[CI] Fix smoke tests

[vmoens]

Stack from ghstack (oldest at bottom):

• [CI] Add missing packages for smoke test #1149
• [CI] Fix nightly build #1148
• -> [CI] Fix smoke tests #1147

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}14$. Worsened: $\large\color{#d91a1a}32$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	49.5820μs	21.5970μs	46.3028 KOps/s	51.3857 KOps/s	$\textbf{\color{#d91a1a}-9.89\%}$
test_plain_set_stack_nested	50.2440μs	22.1197μs	45.2086 KOps/s	51.2169 KOps/s	$\textbf{\color{#d91a1a}-11.73\%}$
test_plain_set_nested_inplace	74.3280μs	23.7815μs	42.0494 KOps/s	46.9039 KOps/s	$\textbf{\color{#d91a1a}-10.35\%}$
test_plain_set_stack_nested_inplace	61.7250μs	23.2403μs	43.0287 KOps/s	46.3365 KOps/s	$\textbf{\color{#d91a1a}-7.14\%}$
test_items	29.0240μs	4.1960μs	238.3201 KOps/s	239.9034 KOps/s	$\color{#d91a1a}-0.66\%$
test_items_nested	0.6034ms	0.4035ms	2.4785 KOps/s	2.5132 KOps/s	$\color{#d91a1a}-1.38\%$
test_items_nested_locked	0.5402ms	0.4022ms	2.4866 KOps/s	2.4907 KOps/s	$\color{#d91a1a}-0.16\%$
test_items_nested_leaf	0.1391ms	77.9807μs	12.8237 KOps/s	12.9611 KOps/s	$\color{#d91a1a}-1.06\%$
test_items_stack_nested	0.7341ms	0.4074ms	2.4545 KOps/s	2.4875 KOps/s	$\color{#d91a1a}-1.33\%$
test_items_stack_nested_leaf	0.1581ms	80.2839μs	12.4558 KOps/s	12.3784 KOps/s	$\color{#35bf28}+0.62\%$
test_items_stack_nested_locked	0.6040ms	0.4063ms	2.4610 KOps/s	2.4969 KOps/s	$\color{#d91a1a}-1.44\%$
test_keys	18.8150μs	3.4691μs	288.2567 KOps/s	287.9311 KOps/s	$\color{#35bf28}+0.11\%$
test_keys_nested	0.2708ms	0.1646ms	6.0742 KOps/s	6.1049 KOps/s	$\color{#d91a1a}-0.50\%$
test_keys_nested_locked	1.6780ms	0.1702ms	5.8758 KOps/s	5.8158 KOps/s	$\color{#35bf28}+1.03\%$
test_keys_nested_leaf	0.2670ms	0.1442ms	6.9371 KOps/s	7.0098 KOps/s	$\color{#d91a1a}-1.04\%$
test_keys_stack_nested	0.2738ms	0.1620ms	6.1730 KOps/s	6.0559 KOps/s	$\color{#35bf28}+1.93\%$
test_keys_stack_nested_leaf	0.2672ms	0.1412ms	7.0800 KOps/s	6.9614 KOps/s	$\color{#35bf28}+1.70\%$
test_keys_stack_nested_locked	0.2902ms	0.1677ms	5.9647 KOps/s	5.8427 KOps/s	$\color{#35bf28}+2.09\%$
test_values	8.7484μs	1.0546μs	948.1843 KOps/s	958.0204 KOps/s	$\color{#d91a1a}-1.03\%$
test_values_nested	0.1183ms	62.6379μs	15.9648 KOps/s	16.0626 KOps/s	$\color{#d91a1a}-0.61\%$
test_values_nested_locked	0.1147ms	62.4162μs	16.0215 KOps/s	16.0536 KOps/s	$\color{#d91a1a}-0.20\%$
test_values_nested_leaf	0.1358ms	72.0001μs	13.8889 KOps/s	12.7737 KOps/s	$\textbf{\color{#35bf28}+8.73\%}$
test_values_stack_nested	0.1212ms	62.8762μs	15.9043 KOps/s	14.8775 KOps/s	$\textbf{\color{#35bf28}+6.90\%}$
test_values_stack_nested_leaf	0.1238ms	71.6666μs	13.9535 KOps/s	13.7132 KOps/s	$\color{#35bf28}+1.75\%$
test_values_stack_nested_locked	0.1360ms	63.0705μs	15.8553 KOps/s	15.7977 KOps/s	$\color{#35bf28}+0.36\%$
test_membership	21.2790μs	0.8820μs	1.1338 MOps/s	1.1425 MOps/s	$\color{#d91a1a}-0.76\%$
test_membership_nested	16.9920μs	2.9017μs	344.6252 KOps/s	345.6301 KOps/s	$\color{#d91a1a}-0.29\%$
test_membership_nested_leaf	45.3750μs	2.9358μs	340.6217 KOps/s	341.7766 KOps/s	$\color{#d91a1a}-0.34\%$
test_membership_stacked_nested	17.9840μs	2.9276μs	341.5774 KOps/s	343.6467 KOps/s	$\color{#d91a1a}-0.60\%$
test_membership_stacked_nested_leaf	46.2960μs	2.9000μs	344.8257 KOps/s	342.6287 KOps/s	$\color{#35bf28}+0.64\%$
test_membership_nested_last	27.5610μs	4.3907μs	227.7558 KOps/s	227.8838 KOps/s	$\color{#d91a1a}-0.06\%$
test_membership_nested_leaf_last	51.2060μs	4.4642μs	224.0021 KOps/s	220.6365 KOps/s	$\color{#35bf28}+1.53\%$
test_membership_stacked_nested_last	38.1210μs	5.2049μs	192.1262 KOps/s	234.0968 KOps/s	$\textbf{\color{#d91a1a}-17.93\%}$
test_membership_stacked_nested_leaf_last	21.8710μs	5.2096μs	191.9540 KOps/s	235.8808 KOps/s	$\textbf{\color{#d91a1a}-18.62\%}$
test_nested_getleaf	35.0960μs	11.0966μs	90.1178 KOps/s	93.2926 KOps/s	$\color{#d91a1a}-3.40\%$
test_nested_get	37.3200μs	10.6555μs	93.8483 KOps/s	97.2658 KOps/s	$\color{#d91a1a}-3.51\%$
test_stacked_getleaf	55.4230μs	11.1610μs	89.5979 KOps/s	92.7993 KOps/s	$\color{#d91a1a}-3.45\%$
test_stacked_get	31.5190μs	10.6866μs	93.5748 KOps/s	97.6530 KOps/s	$\color{#d91a1a}-4.18\%$
test_nested_getitemleaf	51.5260μs	11.2486μs	88.9002 KOps/s	88.2654 KOps/s	$\color{#35bf28}+0.72\%$
test_nested_getitem	51.4550μs	10.9651μs	91.1983 KOps/s	93.4486 KOps/s	$\color{#d91a1a}-2.41\%$
test_stacked_getitemleaf	55.7820μs	11.5570μs	86.5276 KOps/s	87.6050 KOps/s	$\color{#d91a1a}-1.23\%$
test_stacked_getitem	41.5690μs	10.4940μs	95.2929 KOps/s	93.6262 KOps/s	$\color{#35bf28}+1.78\%$
test_lock_nested	4.3488ms	0.4596ms	2.1758 KOps/s	2.1563 KOps/s	$\color{#35bf28}+0.91\%$
test_lock_stack_nested	0.8625ms	0.4257ms	2.3489 KOps/s	2.3200 KOps/s	$\color{#35bf28}+1.25\%$
test_unlock_nested	2.3110ms	0.3875ms	2.5808 KOps/s	2.6184 KOps/s	$\color{#d91a1a}-1.44\%$
test_unlock_stack_nested	0.7140ms	0.3483ms	2.8714 KOps/s	2.8560 KOps/s	$\color{#35bf28}+0.54\%$
test_flatten_speed	0.2204ms	0.1010ms	9.8993 KOps/s	9.8635 KOps/s	$\color{#35bf28}+0.36\%$
test_unflatten_speed	1.1497ms	0.5312ms	1.8824 KOps/s	1.8741 KOps/s	$\color{#35bf28}+0.44\%$
test_common_ops	1.7105ms	0.8613ms	1.1610 KOps/s	1.3094 KOps/s	$\textbf{\color{#d91a1a}-11.33\%}$
test_creation	71.8340μs	2.5157μs	397.5100 KOps/s	401.8981 KOps/s	$\color{#d91a1a}-1.09\%$
test_creation_empty	35.6470μs	13.9141μs	71.8698 KOps/s	105.2912 KOps/s	$\textbf{\color{#d91a1a}-31.74\%}$
test_creation_nested_1	48.2000μs	16.9623μs	58.9543 KOps/s	80.1695 KOps/s	$\textbf{\color{#d91a1a}-26.46\%}$
test_creation_nested_2	55.3030μs	21.6667μs	46.1537 KOps/s	58.1230 KOps/s	$\textbf{\color{#d91a1a}-20.59\%}$
test_clone	0.1044ms	13.7618μs	72.6648 KOps/s	75.2020 KOps/s	$\color{#d91a1a}-3.37\%$
test_getitem[int]	0.8250ms	12.7331μs	78.5355 KOps/s	76.8994 KOps/s	$\color{#35bf28}+2.13\%$
test_getitem[slice_int]	0.1419ms	24.3250μs	41.1099 KOps/s	39.5145 KOps/s	$\color{#35bf28}+4.04\%$
test_getitem[range]	0.4757ms	56.2943μs	17.7638 KOps/s	20.7468 KOps/s	$\textbf{\color{#d91a1a}-14.38\%}$
test_getitem[tuple]	0.1289ms	20.2232μs	49.4483 KOps/s	49.8122 KOps/s	$\color{#d91a1a}-0.73\%$
test_getitem[list]	0.1787ms	43.5749μs	22.9490 KOps/s	22.7410 KOps/s	$\color{#35bf28}+0.91\%$
test_setitem_dim[int]	53.6800μs	26.1401μs	38.2554 KOps/s	39.0876 KOps/s	$\color{#d91a1a}-2.13\%$
test_setitem_dim[slice_int]	0.1008ms	52.2216μs	19.1492 KOps/s	19.7005 KOps/s	$\color{#d91a1a}-2.80\%$
test_setitem_dim[range]	0.1391ms	73.6284μs	13.5817 KOps/s	12.5210 KOps/s	$\textbf{\color{#35bf28}+8.47\%}$
test_setitem_dim[tuple]	71.4530μs	41.2172μs	24.2617 KOps/s	20.2480 KOps/s	$\textbf{\color{#35bf28}+19.82\%}$
test_setitem	80.1090μs	22.4816μs	44.4808 KOps/s	52.1578 KOps/s	$\textbf{\color{#d91a1a}-14.72\%}$
test_set	82.7250μs	22.0534μs	45.3445 KOps/s	52.9985 KOps/s	$\textbf{\color{#d91a1a}-14.44\%}$
test_set_shared	2.2618ms	0.1745ms	5.7319 KOps/s	5.8156 KOps/s	$\color{#d91a1a}-1.44\%$
test_update	0.1309ms	26.3726μs	37.9182 KOps/s	46.7295 KOps/s	$\textbf{\color{#d91a1a}-18.86\%}$
test_update_nested	0.1145ms	36.8453μs	27.1405 KOps/s	31.6535 KOps/s	$\textbf{\color{#d91a1a}-14.26\%}$
test_update__nested	0.5788ms	35.6671μs	28.0371 KOps/s	28.6642 KOps/s	$\color{#d91a1a}-2.19\%$
test_set_nested	81.7020μs	24.0517μs	41.5771 KOps/s	46.6377 KOps/s	$\textbf{\color{#d91a1a}-10.85\%}$
test_set_nested_new	89.8270μs	29.0147μs	34.4653 KOps/s	37.9354 KOps/s	$\textbf{\color{#d91a1a}-9.15\%}$
test_select	0.1129ms	46.5965μs	21.4609 KOps/s	23.0645 KOps/s	$\textbf{\color{#d91a1a}-6.95\%}$
test_select_nested	0.1192ms	62.5769μs	15.9803 KOps/s	15.7939 KOps/s	$\color{#35bf28}+1.18\%$
test_exclude_nested	0.1579ms	82.4775μs	12.1245 KOps/s	11.9884 KOps/s	$\color{#35bf28}+1.14\%$
test_empty[True]	0.7328ms	0.4152ms	2.4085 KOps/s	2.4156 KOps/s	$\color{#d91a1a}-0.30\%$
test_empty[False]	7.5515μs	1.3773μs	726.0346 KOps/s	723.9300 KOps/s	$\color{#35bf28}+0.29\%$
test_unbind_speed	0.5711ms	0.2718ms	3.6791 KOps/s	3.6708 KOps/s	$\color{#35bf28}+0.23\%$
test_unbind_speed_stack0	0.4048ms	0.2658ms	3.7623 KOps/s	3.7120 KOps/s	$\color{#35bf28}+1.36\%$
test_unbind_speed_stack1	0.1078s	0.7270ms	1.3755 KOps/s	1.3414 KOps/s	$\color{#35bf28}+2.54\%$
test_split	97.5048ms	1.9051ms	524.8947 Ops/s	559.5020 Ops/s	$\textbf{\color{#d91a1a}-6.19\%}$
test_chunk	1.7972ms	1.5976ms	625.9270 Ops/s	554.1650 Ops/s	$\textbf{\color{#35bf28}+12.95\%}$
test_consolidate_njt[False-None]	0.1086s	9.3331ms	107.1452 Ops/s	118.1733 Ops/s	$\textbf{\color{#d91a1a}-9.33\%}$
test_creation[device0]	0.2280ms	91.0335μs	10.9850 KOps/s	10.5959 KOps/s	$\color{#35bf28}+3.67\%$
test_creation_from_tensor	3.3987ms	95.6017μs	10.4601 KOps/s	10.6287 KOps/s	$\color{#d91a1a}-1.59\%$
test_add_one[memmap_tensor0]	0.1937ms	5.0021μs	199.9141 KOps/s	199.3776 KOps/s	$\color{#35bf28}+0.27\%$
test_contiguous[memmap_tensor0]	23.9250μs	0.5268μs	1.8981 MOps/s	1.9638 MOps/s	$\color{#d91a1a}-3.34\%$
test_stack[memmap_tensor0]	46.6570μs	3.3938μs	294.6518 KOps/s	294.7041 KOps/s	$\color{#d91a1a}-0.02\%$
test_memmaptd_index	1.0463ms	0.2465ms	4.0574 KOps/s	4.1627 KOps/s	$\color{#d91a1a}-2.53\%$
test_memmaptd_index_astensor	0.6698ms	0.3326ms	3.0071 KOps/s	3.0703 KOps/s	$\color{#d91a1a}-2.06\%$
test_memmaptd_index_op	1.0662ms	0.6452ms	1.5499 KOps/s	1.7887 KOps/s	$\textbf{\color{#d91a1a}-13.35\%}$
test_serialize_model	0.1248s	0.1178s	8.4909 Ops/s	8.2557 Ops/s	$\color{#35bf28}+2.85\%$
test_serialize_model_pickle	0.5029s	0.4038s	2.4767 Ops/s	2.4939 Ops/s	$\color{#d91a1a}-0.69\%$
test_serialize_weights	0.1241s	0.1160s	8.6170 Ops/s	7.6216 Ops/s	$\textbf{\color{#35bf28}+13.06\%}$
test_serialize_weights_returnearly	0.1595s	0.1560s	6.4108 Ops/s	6.3267 Ops/s	$\color{#35bf28}+1.33\%$
test_serialize_weights_pickle	0.4573s	0.4078s	2.4522 Ops/s	2.5355 Ops/s	$\color{#d91a1a}-3.29\%$
test_serialize_weights_filesystem	0.1507s	0.1426s	7.0139 Ops/s	7.0105 Ops/s	$\color{#35bf28}+0.05\%$
test_serialize_model_filesystem	0.1575s	0.1497s	6.6821 Ops/s	6.6066 Ops/s	$\color{#35bf28}+1.14\%$
test_reshape_pytree	66.0730μs	26.2896μs	38.0379 KOps/s	36.2371 KOps/s	$\color{#35bf28}+4.97\%$
test_reshape_td	69.2990μs	32.7424μs	30.5414 KOps/s	29.1597 KOps/s	$\color{#35bf28}+4.74\%$
test_view_pytree	74.3460μs	25.9466μs	38.5407 KOps/s	36.7065 KOps/s	$\color{#35bf28}+5.00\%$
test_view_td	97.0410μs	37.7499μs	26.4901 KOps/s	26.2497 KOps/s	$\color{#35bf28}+0.92\%$
test_unbind_pytree	75.5610μs	29.2745μs	34.1594 KOps/s	32.8311 KOps/s	$\color{#35bf28}+4.05\%$
test_unbind_td	0.3559ms	39.5144μs	25.3073 KOps/s	25.0504 KOps/s	$\color{#35bf28}+1.03\%$
test_split_pytree	0.1562ms	29.5476μs	33.8437 KOps/s	33.6822 KOps/s	$\color{#35bf28}+0.48\%$
test_split_td	0.1027s	54.5804μs	18.3216 KOps/s	21.9822 KOps/s	$\textbf{\color{#d91a1a}-16.65\%}$
test_add_pytree	0.1341ms	35.6397μs	28.0586 KOps/s	26.9897 KOps/s	$\color{#35bf28}+3.96\%$
test_add_td	0.1344ms	62.6221μs	15.9688 KOps/s	18.5168 KOps/s	$\textbf{\color{#d91a1a}-13.76\%}$
test_compile_add_one_nested[tensordict-compile]	0.1118ms	62.1193μs	16.0981 KOps/s	16.0690 KOps/s	$\color{#35bf28}+0.18\%$
test_compile_add_one_nested[tensordict-eager]	1.2988ms	0.1725ms	5.7959 KOps/s	5.9149 KOps/s	$\color{#d91a1a}-2.01\%$
test_compile_add_one_nested[pytree-compile]	0.1173ms	46.9538μs	21.2975 KOps/s	21.8765 KOps/s	$\color{#d91a1a}-2.65\%$
test_compile_add_one_nested[pytree-eager]	0.2836ms	0.1209ms	8.2697 KOps/s	8.2888 KOps/s	$\color{#d91a1a}-0.23\%$
test_compile_copy_nested[tensordict-compile]	80.8200μs	26.9542μs	37.1000 KOps/s	39.0813 KOps/s	$\textbf{\color{#d91a1a}-5.07\%}$
test_compile_copy_nested[tensordict-eager]	0.1307ms	59.0223μs	16.9427 KOps/s	17.1959 KOps/s	$\color{#d91a1a}-1.47\%$
test_compile_copy_nested[pytree-compile]	0.1505ms	78.3303μs	12.7665 KOps/s	12.6707 KOps/s	$\color{#35bf28}+0.76\%$
test_compile_copy_nested[pytree-eager]	0.1556ms	66.8346μs	14.9623 KOps/s	14.6239 KOps/s	$\color{#35bf28}+2.31\%$
test_compile_add_one_flat[tensordict-compile]	0.1989ms	0.1048ms	9.5393 KOps/s	9.5311 KOps/s	$\color{#35bf28}+0.09\%$
test_compile_add_one_flat[tensordict-eager]	0.4385ms	0.2170ms	4.6077 KOps/s	4.6324 KOps/s	$\color{#d91a1a}-0.53\%$
test_compile_add_one_flat[tensorclass-compile]	89.8870μs	46.2305μs	21.6307 KOps/s	21.9302 KOps/s	$\color{#d91a1a}-1.37\%$
test_compile_add_one_flat[tensorclass-eager]	0.4604ms	65.4658μs	15.2752 KOps/s	14.9395 KOps/s	$\color{#35bf28}+2.25\%$
test_compile_add_one_flat[pytree-compile]	0.1743ms	0.1033ms	9.6843 KOps/s	9.7012 KOps/s	$\color{#d91a1a}-0.17\%$
test_compile_add_one_flat[pytree-eager]	0.4580ms	0.2033ms	4.9180 KOps/s	4.8944 KOps/s	$\color{#35bf28}+0.48\%$
test_compile_add_self_flat[tensordict-eager]	0.3482ms	0.2327ms	4.2978 KOps/s	4.2841 KOps/s	$\color{#35bf28}+0.32\%$
test_compile_add_self_flat[tensordict-compile]	0.1972ms	0.1072ms	9.3299 KOps/s	9.4521 KOps/s	$\color{#d91a1a}-1.29\%$
test_compile_add_self_flat[tensorclass-eager]	0.2026ms	58.7754μs	17.0139 KOps/s	17.0182 KOps/s	$\color{#d91a1a}-0.03\%$
test_compile_add_self_flat[tensorclass-compile]	0.1436ms	47.2762μs	21.1523 KOps/s	22.1081 KOps/s	$\color{#d91a1a}-4.32\%$
test_compile_add_self_flat[pytree-eager]	0.5659ms	0.1577ms	6.3400 KOps/s	6.2251 KOps/s	$\color{#35bf28}+1.85\%$
test_compile_add_self_flat[pytree-compile]	0.2244ms	0.1047ms	9.5483 KOps/s	9.5963 KOps/s	$\color{#d91a1a}-0.50\%$
test_compile_copy_flat[tensordict-compile]	69.2990μs	21.3576μs	46.8218 KOps/s	47.2155 KOps/s	$\color{#d91a1a}-0.83\%$
test_compile_copy_flat[tensordict-eager]	0.1339ms	65.7279μs	15.2142 KOps/s	15.2298 KOps/s	$\color{#d91a1a}-0.10\%$
test_compile_copy_flat[pytree-compile]	0.2017ms	80.4525μs	12.4297 KOps/s	11.6959 KOps/s	$\textbf{\color{#35bf28}+6.27\%}$
test_compile_copy_flat[pytree-eager]	0.1421ms	68.3273μs	14.6354 KOps/s	14.4496 KOps/s	$\color{#35bf28}+1.29\%$
test_compile_assign_and_add[tensordict-compile]	0.4236ms	0.2125ms	4.7065 KOps/s	4.8187 KOps/s	$\color{#d91a1a}-2.33\%$
test_compile_assign_and_add[tensordict-eager]	2.1510ms	1.3378ms	747.4840 Ops/s	755.1585 Ops/s	$\color{#d91a1a}-1.02\%$
test_compile_assign_and_add[pytree-compile]	0.3317ms	0.2035ms	4.9144 KOps/s	5.0037 KOps/s	$\color{#d91a1a}-1.78\%$
test_compile_assign_and_add[pytree-eager]	0.9957ms	0.7815ms	1.2796 KOps/s	1.2828 KOps/s	$\color{#d91a1a}-0.25\%$
test_compile_assign_and_add_stack[compile]	0.8112ms	0.4575ms	2.1859 KOps/s	2.2212 KOps/s	$\color{#d91a1a}-1.59\%$
test_compile_assign_and_add_stack[eager]	3.2000ms	2.8576ms	349.9495 Ops/s	388.7272 Ops/s	$\textbf{\color{#d91a1a}-9.98\%}$
test_compile_indexing[tensor-tensordict-compile]	0.1086ms	36.2457μs	27.5895 KOps/s	28.0883 KOps/s	$\color{#d91a1a}-1.78\%$
test_compile_indexing[tensor-tensordict-eager]	0.5131ms	33.5673μs	29.7909 KOps/s	29.7026 KOps/s	$\color{#35bf28}+0.30\%$
test_compile_indexing[tensor-tensorclass-compile]	93.2740μs	29.4238μs	33.9861 KOps/s	34.1121 KOps/s	$\color{#d91a1a}-0.37\%$
test_compile_indexing[tensor-tensorclass-eager]	67.1550μs	22.6488μs	44.1524 KOps/s	40.3957 KOps/s	$\textbf{\color{#35bf28}+9.30\%}$
test_compile_indexing[tensor-pytree-compile]	0.1202ms	30.2156μs	33.0955 KOps/s	33.3597 KOps/s	$\color{#d91a1a}-0.79\%$
test_compile_indexing[tensor-pytree-eager]	90.6390μs	22.6442μs	44.1614 KOps/s	41.9949 KOps/s	$\textbf{\color{#35bf28}+5.16\%}$
test_compile_indexing[slice-tensordict-compile]	0.1242ms	51.5375μs	19.4033 KOps/s	19.6557 KOps/s	$\color{#d91a1a}-1.28\%$
test_compile_indexing[slice-tensordict-eager]	0.5465ms	20.2712μs	49.3312 KOps/s	48.8158 KOps/s	$\color{#35bf28}+1.06\%$
test_compile_indexing[slice-tensorclass-compile]	97.1010μs	43.8186μs	22.8214 KOps/s	22.4678 KOps/s	$\color{#35bf28}+1.57\%$
test_compile_indexing[slice-tensorclass-eager]	63.5990μs	18.5221μs	53.9895 KOps/s	52.8792 KOps/s	$\color{#35bf28}+2.10\%$
test_compile_indexing[slice-pytree-compile]	96.6000μs	44.2098μs	22.6194 KOps/s	21.7320 KOps/s	$\color{#35bf28}+4.08\%$
test_compile_indexing[slice-pytree-eager]	78.8270μs	18.4389μs	54.2332 KOps/s	49.8971 KOps/s	$\textbf{\color{#35bf28}+8.69\%}$
test_compile_indexing[int-tensordict-compile]	0.1240ms	52.1095μs	19.1904 KOps/s	19.2644 KOps/s	$\color{#d91a1a}-0.38\%$
test_compile_indexing[int-tensordict-eager]	0.9062ms	20.0236μs	49.9411 KOps/s	50.0964 KOps/s	$\color{#d91a1a}-0.31\%$
test_compile_indexing[int-tensorclass-compile]	0.1325ms	44.1250μs	22.6629 KOps/s	22.0879 KOps/s	$\color{#35bf28}+2.60\%$
test_compile_indexing[int-tensorclass-eager]	89.1160μs	18.3608μs	54.4638 KOps/s	53.3659 KOps/s	$\color{#35bf28}+2.06\%$
test_compile_indexing[int-pytree-compile]	0.1163ms	44.3362μs	22.5549 KOps/s	22.1801 KOps/s	$\color{#35bf28}+1.69\%$
test_compile_indexing[int-pytree-eager]	70.2400μs	18.1801μs	55.0052 KOps/s	53.3025 KOps/s	$\color{#35bf28}+3.19\%$
test_mod_add[eager]	81.0510μs	35.5289μs	28.1461 KOps/s	30.6534 KOps/s	$\textbf{\color{#d91a1a}-8.18\%}$
test_mod_add[compile]	90.8990μs	47.9965μs	20.8349 KOps/s	20.8811 KOps/s	$\color{#d91a1a}-0.22\%$
test_mod_add[compile-overhead]	0.1246ms	48.6567μs	20.5522 KOps/s	20.7879 KOps/s	$\color{#d91a1a}-1.13\%$
test_mod_wrap[eager]	0.4420ms	0.2260ms	4.4250 KOps/s	4.4140 KOps/s	$\color{#35bf28}+0.25\%$
test_mod_wrap[compile]	0.3345ms	0.2076ms	4.8180 KOps/s	4.9079 KOps/s	$\color{#d91a1a}-1.83\%$
test_mod_wrap[compile-overhead]	0.3458ms	0.2015ms	4.9635 KOps/s	4.8913 KOps/s	$\color{#35bf28}+1.48\%$
test_mod_wrap_and_backward[eager]	12.3802ms	10.8314ms	92.3239 Ops/s	90.6723 Ops/s	$\color{#35bf28}+1.82\%$
test_mod_wrap_and_backward[compile]	11.7863ms	10.6300ms	94.0736 Ops/s	91.1693 Ops/s	$\color{#35bf28}+3.19\%$
test_mod_wrap_and_backward[compile-overhead]	12.1385ms	10.5996ms	94.3436 Ops/s	90.9870 Ops/s	$\color{#35bf28}+3.69\%$
test_seq_add[eager]	0.2914ms	0.1205ms	8.3016 KOps/s	8.8548 KOps/s	$\textbf{\color{#d91a1a}-6.25\%}$
test_seq_add[compile]	0.1469ms	62.7448μs	15.9376 KOps/s	16.1527 KOps/s	$\color{#d91a1a}-1.33\%$
test_seq_add[compile-overhead]	0.1590ms	59.4501μs	16.8208 KOps/s	16.4239 KOps/s	$\color{#35bf28}+2.42\%$
test_seq_wrap[eager]	0.5535ms	0.4564ms	2.1908 KOps/s	2.2526 KOps/s	$\color{#d91a1a}-2.74\%$
test_seq_wrap[compile]	0.4268ms	0.2310ms	4.3285 KOps/s	4.3791 KOps/s	$\color{#d91a1a}-1.16\%$
test_seq_wrap[compile-overhead]	0.3169ms	0.2281ms	4.3848 KOps/s	4.1671 KOps/s	$\textbf{\color{#35bf28}+5.23\%}$
test_func_call_runtime[False-eager]	1.1454ms	0.5575ms	1.7938 KOps/s	1.7993 KOps/s	$\color{#d91a1a}-0.30\%$
test_func_call_runtime[False-compile]	0.5261ms	0.4275ms	2.3390 KOps/s	2.3732 KOps/s	$\color{#d91a1a}-1.44\%$
test_func_call_runtime[False-compile-overhead]	0.5377ms	0.4274ms	2.3397 KOps/s	2.3672 KOps/s	$\color{#d91a1a}-1.16\%$
test_func_call_runtime[True-eager]	0.8799ms	0.7717ms	1.2959 KOps/s	1.3187 KOps/s	$\color{#d91a1a}-1.73\%$
test_func_call_runtime[True-compile]	0.9179ms	0.4705ms	2.1254 KOps/s	2.1440 KOps/s	$\color{#d91a1a}-0.87\%$
test_func_call_runtime[True-compile-overhead]	0.7613ms	0.4786ms	2.0894 KOps/s	2.1344 KOps/s	$\color{#d91a1a}-2.11\%$
test_func_call_cm_runtime[False-eager]	0.9431ms	0.5627ms	1.7771 KOps/s	1.7583 KOps/s	$\color{#35bf28}+1.07\%$
test_func_call_cm_runtime[False-compile]	0.8244ms	0.4299ms	2.3260 KOps/s	2.3790 KOps/s	$\color{#d91a1a}-2.23\%$
test_func_call_cm_runtime[False-compile-overhead]	0.7426ms	0.4345ms	2.3014 KOps/s	2.3607 KOps/s	$\color{#d91a1a}-2.51\%$
test_func_call_cm_runtime[True-eager]	1.0703ms	0.9258ms	1.0801 KOps/s	1.0600 KOps/s	$\color{#35bf28}+1.90\%$
test_func_call_cm_runtime[True-compile]	0.8978ms	0.5009ms	1.9962 KOps/s	2.0368 KOps/s	$\color{#d91a1a}-1.99\%$
test_func_call_cm_runtime[True-compile-overhead]	0.5939ms	0.4971ms	2.0116 KOps/s	2.0403 KOps/s	$\color{#d91a1a}-1.41\%$
test_vmap_func_call_cm_runtime[eager]	2.6963ms	1.9224ms	520.1764 Ops/s	516.2464 Ops/s	$\color{#35bf28}+0.76\%$
test_vmap_func_call_cm_runtime[compile]	0.8595ms	0.5153ms	1.9408 KOps/s	1.9195 KOps/s	$\color{#35bf28}+1.11\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.8616ms	0.5175ms	1.9323 KOps/s	1.9100 KOps/s	$\color{#35bf28}+1.17\%$
test_distributed	0.2218ms	0.1248ms	8.0158 KOps/s	7.7333 KOps/s	$\color{#35bf28}+3.65\%$
test_tdmodule	76.4330μs	27.4746μs	36.3973 KOps/s	37.7989 KOps/s	$\color{#d91a1a}-3.71\%$
test_tdmodule_dispatch	86.4710μs	51.2356μs	19.5177 KOps/s	22.1181 KOps/s	$\textbf{\color{#d91a1a}-11.76\%}$
test_tdseq	50.5140μs	30.4932μs	32.7942 KOps/s	36.3703 KOps/s	$\textbf{\color{#d91a1a}-9.83\%}$
test_tdseq_dispatch	94.2050μs	56.9624μs	17.5554 KOps/s	19.9596 KOps/s	$\textbf{\color{#d91a1a}-12.04\%}$
test_instantiation_functorch	1.7880ms	1.5412ms	648.8386 Ops/s	647.0983 Ops/s	$\color{#35bf28}+0.27\%$
test_exec_functorch	0.3798ms	0.1836ms	5.4471 KOps/s	5.5083 KOps/s	$\color{#d91a1a}-1.11\%$
test_exec_functional_call	0.3490ms	0.1773ms	5.6414 KOps/s	5.7554 KOps/s	$\color{#d91a1a}-1.98\%$
test_exec_td_decorator	0.4650ms	0.2409ms	4.1515 KOps/s	4.2156 KOps/s	$\color{#d91a1a}-1.52\%$
test_vmap_mlp_speed_decorator[True-True]	0.8045ms	0.6633ms	1.5075 KOps/s	1.5046 KOps/s	$\color{#35bf28}+0.20\%$
test_vmap_mlp_speed_decorator[True-False]	1.1434ms	0.6687ms	1.4953 KOps/s	1.4947 KOps/s	$\color{#35bf28}+0.04\%$
test_vmap_mlp_speed_decorator[False-True]	0.7411ms	0.5348ms	1.8697 KOps/s	1.8419 KOps/s	$\color{#35bf28}+1.51\%$
test_vmap_mlp_speed_decorator[False-False]	0.8448ms	0.5363ms	1.8647 KOps/s	1.8394 KOps/s	$\color{#35bf28}+1.37\%$
test_to_module_speed[True]	1.9695ms	1.3506ms	740.4122 Ops/s	746.3987 Ops/s	$\color{#d91a1a}-0.80\%$
test_to_module_speed[False]	1.4402ms	1.3217ms	756.5986 Ops/s	764.7820 Ops/s	$\color{#d91a1a}-1.07\%$
test_tc_init	91.7410μs	51.9877μs	19.2353 KOps/s	21.7189 KOps/s	$\textbf{\color{#d91a1a}-11.43\%}$
test_tc_init_nested	0.1897ms	0.1040ms	9.6136 KOps/s	10.9166 KOps/s	$\textbf{\color{#d91a1a}-11.94\%}$
test_tc_first_layer_tensor	44.5640μs	1.4966μs	668.1846 KOps/s	660.0945 KOps/s	$\color{#35bf28}+1.23\%$
test_tc_first_layer_nontensor	53.1890μs	4.7094μs	212.3433 KOps/s	212.0366 KOps/s	$\color{#35bf28}+0.14\%$
test_tc_second_layer_tensor	38.9930μs	2.7309μs	366.1822 KOps/s	356.5727 KOps/s	$\color{#35bf28}+2.69\%$
test_tc_second_layer_nontensor	45.5650μs	6.0269μs	165.9216 KOps/s	167.3146 KOps/s	$\color{#d91a1a}-0.83\%$
test_unbind	0.2289s	13.6344ms	73.3441 Ops/s	72.8498 Ops/s	$\color{#35bf28}+0.68\%$
test_full_like	9.2943ms	7.7122ms	129.6655 Ops/s	129.2819 Ops/s	$\color{#35bf28}+0.30\%$
test_zeros_like	3.5292ms	2.9792ms	335.6550 Ops/s	178.8194 Ops/s	$\textbf{\color{#35bf28}+87.71\%}$
test_ones_like	4.1501ms	3.4722ms	288.0031 Ops/s	137.6963 Ops/s	$\textbf{\color{#35bf28}+109.16\%}$
test_clone	6.5811ms	5.3672ms	186.3158 Ops/s	115.8048 Ops/s	$\textbf{\color{#35bf28}+60.89\%}$
test_squeeze	63.7580μs	12.1035μs	82.6205 KOps/s	82.9499 KOps/s	$\color{#d91a1a}-0.40\%$
test_unsqueeze	0.2236ms	91.2177μs	10.9628 KOps/s	11.0357 KOps/s	$\color{#d91a1a}-0.66\%$
test_split	0.4868ms	0.1968ms	5.0800 KOps/s	5.1942 KOps/s	$\color{#d91a1a}-2.20\%$
test_permute	0.3700ms	0.2124ms	4.7091 KOps/s	4.8297 KOps/s	$\color{#d91a1a}-2.50\%$
test_stack	32.1792ms	25.6657ms	38.9625 Ops/s	40.4728 Ops/s	$\color{#d91a1a}-3.73\%$
test_cat	25.8734ms	25.1961ms	39.6887 Ops/s	40.0315 Ops/s	$\color{#d91a1a}-0.86\%$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}42$. Worsened: $\large\color{#d91a1a}8$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	34.0400μs	11.0850μs	90.2124 KOps/s	76.9176 KOps/s	$\textbf{\color{#35bf28}+17.28\%}$
test_plain_set_stack_nested	40.2810μs	11.2598μs	88.8119 KOps/s	75.4011 KOps/s	$\textbf{\color{#35bf28}+17.79\%}$
test_plain_set_nested_inplace	44.6100μs	12.2203μs	81.8313 KOps/s	70.7826 KOps/s	$\textbf{\color{#35bf28}+15.61\%}$
test_plain_set_stack_nested_inplace	43.6210μs	12.3282μs	81.1147 KOps/s	72.9068 KOps/s	$\textbf{\color{#35bf28}+11.26\%}$
test_items	32.2710μs	2.9303μs	341.2573 KOps/s	342.4650 KOps/s	$\color{#d91a1a}-0.35\%$
test_items_nested	0.4640ms	0.3564ms	2.8062 KOps/s	2.8016 KOps/s	$\color{#35bf28}+0.17\%$
test_items_nested_locked	0.4563ms	0.3537ms	2.8272 KOps/s	2.7822 KOps/s	$\color{#35bf28}+1.62\%$
test_items_nested_leaf	83.4820μs	57.9595μs	17.2534 KOps/s	17.2060 KOps/s	$\color{#35bf28}+0.28\%$
test_items_stack_nested	0.4014ms	0.3581ms	2.7924 KOps/s	2.7830 KOps/s	$\color{#35bf28}+0.34\%$
test_items_stack_nested_leaf	83.3410μs	58.9939μs	16.9509 KOps/s	16.4633 KOps/s	$\color{#35bf28}+2.96\%$
test_items_stack_nested_locked	0.4060ms	0.3608ms	2.7717 KOps/s	2.7891 KOps/s	$\color{#d91a1a}-0.62\%$
test_keys	24.5810μs	3.4727μs	287.9573 KOps/s	273.2684 KOps/s	$\textbf{\color{#35bf28}+5.38\%}$
test_keys_nested	0.1113ms	80.8643μs	12.3664 KOps/s	12.2847 KOps/s	$\color{#35bf28}+0.66\%$
test_keys_nested_locked	0.7127ms	86.8078μs	11.5197 KOps/s	11.4619 KOps/s	$\color{#35bf28}+0.50\%$
test_keys_nested_leaf	0.1012ms	72.3015μs	13.8310 KOps/s	14.0018 KOps/s	$\color{#d91a1a}-1.22\%$
test_keys_stack_nested	0.1178ms	81.5219μs	12.2666 KOps/s	12.0567 KOps/s	$\color{#35bf28}+1.74\%$
test_keys_stack_nested_leaf	0.1262ms	72.0620μs	13.8769 KOps/s	13.5454 KOps/s	$\color{#35bf28}+2.45\%$
test_keys_stack_nested_locked	0.1161ms	87.1515μs	11.4743 KOps/s	11.3159 KOps/s	$\color{#35bf28}+1.40\%$
test_values	3.4141μs	0.8398μs	1.1908 MOps/s	1.1716 MOps/s	$\color{#35bf28}+1.63\%$
test_values_nested	63.4910μs	35.1217μs	28.4724 KOps/s	29.2252 KOps/s	$\color{#d91a1a}-2.58\%$
test_values_nested_locked	62.3210μs	36.5947μs	27.3264 KOps/s	27.9452 KOps/s	$\color{#d91a1a}-2.21\%$
test_values_nested_leaf	65.0410μs	39.4898μs	25.3230 KOps/s	25.9083 KOps/s	$\color{#d91a1a}-2.26\%$
test_values_stack_nested	67.7710μs	34.6148μs	28.8893 KOps/s	28.8278 KOps/s	$\color{#35bf28}+0.21\%$
test_values_stack_nested_leaf	71.9310μs	39.3860μs	25.3897 KOps/s	25.5769 KOps/s	$\color{#d91a1a}-0.73\%$
test_values_stack_nested_locked	67.9810μs	36.7076μs	27.2423 KOps/s	27.6976 KOps/s	$\color{#d91a1a}-1.64\%$
test_membership	1.5835μs	0.5157μs	1.9390 MOps/s	1.9934 MOps/s	$\color{#d91a1a}-2.73\%$
test_membership_nested	22.5410μs	2.0979μs	476.6711 KOps/s	480.0489 KOps/s	$\color{#d91a1a}-0.70\%$
test_membership_nested_leaf	18.7855μs	2.0520μs	487.3357 KOps/s	487.8884 KOps/s	$\color{#d91a1a}-0.11\%$
test_membership_stacked_nested	38.4010μs	2.0784μs	481.1378 KOps/s	466.5651 KOps/s	$\color{#35bf28}+3.12\%$
test_membership_stacked_nested_leaf	31.0700μs	2.0964μs	477.0123 KOps/s	462.3931 KOps/s	$\color{#35bf28}+3.16\%$
test_membership_nested_last	25.5000μs	3.1293μs	319.5590 KOps/s	321.6692 KOps/s	$\color{#d91a1a}-0.66\%$
test_membership_nested_leaf_last	37.9900μs	3.1260μs	319.8961 KOps/s	317.3016 KOps/s	$\color{#35bf28}+0.82\%$
test_membership_stacked_nested_last	31.7600μs	3.1359μs	318.8903 KOps/s	276.1199 KOps/s	$\textbf{\color{#35bf28}+15.49\%}$
test_membership_stacked_nested_leaf_last	31.6710μs	3.1082μs	321.7263 KOps/s	273.8914 KOps/s	$\textbf{\color{#35bf28}+17.46\%}$
test_nested_getleaf	33.1710μs	6.1372μs	162.9401 KOps/s	159.1570 KOps/s	$\color{#35bf28}+2.38\%$
test_nested_get	39.3810μs	5.8297μs	171.5355 KOps/s	169.0485 KOps/s	$\color{#35bf28}+1.47\%$
test_stacked_getleaf	19.9910μs	6.2097μs	161.0379 KOps/s	161.9250 KOps/s	$\color{#d91a1a}-0.55\%$
test_stacked_get	30.3400μs	5.8413μs	171.1960 KOps/s	171.4933 KOps/s	$\color{#d91a1a}-0.17\%$
test_nested_getitemleaf	21.1310μs	6.2836μs	159.1442 KOps/s	157.6107 KOps/s	$\color{#35bf28}+0.97\%$
test_nested_getitem	36.1110μs	5.9868μs	167.0355 KOps/s	168.2686 KOps/s	$\color{#d91a1a}-0.73\%$
test_stacked_getitemleaf	49.9900μs	6.3818μs	156.6949 KOps/s	159.9121 KOps/s	$\color{#d91a1a}-2.01\%$
test_stacked_getitem	33.1910μs	5.9576μs	167.8528 KOps/s	168.7413 KOps/s	$\color{#d91a1a}-0.53\%$
test_lock_nested	9.3350ms	0.3864ms	2.5881 KOps/s	2.5568 KOps/s	$\color{#35bf28}+1.23\%$
test_lock_stack_nested	0.3811ms	0.3463ms	2.8877 KOps/s	2.8494 KOps/s	$\color{#35bf28}+1.35\%$
test_unlock_nested	0.7719ms	0.3164ms	3.1603 KOps/s	3.0863 KOps/s	$\color{#35bf28}+2.40\%$
test_unlock_stack_nested	0.3227ms	0.2838ms	3.5231 KOps/s	3.4458 KOps/s	$\color{#35bf28}+2.25\%$
test_flatten_speed	0.1284ms	75.1137μs	13.3131 KOps/s	13.2805 KOps/s	$\color{#35bf28}+0.25\%$
test_unflatten_speed	0.3660ms	0.3238ms	3.0883 KOps/s	3.0698 KOps/s	$\color{#35bf28}+0.60\%$
test_common_ops	1.6244ms	0.5727ms	1.7462 KOps/s	1.5296 KOps/s	$\textbf{\color{#35bf28}+14.16\%}$
test_creation	0.1031ms	1.7559μs	569.5175 KOps/s	566.3543 KOps/s	$\color{#35bf28}+0.56\%$
test_creation_empty	40.6410μs	6.4642μs	154.6978 KOps/s	102.9568 KOps/s	$\textbf{\color{#35bf28}+50.26\%}$
test_creation_nested_1	34.1510μs	8.1592μs	122.5611 KOps/s	87.5482 KOps/s	$\textbf{\color{#35bf28}+39.99\%}$
test_creation_nested_2	46.1900μs	10.9249μs	91.5343 KOps/s	70.5961 KOps/s	$\textbf{\color{#35bf28}+29.66\%}$
test_clone	90.3220μs	10.8504μs	92.1625 KOps/s	86.5107 KOps/s	$\textbf{\color{#35bf28}+6.53\%}$
test_getitem[int]	1.8172ms	10.7879μs	92.6966 KOps/s	90.3369 KOps/s	$\color{#35bf28}+2.61\%$
test_getitem[slice_int]	0.1128ms	20.8179μs	48.0356 KOps/s	45.2766 KOps/s	$\textbf{\color{#35bf28}+6.09\%}$
test_getitem[range]	0.1268ms	38.1071μs	26.2418 KOps/s	25.4362 KOps/s	$\color{#35bf28}+3.17\%$
test_getitem[tuple]	0.1088ms	18.3570μs	54.4750 KOps/s	52.1526 KOps/s	$\color{#35bf28}+4.45\%$
test_getitem[list]	0.2219ms	33.5584μs	29.7988 KOps/s	28.5515 KOps/s	$\color{#35bf28}+4.37\%$
test_setitem_dim[int]	27.8200μs	19.2318μs	51.9971 KOps/s	48.8281 KOps/s	$\textbf{\color{#35bf28}+6.49\%}$
test_setitem_dim[slice_int]	61.8310μs	39.2173μs	25.4990 KOps/s	24.9884 KOps/s	$\color{#35bf28}+2.04\%$
test_setitem_dim[range]	76.8310μs	53.6766μs	18.6301 KOps/s	18.5817 KOps/s	$\color{#35bf28}+0.26\%$
test_setitem_dim[tuple]	53.3110μs	32.9202μs	30.3765 KOps/s	30.3809 KOps/s	$\color{#d91a1a}-0.01\%$
test_setitem	95.7920μs	14.3987μs	69.4508 KOps/s	59.0512 KOps/s	$\textbf{\color{#35bf28}+17.61\%}$
test_set	91.3820μs	13.8150μs	72.3848 KOps/s	60.1896 KOps/s	$\textbf{\color{#35bf28}+20.26\%}$
test_set_shared	1.4321ms	0.1492ms	6.7022 KOps/s	6.5795 KOps/s	$\color{#35bf28}+1.86\%$
test_update	0.3182ms	15.6245μs	64.0022 KOps/s	50.1131 KOps/s	$\textbf{\color{#35bf28}+27.72\%}$
test_update_nested	92.7220μs	20.9369μs	47.7625 KOps/s	38.8867 KOps/s	$\textbf{\color{#35bf28}+22.82\%}$
test_update__nested	0.7050ms	25.7106μs	38.8945 KOps/s	37.3559 KOps/s	$\color{#35bf28}+4.12\%$
test_set_nested	99.4020μs	15.1834μs	65.8614 KOps/s	56.6265 KOps/s	$\textbf{\color{#35bf28}+16.31\%}$
test_set_nested_new	81.6010μs	17.4666μs	57.2521 KOps/s	50.3616 KOps/s	$\textbf{\color{#35bf28}+13.68\%}$
test_select	0.1287ms	29.4802μs	33.9211 KOps/s	30.9265 KOps/s	$\textbf{\color{#35bf28}+9.68\%}$
test_select_nested	93.9810μs	43.6105μs	22.9303 KOps/s	22.7372 KOps/s	$\color{#35bf28}+0.85\%$
test_exclude_nested	93.0910μs	62.5688μs	15.9824 KOps/s	15.6221 KOps/s	$\color{#35bf28}+2.31\%$
test_empty[True]	0.3196ms	0.2865ms	3.4902 KOps/s	3.4342 KOps/s	$\color{#35bf28}+1.63\%$
test_empty[False]	3.7651μs	0.8246μs	1.2127 MOps/s	1.2093 MOps/s	$\color{#35bf28}+0.28\%$
test_to	87.7020μs	57.2939μs	17.4539 KOps/s	17.1251 KOps/s	$\color{#35bf28}+1.92\%$
test_to_nonblocking	0.1031ms	48.6458μs	20.5567 KOps/s	19.8840 KOps/s	$\color{#35bf28}+3.38\%$
test_unbind_speed	0.2732ms	0.2381ms	4.1999 KOps/s	4.1215 KOps/s	$\color{#35bf28}+1.90\%$
test_unbind_speed_stack0	0.3419ms	0.2346ms	4.2629 KOps/s	4.1445 KOps/s	$\color{#35bf28}+2.85\%$
test_unbind_speed_stack1	92.1329ms	0.6714ms	1.4893 KOps/s	1.4910 KOps/s	$\color{#d91a1a}-0.11\%$
test_split	92.9753ms	1.7356ms	576.1769 Ops/s	617.0176 Ops/s	$\textbf{\color{#d91a1a}-6.62\%}$
test_chunk	94.3863ms	1.5990ms	625.3963 Ops/s	615.4523 Ops/s	$\color{#35bf28}+1.62\%$
test_consolidate[False-None]	2.9649ms	2.6998ms	370.4008 Ops/s	371.5907 Ops/s	$\color{#d91a1a}-0.32\%$
test_consolidate[default-None]	1.8059ms	1.7055ms	586.3347 Ops/s	582.7741 Ops/s	$\color{#35bf28}+0.61\%$
test_consolidate[reduce-overhead-None]	1.8356ms	1.7481ms	572.0364 Ops/s	568.0549 Ops/s	$\color{#35bf28}+0.70\%$
test_consolidate_njt[False-None]	6.7813ms	6.6240ms	150.9662 Ops/s	150.7512 Ops/s	$\color{#35bf28}+0.14\%$
test_to[False-False-None]	1.8622ms	1.7820ms	561.1712 Ops/s	561.5592 Ops/s	$\color{#d91a1a}-0.07\%$
test_to[True-False-None]	1.6435ms	1.3922ms	718.2806 Ops/s	720.4531 Ops/s	$\color{#d91a1a}-0.30\%$
test_to[within-False-None]	4.4798ms	4.2464ms	235.4932 Ops/s	234.4219 Ops/s	$\color{#35bf28}+0.46\%$
test_to[True-default-None]	5.6555ms	5.4458ms	183.6293 Ops/s	183.7283 Ops/s	$\color{#d91a1a}-0.05\%$
test_to_njt[False-False-None]	7.2524ms	7.0795ms	141.2526 Ops/s	141.7970 Ops/s	$\color{#d91a1a}-0.38\%$
test_to_njt[True-False-None]	5.7924ms	5.6350ms	177.4621 Ops/s	177.6357 Ops/s	$\color{#d91a1a}-0.10\%$
test_to_njt[within-False-None]	12.4800ms	12.3673ms	80.8581 Ops/s	80.9618 Ops/s	$\color{#d91a1a}-0.13\%$
test_creation[device0]	0.4601ms	81.3521μs	12.2922 KOps/s	12.6116 KOps/s	$\color{#d91a1a}-2.53\%$
test_creation_from_tensor	0.4402ms	83.3588μs	11.9963 KOps/s	11.9879 KOps/s	$\color{#35bf28}+0.07\%$
test_add_one[memmap_tensor0]	0.2511ms	7.0653μs	141.5371 KOps/s	138.8560 KOps/s	$\color{#35bf28}+1.93\%$
test_contiguous[memmap_tensor0]	1.9741μs	0.4242μs	2.3574 MOps/s	2.4111 MOps/s	$\color{#d91a1a}-2.23\%$
test_stack[memmap_tensor0]	44.8410μs	4.4069μs	226.9158 KOps/s	221.0067 KOps/s	$\color{#35bf28}+2.67\%$
test_memmaptd_index	0.5853ms	0.2549ms	3.9224 KOps/s	3.8064 KOps/s	$\color{#35bf28}+3.05\%$
test_memmaptd_index_astensor	0.6179ms	0.3168ms	3.1562 KOps/s	3.0715 KOps/s	$\color{#35bf28}+2.76\%$
test_memmaptd_index_op	0.9842ms	0.5739ms	1.7425 KOps/s	1.5601 KOps/s	$\textbf{\color{#35bf28}+11.69\%}$
test_serialize_model	0.1312s	0.1304s	7.6708 Ops/s	7.6490 Ops/s	$\color{#35bf28}+0.29\%$
test_serialize_model_pickle	1.3508s	1.2164s	0.8221 Ops/s	0.8215 Ops/s	$\color{#35bf28}+0.07\%$
test_serialize_weights	0.4309s	0.1729s	5.7826 Ops/s	7.6932 Ops/s	$\textbf{\color{#d91a1a}-24.84\%}$
test_serialize_weights_returnearly	0.3254s	53.9288ms	18.5430 Ops/s	23.3750 Ops/s	$\textbf{\color{#d91a1a}-20.67\%}$
test_serialize_weights_pickle	1.3478s	1.2142s	0.8236 Ops/s	0.8222 Ops/s	$\color{#35bf28}+0.17\%$
test_reshape_pytree	0.1169ms	22.0613μs	45.3283 KOps/s	43.6192 KOps/s	$\color{#35bf28}+3.92\%$
test_reshape_td	60.2110μs	26.8733μs	37.2116 KOps/s	35.7420 KOps/s	$\color{#35bf28}+4.11\%$
test_view_pytree	55.6910μs	22.0557μs	45.3398 KOps/s	44.4793 KOps/s	$\color{#35bf28}+1.93\%$
test_view_td	67.2010μs	31.2274μs	32.0231 KOps/s	32.4737 KOps/s	$\color{#d91a1a}-1.39\%$
test_unbind_pytree	70.3410μs	28.0764μs	35.6171 KOps/s	34.7274 KOps/s	$\color{#35bf28}+2.56\%$
test_unbind_td	0.7433ms	36.9875μs	27.0362 KOps/s	26.5027 KOps/s	$\color{#35bf28}+2.01\%$
test_split_pytree	0.1079ms	29.9144μs	33.4287 KOps/s	32.0448 KOps/s	$\color{#35bf28}+4.32\%$
test_split_td	0.9270ms	38.8244μs	25.7570 KOps/s	24.9253 KOps/s	$\color{#35bf28}+3.34\%$
test_add_pytree	0.1479ms	34.8154μs	28.7229 KOps/s	27.1706 KOps/s	$\textbf{\color{#35bf28}+5.71\%}$
test_add_td	94.4320μs	46.0840μs	21.6995 KOps/s	18.5618 KOps/s	$\textbf{\color{#35bf28}+16.90\%}$
test_compile_add_one_nested[tensordict-compile]	0.1826ms	0.1219ms	8.2050 KOps/s	8.0802 KOps/s	$\color{#35bf28}+1.54\%$
test_compile_add_one_nested[tensordict-eager]	0.2191ms	0.1298ms	7.7031 KOps/s	7.5649 KOps/s	$\color{#35bf28}+1.83\%$
test_compile_add_one_nested[pytree-compile]	0.1665ms	96.0826μs	10.4077 KOps/s	10.1062 KOps/s	$\color{#35bf28}+2.98\%$
test_compile_add_one_nested[pytree-eager]	0.2375ms	0.1510ms	6.6232 KOps/s	6.5003 KOps/s	$\color{#35bf28}+1.89\%$
test_compile_copy_nested[tensordict-compile]	57.0510μs	23.3472μs	42.8317 KOps/s	44.3173 KOps/s	$\color{#d91a1a}-3.35\%$
test_compile_copy_nested[tensordict-eager]	80.6710μs	29.5168μs	33.8790 KOps/s	33.9032 KOps/s	$\color{#d91a1a}-0.07\%$
test_compile_copy_nested[pytree-compile]	0.2317ms	65.4004μs	15.2904 KOps/s	15.1686 KOps/s	$\color{#35bf28}+0.80\%$
test_compile_copy_nested[pytree-eager]	98.2120μs	49.6872μs	20.1259 KOps/s	20.2425 KOps/s	$\color{#d91a1a}-0.58\%$
test_compile_add_one_flat[tensordict-compile]	0.2109ms	0.1415ms	7.0664 KOps/s	6.9587 KOps/s	$\color{#35bf28}+1.55\%$
test_compile_add_one_flat[tensordict-eager]	0.3043ms	0.2176ms	4.5961 KOps/s	4.6301 KOps/s	$\color{#d91a1a}-0.73\%$
test_compile_add_one_flat[tensorclass-compile]	0.1487ms	98.0907μs	10.1946 KOps/s	10.1776 KOps/s	$\color{#35bf28}+0.17\%$
test_compile_add_one_flat[tensorclass-eager]	0.1353ms	54.1837μs	18.4557 KOps/s	17.8313 KOps/s	$\color{#35bf28}+3.50\%$
test_compile_add_one_flat[pytree-compile]	0.2170ms	0.1362ms	7.3407 KOps/s	7.2715 KOps/s	$\color{#35bf28}+0.95\%$
test_compile_add_one_flat[pytree-eager]	0.5547ms	0.4922ms	2.0318 KOps/s	2.0304 KOps/s	$\color{#35bf28}+0.07\%$
test_compile_add_self_flat[tensordict-eager]	0.3782ms	0.2629ms	3.8041 KOps/s	3.8398 KOps/s	$\color{#d91a1a}-0.93\%$
test_compile_add_self_flat[tensordict-compile]	0.2064ms	0.1480ms	6.7572 KOps/s	6.9820 KOps/s	$\color{#d91a1a}-3.22\%$
test_compile_add_self_flat[tensorclass-eager]	0.1546ms	65.5763μs	15.2494 KOps/s	15.0482 KOps/s	$\color{#35bf28}+1.34\%$
test_compile_add_self_flat[tensorclass-compile]	0.1557ms	0.1018ms	9.8223 KOps/s	10.1080 KOps/s	$\color{#d91a1a}-2.83\%$
test_compile_add_self_flat[pytree-eager]	0.4770ms	0.4174ms	2.3956 KOps/s	2.4252 KOps/s	$\color{#d91a1a}-1.22\%$
test_compile_add_self_flat[pytree-compile]	0.1778ms	0.1352ms	7.3988 KOps/s	7.3937 KOps/s	$\color{#35bf28}+0.07\%$
test_compile_copy_flat[tensordict-compile]	0.1010ms	19.3046μs	51.8012 KOps/s	55.8098 KOps/s	$\textbf{\color{#d91a1a}-7.18\%}$
test_compile_copy_flat[tensordict-eager]	70.5510μs	30.9181μs	32.3435 KOps/s	32.2729 KOps/s	$\color{#35bf28}+0.22\%$
test_compile_copy_flat[pytree-compile]	0.1554ms	70.2413μs	14.2366 KOps/s	14.1142 KOps/s	$\color{#35bf28}+0.87\%$
test_compile_copy_flat[pytree-eager]	91.1920μs	51.0783μs	19.5778 KOps/s	19.1262 KOps/s	$\color{#35bf28}+2.36\%$
test_compile_assign_and_add[tensordict-compile]	1.6261ms	0.3891ms	2.5698 KOps/s	2.1847 KOps/s	$\textbf{\color{#35bf28}+17.62\%}$
test_compile_assign_and_add[tensordict-eager]	2.7811ms	2.6668ms	374.9757 Ops/s	375.8063 Ops/s	$\color{#d91a1a}-0.22\%$
test_compile_assign_and_add[pytree-compile]	1.6445ms	0.4015ms	2.4907 KOps/s	2.2671 KOps/s	$\textbf{\color{#35bf28}+9.86\%}$
test_compile_assign_and_add[pytree-eager]	2.8505ms	2.7475ms	363.9647 Ops/s	369.6176 Ops/s	$\color{#d91a1a}-1.53\%$
test_compile_indexing[tensor-tensordict-compile]	0.6210ms	0.1213ms	8.2425 KOps/s	8.3514 KOps/s	$\color{#d91a1a}-1.30\%$
test_compile_indexing[tensor-tensordict-eager]	0.6249ms	84.5875μs	11.8221 KOps/s	11.5750 KOps/s	$\color{#35bf28}+2.13\%$
test_compile_indexing[tensor-tensorclass-compile]	0.3760ms	0.1147ms	8.7212 KOps/s	8.8407 KOps/s	$\color{#d91a1a}-1.35\%$
test_compile_indexing[tensor-tensorclass-eager]	0.1868ms	72.2551μs	13.8398 KOps/s	13.9721 KOps/s	$\color{#d91a1a}-0.95\%$
test_compile_indexing[tensor-pytree-compile]	0.1726ms	0.1160ms	8.6176 KOps/s	9.1690 KOps/s	$\textbf{\color{#d91a1a}-6.01\%}$
test_compile_indexing[tensor-pytree-eager]	0.1643ms	71.1523μs	14.0544 KOps/s	14.0531 KOps/s	$+0.01\%$
test_compile_indexing[slice-tensordict-compile]	0.1415ms	0.1012ms	9.8829 KOps/s	9.8154 KOps/s	$\color{#35bf28}+0.69\%$
test_compile_indexing[slice-tensordict-eager]	0.1421ms	17.6421μs	56.6826 KOps/s	54.4889 KOps/s	$\color{#35bf28}+4.03\%$
test_compile_indexing[slice-tensorclass-compile]	0.1275ms	97.4449μs	10.2622 KOps/s	10.2480 KOps/s	$\color{#35bf28}+0.14\%$
test_compile_indexing[slice-tensorclass-eager]	49.6010μs	16.0972μs	62.1226 KOps/s	60.8304 KOps/s	$\color{#35bf28}+2.12\%$
test_compile_indexing[slice-pytree-compile]	0.1458ms	99.1103μs	10.0898 KOps/s	10.0893 KOps/s	$+0.01\%$
test_compile_indexing[slice-pytree-eager]	47.7210μs	16.0060μs	62.4764 KOps/s	61.3001 KOps/s	$\color{#35bf28}+1.92\%$
test_compile_indexing[int-tensordict-compile]	0.1527ms	0.1016ms	9.8453 KOps/s	9.4423 KOps/s	$\color{#35bf28}+4.27\%$
test_compile_indexing[int-tensordict-eager]	0.5581ms	17.5086μs	57.1147 KOps/s	54.9659 KOps/s	$\color{#35bf28}+3.91\%$
test_compile_indexing[int-tensorclass-compile]	0.1407ms	97.9524μs	10.2090 KOps/s	9.9642 KOps/s	$\color{#35bf28}+2.46\%$
test_compile_indexing[int-tensorclass-eager]	0.1633ms	16.5637μs	60.3732 KOps/s	61.6332 KOps/s	$\color{#d91a1a}-2.04\%$
test_compile_indexing[int-pytree-compile]	0.1415ms	97.9685μs	10.2074 KOps/s	10.0638 KOps/s	$\color{#35bf28}+1.43\%$
test_compile_indexing[int-pytree-eager]	56.9510μs	15.9348μs	62.7556 KOps/s	61.2801 KOps/s	$\color{#35bf28}+2.41\%$
test_mod_add[eager]	80.1210μs	37.3412μs	26.7801 KOps/s	24.2318 KOps/s	$\textbf{\color{#35bf28}+10.52\%}$
test_mod_add[compile]	0.3656ms	82.3187μs	12.1479 KOps/s	11.9886 KOps/s	$\color{#35bf28}+1.33\%$
test_mod_add[compile-overhead]	0.3214ms	0.1657ms	6.0366 KOps/s	5.6255 KOps/s	$\textbf{\color{#35bf28}+7.31\%}$
test_mod_wrap[eager]	0.3442ms	0.2518ms	3.9722 KOps/s	3.8365 KOps/s	$\color{#35bf28}+3.54\%$
test_mod_wrap[compile]	0.9801ms	0.2884ms	3.4673 KOps/s	3.4355 KOps/s	$\color{#35bf28}+0.93\%$
test_mod_wrap[compile-overhead]	7.1876ms	3.7471ms	266.8699 Ops/s	275.3144 Ops/s	$\color{#d91a1a}-3.07\%$
test_mod_wrap_and_backward[eager]	1.5096ms	1.3748ms	727.3734 Ops/s	674.3795 Ops/s	$\textbf{\color{#35bf28}+7.86\%}$
test_mod_wrap_and_backward[compile]	1.4310ms	1.2821ms	779.9813 Ops/s	715.9103 Ops/s	$\textbf{\color{#35bf28}+8.95\%}$
test_mod_wrap_and_backward[compile-overhead]	1.3816ms	0.9415ms	1.0622 KOps/s	958.9105 Ops/s	$\textbf{\color{#35bf28}+10.77\%}$
test_seq_add[eager]	0.2349ms	0.1134ms	8.8208 KOps/s	8.1944 KOps/s	$\textbf{\color{#35bf28}+7.64\%}$
test_seq_add[compile]	0.1676ms	88.3963μs	11.3127 KOps/s	11.1439 KOps/s	$\color{#35bf28}+1.51\%$
test_seq_add[compile-overhead]	0.1802ms	0.1286ms	7.7771 KOps/s	7.2912 KOps/s	$\textbf{\color{#35bf28}+6.66\%}$
test_seq_wrap[eager]	0.5229ms	0.4127ms	2.4228 KOps/s	2.2794 KOps/s	$\textbf{\color{#35bf28}+6.29\%}$
test_seq_wrap[compile]	0.3872ms	0.3138ms	3.1866 KOps/s	3.2472 KOps/s	$\color{#d91a1a}-1.87\%$
test_seq_wrap[compile-overhead]	0.2960ms	0.2286ms	4.3740 KOps/s	4.3825 KOps/s	$\color{#d91a1a}-0.19\%$
test_func_call_runtime[False-eager]	0.8436ms	0.7651ms	1.3070 KOps/s	1.2933 KOps/s	$\color{#35bf28}+1.06\%$
test_func_call_runtime[False-compile]	0.8339ms	0.7540ms	1.3263 KOps/s	1.3125 KOps/s	$\color{#35bf28}+1.05\%$
test_func_call_runtime[False-compile-overhead]	0.5196ms	0.3697ms	2.7048 KOps/s	2.7100 KOps/s	$\color{#d91a1a}-0.19\%$
test_func_call_runtime[True-eager]	1.0303ms	0.9259ms	1.0800 KOps/s	1.0678 KOps/s	$\color{#35bf28}+1.15\%$
test_func_call_runtime[True-compile]	0.8753ms	0.7848ms	1.2742 KOps/s	1.2774 KOps/s	$\color{#d91a1a}-0.25\%$
test_func_call_runtime[True-compile-overhead]	0.4721ms	0.3933ms	2.5423 KOps/s	2.5754 KOps/s	$\color{#d91a1a}-1.28\%$
test_func_call_cm_runtime[False-eager]	0.9232ms	0.8059ms	1.2409 KOps/s	1.3030 KOps/s	$\color{#d91a1a}-4.76\%$
test_func_call_cm_runtime[False-compile]	0.9438ms	0.7985ms	1.2524 KOps/s	1.3062 KOps/s	$\color{#d91a1a}-4.12\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4287ms	0.3708ms	2.6967 KOps/s	2.6858 KOps/s	$\color{#35bf28}+0.41\%$
test_func_call_cm_runtime[True-eager]	1.1712ms	1.0290ms	971.7875 Ops/s	958.7190 Ops/s	$\color{#35bf28}+1.36\%$
test_func_call_cm_runtime[True-compile]	0.9189ms	0.8038ms	1.2441 KOps/s	1.2350 KOps/s	$\color{#35bf28}+0.74\%$
test_func_call_cm_runtime[True-compile-overhead]	0.5363ms	0.4154ms	2.4071 KOps/s	2.4026 KOps/s	$\color{#35bf28}+0.19\%$
test_vmap_func_call_cm_runtime[eager]	2.5848ms	2.1221ms	471.2321 Ops/s	468.3320 Ops/s	$\color{#35bf28}+0.62\%$
test_vmap_func_call_cm_runtime[compile]	0.8841ms	0.8164ms	1.2248 KOps/s	1.2048 KOps/s	$\color{#35bf28}+1.66\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.4776ms	0.4169ms	2.3987 KOps/s	2.3957 KOps/s	$\color{#35bf28}+0.12\%$
test_distributed	2.9458ms	0.1761ms	5.6801 KOps/s	8.6041 KOps/s	$\textbf{\color{#d91a1a}-33.98\%}$
test_tdmodule	70.6610μs	18.6156μs	53.7183 KOps/s	48.3701 KOps/s	$\textbf{\color{#35bf28}+11.06\%}$
test_tdmodule_dispatch	76.7010μs	33.2680μs	30.0589 KOps/s	26.8470 KOps/s	$\textbf{\color{#35bf28}+11.96\%}$
test_tdseq	39.6000μs	19.4427μs	51.4333 KOps/s	45.7709 KOps/s	$\textbf{\color{#35bf28}+12.37\%}$
test_tdseq_dispatch	66.2210μs	36.2528μs	27.5841 KOps/s	24.5815 KOps/s	$\textbf{\color{#35bf28}+12.21\%}$
test_instantiation_functorch	1.9840ms	1.5683ms	637.6489 Ops/s	619.3383 Ops/s	$\color{#35bf28}+2.96\%$
test_exec_functorch	0.1864ms	0.1458ms	6.8567 KOps/s	6.6635 KOps/s	$\color{#35bf28}+2.90\%$
test_exec_functional_call	0.1777ms	0.1403ms	7.1255 KOps/s	6.8237 KOps/s	$\color{#35bf28}+4.42\%$
test_exec_td_decorator	0.3815ms	0.1875ms	5.3334 KOps/s	5.1595 KOps/s	$\color{#35bf28}+3.37\%$
test_vmap_mlp_speed_decorator[True-True]	0.8494ms	0.6926ms	1.4438 KOps/s	1.4330 KOps/s	$\color{#35bf28}+0.75\%$
test_vmap_mlp_speed_decorator[True-False]	0.8196ms	0.6896ms	1.4501 KOps/s	1.4313 KOps/s	$\color{#35bf28}+1.32\%$
test_vmap_mlp_speed_decorator[False-True]	0.7276ms	0.6051ms	1.6526 KOps/s	1.6515 KOps/s	$\color{#35bf28}+0.07\%$
test_vmap_mlp_speed_decorator[False-False]	0.7545ms	0.6282ms	1.5918 KOps/s	1.6459 KOps/s	$\color{#d91a1a}-3.28\%$
test_vmap_transformer_speed_decorator[True-True]	19.6567ms	19.5553ms	51.1369 Ops/s	51.3397 Ops/s	$\color{#d91a1a}-0.40\%$
test_vmap_transformer_speed_decorator[True-False]	19.6729ms	19.5626ms	51.1178 Ops/s	51.2582 Ops/s	$\color{#d91a1a}-0.27\%$
test_vmap_transformer_speed_decorator[False-True]	19.6100ms	19.4817ms	51.3303 Ops/s	51.8067 Ops/s	$\color{#d91a1a}-0.92\%$
test_vmap_transformer_speed_decorator[False-False]	19.5067ms	19.4247ms	51.4809 Ops/s	51.7390 Ops/s	$\color{#d91a1a}-0.50\%$
test_to_module_speed[True]	1.0624ms	0.9785ms	1.0220 KOps/s	1.0206 KOps/s	$\color{#35bf28}+0.14\%$
test_to_module_speed[False]	1.5194ms	0.9570ms	1.0450 KOps/s	1.0500 KOps/s	$\color{#d91a1a}-0.48\%$
test_tc_init	66.2810μs	35.8672μs	27.8806 KOps/s	24.8393 KOps/s	$\textbf{\color{#35bf28}+12.24\%}$
test_tc_init_nested	0.1078ms	71.2288μs	14.0393 KOps/s	12.2377 KOps/s	$\textbf{\color{#35bf28}+14.72\%}$
test_tc_first_layer_tensor	5.3916μs	0.6915μs	1.4462 MOps/s	1.3234 MOps/s	$\textbf{\color{#35bf28}+9.28\%}$
test_tc_first_layer_nontensor	35.7500μs	2.3298μs	429.2214 KOps/s	429.6865 KOps/s	$\color{#d91a1a}-0.11\%$
test_tc_second_layer_tensor	17.7077μs	1.4245μs	701.9802 KOps/s	661.5087 KOps/s	$\textbf{\color{#35bf28}+6.12\%}$
test_tc_second_layer_nontensor	47.2000μs	3.0561μs	327.2112 KOps/s	324.9279 KOps/s	$\color{#35bf28}+0.70\%$
test_unbind	0.2391s	10.2172ms	97.8743 Ops/s	143.4284 Ops/s	$\textbf{\color{#d91a1a}-31.76\%}$
test_full_like	9.6371ms	9.3140ms	107.3650 Ops/s	108.0953 Ops/s	$\color{#d91a1a}-0.68\%$
test_zeros_like	9.3373ms	7.2741ms	137.4742 Ops/s	230.8319 Ops/s	$\textbf{\color{#d91a1a}-40.44\%}$
test_ones_like	5.0358ms	4.2117ms	237.4336 Ops/s	231.3204 Ops/s	$\color{#35bf28}+2.64\%$
test_clone	6.7545ms	6.4301ms	155.5194 Ops/s	155.0675 Ops/s	$\color{#35bf28}+0.29\%$
test_squeeze	81.1120μs	9.3438μs	107.0226 KOps/s	103.0522 KOps/s	$\color{#35bf28}+3.85\%$
test_unsqueeze	0.1249ms	71.2058μs	14.0438 KOps/s	13.8102 KOps/s	$\color{#35bf28}+1.69\%$
test_split	0.3516ms	0.1592ms	6.2821 KOps/s	6.0790 KOps/s	$\color{#35bf28}+3.34\%$
test_permute	0.2295ms	0.1817ms	5.5043 KOps/s	5.3838 KOps/s	$\color{#35bf28}+2.24\%$
test_stack	51.7166ms	50.7568ms	19.7018 Ops/s	19.6638 Ops/s	$\color{#35bf28}+0.19\%$
test_cat	51.5214ms	50.7187ms	19.7166 Ops/s	19.6967 Ops/s	$\color{#35bf28}+0.10\%$