.4148 KOps/s	25.6078 KOps/s	$\color{#d91a1a}-0.75\%$
test_values_nested_leaf	0.1337ms	42.3877μs	23.5918 KOps/s	23.9066 KOps/s	$\color{#d91a1a}-1.32\%$
test_values_stack_nested	77.4110μs	38.5448μs	25.9439 KOps/s	26.4399 KOps/s	$\color{#d91a1a}-1.88\%$
test_values_stack_nested_leaf	81.8610μs	43.1330μs	23.1841 KOps/s	23.6338 KOps/s	$\color{#d91a1a}-1.90\%$
test_values_stack_nested_locked	67.8810μs	39.8207μs	25.1126 KOps/s	25.4984 KOps/s	$\color{#d91a1a}-1.51\%$
test_membership	1.6230μs	0.5101μs	1.9605 MOps/s	1.9873 MOps/s	$\color{#d91a1a}-1.35\%$
test_membership_nested	28.7910μs	2.1222μs	471.2022 KOps/s	492.6942 KOps/s	$\color{#d91a1a}-4.36\%$
test_membership_nested_leaf	16.7150μs	2.0306μs	492.4674 KOps/s	493.3532 KOps/s	$\color{#d91a1a}-0.18\%$
test_membership_stacked_nested	40.0510μs	2.1206μs	471.5590 KOps/s	473.2419 KOps/s	$\color{#d91a1a}-0.36\%$
test_membership_stacked_nested_leaf	24.7500μs	2.1119μs	473.5014 KOps/s	462.3722 KOps/s	$\color{#35bf28}+2.41\%$
test_membership_nested_last	38.3300μs	3.2172μs	310.8315 KOps/s	320.1553 KOps/s	$\color{#d91a1a}-2.91\%$
test_membership_nested_leaf_last	29.4400μs	3.1573μs	316.7305 KOps/s	318.4955 KOps/s	$\color{#d91a1a}-0.55\%$
test_membership_stacked_nested_last	35.6000μs	6.8389μs	146.2222 KOps/s	318.6518 KOps/s	$\textbf{\color{#d91a1a}-54.11\%}$
test_membership_stacked_nested_leaf_last	44.0210μs	6.8006μs	147.0463 KOps/s	319.6473 KOps/s	$\textbf{\color{#d91a1a}-54.00\%}$
test_nested_getleaf	34.0900μs	6.1715μs	162.0346 KOps/s	161.4048 KOps/s	$\color{#35bf28}+0.39\%$
test_nested_get	41.3100μs	5.8324μs	171.4568 KOps/s	168.5970 KOps/s	$\color{#35bf28}+1.70\%$
test_stacked_getleaf	48.1910μs	6.1570μs	162.4172 KOps/s	161.8906 KOps/s	$\color{#35bf28}+0.33\%$
test_stacked_get	36.8500μs	5.8715μs	170.3156 KOps/s	170.6999 KOps/s	$\color{#d91a1a}-0.23\%$
test_nested_getitemleaf	29.9600μs	6.4369μs	155.3539 KOps/s	155.7804 KOps/s	$\color{#d91a1a}-0.27\%$
test_nested_getitem	30.6100μs	6.2271μs	160.5897 KOps/s	161.8402 KOps/s	$\color{#d91a1a}-0.77\%$
test_stacked_getitemleaf	43.3710μs	6.5886μs	151.7777 KOps/s	154.7392 KOps/s	$\color{#d91a1a}-1.91\%$
test_stacked_getitem	32.3210μs	6.1344μs	163.0141 KOps/s	161.9394 KOps/s	$\color{#35bf28}+0.66\%$
test_lock_nested	8.8174ms	0.3522ms	2.8391 KOps/s	2.8206 KOps/s	$\color{#35bf28}+0.66\%$
test_lock_stack_nested	0.4354ms	0.3419ms	2.9251 KOps/s	2.8604 KOps/s	$\color{#35bf28}+2.26\%$
test_unlock_nested	0.5386ms	0.2855ms	3.5022 KOps/s	3.5121 KOps/s	$\color{#d91a1a}-0.28\%$
test_unlock_stack_nested	0.3367ms	0.2777ms	3.6006 KOps/s	3.4531 KOps/s	$\color{#35bf28}+4.27\%$
test_flatten_speed	0.1129ms	77.0375μs	12.9807 KOps/s	12.9088 KOps/s	$\color{#35bf28}+0.56\%$
test_unflatten_speed	0.3654ms	0.3295ms	3.0346 KOps/s	3.0825 KOps/s	$\color{#d91a1a}-1.55\%$
test_common_ops	0.7555ms	0.5778ms	1.7307 KOps/s	1.4947 KOps/s	$\textbf{\color{#35bf28}+15.79\%}$
test_creation	0.1136ms	1.7559μs	569.4967 KOps/s	587.7570 KOps/s	$\color{#d91a1a}-3.11\%$
test_creation_empty	27.0800μs	6.5156μs	153.4771 KOps/s	99.3935 KOps/s	$\textbf{\color{#35bf28}+54.41\%}$
test_creation_nested_1	30.3200μs	8.2287μs	121.5257 KOps/s	84.7385 KOps/s	$\textbf{\color{#35bf28}+43.41\%}$
test_creation_nested_2	47.5310μs	10.8771μs	91.9361 KOps/s	68.4206 KOps/s	$\textbf{\color{#35bf28}+34.37\%}$
test_clone	58.1410μs	10.6370μs	94.0117 KOps/s	86.8943 KOps/s	$\textbf{\color{#35bf28}+8.19\%}$
test_getitem[int]	1.2873ms	10.5455μs	94.8274 KOps/s	91.9573 KOps/s	$\color{#35bf28}+3.12\%$
test_getitem[slice_int]	0.1087ms	20.8337μs	47.9993 KOps/s	48.2119 KOps/s	$\color{#d91a1a}-0.44\%$
test_getitem[range]	0.1382ms	37.0567μs	26.9857 KOps/s	26.3873 KOps/s	$\color{#35bf28}+2.27\%$
test_getitem[tuple]	0.1071ms	18.0585μs	55.3756 KOps/s	53.8125 KOps/s	$\color{#35bf28}+2.90\%$
test_getitem[list]	0.1322ms	33.5537μs	29.8029 KOps/s	29.5358 KOps/s	$\color{#35bf28}+0.90\%$
test_setitem_dim[int]	57.0110μs	19.0272μs	52.5564 KOps/s	48.9652 KOps/s	$\textbf{\color{#35bf28}+7.33\%}$
test_setitem_dim[slice_int]	78.4400μs	38.6099μs	25.9001 KOps/s	25.3157 KOps/s	$\color{#35bf28}+2.31\%$
test_setitem_dim[range]	90.9110μs	53.2763μs	18.7701 KOps/s	18.5588 KOps/s	$\color{#35bf28}+1.14\%$
test_setitem_dim[tuple]	52.4310μs	31.2135μs	32.0374 KOps/s	29.3524 KOps/s	$\textbf{\color{#35bf28}+9.15\%}$
test_setitem	64.9910μs	14.3878μs	69.5034 KOps/s	57.8397 KOps/s	$\textbf{\color{#35bf28}+20.17\%}$
test_set	62.4110μs	14.0654μs	71.0967 KOps/s	60.9970 KOps/s	$\textbf{\color{#35bf28}+16.56\%}$
test_set_shared	0.5214ms	0.1666ms	6.0022 KOps/s	6.2251 KOps/s	$\color{#d91a1a}-3.58\%$
test_update	0.4010ms	15.5710μs	64.2221 KOps/s	50.1540 KOps/s	$\textbf{\color{#35bf28}+28.05\%}$
test_update_nested	78.0400μs	22.2364μs	44.9713 KOps/s	38.1439 KOps/s	$\textbf{\color{#35bf28}+17.90\%}$
test_update__nested	0.5407ms	28.0970μs	35.5910 KOps/s	37.5250 KOps/s	$\textbf{\color{#d91a1a}-5.15\%}$
test_set_nested	68.9210μs	16.2731μs	61.4510 KOps/s	56.2941 KOps/s	$\textbf{\color{#35bf28}+9.16\%}$
test_set_nested_new	64.6810μs	19.6027μs	51.0133 KOps/s	48.5642 KOps/s	$\textbf{\color{#35bf28}+5.04\%}$
test_select	88.5800μs	30.9948μs	32.2634 KOps/s	30.5621 KOps/s	$\textbf{\color{#35bf28}+5.57\%}$
test_select_nested	78.2510μs	43.9568μs	22.7496 KOps/s	22.8212 KOps/s	$\color{#d91a1a}-0.31\%$
test_exclude_nested	0.1033ms	64.3280μs	15.5453 KOps/s	15.6822 KOps/s	$\color{#d91a1a}-0.87\%$
test_empty[True]	0.3486ms	0.3031ms	3.2996 KOps/s	3.3299 KOps/s	$\color{#d91a1a}-0.91\%$
test_empty[False]	3.3991μs	0.8413μs	1.1887 MOps/s	1.2000 MOps/s	$\color{#d91a1a}-0.95\%$
test_to	85.3510μs	57.6449μs	17.3476 KOps/s	15.5147 KOps/s	$\textbf{\color{#35bf28}+11.81\%}$
test_to_nonblocking	90.6410μs	47.6275μs	20.9963 KOps/s	19.3672 KOps/s	$\textbf{\color{#35bf28}+8.41\%}$
test_unbind_speed	0.2865ms	0.2368ms	4.2223 KOps/s	4.0010 KOps/s	$\textbf{\color{#35bf28}+5.53\%}$
test_unbind_speed_stack0	0.3519ms	0.2359ms	4.2383 KOps/s	4.0580 KOps/s	$\color{#35bf28}+4.44\%$
test_unbind_speed_stack1	92.8934ms	0.7284ms	1.3729 KOps/s	1.3422 KOps/s	$\color{#35bf28}+2.29\%$
test_split	1.5821ms	1.4622ms	683.8949 Ops/s	629.7114 Ops/s	$\textbf{\color{#35bf28}+8.60\%}$
test_chunk	95.4813ms	1.7303ms	577.9414 Ops/s	625.0394 Ops/s	$\textbf{\color{#d91a1a}-7.54\%}$
test_consolidate[False-None]	3.3636ms	2.6853ms	372.4013 Ops/s	368.4247 Ops/s	$\color{#35bf28}+1.08\%$
test_consolidate[default-None]	1.7522ms	1.6855ms	593.2818 Ops/s	603.3532 Ops/s	$\color{#d91a1a}-1.67\%$
test_consolidate[reduce-overhead-None]	1.7974ms	1.7232ms	580.3218 Ops/s	595.1270 Ops/s	$\color{#d91a1a}-2.49\%$
test_consolidate_njt[False-None]	6.9940ms	6.6503ms	150.3696 Ops/s	152.0889 Ops/s	$\color{#d91a1a}-1.13\%$
test_to[False-False-None]	1.8208ms	1.7272ms	578.9700 Ops/s	574.7510 Ops/s	$\color{#35bf28}+0.73\%$
test_to[True-False-None]	1.5663ms	1.3208ms	757.1003 Ops/s	747.6265 Ops/s	$\color{#35bf28}+1.27\%$
test_to[within-False-None]	4.2326ms	4.1136ms	243.0940 Ops/s	239.4193 Ops/s	$\color{#35bf28}+1.53\%$
test_to[True-default-None]	5.8267ms	5.4522ms	183.4131 Ops/s	177.4522 Ops/s	$\color{#35bf28}+3.36\%$
test_to_njt[False-False-None]	7.3249ms	7.0166ms	142.5182 Ops/s	140.4201 Ops/s	$\color{#35bf28}+1.49\%$
test_to_njt[True-False-None]	5.9812ms	5.5533ms	180.0734 Ops/s	175.1844 Ops/s	$\color{#35bf28}+2.79\%$
test_to_njt[within-False-None]	12.9237ms	12.2764ms	81.4572 Ops/s	80.5714 Ops/s	$\color{#35bf28}+1.10\%$
test_creation[device0]	0.4498ms	84.3632μs	11.8535 KOps/s	11.8487 KOps/s	$\color{#35bf28}+0.04\%$
test_creation_from_tensor	0.4598ms	85.4832μs	11.6982 KOps/s	11.8112 KOps/s	$\color{#d91a1a}-0.96\%$
test_add_one[memmap_tensor0]	0.4568ms	6.6389μs	150.6268 KOps/s	137.0051 KOps/s	$\textbf{\color{#35bf28}+9.94\%}$
test_contiguous[memmap_tensor0]	2.0145μs	0.4172μs	2.3971 MOps/s	2.3844 MOps/s	$\color{#35bf28}+0.53\%$
test_stack[memmap_tensor0]	41.5500μs	4.3876μs	227.9169 KOps/s	223.1432 KOps/s	$\color{#35bf28}+2.14\%$
test_memmaptd_index	1.6174ms	0.2410ms	4.1500 KOps/s	4.1503 KOps/s	$-0.01\%$
test_memmaptd_index_astensor	0.4349ms	0.3048ms	3.2809 KOps/s	3.2786 KOps/s	$\color{#35bf28}+0.07\%$
test_memmaptd_index_op	0.6567ms	0.5472ms	1.8275 KOps/s	1.6118 KOps/s	$\textbf{\color{#35bf28}+13.38\%}$
test_serialize_model	0.4538s	0.1763s	5.6708 Ops/s	7.7031 Ops/s	$\textbf{\color{#d91a1a}-26.38\%}$
test_serialize_model_pickle	1.3454s	1.1912s	0.8395 Ops/s	0.8252 Ops/s	$\color{#35bf28}+1.73\%$
test_serialize_weights	0.1313s	0.1298s	7.7021 Ops/s	7.7351 Ops/s	$\color{#d91a1a}-0.43\%$
test_serialize_weights_returnearly	0.3368s	55.1331ms	18.1379 Ops/s	22.8396 Ops/s	$\textbf{\color{#d91a1a}-20.59\%}$
test_serialize_weights_pickle	1.3741s	1.1947s	0.8370 Ops/s	0.8193 Ops/s	$\color{#35bf28}+2.17\%$
test_reshape_pytree	59.7110μs	22.1821μs	45.0813 KOps/s	44.3987 KOps/s	$\color{#35bf28}+1.54\%$
test_reshape_td	61.0600μs	27.3808μs	36.5220 KOps/s	35.4386 KOps/s	$\color{#35bf28}+3.06\%$
test_view_pytree	49.6800μs	22.5238μs	44.3974 KOps/s	44.6533 KOps/s	$\color{#d91a1a}-0.57\%$
test_view_td	71.9900μs	32.1827μs	31.0726 KOps/s	27.8505 KOps/s	$\textbf{\color{#35bf28}+11.57\%}$
test_unbind_pytree	56.6910μs	28.0294μs	35.6768 KOps/s	35.1528 KOps/s	$\color{#35bf28}+1.49\%$
test_unbind_td	0.7173ms	36.4772μs	27.4144 KOps/s	26.7809 KOps/s	$\color{#35bf28}+2.37\%$
test_split_pytree	67.7810μs	31.4416μs	31.8050 KOps/s	32.8956 KOps/s	$\color{#d91a1a}-3.32\%$
test_split_td	0.9177ms	38.5282μs	25.9550 KOps/s	25.0164 KOps/s	$\color{#35bf28}+3.75\%$
test_add_pytree	81.8410μs	34.7495μs	28.7774 KOps/s	26.8524 KOps/s	$\textbf{\color{#35bf28}+7.17\%}$
test_add_td	0.1824ms	47.4006μs	21.0968 KOps/s	18.3472 KOps/s	$\textbf{\color{#35bf28}+14.99\%}$
test_compile_add_one_nested[tensordict-compile]	0.1829ms	0.1282ms	7.8014 KOps/s	7.6857 KOps/s	$\color{#35bf28}+1.51\%$
test_compile_add_one_nested[tensordict-eager]	0.2519ms	0.1344ms	7.4413 KOps/s	7.3010 KOps/s	$\color{#35bf28}+1.92\%$
test_compile_add_one_nested[pytree-compile]	0.1351ms	97.3163μs	10.2758 KOps/s	10.1922 KOps/s	$\color{#35bf28}+0.82\%$
test_compile_add_one_nested[pytree-eager]	1.4343ms	0.1494ms	6.6928 KOps/s	6.4452 KOps/s	$\color{#35bf28}+3.84\%$
test_compile_copy_nested[tensordict-compile]	60.4100μs	25.1777μs	39.7177 KOps/s	40.7287 KOps/s	$\color{#d91a1a}-2.48\%$
test_compile_copy_nested[tensordict-eager]	72.3200μs	29.4899μs	33.9100 KOps/s	33.6491 KOps/s	$\color{#35bf28}+0.78\%$
test_compile_copy_nested[pytree-compile]	98.9510μs	65.1671μs	15.3452 KOps/s	15.7283 KOps/s	$\color{#d91a1a}-2.44\%$
test_compile_copy_nested[pytree-eager]	89.5800μs	49.4758μs	20.2119 KOps/s	20.2317 KOps/s	$\color{#d91a1a}-0.10\%$
test_compile_add_one_flat[tensordict-compile]	0.2021ms	0.1430ms	6.9953 KOps/s	7.0468 KOps/s	$\color{#d91a1a}-0.73\%$
test_compile_add_one_flat[tensordict-eager]	0.3167ms	0.2172ms	4.6041 KOps/s	4.5541 KOps/s	$\color{#35bf28}+1.10\%$
test_compile_add_one_flat[tensorclass-compile]	0.1467ms	97.4922μs	10.2572 KOps/s	9.9880 KOps/s	$\color{#35bf28}+2.70\%$
test_compile_add_one_flat[tensorclass-eager]	0.1146ms	55.3484μs	18.0674 KOps/s	16.8540 KOps/s	$\textbf{\color{#35bf28}+7.20\%}$
test_compile_add_one_flat[pytree-compile]	0.1901ms	0.1407ms	7.1093 KOps/s	7.3482 KOps/s	$\color{#d91a1a}-3.25\%$
test_compile_add_one_flat[pytree-eager]	0.5384ms	0.4776ms	2.0939 KOps/s	2.0001 KOps/s	$\color{#35bf28}+4.69\%$
test_compile_add_self_flat[tensordict-eager]	0.4157ms	0.2621ms	3.8153 KOps/s	3.7964 KOps/s	$\color{#35bf28}+0.50\%$
test_compile_add_self_flat[tensordict-compile]	0.2103ms	0.1445ms	6.9193 KOps/s	6.7947 KOps/s	$\color{#35bf28}+1.83\%$
test_compile_add_self_flat[tensorclass-eager]	0.1649ms	67.8231μs	14.7442 KOps/s	14.0381 KOps/s	$\textbf{\color{#35bf28}+5.03\%}$
test_compile_add_self_flat[tensorclass-compile]	0.1448ms	0.1003ms	9.9707 KOps/s	9.5957 KOps/s	$\color{#35bf28}+3.91\%$
test_compile_add_self_flat[pytree-eager]	0.4770ms	0.4062ms	2.4618 KOps/s	2.4421 KOps/s	$\color{#35bf28}+0.81\%$
test_compile_add_self_flat[pytree-compile]	0.1745ms	0.1367ms	7.3156 KOps/s	7.4194 KOps/s	$\color{#d91a1a}-1.40\%$
test_compile_copy_flat[tensordict-compile]	45.0600μs	19.5587μs	51.1282 KOps/s	52.8573 KOps/s	$\color{#d91a1a}-3.27\%$
test_compile_copy_flat[tensordict-eager]	67.4610μs	31.4959μs	31.7501 KOps/s	32.2290 KOps/s	$\color{#d91a1a}-1.49\%$
test_compile_copy_flat[pytree-compile]	0.1050ms	70.6913μs	14.1460 KOps/s	14.2827 KOps/s	$\color{#d91a1a}-0.96\%$
test_compile_copy_flat[pytree-eager]	0.1395ms	51.4032μs	19.4541 KOps/s	19.3362 KOps/s	$\color{#35bf28}+0.61\%$
test_compile_assign_and_add[tensordict-compile]	1.6272ms	0.3931ms	2.5438 KOps/s	2.2335 KOps/s	$\textbf{\color{#35bf28}+13.89\%}$
test_compile_assign_and_add[tensordict-eager]	2.9652ms	2.7324ms	365.9796 Ops/s	368.3649 Ops/s	$\color{#d91a1a}-0.65\%$
test_compile_assign_and_add[pytree-compile]	1.5697ms	0.4276ms	2.3386 KOps/s	2.1996 KOps/s	$\textbf{\color{#35bf28}+6.32\%}$
test_compile_assign_and_add[pytree-eager]	2.8119ms	2.6481ms	377.6232 Ops/s	369.6093 Ops/s	$\color{#35bf28}+2.17\%$
test_compile_indexing[tensor-tensordict-compile]	0.5941ms	0.1208ms	8.2755 KOps/s	8.2725 KOps/s	$\color{#35bf28}+0.04\%$
test_compile_indexing[tensor-tensordict-eager]	0.6424ms	85.4149μs	11.7076 KOps/s	11.6985 KOps/s	$\color{#35bf28}+0.08\%$
test_compile_indexing[tensor-tensorclass-compile]	0.4365ms	0.1127ms	8.8733 KOps/s	8.8510 KOps/s	$\color{#35bf28}+0.25\%$
test_compile_indexing[tensor-tensorclass-eager]	0.1052ms	68.7010μs	14.5558 KOps/s	13.4912 KOps/s	$\textbf{\color{#35bf28}+7.89\%}$
test_compile_indexing[tensor-pytree-compile]	0.1716ms	0.1078ms	9.2750 KOps/s	8.7332 KOps/s	$\textbf{\color{#35bf28}+6.20\%}$
test_compile_indexing[tensor-pytree-eager]	0.1207ms	71.7924μs	13.9291 KOps/s	13.5088 KOps/s	$\color{#35bf28}+3.11\%$
test_compile_indexing[slice-tensordict-compile]	0.1510ms	0.1040ms	9.6110 KOps/s	9.4226 KOps/s	$\color{#35bf28}+2.00\%$
test_compile_indexing[slice-tensordict-eager]	0.1550ms	18.9258μs	52.8378 KOps/s	52.2490 KOps/s	$\color{#35bf28}+1.13\%$
test_compile_indexing[slice-tensorclass-compile]	0.1556ms	96.8789μs	10.3222 KOps/s	10.4082 KOps/s	$\color{#d91a1a}-0.83\%$
test_compile_indexing[slice-tensorclass-eager]	68.2910μs	16.1161μs	62.0499 KOps/s	61.9189 KOps/s	$\color{#35bf28}+0.21\%$
test_compile_indexing[slice-pytree-compile]	0.1501ms	98.4032μs	10.1623 KOps/s	9.9141 KOps/s	$\color{#35bf28}+2.50\%$
test_compile_indexing[slice-pytree-eager]	61.0610μs	16.2478μs	61.5469 KOps/s	61.2745 KOps/s	$\color{#35bf28}+0.44\%$
test_compile_indexing[int-tensordict-compile]	0.1564ms	0.1062ms	9.4196 KOps/s	9.3314 KOps/s	$\color{#35bf28}+0.94\%$
test_compile_indexing[int-tensordict-eager]	0.5852ms	18.5631μs	53.8703 KOps/s	54.5752 KOps/s	$\color{#d91a1a}-1.29\%$
test_compile_indexing[int-tensorclass-compile]	0.1591ms	0.1013ms	9.8714 KOps/s	9.6548 KOps/s	$\color{#35bf28}+2.24\%$
test_compile_indexing[int-tensorclass-eager]	64.8310μs	15.9995μs	62.5020 KOps/s	61.5621 KOps/s	$\color{#35bf28}+1.53\%$
test_compile_indexing[int-pytree-compile]	0.1536ms	96.1248μs	10.4031 KOps/s	9.7468 KOps/s	$\textbf{\color{#35bf28}+6.73\%}$
test_compile_indexing[int-pytree-eager]	42.8710μs	16.0195μs	62.4239 KOps/s	61.4608 KOps/s	$\color{#35bf28}+1.57\%$
test_mod_add[eager]	0.1262ms	37.3214μs	26.7943 KOps/s	22.8649 KOps/s	$\textbf{\color{#35bf28}+17.18\%}$
test_mod_add[compile]	0.4106ms	81.3505μs	12.2925 KOps/s	11.7005 KOps/s	$\textbf{\color{#35bf28}+5.06\%}$
test_mod_add[compile-overhead]	0.3418ms	0.1714ms	5.8347 KOps/s	5.7598 KOps/s	$\color{#35bf28}+1.30\%$
test_mod_wrap[eager]	0.3287ms	0.2487ms	4.0204 KOps/s	3.8829 KOps/s	$\color{#35bf28}+3.54\%$
test_mod_wrap[compile]	0.6306ms	0.2957ms	3.3819 KOps/s	3.4748 KOps/s	$\color{#d91a1a}-2.67\%$
test_mod_wrap[compile-overhead]	6.9695ms	3.7183ms	268.9401 Ops/s	268.1232 Ops/s	$\color{#35bf28}+0.30\%$
test_mod_wrap_and_backward[eager]	1.5123ms	1.3613ms	734.5931 Ops/s	676.9530 Ops/s	$\textbf{\color{#35bf28}+8.51\%}$
test_mod_wrap_and_backward[compile]	1.5055ms	1.2778ms	782.5868 Ops/s	722.3606 Ops/s	$\textbf{\color{#35bf28}+8.34\%}$
test_mod_wrap_and_backward[compile-overhead]	1.4185ms	0.9337ms	1.0710 KOps/s	963.2584 Ops/s	$\textbf{\color{#35bf28}+11.18\%}$
test_seq_add[eager]	0.1814ms	0.1246ms	8.0239 KOps/s	8.2413 KOps/s	$\color{#d91a1a}-2.64\%$
test_seq_add[compile]	0.1447ms	94.5986μs	10.5710 KOps/s	11.4898 KOps/s	$\textbf{\color{#d91a1a}-8.00\%}$
test_seq_add[compile-overhead]	0.1822ms	0.1371ms	7.2932 KOps/s	7.7384 KOps/s	$\textbf{\color{#d91a1a}-5.75\%}$
test_seq_wrap[eager]	0.5584ms	0.4429ms	2.2576 KOps/s	2.3047 KOps/s	$\color{#d91a1a}-2.04\%$
test_seq_wrap[compile]	0.3719ms	0.3143ms	3.1818 KOps/s	3.3094 KOps/s	$\color{#d91a1a}-3.86\%$
test_seq_wrap[compile-overhead]	0.2791ms	0.2312ms	4.3257 KOps/s	4.4251 KOps/s	$\color{#d91a1a}-2.25\%$
test_func_call_runtime[False-eager]	1.0820ms	0.7784ms	1.2847 KOps/s	1.3350 KOps/s	$\color{#d91a1a}-3.77\%$
test_func_call_runtime[False-compile]	0.9246ms	0.7784ms	1.2847 KOps/s	1.3131 KOps/s	$\color{#d91a1a}-2.17\%$
test_func_call_runtime[False-compile-overhead]	0.4349ms	0.3632ms	2.7531 KOps/s	2.7397 KOps/s	$\color{#35bf28}+0.49\%$
test_func_call_runtime[True-eager]	0.9759ms	0.8953ms	1.1170 KOps/s	1.0872 KOps/s	$\color{#35bf28}+2.74\%$
test_func_call_runtime[True-compile]	0.8808ms	0.7937ms	1.2600 KOps/s	1.2475 KOps/s	$\color{#35bf28}+1.00\%$
test_func_call_runtime[True-compile-overhead]	0.5088ms	0.3959ms	2.5258 KOps/s	2.6035 KOps/s	$\color{#d91a1a}-2.98\%$
test_func_call_cm_runtime[False-eager]	1.1210ms	0.7564ms	1.3220 KOps/s	1.2544 KOps/s	$\textbf{\color{#35bf28}+5.39\%}$
test_func_call_cm_runtime[False-compile]	1.1348ms	0.7439ms	1.3442 KOps/s	1.3003 KOps/s	$\color{#35bf28}+3.37\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4604ms	0.3732ms	2.6794 KOps/s	2.7075 KOps/s	$\color{#d91a1a}-1.04\%$
test_func_call_cm_runtime[True-eager]	1.1748ms	1.0043ms	995.7074 Ops/s	973.5487 Ops/s	$\color{#35bf28}+2.28\%$
test_func_call_cm_runtime[True-compile]	1.4088ms	0.9878ms	1.0124 KOps/s	998.1195 Ops/s	$\color{#35bf28}+1.43\%$
test_func_call_cm_runtime[True-compile-overhead]	1.4087ms	0.9889ms	1.0112 KOps/s	982.0557 Ops/s	$\color{#35bf28}+2.97\%$
test_vmap_func_call_cm_runtime[eager]	2.6056ms	2.1084ms	474.3037 Ops/s	470.5406 Ops/s	$\color{#35bf28}+0.80\%$
test_vmap_func_call_cm_runtime[compile]	1.2080ms	0.8454ms	1.1829 KOps/s	1.1591 KOps/s	$\color{#35bf28}+2.05\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.8354ms	0.4257ms	2.3488 KOps/s	2.3694 KOps/s	$\color{#d91a1a}-0.87\%$
test_distributed	3.0709ms	0.2359ms	4.2390 KOps/s	8.3073 KOps/s	$\textbf{\color{#d91a1a}-48.97\%}$
test_tdmodule	0.1712ms	19.5604μs	51.1237 KOps/s	47.4626 KOps/s	$\textbf{\color{#35bf28}+7.71\%}$
test_tdmodule_dispatch	0.4325ms	34.8469μs	28.6969 KOps/s	26.4580 KOps/s	$\textbf{\color{#35bf28}+8.46\%}$
test_tdseq	37.9410μs	19.2452μs	51.9610 KOps/s	44.8289 KOps/s	$\textbf{\color{#35bf28}+15.91\%}$
test_tdseq_dispatch	58.7310μs	35.8927μs	27.8608 KOps/s	23.9665 KOps/s	$\textbf{\color{#35bf28}+16.25\%}$
test_instantiation_functorch	1.9466ms	1.5721ms	636.1002 Ops/s	627.6643 Ops/s	$\color{#35bf28}+1.34\%$
test_exec_functorch	0.1934ms	0.1422ms	7.0303 KOps/s	6.4288 KOps/s	$\textbf{\color{#35bf28}+9.36\%}$
test_exec_functional_call	0.5199ms	0.1359ms	7.3570 KOps/s	6.5733 KOps/s	$\textbf{\color{#35bf28}+11.92\%}$
test_exec_td_decorator	0.5900ms	0.1864ms	5.3638 KOps/s	4.9847 KOps/s	$\textbf{\color{#35bf28}+7.60\%}$
test_vmap_mlp_speed_decorator[True-True]	1.1099ms	0.7198ms	1.3894 KOps/s	1.3723 KOps/s	$\color{#35bf28}+1.25\%$
test_vmap_mlp_speed_decorator[True-False]	1.1148ms	0.6922ms	1.4447 KOps/s	1.4009 KOps/s	$\color{#35bf28}+3.13\%$
test_vmap_mlp_speed_decorator[False-True]	1.0444ms	0.6360ms	1.5722 KOps/s	1.6478 KOps/s	$\color{#d91a1a}-4.59\%$
test_vmap_mlp_speed_decorator[False-False]	0.7399ms	0.6292ms	1.5892 KOps/s	1.6237 KOps/s	$\color{#d91a1a}-2.13\%$
test_vmap_transformer_speed_decorator[True-True]	19.3854ms	19.2637ms	51.9111 Ops/s	51.6513 Ops/s	$\color{#35bf28}+0.50\%$
test_vmap_transformer_speed_decorator[True-False]	19.3586ms	19.2600ms	51.9211 Ops/s	51.5917 Ops/s	$\color{#35bf28}+0.64\%$
test_vmap_transformer_speed_decorator[False-True]	19.2244ms	19.1130ms	52.3205 Ops/s	51.5296 Ops/s	$\color{#35bf28}+1.53\%$
test_vmap_transformer_speed_decorator[False-False]	19.3283ms	19.1245ms	52.2888 Ops/s	51.5509 Ops/s	$\color{#35bf28}+1.43\%$
test_to_module_speed[True]	1.4207ms	0.9725ms	1.0283 KOps/s	1.0380 KOps/s	$\color{#d91a1a}-0.94\%$
test_to_module_speed[False]	1.1433ms	0.9474ms	1.0556 KOps/s	1.0472 KOps/s	$\color{#35bf28}+0.80\%$
test_tc_init	87.7810μs	35.9337μs	27.8290 KOps/s	25.1544 KOps/s	$\textbf{\color{#35bf28}+10.63\%}$
test_tc_init_nested	0.1076ms	73.0131μs	13.6962 KOps/s	12.5288 KOps/s	$\textbf{\color{#35bf28}+9.32\%}$
test_tc_first_layer_tensor	5.2743μs	0.7005μs	1.4275 MOps/s	1.1888 MOps/s	$\textbf{\color{#35bf28}+20.08\%}$
test_tc_first_layer_nontensor	29.1010μs	2.2605μs	442.3709 KOps/s	440.3719 KOps/s	$\color{#35bf28}+0.45\%$
test_tc_second_layer_tensor	7.9250μs	1.4187μs	704.8944 KOps/s	701.4689 KOps/s	$\color{#35bf28}+0.49\%$
test_tc_second_layer_nontensor	23.0400μs	3.0400μs	328.9454 KOps/s	334.6317 KOps/s	$\color{#d91a1a}-1.70\%$
test_unbind	0.2195s	12.2590ms	81.5725 Ops/s	144.2281 Ops/s	$\textbf{\color{#d91a1a}-43.44\%}$
test_full_like	9.7426ms	9.1609ms	109.1592 Ops/s	107.5303 Ops/s	$\color{#35bf28}+1.51\%$
test_zeros_like	4.8653ms	4.3186ms	231.5580 Ops/s	114.9075 Ops/s	$\textbf{\color{#35bf28}+101.52\%}$
test_ones_like	5.4531ms	4.3359ms	230.6328 Ops/s	230.8668 Ops/s	$\color{#d91a1a}-0.10\%$
test_clone	7.0312ms	6.3979ms	156.3001 Ops/s	155.7481 Ops/s	$\color{#35bf28}+0.35\%$
test_squeeze	61.8410μs	10.2518μs	97.5435 KOps/s	103.1150 KOps/s	$\textbf{\color{#d91a1a}-5.40\%}$
test_unsqueeze	0.1257ms	74.1656μs	13.4833 KOps/s	13.6365 KOps/s	$\color{#d91a1a}-1.12\%$
test_split	0.3788ms	0.1697ms	5.8932 KOps/s	6.2177 KOps/s	$\textbf{\color{#d91a1a}-5.22\%}$
test_permute	0.2895ms	0.1873ms	5.3384 KOps/s	5.5541 KOps/s	$\color{#d91a1a}-3.88\%$
test_stack	53.4303ms	51.9466ms	19.2505 Ops/s	19.8721 Ops/s	$\color{#d91a1a}-3.13\%$
test_cat	50.8474ms	50.3313ms	19.8684 Ops/s	19.8797 Ops/s	$\color{#d91a1a}-0.06\%$