[CI] Add missing packages for smoke test

[vmoens]

Stack from ghstack (oldest at bottom):

• -> [CI] Add missing packages for smoke test #1149

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}15$. Worsened: $\large\color{#d91a1a}17$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	45.6350μs	21.6109μs	46.2730 KOps/s	48.9761 KOps/s	$\textbf{\color{#d91a1a}-5.52\%}$
test_plain_set_stack_nested	42.7790μs	21.6538μs	46.1814 KOps/s	48.1862 KOps/s	$\color{#d91a1a}-4.16\%$
test_plain_set_nested_inplace	70.9120μs	23.4825μs	42.5849 KOps/s	44.7100 KOps/s	$\color{#d91a1a}-4.75\%$
test_plain_set_stack_nested_inplace	77.1840μs	23.5367μs	42.4868 KOps/s	44.6061 KOps/s	$\color{#d91a1a}-4.75\%$
test_items	86.2800μs	4.2006μs	238.0633 KOps/s	240.5506 KOps/s	$\color{#d91a1a}-1.03\%$
test_items_nested	0.7311ms	0.4007ms	2.4959 KOps/s	2.4516 KOps/s	$\color{#35bf28}+1.80\%$
test_items_nested_locked	0.4620ms	0.4019ms	2.4884 KOps/s	2.4578 KOps/s	$\color{#35bf28}+1.24\%$
test_items_nested_leaf	0.1451ms	77.0818μs	12.9732 KOps/s	13.0279 KOps/s	$\color{#d91a1a}-0.42\%$
test_items_stack_nested	0.7365ms	0.4028ms	2.4824 KOps/s	2.4568 KOps/s	$\color{#35bf28}+1.04\%$
test_items_stack_nested_leaf	0.1587ms	76.9808μs	12.9903 KOps/s	12.9379 KOps/s	$\color{#35bf28}+0.40\%$
test_items_stack_nested_locked	0.4833ms	0.4045ms	2.4722 KOps/s	2.4585 KOps/s	$\color{#35bf28}+0.56\%$
test_keys	31.9090μs	3.4966μs	285.9922 KOps/s	284.6050 KOps/s	$\color{#35bf28}+0.49\%$
test_keys_nested	0.3247ms	0.1673ms	5.9755 KOps/s	5.9601 KOps/s	$\color{#35bf28}+0.26\%$
test_keys_nested_locked	1.7162ms	0.1733ms	5.7714 KOps/s	5.7320 KOps/s	$\color{#35bf28}+0.69\%$
test_keys_nested_leaf	0.2583ms	0.1488ms	6.7199 KOps/s	6.8447 KOps/s	$\color{#d91a1a}-1.82\%$
test_keys_stack_nested	0.3178ms	0.1676ms	5.9664 KOps/s	5.9443 KOps/s	$\color{#35bf28}+0.37\%$
test_keys_stack_nested_leaf	0.3120ms	0.1464ms	6.8307 KOps/s	6.8382 KOps/s	$\color{#d91a1a}-0.11\%$
test_keys_stack_nested_locked	0.3126ms	0.1727ms	5.7919 KOps/s	5.8090 KOps/s	$\color{#d91a1a}-0.29\%$
test_values	6.6484μs	1.0711μs	933.5955 KOps/s	973.7252 KOps/s	$\color{#d91a1a}-4.12\%$
test_values_nested	0.1237ms	63.2841μs	15.8018 KOps/s	16.1512 KOps/s	$\color{#d91a1a}-2.16\%$
test_values_nested_locked	0.1125ms	62.6682μs	15.9571 KOps/s	15.9546 KOps/s	$\color{#35bf28}+0.02\%$
test_values_nested_leaf	0.1640ms	72.2646μs	13.8380 KOps/s	13.5603 KOps/s	$\color{#35bf28}+2.05\%$
test_values_stack_nested	0.1128ms	63.1301μs	15.8403 KOps/s	16.2539 KOps/s	$\color{#d91a1a}-2.54\%$
test_values_stack_nested_leaf	0.1319ms	71.8173μs	13.9242 KOps/s	13.9660 KOps/s	$\color{#d91a1a}-0.30\%$
test_values_stack_nested_locked	0.1269ms	62.4604μs	16.0101 KOps/s	16.0532 KOps/s	$\color{#d91a1a}-0.27\%$
test_membership	20.4680μs	0.8893μs	1.1245 MOps/s	1.1052 MOps/s	$\color{#35bf28}+1.75\%$
test_membership_nested	42.8100μs	2.9030μs	344.4745 KOps/s	346.7499 KOps/s	$\color{#d91a1a}-0.66\%$
test_membership_nested_leaf	21.3300μs	2.8440μs	351.6116 KOps/s	340.7638 KOps/s	$\color{#35bf28}+3.18\%$
test_membership_stacked_nested	39.3830μs	2.8955μs	345.3632 KOps/s	345.4190 KOps/s	$\color{#d91a1a}-0.02\%$
test_membership_stacked_nested_leaf	18.9560μs	2.8796μs	347.2716 KOps/s	342.3222 KOps/s	$\color{#35bf28}+1.45\%$
test_membership_nested_last	43.5810μs	4.3669μs	228.9967 KOps/s	231.6805 KOps/s	$\color{#d91a1a}-1.16\%$
test_membership_nested_leaf_last	50.6140μs	4.3367μs	230.5874 KOps/s	231.2988 KOps/s	$\color{#d91a1a}-0.31\%$
test_membership_stacked_nested_last	24.5260μs	4.3323μs	230.8245 KOps/s	232.6235 KOps/s	$\color{#d91a1a}-0.77\%$
test_membership_stacked_nested_leaf_last	25.1060μs	4.2917μs	233.0056 KOps/s	232.6206 KOps/s	$\color{#35bf28}+0.17\%$
test_nested_getleaf	45.6650μs	10.9526μs	91.3023 KOps/s	92.6439 KOps/s	$\color{#d91a1a}-1.45\%$
test_nested_get	37.0590μs	10.5077μs	95.1684 KOps/s	98.9350 KOps/s	$\color{#d91a1a}-3.81\%$
test_stacked_getleaf	42.3990μs	10.7823μs	92.7443 KOps/s	93.4391 KOps/s	$\color{#d91a1a}-0.74\%$
test_stacked_get	43.5410μs	10.3208μs	96.8916 KOps/s	97.9811 KOps/s	$\color{#d91a1a}-1.11\%$
test_nested_getitemleaf	39.7040μs	11.3487μs	88.1156 KOps/s	90.4723 KOps/s	$\color{#d91a1a}-2.60\%$
test_nested_getitem	35.6660μs	10.5135μs	95.1160 KOps/s	96.5561 KOps/s	$\color{#d91a1a}-1.49\%$
test_stacked_getitemleaf	50.9150μs	11.1258μs	89.8813 KOps/s	89.5639 KOps/s	$\color{#35bf28}+0.35\%$
test_stacked_getitem	78.0550μs	10.3962μs	96.1891 KOps/s	95.1167 KOps/s	$\color{#35bf28}+1.13\%$
test_lock_nested	4.6162ms	0.4693ms	2.1307 KOps/s	2.1836 KOps/s	$\color{#d91a1a}-2.42\%$
test_lock_stack_nested	0.7217ms	0.4341ms	2.3037 KOps/s	2.3652 KOps/s	$\color{#d91a1a}-2.60\%$
test_unlock_nested	0.8568ms	0.3794ms	2.6358 KOps/s	2.6836 KOps/s	$\color{#d91a1a}-1.78\%$
test_unlock_stack_nested	0.5296ms	0.3506ms	2.8525 KOps/s	2.8930 KOps/s	$\color{#d91a1a}-1.40\%$
test_flatten_speed	0.2432ms	99.8697μs	10.0130 KOps/s	10.0770 KOps/s	$\color{#d91a1a}-0.64\%$
test_unflatten_speed	0.7056ms	0.5295ms	1.8887 KOps/s	1.9173 KOps/s	$\color{#d91a1a}-1.49\%$
test_common_ops	1.6823ms	0.7971ms	1.2545 KOps/s	1.3180 KOps/s	$\color{#d91a1a}-4.82\%$
test_creation	65.6310μs	2.5492μs	392.2752 KOps/s	406.1558 KOps/s	$\color{#d91a1a}-3.42\%$
test_creation_empty	40.2250μs	12.5856μs	79.4559 KOps/s	96.3061 KOps/s	$\textbf{\color{#d91a1a}-17.50\%}$
test_creation_nested_1	38.7120μs	15.5867μs	64.1571 KOps/s	77.2668 KOps/s	$\textbf{\color{#d91a1a}-16.97\%}$
test_creation_nested_2	56.6260μs	19.8489μs	50.3807 KOps/s	56.6271 KOps/s	$\textbf{\color{#d91a1a}-11.03\%}$
test_clone	75.9510μs	13.3129μs	75.1153 KOps/s	72.3093 KOps/s	$\color{#35bf28}+3.88\%$
test_getitem[int]	0.8641ms	12.7435μs	78.4714 KOps/s	75.7028 KOps/s	$\color{#35bf28}+3.66\%$
test_getitem[slice_int]	0.1370ms	24.5665μs	40.7058 KOps/s	39.5097 KOps/s	$\color{#35bf28}+3.03\%$
test_getitem[range]	0.2042ms	48.9003μs	20.4498 KOps/s	20.5665 KOps/s	$\color{#d91a1a}-0.57\%$
test_getitem[tuple]	0.1340ms	20.2939μs	49.2759 KOps/s	48.2998 KOps/s	$\color{#35bf28}+2.02\%$
test_getitem[list]	0.1861ms	44.0141μs	22.7200 KOps/s	22.9544 KOps/s	$\color{#d91a1a}-1.02\%$
test_setitem_dim[int]	62.7660μs	25.3770μs	39.4058 KOps/s	40.7493 KOps/s	$\color{#d91a1a}-3.30\%$
test_setitem_dim[slice_int]	0.1076ms	50.5858μs	19.7684 KOps/s	19.3673 KOps/s	$\color{#35bf28}+2.07\%$
test_setitem_dim[range]	0.1212ms	72.2706μs	13.8369 KOps/s	13.7576 KOps/s	$\color{#35bf28}+0.58\%$
test_setitem_dim[tuple]	94.6760μs	41.6151μs	24.0297 KOps/s	24.9953 KOps/s	$\color{#d91a1a}-3.86\%$
test_setitem	81.8220μs	20.9483μs	47.7365 KOps/s	50.7980 KOps/s	$\textbf{\color{#d91a1a}-6.03\%}$
test_set	0.1166ms	20.3427μs	49.1577 KOps/s	51.4241 KOps/s	$\color{#d91a1a}-4.41\%$
test_set_shared	5.1673ms	0.1723ms	5.8022 KOps/s	5.8879 KOps/s	$\color{#d91a1a}-1.45\%$
test_update	0.1303ms	23.5806μs	42.4078 KOps/s	47.0188 KOps/s	$\textbf{\color{#d91a1a}-9.81\%}$
test_update_nested	0.2249ms	34.5824μs	28.9165 KOps/s	30.5745 KOps/s	$\textbf{\color{#d91a1a}-5.42\%}$
test_update__nested	0.4827ms	33.7950μs	29.5902 KOps/s	28.9186 KOps/s	$\color{#35bf28}+2.32\%$
test_set_nested	0.1156ms	22.4285μs	44.5862 KOps/s	46.3947 KOps/s	$\color{#d91a1a}-3.90\%$
test_set_nested_new	0.1713ms	27.5347μs	36.3178 KOps/s	38.0894 KOps/s	$\color{#d91a1a}-4.65\%$
test_select	0.2208ms	44.4288μs	22.5079 KOps/s	23.4088 KOps/s	$\color{#d91a1a}-3.85\%$
test_select_nested	0.1237ms	62.7027μs	15.9483 KOps/s	15.8824 KOps/s	$\color{#35bf28}+0.41\%$
test_exclude_nested	0.1574ms	81.9007μs	12.2099 KOps/s	12.0784 KOps/s	$\color{#35bf28}+1.09\%$
test_empty[True]	0.7297ms	0.4134ms	2.4188 KOps/s	2.4021 KOps/s	$\color{#35bf28}+0.70\%$
test_empty[False]	12.0023μs	1.4060μs	711.2598 KOps/s	709.1523 KOps/s	$\color{#35bf28}+0.30\%$
test_unbind_speed	0.6644ms	0.2849ms	3.5102 KOps/s	3.7161 KOps/s	$\textbf{\color{#d91a1a}-5.54\%}$
test_unbind_speed_stack0	0.6728ms	0.2728ms	3.6657 KOps/s	3.7468 KOps/s	$\color{#d91a1a}-2.16\%$
test_unbind_speed_stack1	0.1071s	0.8055ms	1.2414 KOps/s	1.3692 KOps/s	$\textbf{\color{#d91a1a}-9.33\%}$
test_split	1.8817ms	1.5926ms	627.8935 Ops/s	555.5820 Ops/s	$\textbf{\color{#35bf28}+13.02\%}$
test_chunk	0.1048s	1.9304ms	518.0178 Ops/s	566.9586 Ops/s	$\textbf{\color{#d91a1a}-8.63\%}$
test_consolidate_njt[False-None]	9.8369ms	8.1623ms	122.5151 Ops/s	120.9927 Ops/s	$\color{#35bf28}+1.26\%$
test_creation[device0]	3.7014ms	91.3595μs	10.9458 KOps/s	11.0237 KOps/s	$\color{#d91a1a}-0.71\%$
test_creation_from_tensor	0.3638ms	93.1368μs	10.7369 KOps/s	10.5050 KOps/s	$\color{#35bf28}+2.21\%$
test_add_one[memmap_tensor0]	0.3202ms	4.7011μs	212.7141 KOps/s	210.0717 KOps/s	$\color{#35bf28}+1.26\%$
test_contiguous[memmap_tensor0]	12.3230μs	0.5209μs	1.9196 MOps/s	1.9601 MOps/s	$\color{#d91a1a}-2.06\%$
test_stack[memmap_tensor0]	45.5950μs	3.3358μs	299.7761 KOps/s	307.4237 KOps/s	$\color{#d91a1a}-2.49\%$
test_memmaptd_index	1.1329ms	0.2351ms	4.2532 KOps/s	4.2655 KOps/s	$\color{#d91a1a}-0.29\%$
test_memmaptd_index_astensor	0.5808ms	0.3219ms	3.1070 KOps/s	3.0889 KOps/s	$\color{#35bf28}+0.59\%$
test_memmaptd_index_op	1.1968ms	0.5938ms	1.6842 KOps/s	1.7863 KOps/s	$\textbf{\color{#d91a1a}-5.72\%}$
test_serialize_model	0.1296s	0.1183s	8.4539 Ops/s	7.5102 Ops/s	$\textbf{\color{#35bf28}+12.57\%}$
test_serialize_model_pickle	0.4348s	0.3900s	2.5643 Ops/s	2.5680 Ops/s	$\color{#d91a1a}-0.15\%$
test_serialize_weights	0.2264s	0.1330s	7.5171 Ops/s	8.6421 Ops/s	$\textbf{\color{#d91a1a}-13.02\%}$
test_serialize_weights_returnearly	0.1851s	0.1616s	6.1873 Ops/s	6.3976 Ops/s	$\color{#d91a1a}-3.29\%$
test_serialize_weights_pickle	1.3042s	0.7009s	1.4268 Ops/s	2.4822 Ops/s	$\textbf{\color{#d91a1a}-42.52\%}$
test_serialize_weights_filesystem	0.1592s	0.1448s	6.9078 Ops/s	7.0742 Ops/s	$\color{#d91a1a}-2.35\%$
test_serialize_model_filesystem	0.2483s	0.1583s	6.3169 Ops/s	6.6150 Ops/s	$\color{#d91a1a}-4.51\%$
test_reshape_pytree	68.2370μs	26.5037μs	37.7306 KOps/s	37.6453 KOps/s	$\color{#35bf28}+0.23\%$
test_reshape_td	0.1062ms	32.2536μs	31.0043 KOps/s	30.0575 KOps/s	$\color{#35bf28}+3.15\%$
test_view_pytree	68.9380μs	26.5495μs	37.6654 KOps/s	37.2625 KOps/s	$\color{#35bf28}+1.08\%$
test_view_td	0.1025ms	38.1779μs	26.1932 KOps/s	25.8867 KOps/s	$\color{#35bf28}+1.18\%$
test_unbind_pytree	95.9580μs	29.5788μs	33.8080 KOps/s	33.2764 KOps/s	$\color{#35bf28}+1.60\%$
test_unbind_td	0.3691ms	39.6698μs	25.2081 KOps/s	24.8324 KOps/s	$\color{#35bf28}+1.51\%$
test_split_pytree	74.5280μs	29.2240μs	34.2185 KOps/s	33.9435 KOps/s	$\color{#35bf28}+0.81\%$
test_split_td	0.5429ms	45.1877μs	22.1299 KOps/s	22.1939 KOps/s	$\color{#d91a1a}-0.29\%$
test_add_pytree	93.6330μs	35.3471μs	28.2908 KOps/s	27.8121 KOps/s	$\color{#35bf28}+1.72\%$
test_add_td	0.1142ms	55.2444μs	18.1014 KOps/s	18.1744 KOps/s	$\color{#d91a1a}-0.40\%$
test_compile_add_one_nested[tensordict-compile]	0.1604ms	61.7117μs	16.2044 KOps/s	15.9850 KOps/s	$\color{#35bf28}+1.37\%$
test_compile_add_one_nested[tensordict-eager]	1.4847ms	0.1684ms	5.9385 KOps/s	5.9572 KOps/s	$\color{#d91a1a}-0.31\%$
test_compile_add_one_nested[pytree-compile]	0.1363ms	45.2655μs	22.0919 KOps/s	22.1305 KOps/s	$\color{#d91a1a}-0.17\%$
test_compile_add_one_nested[pytree-eager]	0.1987ms	0.1183ms	8.4566 KOps/s	8.5325 KOps/s	$\color{#d91a1a}-0.89\%$
test_compile_copy_nested[tensordict-compile]	0.1205ms	26.4622μs	37.7898 KOps/s	38.1872 KOps/s	$\color{#d91a1a}-1.04\%$
test_compile_copy_nested[tensordict-eager]	0.1133ms	59.2429μs	16.8797 KOps/s	16.9405 KOps/s	$\color{#d91a1a}-0.36\%$
test_compile_copy_nested[pytree-compile]	0.1935ms	79.2478μs	12.6187 KOps/s	12.4835 KOps/s	$\color{#35bf28}+1.08\%$
test_compile_copy_nested[pytree-eager]	0.1204ms	67.7370μs	14.7630 KOps/s	14.5645 KOps/s	$\color{#35bf28}+1.36\%$
test_compile_add_one_flat[tensordict-compile]	0.1903ms	0.1033ms	9.6789 KOps/s	9.4644 KOps/s	$\color{#35bf28}+2.27\%$
test_compile_add_one_flat[tensordict-eager]	0.4227ms	0.2130ms	4.6949 KOps/s	4.5940 KOps/s	$\color{#35bf28}+2.20\%$
test_compile_add_one_flat[tensorclass-compile]	0.1423ms	44.3599μs	22.5429 KOps/s	22.3275 KOps/s	$\color{#35bf28}+0.96\%$
test_compile_add_one_flat[tensorclass-eager]	0.5133ms	62.4709μs	16.0074 KOps/s	15.7374 KOps/s	$\color{#35bf28}+1.72\%$
test_compile_add_one_flat[pytree-compile]	0.2471ms	0.1036ms	9.6485 KOps/s	9.6965 KOps/s	$\color{#d91a1a}-0.50\%$
test_compile_add_one_flat[pytree-eager]	0.3322ms	0.1997ms	5.0084 KOps/s	4.9337 KOps/s	$\color{#35bf28}+1.51\%$
test_compile_add_self_flat[tensordict-eager]	0.5606ms	0.2369ms	4.2219 KOps/s	4.2879 KOps/s	$\color{#d91a1a}-1.54\%$
test_compile_add_self_flat[tensordict-compile]	0.2284ms	0.1058ms	9.4490 KOps/s	9.5311 KOps/s	$\color{#d91a1a}-0.86\%$
test_compile_add_self_flat[tensorclass-eager]	0.2534ms	60.1874μs	16.6148 KOps/s	17.2768 KOps/s	$\color{#d91a1a}-3.83\%$
test_compile_add_self_flat[tensorclass-compile]	0.1294ms	46.4521μs	21.5276 KOps/s	21.8524 KOps/s	$\color{#d91a1a}-1.49\%$
test_compile_add_self_flat[pytree-eager]	0.6369ms	0.1561ms	6.4046 KOps/s	6.2229 KOps/s	$\color{#35bf28}+2.92\%$
test_compile_add_self_flat[pytree-compile]	0.3366ms	0.1016ms	9.8427 KOps/s	9.4540 KOps/s	$\color{#35bf28}+4.11\%$
test_compile_copy_flat[tensordict-compile]	61.4140μs	21.2525μs	47.0532 KOps/s	45.5449 KOps/s	$\color{#35bf28}+3.31\%$
test_compile_copy_flat[tensordict-eager]	0.1081ms	67.2289μs	14.8746 KOps/s	14.8768 KOps/s	$\color{#d91a1a}-0.02\%$
test_compile_copy_flat[pytree-compile]	0.1438ms	81.9602μs	12.2010 KOps/s	12.1610 KOps/s	$\color{#35bf28}+0.33\%$
test_compile_copy_flat[pytree-eager]	0.1551ms	68.4358μs	14.6122 KOps/s	14.3427 KOps/s	$\color{#35bf28}+1.88\%$
test_compile_assign_and_add[tensordict-compile]	0.4554ms	0.2053ms	4.8716 KOps/s	4.7869 KOps/s	$\color{#35bf28}+1.77\%$
test_compile_assign_and_add[tensordict-eager]	1.5201ms	1.3035ms	767.1524 Ops/s	768.8583 Ops/s	$\color{#d91a1a}-0.22\%$
test_compile_assign_and_add[pytree-compile]	0.2663ms	0.1978ms	5.0563 KOps/s	4.8709 KOps/s	$\color{#35bf28}+3.81\%$
test_compile_assign_and_add[pytree-eager]	0.9206ms	0.7678ms	1.3025 KOps/s	1.2865 KOps/s	$\color{#35bf28}+1.24\%$
test_compile_assign_and_add_stack[compile]	0.7830ms	0.4505ms	2.2196 KOps/s	2.1638 KOps/s	$\color{#35bf28}+2.58\%$
test_compile_assign_and_add_stack[eager]	2.9074ms	2.6620ms	375.6638 Ops/s	384.0023 Ops/s	$\color{#d91a1a}-2.17\%$
test_compile_indexing[tensor-tensordict-compile]	0.1520ms	36.6884μs	27.2566 KOps/s	26.8514 KOps/s	$\color{#35bf28}+1.51\%$
test_compile_indexing[tensor-tensordict-eager]	0.4629ms	31.6910μs	31.5547 KOps/s	29.3300 KOps/s	$\textbf{\color{#35bf28}+7.59\%}$
test_compile_indexing[tensor-tensorclass-compile]	74.6880μs	28.9771μs	34.5100 KOps/s	33.7043 KOps/s	$\color{#35bf28}+2.39\%$
test_compile_indexing[tensor-tensorclass-eager]	71.9640μs	22.7010μs	44.0508 KOps/s	42.2615 KOps/s	$\color{#35bf28}+4.23\%$
test_compile_indexing[tensor-pytree-compile]	84.2560μs	29.8975μs	33.4476 KOps/s	32.9538 KOps/s	$\color{#35bf28}+1.50\%$
test_compile_indexing[tensor-pytree-eager]	78.9060μs	22.5218μs	44.4014 KOps/s	42.4553 KOps/s	$\color{#35bf28}+4.58\%$
test_compile_indexing[slice-tensordict-compile]	0.1150ms	52.5049μs	19.0458 KOps/s	18.9685 KOps/s	$\color{#35bf28}+0.41\%$
test_compile_indexing[slice-tensordict-eager]	0.5590ms	19.2855μs	51.8525 KOps/s	46.9524 KOps/s	$\textbf{\color{#35bf28}+10.44\%}$
test_compile_indexing[slice-tensorclass-compile]	0.1375ms	44.4964μs	22.4737 KOps/s	21.8293 KOps/s	$\color{#35bf28}+2.95\%$
test_compile_indexing[slice-tensorclass-eager]	53.8400μs	18.4103μs	54.3174 KOps/s	51.0352 KOps/s	$\textbf{\color{#35bf28}+6.43\%}$
test_compile_indexing[slice-pytree-compile]	0.1104ms	45.0474μs	22.1988 KOps/s	21.4116 KOps/s	$\color{#35bf28}+3.68\%$
test_compile_indexing[slice-pytree-eager]	59.4700μs	18.3862μs	54.3885 KOps/s	49.9455 KOps/s	$\textbf{\color{#35bf28}+8.90\%}$
test_compile_indexing[int-tensordict-compile]	0.1146ms	53.5828μs	18.6627 KOps/s	18.2878 KOps/s	$\color{#35bf28}+2.05\%$
test_compile_indexing[int-tensordict-eager]	1.2031ms	19.2210μs	52.0263 KOps/s	47.0340 KOps/s	$\textbf{\color{#35bf28}+10.61\%}$
test_compile_indexing[int-tensorclass-compile]	0.1342ms	45.4380μs	22.0080 KOps/s	21.4791 KOps/s	$\color{#35bf28}+2.46\%$
test_compile_indexing[int-tensorclass-eager]	81.6220μs	18.2324μs	54.8473 KOps/s	52.1943 KOps/s	$\textbf{\color{#35bf28}+5.08\%}$
test_compile_indexing[int-pytree-compile]	0.1083ms	44.5983μs	22.4224 KOps/s	21.4175 KOps/s	$\color{#35bf28}+4.69\%$
test_compile_indexing[int-pytree-eager]	57.0370μs	18.2127μs	54.9069 KOps/s	52.3566 KOps/s	$\color{#35bf28}+4.87\%$
test_mod_add[eager]	0.1113ms	35.4028μs	28.2463 KOps/s	29.2126 KOps/s	$\color{#d91a1a}-3.31\%$
test_mod_add[compile]	0.1333ms	48.1805μs	20.7553 KOps/s	19.8407 KOps/s	$\color{#35bf28}+4.61\%$
test_mod_add[compile-overhead]	91.9310μs	47.4172μs	21.0894 KOps/s	19.8871 KOps/s	$\textbf{\color{#35bf28}+6.05\%}$
test_mod_wrap[eager]	0.3346ms	0.2282ms	4.3823 KOps/s	4.4076 KOps/s	$\color{#d91a1a}-0.57\%$
test_mod_wrap[compile]	0.3084ms	0.2070ms	4.8301 KOps/s	4.6493 KOps/s	$\color{#35bf28}+3.89\%$
test_mod_wrap[compile-overhead]	0.3133ms	0.2057ms	4.8624 KOps/s	4.7204 KOps/s	$\color{#35bf28}+3.01\%$
test_mod_wrap_and_backward[eager]	19.6830ms	12.6572ms	79.0063 Ops/s	89.7759 Ops/s	$\textbf{\color{#d91a1a}-12.00\%}$
test_mod_wrap_and_backward[compile]	19.0979ms	13.1782ms	75.8827 Ops/s	78.6843 Ops/s	$\color{#d91a1a}-3.56\%$
test_mod_wrap_and_backward[compile-overhead]	15.7388ms	12.7809ms	78.2421 Ops/s	83.8044 Ops/s	$\textbf{\color{#d91a1a}-6.64\%}$
test_seq_add[eager]	0.2588ms	0.1128ms	8.8643 KOps/s	8.4693 KOps/s	$\color{#35bf28}+4.66\%$
test_seq_add[compile]	0.1318ms	61.6454μs	16.2218 KOps/s	15.7618 KOps/s	$\color{#35bf28}+2.92\%$
test_seq_add[compile-overhead]	0.1649ms	60.3384μs	16.5732 KOps/s	16.3372 KOps/s	$\color{#35bf28}+1.44\%$
test_seq_wrap[eager]	0.7348ms	0.4546ms	2.2000 KOps/s	2.2568 KOps/s	$\color{#d91a1a}-2.52\%$
test_seq_wrap[compile]	0.4165ms	0.2284ms	4.3790 KOps/s	4.3195 KOps/s	$\color{#35bf28}+1.38\%$
test_seq_wrap[compile-overhead]	0.3704ms	0.2312ms	4.3251 KOps/s	4.3324 KOps/s	$\color{#d91a1a}-0.17\%$
test_func_call_runtime[False-eager]	0.9954ms	0.5534ms	1.8071 KOps/s	1.8164 KOps/s	$\color{#d91a1a}-0.51\%$
test_func_call_runtime[False-compile]	0.5842ms	0.4286ms	2.3333 KOps/s	2.2952 KOps/s	$\color{#35bf28}+1.66\%$
test_func_call_runtime[False-compile-overhead]	0.8362ms	0.4240ms	2.3584 KOps/s	2.2980 KOps/s	$\color{#35bf28}+2.63\%$
test_func_call_runtime[True-eager]	1.5883ms	0.7763ms	1.2882 KOps/s	1.3192 KOps/s	$\color{#d91a1a}-2.34\%$
test_func_call_runtime[True-compile]	0.7045ms	0.4665ms	2.1435 KOps/s	2.1132 KOps/s	$\color{#35bf28}+1.43\%$
test_func_call_runtime[True-compile-overhead]	0.5872ms	0.4649ms	2.1511 KOps/s	2.1251 KOps/s	$\color{#35bf28}+1.22\%$
test_func_call_cm_runtime[False-eager]	0.6910ms	0.5499ms	1.8184 KOps/s	1.8004 KOps/s	$\color{#35bf28}+1.00\%$
test_func_call_cm_runtime[False-compile]	0.5231ms	0.4237ms	2.3600 KOps/s	2.3098 KOps/s	$\color{#35bf28}+2.18\%$
test_func_call_cm_runtime[False-compile-overhead]	0.8355ms	0.4287ms	2.3325 KOps/s	2.2944 KOps/s	$\color{#35bf28}+1.66\%$
test_func_call_cm_runtime[True-eager]	1.0447ms	0.9060ms	1.1037 KOps/s	1.1132 KOps/s	$\color{#d91a1a}-0.85\%$
test_func_call_cm_runtime[True-compile]	0.6411ms	0.4927ms	2.0296 KOps/s	2.0234 KOps/s	$\color{#35bf28}+0.31\%$
test_func_call_cm_runtime[True-compile-overhead]	0.8656ms	0.4946ms	2.0220 KOps/s	2.0057 KOps/s	$\color{#35bf28}+0.81\%$
test_vmap_func_call_cm_runtime[eager]	2.7293ms	1.9281ms	518.6441 Ops/s	524.6508 Ops/s	$\color{#d91a1a}-1.14\%$
test_vmap_func_call_cm_runtime[compile]	0.9009ms	0.5153ms	1.9405 KOps/s	1.9551 KOps/s	$\color{#d91a1a}-0.75\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.6383ms	0.5245ms	1.9065 KOps/s	1.9311 KOps/s	$\color{#d91a1a}-1.28\%$
test_distributed	0.2911ms	0.1254ms	7.9762 KOps/s	7.7543 KOps/s	$\color{#35bf28}+2.86\%$
test_tdmodule	57.4770μs	25.5118μs	39.1976 KOps/s	37.6778 KOps/s	$\color{#35bf28}+4.03\%$
test_tdmodule_dispatch	95.2770μs	47.3293μs	21.1285 KOps/s	20.8876 KOps/s	$\color{#35bf28}+1.15\%$
test_tdseq	54.7720μs	28.6499μs	34.9041 KOps/s	34.9783 KOps/s	$\color{#d91a1a}-0.21\%$
test_tdseq_dispatch	88.9250μs	54.5682μs	18.3257 KOps/s	18.7408 KOps/s	$\color{#d91a1a}-2.22\%$
test_instantiation_functorch	2.2113ms	1.5329ms	652.3794 Ops/s	655.1296 Ops/s	$\color{#d91a1a}-0.42\%$
test_exec_functorch	0.3128ms	0.1813ms	5.5160 KOps/s	5.5244 KOps/s	$\color{#d91a1a}-0.15\%$
test_exec_functional_call	0.3925ms	0.1739ms	5.7498 KOps/s	5.7450 KOps/s	$\color{#35bf28}+0.08\%$
test_exec_td_decorator	0.4860ms	0.2402ms	4.1639 KOps/s	4.2207 KOps/s	$\color{#d91a1a}-1.35\%$
test_vmap_mlp_speed_decorator[True-True]	1.0912ms	0.6619ms	1.5109 KOps/s	1.5369 KOps/s	$\color{#d91a1a}-1.69\%$
test_vmap_mlp_speed_decorator[True-False]	1.1482ms	0.6768ms	1.4775 KOps/s	1.5339 KOps/s	$\color{#d91a1a}-3.68\%$
test_vmap_mlp_speed_decorator[False-True]	1.2166ms	0.5292ms	1.8895 KOps/s	1.8878 KOps/s	$\color{#35bf28}+0.09\%$
test_vmap_mlp_speed_decorator[False-False]	0.8077ms	0.5305ms	1.8850 KOps/s	1.8862 KOps/s	$\color{#d91a1a}-0.06\%$
test_to_module_speed[True]	1.4479ms	1.3325ms	750.4445 Ops/s	738.8871 Ops/s	$\color{#35bf28}+1.56\%$
test_to_module_speed[False]	1.4196ms	1.3046ms	766.5111 Ops/s	760.7333 Ops/s	$\color{#35bf28}+0.76\%$
test_tc_init	0.1178ms	48.5956μs	20.5780 KOps/s	22.2522 KOps/s	$\textbf{\color{#d91a1a}-7.52\%}$
test_tc_init_nested	0.2176ms	95.4781μs	10.4736 KOps/s	11.1015 KOps/s	$\textbf{\color{#d91a1a}-5.66\%}$
test_tc_first_layer_tensor	28.1030μs	1.5103μs	662.1138 KOps/s	659.7567 KOps/s	$\color{#35bf28}+0.36\%$
test_tc_first_layer_nontensor	30.9470μs	4.6601μs	214.5878 KOps/s	217.7249 KOps/s	$\color{#d91a1a}-1.44\%$
test_tc_second_layer_tensor	17.3120μs	2.8044μs	356.5788 KOps/s	349.4903 KOps/s	$\color{#35bf28}+2.03\%$
test_tc_second_layer_nontensor	36.1570μs	5.9212μs	168.8850 KOps/s	164.2180 KOps/s	$\color{#35bf28}+2.84\%$
test_unbind	0.2385s	13.6546ms	73.2356 Ops/s	75.6552 Ops/s	$\color{#d91a1a}-3.20\%$
test_full_like	8.6858ms	7.4148ms	134.8661 Ops/s	80.7252 Ops/s	$\textbf{\color{#35bf28}+67.07\%}$
test_zeros_like	4.0054ms	2.9093ms	343.7221 Ops/s	124.8517 Ops/s	$\textbf{\color{#35bf28}+175.30\%}$
test_ones_like	3.7836ms	3.2938ms	303.6032 Ops/s	127.7508 Ops/s	$\textbf{\color{#35bf28}+137.65\%}$
test_clone	6.0285ms	5.2843ms	189.2399 Ops/s	106.7570 Ops/s	$\textbf{\color{#35bf28}+77.26\%}$
test_squeeze	86.6210μs	12.1049μs	82.6115 KOps/s	79.6637 KOps/s	$\color{#35bf28}+3.70\%$
test_unsqueeze	0.1613ms	90.7151μs	11.0235 KOps/s	10.9890 KOps/s	$\color{#35bf28}+0.31\%$
test_split	0.3637ms	0.1934ms	5.1694 KOps/s	5.0060 KOps/s	$\color{#35bf28}+3.27\%$
test_permute	0.3121ms	0.2086ms	4.7948 KOps/s	4.8640 KOps/s	$\color{#d91a1a}-1.42\%$
test_stack	28.8100ms	25.0397ms	39.9366 Ops/s	37.8852 Ops/s	$\textbf{\color{#35bf28}+5.41\%}$
test_cat	27.1532ms	24.7070ms	40.4744 Ops/s	37.9450 Ops/s	$\textbf{\color{#35bf28}+6.67\%}$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}36$. Worsened: $\large\color{#d91a1a}11$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	37.7400μs	11.5768μs	86.3795 KOps/s	76.1494 KOps/s	$\textbf{\color{#35bf28}+13.43\%}$
test_plain_set_stack_nested	35.7110μs	11.4697μs	87.1863 KOps/s	74.9186 KOps/s	$\textbf{\color{#35bf28}+16.37\%}$
test_plain_set_nested_inplace	36.4500μs	12.4631μs	80.2371 KOps/s	70.5957 KOps/s	$\textbf{\color{#35bf28}+13.66\%}$
test_plain_set_stack_nested_inplace	35.5910μs	12.4392μs	80.3912 KOps/s	70.1141 KOps/s	$\textbf{\color{#35bf28}+14.66\%}$
test_items	24.0100μs	2.8947μs	345.4595 KOps/s	344.8690 KOps/s	$\color{#35bf28}+0.17\%$
test_items_nested	0.4149ms	0.3617ms	2.7644 KOps/s	2.7464 KOps/s	$\color{#35bf28}+0.65\%$
test_items_nested_locked	0.4167ms	0.3613ms	2.7677 KOps/s	2.7706 KOps/s	$\color{#d91a1a}-0.10\%$
test_items_nested_leaf	87.1010μs	58.6274μs	17.0569 KOps/s	16.9273 KOps/s	$\color{#35bf28}+0.77\%$
test_items_stack_nested	0.4205ms	0.3647ms	2.7417 KOps/s	2.7685 KOps/s	$\color{#d91a1a}-0.97\%$
test_items_stack_nested_leaf	0.1051ms	60.6241μs	16.4951 KOps/s	16.4514 KOps/s	$\color{#35bf28}+0.27\%$
test_items_stack_nested_locked	0.4174ms	0.3612ms	2.7683 KOps/s	2.7509 KOps/s	$\color{#35bf28}+0.63\%$
test_keys	24.7410μs	3.4439μs	290.3649 KOps/s	287.5110 KOps/s	$\color{#35bf28}+0.99\%$
test_keys_nested	0.1152ms	81.9556μs	12.2017 KOps/s	12.0671 KOps/s	$\color{#35bf28}+1.12\%$
test_keys_nested_locked	0.7105ms	88.0399μs	11.3585 KOps/s	11.2437 KOps/s	$\color{#35bf28}+1.02\%$
test_keys_nested_leaf	0.1056ms	72.4923μs	13.7946 KOps/s	13.4917 KOps/s	$\color{#35bf28}+2.24\%$
test_keys_stack_nested	0.1124ms	83.5616μs	11.9672 KOps/s	11.9330 KOps/s	$\color{#35bf28}+0.29\%$
test_keys_stack_nested_leaf	0.1100ms	73.6137μs	13.5844 KOps/s	13.2195 KOps/s	$\color{#35bf28}+2.76\%$
test_keys_stack_nested_locked	0.1274ms	89.1880μs	11.2123 KOps/s	11.0292 KOps/s	$\color{#35bf28}+1.66\%$
test_values	6.1302μs	0.8523μs	1.1733 MOps/s	1.1675 MOps/s	$\color{#35bf28}+0.49\%$
test_values_nested	66.2310μs	34.1954μs	29.2437 KOps/s	28.8289 KOps/s	$\color{#35bf28}+1.44\%$
test_values_nested_locked	68.1510μs	35.7849μs	27.9448 KOps/s	27.5581 KOps/s	$\color{#35bf28}+1.40\%$
test_values_nested_leaf	62.7910μs	39.0009μs	25.6404 KOps/s	25.4967 KOps/s	$\color{#35bf28}+0.56\%$
test_values_stack_nested	67.0510μs	34.7162μs	28.8050 KOps/s	28.8074 KOps/s	$-0.01\%$
test_values_stack_nested_leaf	77.7120μs	39.2814μs	25.4574 KOps/s	25.3169 KOps/s	$\color{#35bf28}+0.55\%$
test_values_stack_nested_locked	74.8110μs	36.3154μs	27.5365 KOps/s	27.4288 KOps/s	$\color{#35bf28}+0.39\%$
test_membership	2.3301μs	0.5170μs	1.9342 MOps/s	1.9540 MOps/s	$\color{#d91a1a}-1.02\%$
test_membership_nested	15.4055μs	2.0479μs	488.3072 KOps/s	488.1466 KOps/s	$\color{#35bf28}+0.03\%$
test_membership_nested_leaf	29.7055μs	2.0754μs	481.8324 KOps/s	484.9108 KOps/s	$\color{#d91a1a}-0.63\%$
test_membership_stacked_nested	23.9000μs	2.1231μs	471.0180 KOps/s	458.7036 KOps/s	$\color{#35bf28}+2.68\%$
test_membership_stacked_nested_leaf	33.2700μs	2.1143μs	472.9618 KOps/s	464.0475 KOps/s	$\color{#35bf28}+1.92\%$
test_membership_nested_last	49.1610μs	3.1158μs	320.9440 KOps/s	319.5997 KOps/s	$\color{#35bf28}+0.42\%$
test_membership_nested_leaf_last	27.5900μs	3.0908μs	323.5433 KOps/s	318.1838 KOps/s	$\color{#35bf28}+1.68\%$
test_membership_stacked_nested_last	32.2510μs	3.1387μs	318.6025 KOps/s	190.4649 KOps/s	$\textbf{\color{#35bf28}+67.28\%}$
test_membership_stacked_nested_leaf_last	32.9610μs	3.1610μs	316.3543 KOps/s	186.5954 KOps/s	$\textbf{\color{#35bf28}+69.54\%}$
test_nested_getleaf	41.0500μs	6.1857μs	161.6630 KOps/s	159.0052 KOps/s	$\color{#35bf28}+1.67\%$
test_nested_get	30.3410μs	5.8248μs	171.6789 KOps/s	169.6771 KOps/s	$\color{#35bf28}+1.18\%$
test_stacked_getleaf	46.7710μs	6.1656μs	162.1891 KOps/s	160.8067 KOps/s	$\color{#35bf28}+0.86\%$
test_stacked_get	26.6710μs	5.8576μs	170.7192 KOps/s	170.1448 KOps/s	$\color{#35bf28}+0.34\%$
test_nested_getitemleaf	51.9510μs	6.2529μs	159.9249 KOps/s	159.7574 KOps/s	$\color{#35bf28}+0.10\%$
test_nested_getitem	86.4520μs	5.9400μs	168.3497 KOps/s	167.5984 KOps/s	$\color{#35bf28}+0.45\%$
test_stacked_getitemleaf	50.5710μs	6.2551μs	159.8700 KOps/s	158.5746 KOps/s	$\color{#35bf28}+0.82\%$
test_stacked_getitem	29.9100μs	5.9178μs	168.9830 KOps/s	167.1111 KOps/s	$\color{#35bf28}+1.12\%$
test_lock_nested	8.9793ms	0.4007ms	2.4958 KOps/s	2.5295 KOps/s	$\color{#d91a1a}-1.33\%$
test_lock_stack_nested	0.4106ms	0.3581ms	2.7928 KOps/s	2.7901 KOps/s	$\color{#35bf28}+0.09\%$
test_unlock_nested	0.6304ms	0.3323ms	3.0094 KOps/s	3.0277 KOps/s	$\color{#d91a1a}-0.61\%$
test_unlock_stack_nested	0.4288ms	0.2995ms	3.3393 KOps/s	3.3710 KOps/s	$\color{#d91a1a}-0.94\%$
test_flatten_speed	0.1200ms	75.5253μs	13.2406 KOps/s	13.0564 KOps/s	$\color{#35bf28}+1.41\%$
test_unflatten_speed	0.3811ms	0.3279ms	3.0499 KOps/s	3.0552 KOps/s	$\color{#d91a1a}-0.17\%$
test_common_ops	1.6885ms	0.6010ms	1.6638 KOps/s	1.5240 KOps/s	$\textbf{\color{#35bf28}+9.18\%}$
test_creation	0.1627ms	1.7810μs	561.4964 KOps/s	550.3152 KOps/s	$\color{#35bf28}+2.03\%$
test_creation_empty	39.4610μs	6.5744μs	152.1040 KOps/s	99.7754 KOps/s	$\textbf{\color{#35bf28}+52.45\%}$
test_creation_nested_1	28.4800μs	8.1900μs	122.1008 KOps/s	84.8523 KOps/s	$\textbf{\color{#35bf28}+43.90\%}$
test_creation_nested_2	35.2410μs	11.0646μs	90.3782 KOps/s	69.0116 KOps/s	$\textbf{\color{#35bf28}+30.96\%}$
test_clone	73.7920μs	11.9768μs	83.4950 KOps/s	87.9041 KOps/s	$\textbf{\color{#d91a1a}-5.02\%}$
test_getitem[int]	1.5463ms	11.5120μs	86.8656 KOps/s	88.9897 KOps/s	$\color{#d91a1a}-2.39\%$
test_getitem[slice_int]	0.1138ms	22.3455μs	44.7518 KOps/s	45.4066 KOps/s	$\color{#d91a1a}-1.44\%$
test_getitem[range]	0.1306ms	40.4207μs	24.7398 KOps/s	25.1925 KOps/s	$\color{#d91a1a}-1.80\%$
test_getitem[tuple]	0.1042ms	19.2133μs	52.0472 KOps/s	52.8953 KOps/s	$\color{#d91a1a}-1.60\%$
test_getitem[list]	0.1950ms	35.7507μs	27.9715 KOps/s	28.2979 KOps/s	$\color{#d91a1a}-1.15\%$
test_setitem_dim[int]	39.1700μs	20.5672μs	48.6212 KOps/s	49.1197 KOps/s	$\color{#d91a1a}-1.01\%$
test_setitem_dim[slice_int]	62.1910μs	40.1302μs	24.9189 KOps/s	24.7240 KOps/s	$\color{#35bf28}+0.79\%$
test_setitem_dim[range]	77.4810μs	54.5332μs	18.3375 KOps/s	18.0194 KOps/s	$\color{#35bf28}+1.76\%$
test_setitem_dim[tuple]	65.5010μs	33.5962μs	29.7653 KOps/s	29.2870 KOps/s	$\color{#35bf28}+1.63\%$
test_setitem	77.4320μs	15.8688μs	63.0167 KOps/s	58.2304 KOps/s	$\textbf{\color{#35bf28}+8.22\%}$
test_set	80.6120μs	15.1069μs	66.1948 KOps/s	60.1689 KOps/s	$\textbf{\color{#35bf28}+10.01\%}$
test_set_shared	1.5956ms	0.1521ms	6.5763 KOps/s	6.5897 KOps/s	$\color{#d91a1a}-0.20\%$
test_update	0.2058ms	17.4500μs	57.3066 KOps/s	49.6697 KOps/s	$\textbf{\color{#35bf28}+15.38\%}$
test_update_nested	92.0510μs	22.9123μs	43.6447 KOps/s	38.5717 KOps/s	$\textbf{\color{#35bf28}+13.15\%}$
test_update__nested	0.1356ms	27.2356μs	36.7167 KOps/s	36.6825 KOps/s	$\color{#35bf28}+0.09\%$
test_set_nested	80.3210μs	16.8283μs	59.4237 KOps/s	55.9226 KOps/s	$\textbf{\color{#35bf28}+6.26\%}$
test_set_nested_new	88.4920μs	19.0590μs	52.4687 KOps/s	49.4929 KOps/s	$\textbf{\color{#35bf28}+6.01\%}$
test_select	91.2120μs	29.8089μs	33.5470 KOps/s	30.5020 KOps/s	$\textbf{\color{#35bf28}+9.98\%}$
test_select_nested	86.4210μs	44.9233μs	22.2602 KOps/s	22.2557 KOps/s	$\color{#35bf28}+0.02\%$
test_exclude_nested	94.5620μs	65.7305μs	15.2136 KOps/s	15.2968 KOps/s	$\color{#d91a1a}-0.54\%$
test_empty[True]	0.3548ms	0.2947ms	3.3929 KOps/s	3.3605 KOps/s	$\color{#35bf28}+0.96\%$
test_empty[False]	3.4690μs	0.8250μs	1.2121 MOps/s	1.2047 MOps/s	$\color{#35bf28}+0.61\%$
test_to	0.1204ms	64.2156μs	15.5725 KOps/s	17.3758 KOps/s	$\textbf{\color{#d91a1a}-10.38\%}$
test_to_nonblocking	84.8220μs	49.5599μs	20.1776 KOps/s	20.1072 KOps/s	$\color{#35bf28}+0.35\%$
test_unbind_speed	1.5687ms	0.2518ms	3.9715 KOps/s	4.0698 KOps/s	$\color{#d91a1a}-2.42\%$
test_unbind_speed_stack0	0.3332ms	0.2533ms	3.9485 KOps/s	4.0420 KOps/s	$\color{#d91a1a}-2.31\%$
test_unbind_speed_stack1	91.5298ms	0.6975ms	1.4337 KOps/s	1.4738 KOps/s	$\color{#d91a1a}-2.73\%$
test_split	93.2217ms	1.6669ms	599.9094 Ops/s	615.2880 Ops/s	$\color{#d91a1a}-2.50\%$
test_chunk	93.3932ms	1.6708ms	598.5172 Ops/s	612.0057 Ops/s	$\color{#d91a1a}-2.20\%$
test_consolidate[False-None]	96.1194ms	3.0542ms	327.4133 Ops/s	327.2565 Ops/s	$\color{#35bf28}+0.05\%$
test_consolidate[default-None]	2.2063ms	1.8087ms	552.8838 Ops/s	567.9491 Ops/s	$\color{#d91a1a}-2.65\%$
test_consolidate[reduce-overhead-None]	2.0179ms	1.8324ms	545.7248 Ops/s	564.7843 Ops/s	$\color{#d91a1a}-3.37\%$
test_consolidate_njt[False-None]	7.2683ms	6.9159ms	144.5944 Ops/s	108.9073 Ops/s	$\textbf{\color{#35bf28}+32.77\%}$
test_to[False-False-None]	1.9547ms	1.7928ms	557.7893 Ops/s	565.2088 Ops/s	$\color{#d91a1a}-1.31\%$
test_to[True-False-None]	1.6373ms	1.4675ms	681.4530 Ops/s	714.2225 Ops/s	$\color{#d91a1a}-4.59\%$
test_to[within-False-None]	4.6052ms	4.3747ms	228.5881 Ops/s	233.0220 Ops/s	$\color{#d91a1a}-1.90\%$
test_to[True-default-None]	5.7705ms	5.5233ms	181.0503 Ops/s	179.8920 Ops/s	$\color{#35bf28}+0.64\%$
test_to_njt[False-False-None]	7.5964ms	7.2123ms	138.6512 Ops/s	140.6943 Ops/s	$\color{#d91a1a}-1.45\%$
test_to_njt[True-False-None]	6.2685ms	5.9313ms	168.5972 Ops/s	174.8105 Ops/s	$\color{#d91a1a}-3.55\%$
test_to_njt[within-False-None]	13.8543ms	12.7763ms	78.2700 Ops/s	79.3445 Ops/s	$\color{#d91a1a}-1.35\%$
test_creation[device0]	0.4709ms	81.7543μs	12.2318 KOps/s	12.3156 KOps/s	$\color{#d91a1a}-0.68\%$
test_creation_from_tensor	0.5150ms	85.9920μs	11.6290 KOps/s	11.8133 KOps/s	$\color{#d91a1a}-1.56\%$
test_add_one[memmap_tensor0]	0.3799ms	7.5356μs	132.7037 KOps/s	139.5651 KOps/s	$\color{#d91a1a}-4.92\%$
test_contiguous[memmap_tensor0]	2.3805μs	0.4313μs	2.3186 MOps/s	2.3249 MOps/s	$\color{#d91a1a}-0.27\%$
test_stack[memmap_tensor0]	41.3900μs	4.8278μs	207.1356 KOps/s	210.5310 KOps/s	$\color{#d91a1a}-1.61\%$
test_memmaptd_index	0.6076ms	0.2711ms	3.6891 KOps/s	3.7844 KOps/s	$\color{#d91a1a}-2.52\%$
test_memmaptd_index_astensor	0.7071ms	0.3342ms	2.9926 KOps/s	3.0405 KOps/s	$\color{#d91a1a}-1.58\%$
test_memmaptd_index_op	1.0448ms	0.6039ms	1.6558 KOps/s	1.5555 KOps/s	$\textbf{\color{#35bf28}+6.45\%}$
test_serialize_model	0.1321s	0.1311s	7.6260 Ops/s	7.6397 Ops/s	$\color{#d91a1a}-0.18\%$
test_serialize_model_pickle	1.3490s	1.2149s	0.8231 Ops/s	0.8251 Ops/s	$\color{#d91a1a}-0.24\%$
test_serialize_weights	0.1328s	0.1307s	7.6495 Ops/s	7.6642 Ops/s	$\color{#d91a1a}-0.19\%$
test_serialize_weights_returnearly	0.5489s	62.7710ms	15.9309 Ops/s	15.3351 Ops/s	$\color{#35bf28}+3.89\%$
test_serialize_weights_pickle	1.3456s	1.2207s	0.8192 Ops/s	0.8206 Ops/s	$\color{#d91a1a}-0.17\%$
test_reshape_pytree	55.3210μs	22.8356μs	43.7913 KOps/s	43.4898 KOps/s	$\color{#35bf28}+0.69\%$
test_reshape_td	56.9410μs	27.7317μs	36.0598 KOps/s	36.0437 KOps/s	$\color{#35bf28}+0.04\%$
test_view_pytree	61.1510μs	22.7180μs	44.0179 KOps/s	44.1500 KOps/s	$\color{#d91a1a}-0.30\%$
test_view_td	58.5810μs	30.8584μs	32.4061 KOps/s	29.1793 KOps/s	$\textbf{\color{#35bf28}+11.06\%}$
test_unbind_pytree	56.3010μs	29.0135μs	34.4668 KOps/s	34.4020 KOps/s	$\color{#35bf28}+0.19\%$
test_unbind_td	0.8025ms	38.1480μs	26.2137 KOps/s	26.1773 KOps/s	$\color{#35bf28}+0.14\%$
test_split_pytree	91.5020μs	30.8740μs	32.3897 KOps/s	32.1951 KOps/s	$\color{#35bf28}+0.60\%$
test_split_td	0.9747ms	41.1689μs	24.2902 KOps/s	24.9304 KOps/s	$\color{#d91a1a}-2.57\%$
test_add_pytree	62.8110μs	36.8366μs	27.1469 KOps/s	27.7519 KOps/s	$\color{#d91a1a}-2.18\%$
test_add_td	0.1937ms	48.6377μs	20.5602 KOps/s	18.8812 KOps/s	$\textbf{\color{#35bf28}+8.89\%}$
test_compile_add_one_nested[tensordict-compile]	0.1763ms	0.1230ms	8.1301 KOps/s	7.8442 KOps/s	$\color{#35bf28}+3.65\%$
test_compile_add_one_nested[tensordict-eager]	0.2436ms	0.1313ms	7.6167 KOps/s	7.5982 KOps/s	$\color{#35bf28}+0.24\%$
test_compile_add_one_nested[pytree-compile]	0.1448ms	97.0291μs	10.3062 KOps/s	10.2286 KOps/s	$\color{#35bf28}+0.76\%$
test_compile_add_one_nested[pytree-eager]	0.2163ms	0.1570ms	6.3702 KOps/s	6.5206 KOps/s	$\color{#d91a1a}-2.31\%$
test_compile_copy_nested[tensordict-compile]	48.9410μs	23.4899μs	42.5714 KOps/s	44.5554 KOps/s	$\color{#d91a1a}-4.45\%$
test_compile_copy_nested[tensordict-eager]	60.4620μs	30.0534μs	33.2741 KOps/s	33.1083 KOps/s	$\color{#35bf28}+0.50\%$
test_compile_copy_nested[pytree-compile]	0.4312ms	65.3767μs	15.2960 KOps/s	15.0975 KOps/s	$\color{#35bf28}+1.31\%$
test_compile_copy_nested[pytree-eager]	76.7420μs	49.3405μs	20.2673 KOps/s	20.2449 KOps/s	$\color{#35bf28}+0.11\%$
test_compile_add_one_flat[tensordict-compile]	0.1885ms	0.1466ms	6.8200 KOps/s	7.0696 KOps/s	$\color{#d91a1a}-3.53\%$
test_compile_add_one_flat[tensordict-eager]	0.3093ms	0.2175ms	4.5973 KOps/s	4.5620 KOps/s	$\color{#35bf28}+0.77\%$
test_compile_add_one_flat[tensorclass-compile]	0.3476ms	0.1028ms	9.7288 KOps/s	9.7440 KOps/s	$\color{#d91a1a}-0.16\%$
test_compile_add_one_flat[tensorclass-eager]	0.1218ms	56.2835μs	17.7672 KOps/s	17.7946 KOps/s	$\color{#d91a1a}-0.15\%$
test_compile_add_one_flat[pytree-compile]	0.1895ms	0.1403ms	7.1286 KOps/s	7.3433 KOps/s	$\color{#d91a1a}-2.92\%$
test_compile_add_one_flat[pytree-eager]	0.5927ms	0.5135ms	1.9474 KOps/s	1.9761 KOps/s	$\color{#d91a1a}-1.45\%$
test_compile_add_self_flat[tensordict-eager]	0.3805ms	0.2610ms	3.8314 KOps/s	3.8315 KOps/s	$-0.00\%$
test_compile_add_self_flat[tensordict-compile]	0.1879ms	0.1463ms	6.8351 KOps/s	7.0093 KOps/s	$\color{#d91a1a}-2.49\%$
test_compile_add_self_flat[tensorclass-eager]	0.1521ms	67.3226μs	14.8539 KOps/s	15.1641 KOps/s	$\color{#d91a1a}-2.05\%$
test_compile_add_self_flat[tensorclass-compile]	0.1553ms	0.1016ms	9.8440 KOps/s	10.1093 KOps/s	$\color{#d91a1a}-2.62\%$
test_compile_add_self_flat[pytree-eager]	0.4956ms	0.4281ms	2.3358 KOps/s	2.3752 KOps/s	$\color{#d91a1a}-1.66\%$
test_compile_add_self_flat[pytree-compile]	0.2292ms	0.1394ms	7.1736 KOps/s	7.0949 KOps/s	$\color{#35bf28}+1.11\%$
test_compile_copy_flat[tensordict-compile]	57.4710μs	19.8421μs	50.3979 KOps/s	55.2526 KOps/s	$\textbf{\color{#d91a1a}-8.79\%}$
test_compile_copy_flat[tensordict-eager]	63.8910μs	32.3589μs	30.9034 KOps/s	31.2419 KOps/s	$\color{#d91a1a}-1.08\%$
test_compile_copy_flat[pytree-compile]	0.1254ms	71.1027μs	14.0642 KOps/s	14.0149 KOps/s	$\color{#35bf28}+0.35\%$
test_compile_copy_flat[pytree-eager]	87.7810μs	51.5293μs	19.4064 KOps/s	19.1958 KOps/s	$\color{#35bf28}+1.10\%$
test_compile_assign_and_add[tensordict-compile]	1.6870ms	0.4044ms	2.4726 KOps/s	2.2174 KOps/s	$\textbf{\color{#35bf28}+11.51\%}$
test_compile_assign_and_add[tensordict-eager]	3.1407ms	2.7555ms	362.9099 Ops/s	367.8918 Ops/s	$\color{#d91a1a}-1.35\%$
test_compile_assign_and_add[pytree-compile]	1.6643ms	0.4479ms	2.2328 KOps/s	2.2353 KOps/s	$\color{#d91a1a}-0.11\%$
test_compile_assign_and_add[pytree-eager]	2.9446ms	2.8027ms	356.8024 Ops/s	360.5573 Ops/s	$\color{#d91a1a}-1.04\%$
test_compile_indexing[tensor-tensordict-compile]	0.1854ms	0.1194ms	8.3785 KOps/s	8.1995 KOps/s	$\color{#35bf28}+2.18\%$
test_compile_indexing[tensor-tensordict-eager]	0.5694ms	84.3104μs	11.8609 KOps/s	12.1093 KOps/s	$\color{#d91a1a}-2.05\%$
test_compile_indexing[tensor-tensorclass-compile]	0.2046ms	0.1122ms	8.9110 KOps/s	9.1742 KOps/s	$\color{#d91a1a}-2.87\%$
test_compile_indexing[tensor-tensorclass-eager]	0.4558ms	73.0520μs	13.6889 KOps/s	13.4606 KOps/s	$\color{#35bf28}+1.70\%$
test_compile_indexing[tensor-pytree-compile]	0.5158ms	0.1165ms	8.5835 KOps/s	8.6762 KOps/s	$\color{#d91a1a}-1.07\%$
test_compile_indexing[tensor-pytree-eager]	0.4697ms	73.0785μs	13.6839 KOps/s	13.6018 KOps/s	$\color{#35bf28}+0.60\%$
test_compile_indexing[slice-tensordict-compile]	0.5030ms	0.1034ms	9.6758 KOps/s	9.7905 KOps/s	$\color{#d91a1a}-1.17\%$
test_compile_indexing[slice-tensordict-eager]	0.1425ms	18.8005μs	53.1900 KOps/s	49.3225 KOps/s	$\textbf{\color{#35bf28}+7.84\%}$
test_compile_indexing[slice-tensorclass-compile]	0.1385ms	98.6346μs	10.1384 KOps/s	10.1213 KOps/s	$\color{#35bf28}+0.17\%$
test_compile_indexing[slice-tensorclass-eager]	0.4040ms	16.7901μs	59.5590 KOps/s	60.0882 KOps/s	$\color{#d91a1a}-0.88\%$
test_compile_indexing[slice-pytree-compile]	0.5041ms	0.1043ms	9.5917 KOps/s	10.0610 KOps/s	$\color{#d91a1a}-4.66\%$
test_compile_indexing[slice-pytree-eager]	0.3994ms	17.8707μs	55.9574 KOps/s	60.1358 KOps/s	$\textbf{\color{#d91a1a}-6.95\%}$
test_compile_indexing[int-tensordict-compile]	0.2009ms	0.1089ms	9.1850 KOps/s	9.3365 KOps/s	$\color{#d91a1a}-1.62\%$
test_compile_indexing[int-tensordict-eager]	0.5401ms	18.5299μs	53.9668 KOps/s	54.8043 KOps/s	$\color{#d91a1a}-1.53\%$
test_compile_indexing[int-tensorclass-compile]	0.5027ms	0.1038ms	9.6294 KOps/s	9.6761 KOps/s	$\color{#d91a1a}-0.48\%$
test_compile_indexing[int-tensorclass-eager]	0.4093ms	17.7016μs	56.4921 KOps/s	60.1257 KOps/s	$\textbf{\color{#d91a1a}-6.04\%}$
test_compile_indexing[int-pytree-compile]	0.5035ms	0.1042ms	9.5934 KOps/s	10.1489 KOps/s	$\textbf{\color{#d91a1a}-5.47\%}$
test_compile_indexing[int-pytree-eager]	0.3978ms	16.8979μs	59.1790 KOps/s	60.5814 KOps/s	$\color{#d91a1a}-2.32\%$
test_mod_add[eager]	0.4371ms	38.0091μs	26.3095 KOps/s	24.8808 KOps/s	$\textbf{\color{#35bf28}+5.74\%}$
test_mod_add[compile]	0.4835ms	82.8171μs	12.0748 KOps/s	11.4401 KOps/s	$\textbf{\color{#35bf28}+5.55\%}$
test_mod_add[compile-overhead]	0.3283ms	0.1718ms	5.8194 KOps/s	5.6582 KOps/s	$\color{#35bf28}+2.85\%$
test_mod_wrap[eager]	0.6579ms	0.2539ms	3.9379 KOps/s	3.6770 KOps/s	$\textbf{\color{#35bf28}+7.10\%}$
test_mod_wrap[compile]	0.3716ms	0.2934ms	3.4086 KOps/s	3.2189 KOps/s	$\textbf{\color{#35bf28}+5.89\%}$
test_mod_wrap[compile-overhead]	6.6466ms	3.6854ms	271.3409 Ops/s	271.3332 Ops/s	$+0.00\%$
test_mod_wrap_and_backward[eager]	1.5422ms	1.3909ms	718.9579 Ops/s	676.0073 Ops/s	$\textbf{\color{#35bf28}+6.35\%}$
test_mod_wrap_and_backward[compile]	1.4196ms	1.3051ms	766.2034 Ops/s	759.1150 Ops/s	$\color{#35bf28}+0.93\%$
test_mod_wrap_and_backward[compile-overhead]	1.4067ms	0.9473ms	1.0557 KOps/s	1.0563 KOps/s	$\color{#d91a1a}-0.06\%$
test_seq_add[eager]	0.2042ms	0.1204ms	8.3069 KOps/s	8.2316 KOps/s	$\color{#35bf28}+0.91\%$
test_seq_add[compile]	0.2541ms	91.7790μs	10.8957 KOps/s	10.5128 KOps/s	$\color{#35bf28}+3.64\%$
test_seq_add[compile-overhead]	0.2013ms	0.1329ms	7.5234 KOps/s	7.5414 KOps/s	$\color{#d91a1a}-0.24\%$
test_seq_wrap[eager]	0.4896ms	0.4204ms	2.3785 KOps/s	2.1933 KOps/s	$\textbf{\color{#35bf28}+8.44\%}$
test_seq_wrap[compile]	0.3625ms	0.3091ms	3.2352 KOps/s	3.1979 KOps/s	$\color{#35bf28}+1.17\%$
test_seq_wrap[compile-overhead]	0.2851ms	0.2308ms	4.3334 KOps/s	4.2922 KOps/s	$\color{#35bf28}+0.96\%$
test_func_call_runtime[False-eager]	0.8472ms	0.7511ms	1.3315 KOps/s	1.3188 KOps/s	$\color{#35bf28}+0.96\%$
test_func_call_runtime[False-compile]	0.8993ms	0.7717ms	1.2958 KOps/s	1.2850 KOps/s	$\color{#35bf28}+0.84\%$
test_func_call_runtime[False-compile-overhead]	0.4388ms	0.3754ms	2.6639 KOps/s	2.6703 KOps/s	$\color{#d91a1a}-0.24\%$
test_func_call_runtime[True-eager]	1.0618ms	0.9245ms	1.0817 KOps/s	1.0629 KOps/s	$\color{#35bf28}+1.77\%$
test_func_call_runtime[True-compile]	0.8557ms	0.7897ms	1.2663 KOps/s	1.2558 KOps/s	$\color{#35bf28}+0.84\%$
test_func_call_runtime[True-compile-overhead]	0.4745ms	0.4038ms	2.4764 KOps/s	2.5280 KOps/s	$\color{#d91a1a}-2.04\%$
test_func_call_cm_runtime[False-eager]	0.9210ms	0.8082ms	1.2373 KOps/s	1.3308 KOps/s	$\textbf{\color{#d91a1a}-7.03\%}$
test_func_call_cm_runtime[False-compile]	0.9364ms	0.8262ms	1.2104 KOps/s	1.2820 KOps/s	$\textbf{\color{#d91a1a}-5.58\%}$
test_func_call_cm_runtime[False-compile-overhead]	0.4589ms	0.3774ms	2.6497 KOps/s	2.6533 KOps/s	$\color{#d91a1a}-0.14\%$
test_func_call_cm_runtime[True-eager]	1.1730ms	1.0241ms	976.4357 Ops/s	967.4522 Ops/s	$\color{#35bf28}+0.93\%$
test_func_call_cm_runtime[True-compile]	0.9275ms	0.8208ms	1.2184 KOps/s	1.2127 KOps/s	$\color{#35bf28}+0.47\%$
test_func_call_cm_runtime[True-compile-overhead]	0.4773ms	0.4249ms	2.3533 KOps/s	2.3615 KOps/s	$\color{#d91a1a}-0.35\%$
test_vmap_func_call_cm_runtime[eager]	2.5734ms	2.1306ms	469.3575 Ops/s	467.9958 Ops/s	$\color{#35bf28}+0.29\%$
test_vmap_func_call_cm_runtime[compile]	0.9607ms	0.8698ms	1.1497 KOps/s	1.1773 KOps/s	$\color{#d91a1a}-2.35\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.4896ms	0.4259ms	2.3479 KOps/s	2.3445 KOps/s	$\color{#35bf28}+0.14\%$
test_distributed	2.0693ms	0.1781ms	5.6154 KOps/s	8.7632 KOps/s	$\textbf{\color{#d91a1a}-35.92\%}$
test_tdmodule	38.5500μs	19.0287μs	52.5521 KOps/s	46.0823 KOps/s	$\textbf{\color{#35bf28}+14.04\%}$
test_tdmodule_dispatch	0.2787ms	34.7041μs	28.8151 KOps/s	25.9306 KOps/s	$\textbf{\color{#35bf28}+11.12\%}$
test_tdseq	42.2610μs	19.7290μs	50.6869 KOps/s	44.7231 KOps/s	$\textbf{\color{#35bf28}+13.33\%}$
test_tdseq_dispatch	58.8010μs	36.6310μs	27.2993 KOps/s	23.9465 KOps/s	$\textbf{\color{#35bf28}+14.00\%}$
test_instantiation_functorch	1.7211ms	1.6123ms	620.2182 Ops/s	629.4023 Ops/s	$\color{#d91a1a}-1.46\%$
test_exec_functorch	0.2893ms	0.1576ms	6.3465 KOps/s	6.5204 KOps/s	$\color{#d91a1a}-2.67\%$
test_exec_functional_call	0.2054ms	0.1475ms	6.7818 KOps/s	6.8374 KOps/s	$\color{#d91a1a}-0.81\%$
test_exec_td_decorator	0.3856ms	0.1962ms	5.0965 KOps/s	5.0817 KOps/s	$\color{#35bf28}+0.29\%$
test_vmap_mlp_speed_decorator[True-True]	0.7972ms	0.6923ms	1.4444 KOps/s	1.4259 KOps/s	$\color{#35bf28}+1.29\%$
test_vmap_mlp_speed_decorator[True-False]	0.8013ms	0.6902ms	1.4489 KOps/s	1.4253 KOps/s	$\color{#35bf28}+1.65\%$
test_vmap_mlp_speed_decorator[False-True]	0.7304ms	0.6074ms	1.6462 KOps/s	1.6507 KOps/s	$\color{#d91a1a}-0.27\%$
test_vmap_mlp_speed_decorator[False-False]	0.7315ms	0.6082ms	1.6441 KOps/s	1.6460 KOps/s	$\color{#d91a1a}-0.12\%$
test_vmap_transformer_speed_decorator[True-True]	19.9041ms	19.5834ms	51.0636 Ops/s	51.3822 Ops/s	$\color{#d91a1a}-0.62\%$
test_vmap_transformer_speed_decorator[True-False]	19.8032ms	19.5697ms	51.0995 Ops/s	51.3599 Ops/s	$\color{#d91a1a}-0.51\%$
test_vmap_transformer_speed_decorator[False-True]	19.8049ms	19.5072ms	51.2632 Ops/s	51.8207 Ops/s	$\color{#d91a1a}-1.08\%$
test_vmap_transformer_speed_decorator[False-False]	19.7636ms	19.4524ms	51.4074 Ops/s	51.7368 Ops/s	$\color{#d91a1a}-0.64\%$
test_to_module_speed[True]	1.0968ms	0.9894ms	1.0107 KOps/s	1.0077 KOps/s	$\color{#35bf28}+0.29\%$
test_to_module_speed[False]	1.5388ms	0.9718ms	1.0291 KOps/s	1.0288 KOps/s	$\color{#35bf28}+0.02\%$
test_tc_init	89.7020μs	36.1989μs	27.6251 KOps/s	24.2897 KOps/s	$\textbf{\color{#35bf28}+13.73\%}$
test_tc_init_nested	0.1087ms	72.5923μs	13.7756 KOps/s	12.2609 KOps/s	$\textbf{\color{#35bf28}+12.35\%}$
test_tc_first_layer_tensor	4.8959μs	0.7078μs	1.4129 MOps/s	1.4270 MOps/s	$\color{#d91a1a}-0.99\%$
test_tc_first_layer_nontensor	30.2600μs	2.3787μs	420.3952 KOps/s	418.1248 KOps/s	$\color{#35bf28}+0.54\%$
test_tc_second_layer_tensor	9.0852μs	1.4309μs	698.8520 KOps/s	700.3483 KOps/s	$\color{#d91a1a}-0.21\%$
test_tc_second_layer_nontensor	31.5800μs	3.1334μs	319.1458 KOps/s	317.6426 KOps/s	$\color{#35bf28}+0.47\%$
test_unbind	0.2375s	10.6590ms	93.8172 Ops/s	140.1949 Ops/s	$\textbf{\color{#d91a1a}-33.08\%}$
test_full_like	10.2366ms	9.1085ms	109.7877 Ops/s	109.4485 Ops/s	$\color{#35bf28}+0.31\%$
test_zeros_like	4.8254ms	4.3226ms	231.3438 Ops/s	137.2173 Ops/s	$\textbf{\color{#35bf28}+68.60\%}$
test_ones_like	4.6221ms	4.3196ms	231.5043 Ops/s	231.7171 Ops/s	$\color{#d91a1a}-0.09\%$
test_clone	6.9790ms	6.3426ms	157.6643 Ops/s	157.8505 Ops/s	$\color{#d91a1a}-0.12\%$
test_squeeze	82.3710μs	10.0214μs	99.7866 KOps/s	103.3867 KOps/s	$\color{#d91a1a}-3.48\%$
test_unsqueeze	0.1320ms	77.5356μs	12.8973 KOps/s	13.9773 KOps/s	$\textbf{\color{#d91a1a}-7.73\%}$
test_split	0.2914ms	0.1631ms	6.1316 KOps/s	6.0499 KOps/s	$\color{#35bf28}+1.35\%$
test_permute	0.2518ms	0.1866ms	5.3584 KOps/s	5.5144 KOps/s	$\color{#d91a1a}-2.83\%$
test_stack	50.8125ms	50.6235ms	19.7537 Ops/s	19.7680 Ops/s	$\color{#d91a1a}-0.07\%$
test_cat	50.8735ms	50.5898ms	19.7668 Ops/s	19.8231 Ops/s	$\color{#d91a1a}-0.28\%$