[CI] Fix nightly build

[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: $\large\color{#35bf28}13$. Worsened: $\large\color{#d91a1a}33$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	40.5360μs	21.0946μs	47.4054 KOps/s	50.3246 KOps/s	$\textbf{\color{#d91a1a}-5.80\%}$
test_plain_set_stack_nested	54.0510μs	21.2337μs	47.0950 KOps/s	49.3381 KOps/s	$\color{#d91a1a}-4.55\%$
test_plain_set_nested_inplace	90.7900μs	22.9773μs	43.5213 KOps/s	45.8995 KOps/s	$\textbf{\color{#d91a1a}-5.18\%}$
test_plain_set_stack_nested_inplace	0.1058ms	22.8159μs	43.8291 KOps/s	45.9830 KOps/s	$\color{#d91a1a}-4.68\%$
test_items	41.0570μs	4.1545μs	240.7036 KOps/s	236.7977 KOps/s	$\color{#35bf28}+1.65\%$
test_items_nested	0.5112ms	0.4010ms	2.4939 KOps/s	2.4717 KOps/s	$\color{#35bf28}+0.90\%$
test_items_nested_locked	0.8235ms	0.4027ms	2.4832 KOps/s	2.4633 KOps/s	$\color{#35bf28}+0.81\%$
test_items_nested_leaf	0.1493ms	77.3469μs	12.9288 KOps/s	12.3016 KOps/s	$\textbf{\color{#35bf28}+5.10\%}$
test_items_stack_nested	0.5656ms	0.4053ms	2.4675 KOps/s	2.4390 KOps/s	$\color{#35bf28}+1.17\%$
test_items_stack_nested_leaf	0.1379ms	79.7521μs	12.5388 KOps/s	12.3180 KOps/s	$\color{#35bf28}+1.79\%$
test_items_stack_nested_locked	0.5282ms	0.4029ms	2.4818 KOps/s	2.4272 KOps/s	$\color{#35bf28}+2.25\%$
test_keys	26.7400μs	3.4851μs	286.9318 KOps/s	286.4858 KOps/s	$\color{#35bf28}+0.16\%$
test_keys_nested	0.2698ms	0.1669ms	5.9924 KOps/s	5.9716 KOps/s	$\color{#35bf28}+0.35\%$
test_keys_nested_locked	1.8304ms	0.1722ms	5.8070 KOps/s	5.7365 KOps/s	$\color{#35bf28}+1.23\%$
test_keys_nested_leaf	0.2273ms	0.1451ms	6.8927 KOps/s	6.9048 KOps/s	$\color{#d91a1a}-0.17\%$
test_keys_stack_nested	0.2701ms	0.1635ms	6.1150 KOps/s	5.9563 KOps/s	$\color{#35bf28}+2.67\%$
test_keys_stack_nested_leaf	0.2283ms	0.1401ms	7.1373 KOps/s	6.9180 KOps/s	$\color{#35bf28}+3.17\%$
test_keys_stack_nested_locked	0.2306ms	0.1688ms	5.9235 KOps/s	5.7236 KOps/s	$\color{#35bf28}+3.49\%$
test_values	6.6604μs	1.0419μs	959.7676 KOps/s	967.7174 KOps/s	$\color{#d91a1a}-0.82\%$
test_values_nested	0.1184ms	62.1259μs	16.0964 KOps/s	14.9968 KOps/s	$\textbf{\color{#35bf28}+7.33\%}$
test_values_nested_locked	0.1163ms	62.5503μs	15.9871 KOps/s	15.8153 KOps/s	$\color{#35bf28}+1.09\%$
test_values_nested_leaf	0.1549ms	72.6200μs	13.7703 KOps/s	13.6447 KOps/s	$\color{#35bf28}+0.92\%$
test_values_stack_nested	0.1248ms	63.8098μs	15.6716 KOps/s	15.4716 KOps/s	$\color{#35bf28}+1.29\%$
test_values_stack_nested_leaf	0.1329ms	70.4450μs	14.1955 KOps/s	13.6619 KOps/s	$\color{#35bf28}+3.91\%$
test_values_stack_nested_locked	0.1224ms	64.1417μs	15.5905 KOps/s	15.4771 KOps/s	$\color{#35bf28}+0.73\%$
test_membership	14.6580μs	0.8867μs	1.1277 MOps/s	1.2756 MOps/s	$\textbf{\color{#d91a1a}-11.59\%}$
test_membership_nested	42.9600μs	2.9185μs	342.6378 KOps/s	346.8573 KOps/s	$\color{#d91a1a}-1.22\%$
test_membership_nested_leaf	52.3280μs	2.9420μs	339.9000 KOps/s	340.3607 KOps/s	$\color{#d91a1a}-0.14\%$
test_membership_stacked_nested	29.7560μs	2.9054μs	344.1848 KOps/s	346.5567 KOps/s	$\color{#d91a1a}-0.68\%$
test_membership_stacked_nested_leaf	21.8510μs	2.9553μs	338.3783 KOps/s	343.4691 KOps/s	$\color{#d91a1a}-1.48\%$
test_membership_nested_last	64.1290μs	4.3149μs	231.7560 KOps/s	228.4797 KOps/s	$\color{#35bf28}+1.43\%$
test_membership_nested_leaf_last	25.7280μs	4.3530μs	229.7274 KOps/s	228.8659 KOps/s	$\color{#35bf28}+0.38\%$
test_membership_stacked_nested_last	75.8720μs	13.1545μs	76.0198 KOps/s	229.6119 KOps/s	$\textbf{\color{#d91a1a}-66.89\%}$
test_membership_stacked_nested_leaf_last	41.4670μs	13.2216μs	75.6337 KOps/s	229.1941 KOps/s	$\textbf{\color{#d91a1a}-67.00\%}$
test_nested_getleaf	32.8610μs	10.5291μs	94.9747 KOps/s	93.0103 KOps/s	$\color{#35bf28}+2.11\%$
test_nested_get	55.9550μs	10.1417μs	98.6033 KOps/s	97.5794 KOps/s	$\color{#35bf28}+1.05\%$
test_stacked_getleaf	33.9440μs	10.7201μs	93.2830 KOps/s	94.3404 KOps/s	$\color{#d91a1a}-1.12\%$
test_stacked_get	59.9620μs	10.1038μs	98.9728 KOps/s	98.1190 KOps/s	$\color{#35bf28}+0.87\%$
test_nested_getitemleaf	85.8810μs	11.0074μs	90.8481 KOps/s	91.0888 KOps/s	$\color{#d91a1a}-0.26\%$
test_nested_getitem	40.1360μs	10.4594μs	95.6079 KOps/s	95.6198 KOps/s	$\color{#d91a1a}-0.01\%$
test_stacked_getitemleaf	61.0340μs	11.0396μs	90.5833 KOps/s	89.3393 KOps/s	$\color{#35bf28}+1.39\%$
test_stacked_getitem	42.9200μs	10.3776μs	96.3612 KOps/s	95.7790 KOps/s	$\color{#35bf28}+0.61\%$
test_lock_nested	4.4007ms	0.4822ms	2.0736 KOps/s	2.1664 KOps/s	$\color{#d91a1a}-4.28\%$
test_lock_stack_nested	0.6558ms	0.4237ms	2.3600 KOps/s	2.3260 KOps/s	$\color{#35bf28}+1.46\%$
test_unlock_nested	0.9474ms	0.3871ms	2.5833 KOps/s	2.6392 KOps/s	$\color{#d91a1a}-2.12\%$
test_unlock_stack_nested	0.5850ms	0.3382ms	2.9568 KOps/s	2.8720 KOps/s	$\color{#35bf28}+2.95\%$
test_flatten_speed	0.1685ms	0.1014ms	9.8616 KOps/s	9.9817 KOps/s	$\color{#d91a1a}-1.20\%$
test_unflatten_speed	0.7803ms	0.5307ms	1.8844 KOps/s	1.8937 KOps/s	$\color{#d91a1a}-0.49\%$
test_common_ops	6.0740ms	0.8587ms	1.1646 KOps/s	1.3360 KOps/s	$\textbf{\color{#d91a1a}-12.83\%}$
test_creation	31.8300μs	2.4809μs	403.0745 KOps/s	396.2183 KOps/s	$\color{#35bf28}+1.73\%$
test_creation_empty	42.7900μs	12.9918μs	76.9717 KOps/s	97.3276 KOps/s	$\textbf{\color{#d91a1a}-20.91\%}$
test_creation_nested_1	48.8420μs	16.1308μs	61.9932 KOps/s	77.3378 KOps/s	$\textbf{\color{#d91a1a}-19.84\%}$
test_creation_nested_2	56.0140μs	20.5170μs	48.7400 KOps/s	56.9343 KOps/s	$\textbf{\color{#d91a1a}-14.39\%}$
test_clone	0.1533ms	13.2351μs	75.5568 KOps/s	70.3234 KOps/s	$\textbf{\color{#35bf28}+7.44\%}$
test_getitem[int]	1.3913ms	12.8080μs	78.0760 KOps/s	78.8754 KOps/s	$\color{#d91a1a}-1.01\%$
test_getitem[slice_int]	0.1613ms	24.6441μs	40.5777 KOps/s	42.0577 KOps/s	$\color{#d91a1a}-3.52\%$
test_getitem[range]	0.5228ms	53.2487μs	18.7798 KOps/s	20.8750 KOps/s	$\textbf{\color{#d91a1a}-10.04\%}$
test_getitem[tuple]	0.1638ms	20.0754μs	49.8122 KOps/s	49.3502 KOps/s	$\color{#35bf28}+0.94\%$
test_getitem[list]	0.3905ms	43.5427μs	22.9659 KOps/s	22.5357 KOps/s	$\color{#35bf28}+1.91\%$
test_setitem_dim[int]	45.3350μs	25.4666μs	39.2672 KOps/s	40.4373 KOps/s	$\color{#d91a1a}-2.89\%$
test_setitem_dim[slice_int]	98.2140μs	52.6627μs	18.9888 KOps/s	19.9230 KOps/s	$\color{#d91a1a}-4.69\%$
test_setitem_dim[range]	0.1101ms	73.0333μs	13.6924 KOps/s	13.8553 KOps/s	$\color{#d91a1a}-1.18\%$
test_setitem_dim[tuple]	85.9320μs	40.9564μs	24.4162 KOps/s	25.2008 KOps/s	$\color{#d91a1a}-3.11\%$
test_setitem	0.2063ms	21.4789μs	46.5573 KOps/s	50.5588 KOps/s	$\textbf{\color{#d91a1a}-7.91\%}$
test_set	0.2231ms	20.9216μs	47.7975 KOps/s	52.2074 KOps/s	$\textbf{\color{#d91a1a}-8.45\%}$
test_set_shared	1.4444ms	0.1728ms	5.7886 KOps/s	5.8240 KOps/s	$\color{#d91a1a}-0.61\%$
test_update	0.2125ms	24.8863μs	40.1828 KOps/s	47.1540 KOps/s	$\textbf{\color{#d91a1a}-14.78\%}$
test_update_nested	0.2567ms	35.7297μs	27.9879 KOps/s	31.4783 KOps/s	$\textbf{\color{#d91a1a}-11.09\%}$
test_update__nested	0.9385ms	35.3141μs	28.3173 KOps/s	29.0042 KOps/s	$\color{#d91a1a}-2.37\%$
test_set_nested	0.2189ms	23.2214μs	43.0637 KOps/s	46.8312 KOps/s	$\textbf{\color{#d91a1a}-8.04\%}$
test_set_nested_new	0.2203ms	27.8687μs	35.8826 KOps/s	38.7413 KOps/s	$\textbf{\color{#d91a1a}-7.38\%}$
test_select	0.2225ms	44.9677μs	22.2382 KOps/s	23.3442 KOps/s	$\color{#d91a1a}-4.74\%$
test_select_nested	0.1175ms	62.9920μs	15.8750 KOps/s	15.5224 KOps/s	$\color{#35bf28}+2.27\%$
test_exclude_nested	0.3402ms	81.8074μs	12.2238 KOps/s	12.1105 KOps/s	$\color{#35bf28}+0.94\%$
test_empty[True]	0.8266ms	0.4105ms	2.4363 KOps/s	2.4186 KOps/s	$\color{#35bf28}+0.73\%$
test_empty[False]	12.0428μs	1.3705μs	729.6347 KOps/s	700.0071 KOps/s	$\color{#35bf28}+4.23\%$
test_unbind_speed	0.3728ms	0.2707ms	3.6945 KOps/s	3.6794 KOps/s	$\color{#35bf28}+0.41\%$
test_unbind_speed_stack0	0.3821ms	0.2609ms	3.8336 KOps/s	3.7103 KOps/s	$\color{#35bf28}+3.32\%$
test_unbind_speed_stack1	0.1115s	0.7851ms	1.2737 KOps/s	1.3645 KOps/s	$\textbf{\color{#d91a1a}-6.66\%}$
test_split	0.1104s	1.7613ms	567.7708 Ops/s	568.4825 Ops/s	$\color{#d91a1a}-0.13\%$
test_chunk	1.7205ms	1.5981ms	625.7580 Ops/s	572.2387 Ops/s	$\textbf{\color{#35bf28}+9.35\%}$
test_consolidate_njt[False-None]	8.6903ms	8.2436ms	121.3069 Ops/s	123.3248 Ops/s	$\color{#d91a1a}-1.64\%$
test_creation[device0]	0.3210ms	91.0567μs	10.9822 KOps/s	10.9536 KOps/s	$\color{#35bf28}+0.26\%$
test_creation_from_tensor	3.4694ms	94.8816μs	10.5394 KOps/s	10.3688 KOps/s	$\color{#35bf28}+1.65\%$
test_add_one[memmap_tensor0]	0.4663ms	4.9104μs	203.6493 KOps/s	204.8572 KOps/s	$\color{#d91a1a}-0.59\%$
test_contiguous[memmap_tensor0]	27.7420μs	0.5149μs	1.9421 MOps/s	1.9349 MOps/s	$\color{#35bf28}+0.37\%$
test_stack[memmap_tensor0]	49.7730μs	3.3712μs	296.6296 KOps/s	295.1970 KOps/s	$\color{#35bf28}+0.49\%$
test_memmaptd_index	1.1065ms	0.2424ms	4.1253 KOps/s	4.0348 KOps/s	$\color{#35bf28}+2.24\%$
test_memmaptd_index_astensor	0.6008ms	0.3300ms	3.0308 KOps/s	2.9778 KOps/s	$\color{#35bf28}+1.78\%$
test_memmaptd_index_op	1.0456ms	0.6080ms	1.6448 KOps/s	1.7586 KOps/s	$\textbf{\color{#d91a1a}-6.47\%}$
test_serialize_model	0.1250s	0.1180s	8.4765 Ops/s	7.6561 Ops/s	$\textbf{\color{#35bf28}+10.72\%}$
test_serialize_model_pickle	0.4781s	0.3922s	2.5496 Ops/s	2.5402 Ops/s	$\color{#35bf28}+0.37\%$
test_serialize_weights	0.1219s	0.1153s	8.6760 Ops/s	8.8371 Ops/s	$\color{#d91a1a}-1.82\%$
test_serialize_weights_returnearly	0.2690s	0.1788s	5.5914 Ops/s	6.7203 Ops/s	$\textbf{\color{#d91a1a}-16.80\%}$
test_serialize_weights_pickle	1.2079s	0.7506s	1.3322 Ops/s	2.4947 Ops/s	$\textbf{\color{#d91a1a}-46.60\%}$
test_serialize_weights_filesystem	0.1481s	0.1432s	6.9831 Ops/s	6.9689 Ops/s	$\color{#35bf28}+0.20\%$
test_serialize_model_filesystem	0.1462s	0.1417s	7.0596 Ops/s	6.1163 Ops/s	$\textbf{\color{#35bf28}+15.42\%}$
test_reshape_pytree	65.4030μs	26.7741μs	37.3495 KOps/s	36.9327 KOps/s	$\color{#35bf28}+1.13\%$
test_reshape_td	73.6780μs	33.0815μs	30.2283 KOps/s	29.7427 KOps/s	$\color{#35bf28}+1.63\%$
test_view_pytree	62.6180μs	26.4529μs	37.8030 KOps/s	37.1994 KOps/s	$\color{#35bf28}+1.62\%$
test_view_td	91.9630μs	38.7956μs	25.7761 KOps/s	26.3623 KOps/s	$\color{#d91a1a}-2.22\%$
test_unbind_pytree	69.5800μs	29.7724μs	33.5881 KOps/s	33.6821 KOps/s	$\color{#d91a1a}-0.28\%$
test_unbind_td	0.3116ms	39.8807μs	25.0748 KOps/s	24.9570 KOps/s	$\color{#35bf28}+0.47\%$
test_split_pytree	86.8530μs	29.9848μs	33.3502 KOps/s	33.8717 KOps/s	$\color{#d91a1a}-1.54\%$
test_split_td	0.2233ms	44.6979μs	22.3724 KOps/s	22.6143 KOps/s	$\color{#d91a1a}-1.07\%$
test_add_pytree	97.4530μs	36.3625μs	27.5008 KOps/s	27.8862 KOps/s	$\color{#d91a1a}-1.38\%$
test_add_td	0.1272ms	58.8013μs	17.0064 KOps/s	19.0821 KOps/s	$\textbf{\color{#d91a1a}-10.88\%}$
test_compile_add_one_nested[tensordict-compile]	0.1335ms	62.8051μs	15.9223 KOps/s	16.1292 KOps/s	$\color{#d91a1a}-1.28\%$
test_compile_add_one_nested[tensordict-eager]	0.4075ms	0.1758ms	5.6892 KOps/s	5.8218 KOps/s	$\color{#d91a1a}-2.28\%$
test_compile_add_one_nested[pytree-compile]	0.1068ms	46.0542μs	21.7135 KOps/s	22.0939 KOps/s	$\color{#d91a1a}-1.72\%$
test_compile_add_one_nested[pytree-eager]	0.2312ms	0.1194ms	8.3780 KOps/s	8.2638 KOps/s	$\color{#35bf28}+1.38\%$
test_compile_copy_nested[tensordict-compile]	68.0980μs	26.6979μs	37.4562 KOps/s	40.0746 KOps/s	$\textbf{\color{#d91a1a}-6.53\%}$
test_compile_copy_nested[tensordict-eager]	0.1354ms	58.6330μs	17.0552 KOps/s	17.1872 KOps/s	$\color{#d91a1a}-0.77\%$
test_compile_copy_nested[pytree-compile]	0.1556ms	81.0741μs	12.3344 KOps/s	12.6593 KOps/s	$\color{#d91a1a}-2.57\%$
test_compile_copy_nested[pytree-eager]	0.1607ms	66.8649μs	14.9555 KOps/s	14.7031 KOps/s	$\color{#35bf28}+1.72\%$
test_compile_add_one_flat[tensordict-compile]	0.1887ms	0.1039ms	9.6279 KOps/s	9.5532 KOps/s	$\color{#35bf28}+0.78\%$
test_compile_add_one_flat[tensordict-eager]	1.4187ms	0.2163ms	4.6229 KOps/s	4.5930 KOps/s	$\color{#35bf28}+0.65\%$
test_compile_add_one_flat[tensorclass-compile]	0.1034ms	45.5729μs	21.9429 KOps/s	21.8016 KOps/s	$\color{#35bf28}+0.65\%$
test_compile_add_one_flat[tensorclass-eager]	0.4780ms	67.2679μs	14.8659 KOps/s	15.4321 KOps/s	$\color{#d91a1a}-3.67\%$
test_compile_add_one_flat[pytree-compile]	0.2182ms	0.1030ms	9.7066 KOps/s	9.7814 KOps/s	$\color{#d91a1a}-0.76\%$
test_compile_add_one_flat[pytree-eager]	0.4546ms	0.2030ms	4.9253 KOps/s	4.9900 KOps/s	$\color{#d91a1a}-1.30\%$
test_compile_add_self_flat[tensordict-eager]	0.3491ms	0.2330ms	4.2911 KOps/s	4.2251 KOps/s	$\color{#35bf28}+1.56\%$
test_compile_add_self_flat[tensordict-compile]	0.3143ms	0.1066ms	9.3806 KOps/s	9.5364 KOps/s	$\color{#d91a1a}-1.63\%$
test_compile_add_self_flat[tensorclass-eager]	0.1519ms	62.0178μs	16.1244 KOps/s	16.8755 KOps/s	$\color{#d91a1a}-4.45\%$
test_compile_add_self_flat[tensorclass-compile]	0.2386ms	45.5904μs	21.9344 KOps/s	22.2951 KOps/s	$\color{#d91a1a}-1.62\%$
test_compile_add_self_flat[pytree-eager]	0.5873ms	0.1577ms	6.3393 KOps/s	6.2949 KOps/s	$\color{#35bf28}+0.70\%$
test_compile_add_self_flat[pytree-compile]	0.2071ms	0.1025ms	9.7537 KOps/s	9.7089 KOps/s	$\color{#35bf28}+0.46\%$
test_compile_copy_flat[tensordict-compile]	85.8510μs	20.6199μs	48.4969 KOps/s	47.1844 KOps/s	$\color{#35bf28}+2.78\%$
test_compile_copy_flat[tensordict-eager]	0.1449ms	66.2111μs	15.1032 KOps/s	14.8403 KOps/s	$\color{#35bf28}+1.77\%$
test_compile_copy_flat[pytree-compile]	0.1419ms	81.9849μs	12.1974 KOps/s	12.0007 KOps/s	$\color{#35bf28}+1.64\%$
test_compile_copy_flat[pytree-eager]	0.1825ms	69.8972μs	14.3067 KOps/s	13.8114 KOps/s	$\color{#35bf28}+3.59\%$
test_compile_assign_and_add[tensordict-compile]	0.4043ms	0.2070ms	4.8305 KOps/s	5.0096 KOps/s	$\color{#d91a1a}-3.57\%$
test_compile_assign_and_add[tensordict-eager]	1.5245ms	1.3026ms	767.7152 Ops/s	730.0557 Ops/s	$\textbf{\color{#35bf28}+5.16\%}$
test_compile_assign_and_add[pytree-compile]	0.3053ms	0.2041ms	4.9005 KOps/s	4.9619 KOps/s	$\color{#d91a1a}-1.24\%$
test_compile_assign_and_add[pytree-eager]	1.0130ms	0.7740ms	1.2919 KOps/s	1.2739 KOps/s	$\color{#35bf28}+1.42\%$
test_compile_assign_and_add_stack[compile]	0.5748ms	0.4562ms	2.1920 KOps/s	2.2231 KOps/s	$\color{#d91a1a}-1.40\%$
test_compile_assign_and_add_stack[eager]	2.9719ms	2.7312ms	366.1461 Ops/s	377.7826 Ops/s	$\color{#d91a1a}-3.08\%$
test_compile_indexing[tensor-tensordict-compile]	0.1342ms	36.0015μs	27.7766 KOps/s	27.7889 KOps/s	$\color{#d91a1a}-0.04\%$
test_compile_indexing[tensor-tensordict-eager]	0.7460ms	32.1760μs	31.0791 KOps/s	29.8776 KOps/s	$\color{#35bf28}+4.02\%$
test_compile_indexing[tensor-tensorclass-compile]	80.3910μs	29.1681μs	34.2840 KOps/s	33.9544 KOps/s	$\color{#35bf28}+0.97\%$
test_compile_indexing[tensor-tensorclass-eager]	68.2380μs	22.4553μs	44.5329 KOps/s	42.9751 KOps/s	$\color{#35bf28}+3.62\%$
test_compile_indexing[tensor-pytree-compile]	77.4650μs	30.1369μs	33.1819 KOps/s	33.3338 KOps/s	$\color{#d91a1a}-0.46\%$
test_compile_indexing[tensor-pytree-eager]	94.7180μs	22.6192μs	44.2102 KOps/s	43.3359 KOps/s	$\color{#35bf28}+2.02\%$
test_compile_indexing[slice-tensordict-compile]	0.1273ms	50.5959μs	19.7645 KOps/s	19.2500 KOps/s	$\color{#35bf28}+2.67\%$
test_compile_indexing[slice-tensordict-eager]	0.6335ms	20.1948μs	49.5177 KOps/s	49.8692 KOps/s	$\color{#d91a1a}-0.70\%$
test_compile_indexing[slice-tensorclass-compile]	0.1330ms	43.9555μs	22.7503 KOps/s	22.5885 KOps/s	$\color{#35bf28}+0.72\%$
test_compile_indexing[slice-tensorclass-eager]	91.7720μs	19.0339μs	52.5380 KOps/s	53.7161 KOps/s	$\color{#d91a1a}-2.19\%$
test_compile_indexing[slice-pytree-compile]	0.1216ms	45.0142μs	22.2152 KOps/s	22.0799 KOps/s	$\color{#35bf28}+0.61\%$
test_compile_indexing[slice-pytree-eager]	55.4640μs	19.2517μs	51.9434 KOps/s	54.0035 KOps/s	$\color{#d91a1a}-3.81\%$
test_compile_indexing[int-tensordict-compile]	0.1352ms	52.1049μs	19.1921 KOps/s	19.0476 KOps/s	$\color{#35bf28}+0.76\%$
test_compile_indexing[int-tensordict-eager]	1.0711ms	20.2244μs	49.4452 KOps/s	51.3005 KOps/s	$\color{#d91a1a}-3.62\%$
test_compile_indexing[int-tensorclass-compile]	0.1943ms	44.6352μs	22.4038 KOps/s	22.2514 KOps/s	$\color{#35bf28}+0.68\%$
test_compile_indexing[int-tensorclass-eager]	66.1240μs	18.7007μs	53.4739 KOps/s	54.4838 KOps/s	$\color{#d91a1a}-1.85\%$
test_compile_indexing[int-pytree-compile]	0.1355ms	44.3759μs	22.5348 KOps/s	22.3089 KOps/s	$\color{#35bf28}+1.01\%$
test_compile_indexing[int-pytree-eager]	68.8090μs	18.7969μs	53.2004 KOps/s	53.7330 KOps/s	$\color{#d91a1a}-0.99\%$
test_mod_add[eager]	91.5620μs	35.6847μs	28.0232 KOps/s	30.2070 KOps/s	$\textbf{\color{#d91a1a}-7.23\%}$
test_mod_add[compile]	99.4460μs	46.5302μs	21.4914 KOps/s	20.6980 KOps/s	$\color{#35bf28}+3.83\%$
test_mod_add[compile-overhead]	0.2264ms	47.4308μs	21.0834 KOps/s	20.6517 KOps/s	$\color{#35bf28}+2.09\%$
test_mod_wrap[eager]	0.4291ms	0.2298ms	4.3523 KOps/s	4.4220 KOps/s	$\color{#d91a1a}-1.58\%$
test_mod_wrap[compile]	0.3046ms	0.2046ms	4.8885 KOps/s	4.8695 KOps/s	$\color{#35bf28}+0.39\%$
test_mod_wrap[compile-overhead]	0.4027ms	0.2124ms	4.7075 KOps/s	4.9304 KOps/s	$\color{#d91a1a}-4.52\%$
test_mod_wrap_and_backward[eager]	11.9804ms	11.0309ms	90.6542 Ops/s	84.1472 Ops/s	$\textbf{\color{#35bf28}+7.73\%}$
test_mod_wrap_and_backward[compile]	12.2029ms	11.0212ms	90.7339 Ops/s	73.6157 Ops/s	$\textbf{\color{#35bf28}+23.25\%}$
test_mod_wrap_and_backward[compile-overhead]	12.0897ms	10.8786ms	91.9235 Ops/s	73.5067 Ops/s	$\textbf{\color{#35bf28}+25.05\%}$
test_seq_add[eager]	0.2452ms	0.1203ms	8.3152 KOps/s	8.7655 KOps/s	$\textbf{\color{#d91a1a}-5.14\%}$
test_seq_add[compile]	0.1270ms	60.8502μs	16.4338 KOps/s	15.7712 KOps/s	$\color{#35bf28}+4.20\%$
test_seq_add[compile-overhead]	0.1165ms	59.7382μs	16.7397 KOps/s	15.5357 KOps/s	$\textbf{\color{#35bf28}+7.75\%}$
test_seq_wrap[eager]	0.7555ms	0.4574ms	2.1862 KOps/s	2.2268 KOps/s	$\color{#d91a1a}-1.82\%$
test_seq_wrap[compile]	0.4202ms	0.2275ms	4.3952 KOps/s	4.3601 KOps/s	$\color{#35bf28}+0.80\%$
test_seq_wrap[compile-overhead]	0.5705ms	0.2276ms	4.3928 KOps/s	4.4010 KOps/s	$\color{#d91a1a}-0.19\%$
test_func_call_runtime[False-eager]	0.8600ms	0.5597ms	1.7868 KOps/s	1.8166 KOps/s	$\color{#d91a1a}-1.64\%$
test_func_call_runtime[False-compile]	1.0029ms	0.4344ms	2.3022 KOps/s	2.3562 KOps/s	$\color{#d91a1a}-2.29\%$
test_func_call_runtime[False-compile-overhead]	0.5762ms	0.4217ms	2.3712 KOps/s	2.3566 KOps/s	$\color{#35bf28}+0.62\%$
test_func_call_runtime[True-eager]	1.2968ms	0.7681ms	1.3019 KOps/s	1.3106 KOps/s	$\color{#d91a1a}-0.67\%$
test_func_call_runtime[True-compile]	0.6207ms	0.4617ms	2.1657 KOps/s	2.1497 KOps/s	$\color{#35bf28}+0.74\%$
test_func_call_runtime[True-compile-overhead]	0.6117ms	0.4622ms	2.1635 KOps/s	2.1733 KOps/s	$\color{#d91a1a}-0.45\%$
test_func_call_cm_runtime[False-eager]	0.9214ms	0.5550ms	1.8017 KOps/s	1.8523 KOps/s	$\color{#d91a1a}-2.73\%$
test_func_call_cm_runtime[False-compile]	0.6491ms	0.4195ms	2.3838 KOps/s	2.3786 KOps/s	$\color{#35bf28}+0.22\%$
test_func_call_cm_runtime[False-compile-overhead]	0.5933ms	0.4186ms	2.3886 KOps/s	2.3700 KOps/s	$\color{#35bf28}+0.79\%$
test_func_call_cm_runtime[True-eager]	1.5478ms	0.9145ms	1.0935 KOps/s	1.0929 KOps/s	$\color{#35bf28}+0.05\%$
test_func_call_cm_runtime[True-compile]	0.6572ms	0.4817ms	2.0761 KOps/s	2.0439 KOps/s	$\color{#35bf28}+1.57\%$
test_func_call_cm_runtime[True-compile-overhead]	0.6087ms	0.4807ms	2.0802 KOps/s	2.0620 KOps/s	$\color{#35bf28}+0.88\%$
test_vmap_func_call_cm_runtime[eager]	2.5945ms	1.8952ms	527.6605 Ops/s	514.4084 Ops/s	$\color{#35bf28}+2.58\%$
test_vmap_func_call_cm_runtime[compile]	0.6077ms	0.5060ms	1.9763 KOps/s	1.9336 KOps/s	$\color{#35bf28}+2.21\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.9120ms	0.5092ms	1.9637 KOps/s	1.9139 KOps/s	$\color{#35bf28}+2.60\%$
test_distributed	0.7108ms	0.1241ms	8.0602 KOps/s	7.7591 KOps/s	$\color{#35bf28}+3.88\%$
test_tdmodule	56.6960μs	27.2111μs	36.7497 KOps/s	38.5658 KOps/s	$\color{#d91a1a}-4.71\%$
test_tdmodule_dispatch	82.8550μs	49.9444μs	20.0223 KOps/s	21.4684 KOps/s	$\textbf{\color{#d91a1a}-6.74\%}$
test_tdseq	46.2070μs	29.7262μs	33.6404 KOps/s	35.2559 KOps/s	$\color{#d91a1a}-4.58\%$
test_tdseq_dispatch	81.1120μs	55.1771μs	18.1235 KOps/s	19.1683 KOps/s	$\textbf{\color{#d91a1a}-5.45\%}$
test_instantiation_functorch	2.2699ms	1.5277ms	654.5861 Ops/s	643.4220 Ops/s	$\color{#35bf28}+1.74\%$
test_exec_functorch	0.2836ms	0.1818ms	5.5008 KOps/s	5.5069 KOps/s	$\color{#d91a1a}-0.11\%$
test_exec_functional_call	0.3372ms	0.1739ms	5.7520 KOps/s	5.7803 KOps/s	$\color{#d91a1a}-0.49\%$
test_exec_td_decorator	0.5013ms	0.2352ms	4.2526 KOps/s	4.1777 KOps/s	$\color{#35bf28}+1.79\%$
test_vmap_mlp_speed_decorator[True-True]	0.8036ms	0.6497ms	1.5393 KOps/s	1.4955 KOps/s	$\color{#35bf28}+2.92\%$
test_vmap_mlp_speed_decorator[True-False]	0.9635ms	0.6551ms	1.5265 KOps/s	1.5175 KOps/s	$\color{#35bf28}+0.59\%$
test_vmap_mlp_speed_decorator[False-True]	0.7100ms	0.5238ms	1.9091 KOps/s	1.8596 KOps/s	$\color{#35bf28}+2.66\%$
test_vmap_mlp_speed_decorator[False-False]	0.7542ms	0.5240ms	1.9084 KOps/s	1.8578 KOps/s	$\color{#35bf28}+2.72\%$
test_to_module_speed[True]	1.5684ms	1.3303ms	751.7185 Ops/s	729.7856 Ops/s	$\color{#35bf28}+3.01\%$
test_to_module_speed[False]	1.8016ms	1.3070ms	765.0962 Ops/s	754.9235 Ops/s	$\color{#35bf28}+1.35\%$
test_tc_init	87.6540μs	50.1860μs	19.9259 KOps/s	22.3769 KOps/s	$\textbf{\color{#d91a1a}-10.95\%}$
test_tc_init_nested	0.1904ms	0.1008ms	9.9217 KOps/s	10.9889 KOps/s	$\textbf{\color{#d91a1a}-9.71\%}$
test_tc_first_layer_tensor	16.3210μs	1.5365μs	650.8206 KOps/s	649.2019 KOps/s	$\color{#35bf28}+0.25\%$
test_tc_first_layer_nontensor	49.5930μs	4.7349μs	211.1986 KOps/s	210.5758 KOps/s	$\color{#35bf28}+0.30\%$
test_tc_second_layer_tensor	26.4400μs	2.8571μs	350.0047 KOps/s	347.1207 KOps/s	$\color{#35bf28}+0.83\%$
test_tc_second_layer_nontensor	49.1520μs	5.9975μs	166.7363 KOps/s	164.1622 KOps/s	$\color{#35bf28}+1.57\%$
test_unbind	0.2320s	14.4128ms	69.3830 Ops/s	79.0496 Ops/s	$\textbf{\color{#d91a1a}-12.23\%}$
test_full_like	13.6566ms	12.6980ms	78.7526 Ops/s	120.7572 Ops/s	$\textbf{\color{#d91a1a}-34.78\%}$
test_zeros_like	10.7700ms	7.6816ms	130.1810 Ops/s	295.2526 Ops/s	$\textbf{\color{#d91a1a}-55.91\%}$
test_ones_like	8.9730ms	7.5727ms	132.0533 Ops/s	263.9901 Ops/s	$\textbf{\color{#d91a1a}-49.98\%}$
test_clone	14.4163ms	9.2484ms	108.1264 Ops/s	164.7546 Ops/s	$\textbf{\color{#d91a1a}-34.37\%}$
test_squeeze	67.5070μs	12.1545μs	82.2743 KOps/s	81.7733 KOps/s	$\color{#35bf28}+0.61\%$
test_unsqueeze	0.1696ms	91.2447μs	10.9595 KOps/s	10.8732 KOps/s	$\color{#35bf28}+0.79\%$
test_split	0.5114ms	0.1967ms	5.0829 KOps/s	5.0673 KOps/s	$\color{#35bf28}+0.31\%$
test_permute	0.3255ms	0.2096ms	4.7721 KOps/s	4.8517 KOps/s	$\color{#d91a1a}-1.64\%$
test_stack	29.6304ms	24.8778ms	40.1966 Ops/s	37.9791 Ops/s	$\textbf{\color{#35bf28}+5.84\%}$
test_cat	28.7947ms	24.7694ms	40.3724 Ops/s	36.3320 Ops/s	$\textbf{\color{#35bf28}+11.12\%}$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}44$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	35.9300μs	11.1834μs	89.4183 KOps/s	76.4320 KOps/s	$\textbf{\color{#35bf28}+16.99\%}$
test_plain_set_stack_nested	35.5910μs	11.4259μs	87.5202 KOps/s	75.5167 KOps/s	$\textbf{\color{#35bf28}+15.90\%}$
test_plain_set_nested_inplace	50.6210μs	12.3231μs	81.1483 KOps/s	70.4699 KOps/s	$\textbf{\color{#35bf28}+15.15\%}$
test_plain_set_stack_nested_inplace	41.3810μs	12.4176μs	80.5307 KOps/s	69.9956 KOps/s	$\textbf{\color{#35bf28}+15.05\%}$
test_items	24.8500μs	2.9009μs	344.7172 KOps/s	338.8030 KOps/s	$\color{#35bf28}+1.75\%$
test_items_nested	0.4080ms	0.3588ms	2.7872 KOps/s	2.7369 KOps/s	$\color{#35bf28}+1.84\%$
test_items_nested_locked	0.4088ms	0.3625ms	2.7585 KOps/s	2.7189 KOps/s	$\color{#35bf28}+1.46\%$
test_items_nested_leaf	89.6920μs	58.5630μs	17.0756 KOps/s	17.0808 KOps/s	$\color{#d91a1a}-0.03\%$
test_items_stack_nested	0.3980ms	0.3592ms	2.7836 KOps/s	2.7226 KOps/s	$\color{#35bf28}+2.24\%$
test_items_stack_nested_leaf	93.8520μs	59.1162μs	16.9158 KOps/s	17.1800 KOps/s	$\color{#d91a1a}-1.54\%$
test_items_stack_nested_locked	0.4171ms	0.3606ms	2.7732 KOps/s	2.7254 KOps/s	$\color{#35bf28}+1.75\%$
test_keys	26.4410μs	3.4493μs	289.9105 KOps/s	284.9011 KOps/s	$\color{#35bf28}+1.76\%$
test_keys_nested	0.1146ms	81.0690μs	12.3352 KOps/s	12.2584 KOps/s	$\color{#35bf28}+0.63\%$
test_keys_nested_locked	0.7222ms	86.4658μs	11.5653 KOps/s	11.4247 KOps/s	$\color{#35bf28}+1.23\%$
test_keys_nested_leaf	0.1098ms	71.7852μs	13.9305 KOps/s	13.8274 KOps/s	$\color{#35bf28}+0.75\%$
test_keys_stack_nested	0.1127ms	80.9425μs	12.3545 KOps/s	12.2407 KOps/s	$\color{#35bf28}+0.93\%$
test_keys_stack_nested_leaf	0.1293ms	72.0344μs	13.8823 KOps/s	13.7762 KOps/s	$\color{#35bf28}+0.77\%$
test_keys_stack_nested_locked	0.1378ms	87.3934μs	11.4425 KOps/s	11.3889 KOps/s	$\color{#35bf28}+0.47\%$
test_values	5.3983μs	0.8477μs	1.1796 MOps/s	1.1715 MOps/s	$\color{#35bf28}+0.69\%$
test_values_nested	0.1569ms	34.3603μs	29.1034 KOps/s	29.2114 KOps/s	$\color{#d91a1a}-0.37\%$
test_values_nested_locked	64.0010μs	36.1226μs	27.6835 KOps/s	27.5860 KOps/s	$\color{#35bf28}+0.35\%$
test_values_nested_leaf	80.1310μs	39.2363μs	25.4866 KOps/s	25.8754 KOps/s	$\color{#d91a1a}-1.50\%$
test_values_stack_nested	0.1622ms	34.5851μs	28.9141 KOps/s	29.0357 KOps/s	$\color{#d91a1a}-0.42\%$
test_values_stack_nested_leaf	69.1620μs	39.2251μs	25.4939 KOps/s	25.5600 KOps/s	$\color{#d91a1a}-0.26\%$
test_values_stack_nested_locked	62.1410μs	36.0812μs	27.7152 KOps/s	27.6900 KOps/s	$\color{#35bf28}+0.09\%$
test_membership	1.8846μs	0.5112μs	1.9563 MOps/s	1.9613 MOps/s	$\color{#d91a1a}-0.25\%$
test_membership_nested	16.1455μs	2.0224μs	494.4506 KOps/s	470.9635 KOps/s	$\color{#35bf28}+4.99\%$
test_membership_nested_leaf	21.1700μs	2.0274μs	493.2402 KOps/s	491.5642 KOps/s	$\color{#35bf28}+0.34\%$
test_membership_stacked_nested	31.5300μs	2.0644μs	484.4111 KOps/s	471.8407 KOps/s	$\color{#35bf28}+2.66\%$
test_membership_stacked_nested_leaf	31.3710μs	2.0873μs	479.0876 KOps/s	464.2708 KOps/s	$\color{#35bf28}+3.19\%$
test_membership_nested_last	28.7510μs	3.0701μs	325.7237 KOps/s	318.0290 KOps/s	$\color{#35bf28}+2.42\%$
test_membership_nested_leaf_last	27.2210μs	3.0546μs	327.3789 KOps/s	315.8239 KOps/s	$\color{#35bf28}+3.66\%$
test_membership_stacked_nested_last	28.5400μs	3.0623μs	326.5533 KOps/s	320.2963 KOps/s	$\color{#35bf28}+1.95\%$
test_membership_stacked_nested_leaf_last	31.4900μs	3.0741μs	325.2941 KOps/s	318.4720 KOps/s	$\color{#35bf28}+2.14\%$
test_nested_getleaf	40.8210μs	6.1496μs	162.6119 KOps/s	161.2415 KOps/s	$\color{#35bf28}+0.85\%$
test_nested_get	35.8610μs	5.8345μs	171.3950 KOps/s	171.4240 KOps/s	$\color{#d91a1a}-0.02\%$
test_stacked_getleaf	34.5610μs	6.1748μs	161.9481 KOps/s	161.6918 KOps/s	$\color{#35bf28}+0.16\%$
test_stacked_get	51.2010μs	5.8502μs	170.9358 KOps/s	168.7069 KOps/s	$\color{#35bf28}+1.32\%$
test_nested_getitemleaf	27.2600μs	6.2646μs	159.6261 KOps/s	157.0977 KOps/s	$\color{#35bf28}+1.61\%$
test_nested_getitem	39.1410μs	5.9254μs	168.7653 KOps/s	164.9557 KOps/s	$\color{#35bf28}+2.31\%$
test_stacked_getitemleaf	28.7210μs	6.2318μs	160.4666 KOps/s	157.8204 KOps/s	$\color{#35bf28}+1.68\%$
test_stacked_getitem	35.9900μs	6.0036μs	166.5661 KOps/s	166.8682 KOps/s	$\color{#d91a1a}-0.18\%$
test_lock_nested	9.7316ms	0.3917ms	2.5531 KOps/s	2.5524 KOps/s	$\color{#35bf28}+0.03\%$
test_lock_stack_nested	0.3982ms	0.3484ms	2.8707 KOps/s	2.8182 KOps/s	$\color{#35bf28}+1.86\%$
test_unlock_nested	0.6370ms	0.3209ms	3.1161 KOps/s	3.0867 KOps/s	$\color{#35bf28}+0.95\%$
test_unlock_stack_nested	0.3260ms	0.2875ms	3.4782 KOps/s	3.4096 KOps/s	$\color{#35bf28}+2.01\%$
test_flatten_speed	0.1204ms	75.3832μs	13.2656 KOps/s	13.2001 KOps/s	$\color{#35bf28}+0.50\%$
test_unflatten_speed	0.3831ms	0.3247ms	3.0802 KOps/s	3.0670 KOps/s	$\color{#35bf28}+0.43\%$
test_common_ops	1.6529ms	0.5768ms	1.7336 KOps/s	1.5260 KOps/s	$\textbf{\color{#35bf28}+13.61\%}$
test_creation	0.1731ms	1.7674μs	565.8136 KOps/s	553.4415 KOps/s	$\color{#35bf28}+2.24\%$
test_creation_empty	29.8400μs	6.5062μs	153.6997 KOps/s	100.2947 KOps/s	$\textbf{\color{#35bf28}+53.25\%}$
test_creation_nested_1	35.0710μs	8.2136μs	121.7493 KOps/s	86.4355 KOps/s	$\textbf{\color{#35bf28}+40.86\%}$
test_creation_nested_2	47.2410μs	10.9623μs	91.2218 KOps/s	67.7510 KOps/s	$\textbf{\color{#35bf28}+34.64\%}$
test_clone	2.0103ms	11.2799μs	88.6534 KOps/s	87.9453 KOps/s	$\color{#35bf28}+0.81\%$
test_getitem[int]	1.3404ms	10.7648μs	92.8955 KOps/s	88.8073 KOps/s	$\color{#35bf28}+4.60\%$
test_getitem[slice_int]	0.1118ms	21.3737μs	46.7866 KOps/s	45.8703 KOps/s	$\color{#35bf28}+2.00\%$
test_getitem[range]	0.1280ms	37.8680μs	26.4075 KOps/s	26.0532 KOps/s	$\color{#35bf28}+1.36\%$
test_getitem[tuple]	0.1067ms	18.5813μs	53.8175 KOps/s	52.9038 KOps/s	$\color{#35bf28}+1.73\%$
test_getitem[list]	0.2576ms	33.8089μs	29.5780 KOps/s	29.1531 KOps/s	$\color{#35bf28}+1.46\%$
test_setitem_dim[int]	40.4610μs	20.2224μs	49.4502 KOps/s	50.1442 KOps/s	$\color{#d91a1a}-1.38\%$
test_setitem_dim[slice_int]	75.1420μs	40.1162μs	24.9276 KOps/s	25.4040 KOps/s	$\color{#d91a1a}-1.88\%$
test_setitem_dim[range]	80.8920μs	55.3482μs	18.0674 KOps/s	18.5913 KOps/s	$\color{#d91a1a}-2.82\%$
test_setitem_dim[tuple]	52.6910μs	32.7142μs	30.5678 KOps/s	30.3722 KOps/s	$\color{#35bf28}+0.64\%$
test_setitem	98.8120μs	14.8839μs	67.1869 KOps/s	56.1908 KOps/s	$\textbf{\color{#35bf28}+19.57\%}$
test_set	89.2210μs	14.2266μs	70.2910 KOps/s	60.2981 KOps/s	$\textbf{\color{#35bf28}+16.57\%}$
test_set_shared	1.5920ms	0.1507ms	6.6354 KOps/s	6.6554 KOps/s	$\color{#d91a1a}-0.30\%$
test_update	0.2962ms	15.9601μs	62.6563 KOps/s	51.0880 KOps/s	$\textbf{\color{#35bf28}+22.64\%}$
test_update_nested	0.1015ms	21.6374μs	46.2162 KOps/s	39.0342 KOps/s	$\textbf{\color{#35bf28}+18.40\%}$
test_update__nested	1.0384ms	26.4001μs	37.8787 KOps/s	37.2030 KOps/s	$\color{#35bf28}+1.82\%$
test_set_nested	87.2520μs	15.3454μs	65.1663 KOps/s	56.7257 KOps/s	$\textbf{\color{#35bf28}+14.88\%}$
test_set_nested_new	87.9110μs	18.1167μs	55.1978 KOps/s	49.6021 KOps/s	$\textbf{\color{#35bf28}+11.28\%}$
test_select	0.1010ms	28.8742μs	34.6329 KOps/s	30.8477 KOps/s	$\textbf{\color{#35bf28}+12.27\%}$
test_select_nested	0.1336ms	43.5705μs	22.9513 KOps/s	22.2389 KOps/s	$\color{#35bf28}+3.20\%$
test_exclude_nested	97.6720μs	62.5602μs	15.9846 KOps/s	15.5523 KOps/s	$\color{#35bf28}+2.78\%$
test_empty[True]	0.6660ms	0.2881ms	3.4712 KOps/s	3.4157 KOps/s	$\color{#35bf28}+1.62\%$
test_empty[False]	3.0450μs	0.8371μs	1.1946 MOps/s	1.2033 MOps/s	$\color{#d91a1a}-0.72\%$
test_to	85.8220μs	57.1753μs	17.4901 KOps/s	17.5334 KOps/s	$\color{#d91a1a}-0.25\%$
test_to_nonblocking	0.2005ms	50.3608μs	19.8567 KOps/s	20.8500 KOps/s	$\color{#d91a1a}-4.76\%$
test_unbind_speed	0.8035ms	0.2413ms	4.1447 KOps/s	4.1028 KOps/s	$\color{#35bf28}+1.02\%$
test_unbind_speed_stack0	0.2986ms	0.2419ms	4.1333 KOps/s	4.0840 KOps/s	$\color{#35bf28}+1.21\%$
test_unbind_speed_stack1	92.6155ms	0.6784ms	1.4740 KOps/s	1.4665 KOps/s	$\color{#35bf28}+0.51\%$
test_split	93.3175ms	1.6028ms	623.9140 Ops/s	607.2582 Ops/s	$\color{#35bf28}+2.74\%$
test_chunk	95.5759ms	1.7512ms	571.0397 Ops/s	558.3559 Ops/s	$\color{#35bf28}+2.27\%$
test_consolidate[False-None]	3.2647ms	2.6763ms	373.6550 Ops/s	367.5424 Ops/s	$\color{#35bf28}+1.66\%$
test_consolidate[default-None]	1.7654ms	1.6662ms	600.1577 Ops/s	581.9771 Ops/s	$\color{#35bf28}+3.12\%$
test_consolidate[reduce-overhead-None]	1.8684ms	1.7076ms	585.6149 Ops/s	571.0972 Ops/s	$\color{#35bf28}+2.54\%$
test_consolidate_njt[False-None]	6.8558ms	6.5616ms	152.4009 Ops/s	151.9004 Ops/s	$\color{#35bf28}+0.33\%$
test_to[False-False-None]	1.8230ms	1.7092ms	585.0686 Ops/s	585.7936 Ops/s	$\color{#d91a1a}-0.12\%$
test_to[True-False-None]	1.6017ms	1.3338ms	749.7132 Ops/s	745.4936 Ops/s	$\color{#35bf28}+0.57\%$
test_to[within-False-None]	4.3134ms	4.1726ms	239.6605 Ops/s	243.1093 Ops/s	$\color{#d91a1a}-1.42\%$
test_to[True-default-None]	5.4995ms	5.2447ms	190.6672 Ops/s	180.2070 Ops/s	$\textbf{\color{#35bf28}+5.80\%}$
test_to_njt[False-False-None]	7.3325ms	6.9585ms	143.7097 Ops/s	141.1298 Ops/s	$\color{#35bf28}+1.83\%$
test_to_njt[True-False-None]	5.6038ms	5.4757ms	182.6236 Ops/s	173.8439 Ops/s	$\textbf{\color{#35bf28}+5.05\%}$
test_to_njt[within-False-None]	12.5803ms	12.1528ms	82.2853 Ops/s	79.6120 Ops/s	$\color{#35bf28}+3.36\%$
test_creation[device0]	0.5564ms	79.6544μs	12.5542 KOps/s	11.9391 KOps/s	$\textbf{\color{#35bf28}+5.15\%}$
test_creation_from_tensor	0.6043ms	83.8897μs	11.9204 KOps/s	11.9247 KOps/s	$\color{#d91a1a}-0.04\%$
test_add_one[memmap_tensor0]	0.2639ms	6.9571μs	143.7377 KOps/s	141.6812 KOps/s	$\color{#35bf28}+1.45\%$
test_contiguous[memmap_tensor0]	1.8570μs	0.4094μs	2.4425 MOps/s	2.4742 MOps/s	$\color{#d91a1a}-1.28\%$
test_stack[memmap_tensor0]	39.4900μs	4.4754μs	223.4453 KOps/s	213.6839 KOps/s	$\color{#35bf28}+4.57\%$
test_memmaptd_index	1.4783ms	0.2537ms	3.9421 KOps/s	3.7164 KOps/s	$\textbf{\color{#35bf28}+6.07\%}$
test_memmaptd_index_astensor	0.5962ms	0.3147ms	3.1772 KOps/s	2.9755 KOps/s	$\textbf{\color{#35bf28}+6.78\%}$
test_memmaptd_index_op	0.9941ms	0.5691ms	1.7572 KOps/s	1.5511 KOps/s	$\textbf{\color{#35bf28}+13.29\%}$
test_serialize_model	0.1320s	0.1310s	7.6351 Ops/s	7.6778 Ops/s	$\color{#d91a1a}-0.56\%$
test_serialize_model_pickle	1.3540s	1.2115s	0.8254 Ops/s	0.8231 Ops/s	$\color{#35bf28}+0.28\%$
test_serialize_weights	0.4177s	0.1711s	5.8459 Ops/s	7.7489 Ops/s	$\textbf{\color{#d91a1a}-24.56\%}$
test_serialize_weights_returnearly	0.3417s	54.7766ms	18.2560 Ops/s	12.0598 Ops/s	$\textbf{\color{#35bf28}+51.38\%}$
test_serialize_weights_pickle	1.3773s	1.2211s	0.8189 Ops/s	0.8226 Ops/s	$\color{#d91a1a}-0.45\%$
test_reshape_pytree	55.0710μs	21.8295μs	45.8097 KOps/s	44.0556 KOps/s	$\color{#35bf28}+3.98\%$
test_reshape_td	62.6910μs	26.1391μs	38.2568 KOps/s	35.2680 KOps/s	$\textbf{\color{#35bf28}+8.47\%}$
test_view_pytree	0.1692ms	21.6938μs	46.0962 KOps/s	45.2173 KOps/s	$\color{#35bf28}+1.94\%$
test_view_td	61.9710μs	30.1457μs	33.1722 KOps/s	30.5372 KOps/s	$\textbf{\color{#35bf28}+8.63\%}$
test_unbind_pytree	59.0910μs	28.3140μs	35.3182 KOps/s	34.5054 KOps/s	$\color{#35bf28}+2.36\%$
test_unbind_td	0.7777ms	37.6174μs	26.5834 KOps/s	26.5855 KOps/s	$-0.01\%$
test_split_pytree	66.4810μs	29.5200μs	33.8754 KOps/s	32.6199 KOps/s	$\color{#35bf28}+3.85\%$
test_split_td	0.9448ms	39.1777μs	25.5247 KOps/s	24.3382 KOps/s	$\color{#35bf28}+4.88\%$
test_add_pytree	74.6310μs	35.4412μs	28.2157 KOps/s	28.0460 KOps/s	$\color{#35bf28}+0.61\%$
test_add_td	0.1850ms	45.3336μs	22.0587 KOps/s	18.8012 KOps/s	$\textbf{\color{#35bf28}+17.33\%}$
test_compile_add_one_nested[tensordict-compile]	0.1741ms	0.1255ms	7.9698 KOps/s	7.9683 KOps/s	$\color{#35bf28}+0.02\%$
test_compile_add_one_nested[tensordict-eager]	0.2705ms	0.1323ms	7.5558 KOps/s	7.4015 KOps/s	$\color{#35bf28}+2.09\%$
test_compile_add_one_nested[pytree-compile]	0.2373ms	96.1493μs	10.4005 KOps/s	10.2374 KOps/s	$\color{#35bf28}+1.59\%$
test_compile_add_one_nested[pytree-eager]	1.7363ms	0.1501ms	6.6614 KOps/s	6.5296 KOps/s	$\color{#35bf28}+2.02\%$
test_compile_copy_nested[tensordict-compile]	0.1257ms	24.0585μs	41.5654 KOps/s	42.0513 KOps/s	$\color{#d91a1a}-1.16\%$
test_compile_copy_nested[tensordict-eager]	0.1579ms	28.4433μs	35.1576 KOps/s	32.8563 KOps/s	$\textbf{\color{#35bf28}+7.00\%}$
test_compile_copy_nested[pytree-compile]	0.2512ms	64.6193μs	15.4752 KOps/s	15.2562 KOps/s	$\color{#35bf28}+1.44\%$
test_compile_copy_nested[pytree-eager]	85.6010μs	49.0528μs	20.3862 KOps/s	20.2533 KOps/s	$\color{#35bf28}+0.66\%$
test_compile_add_one_flat[tensordict-compile]	0.2172ms	0.1423ms	7.0298 KOps/s	6.7573 KOps/s	$\color{#35bf28}+4.03\%$
test_compile_add_one_flat[tensordict-eager]	0.3127ms	0.2140ms	4.6722 KOps/s	4.6591 KOps/s	$\color{#35bf28}+0.28\%$
test_compile_add_one_flat[tensorclass-compile]	0.2495ms	98.1162μs	10.1920 KOps/s	10.1505 KOps/s	$\color{#35bf28}+0.41\%$
test_compile_add_one_flat[tensorclass-eager]	0.2045ms	53.9409μs	18.5388 KOps/s	18.2329 KOps/s	$\color{#35bf28}+1.68\%$
test_compile_add_one_flat[pytree-compile]	0.1974ms	0.1358ms	7.3633 KOps/s	7.1923 KOps/s	$\color{#35bf28}+2.38\%$
test_compile_add_one_flat[pytree-eager]	0.6276ms	0.4851ms	2.0615 KOps/s	2.0190 KOps/s	$\color{#35bf28}+2.11\%$
test_compile_add_self_flat[tensordict-eager]	0.4003ms	0.2594ms	3.8548 KOps/s	3.8446 KOps/s	$\color{#35bf28}+0.26\%$
test_compile_add_self_flat[tensordict-compile]	0.1897ms	0.1430ms	6.9946 KOps/s	6.9607 KOps/s	$\color{#35bf28}+0.49\%$
test_compile_add_self_flat[tensorclass-eager]	0.2201ms	64.5748μs	15.4859 KOps/s	14.6009 KOps/s	$\textbf{\color{#35bf28}+6.06\%}$
test_compile_add_self_flat[tensorclass-compile]	0.1670ms	0.1000ms	9.9963 KOps/s	10.0277 KOps/s	$\color{#d91a1a}-0.31\%$
test_compile_add_self_flat[pytree-eager]	0.4797ms	0.4121ms	2.4264 KOps/s	2.4255 KOps/s	$\color{#35bf28}+0.04\%$
test_compile_add_self_flat[pytree-compile]	0.1870ms	0.1357ms	7.3717 KOps/s	7.4100 KOps/s	$\color{#d91a1a}-0.52\%$
test_compile_copy_flat[tensordict-compile]	0.1180ms	18.5428μs	53.9294 KOps/s	54.5150 KOps/s	$\color{#d91a1a}-1.07\%$
test_compile_copy_flat[tensordict-eager]	0.1183ms	31.7648μs	31.4814 KOps/s	31.8482 KOps/s	$\color{#d91a1a}-1.15\%$
test_compile_copy_flat[pytree-compile]	0.1398ms	70.9930μs	14.0859 KOps/s	14.2532 KOps/s	$\color{#d91a1a}-1.17\%$
test_compile_copy_flat[pytree-eager]	0.1205ms	51.3291μs	19.4821 KOps/s	19.3413 KOps/s	$\color{#35bf28}+0.73\%$
test_compile_assign_and_add[tensordict-compile]	1.5943ms	0.3858ms	2.5917 KOps/s	2.2398 KOps/s	$\textbf{\color{#35bf28}+15.71\%}$
test_compile_assign_and_add[tensordict-eager]	2.8432ms	2.6711ms	374.3722 Ops/s	354.5308 Ops/s	$\textbf{\color{#35bf28}+5.60\%}$
test_compile_assign_and_add[pytree-compile]	1.5752ms	0.3766ms	2.6556 KOps/s	2.2910 KOps/s	$\textbf{\color{#35bf28}+15.91\%}$
test_compile_assign_and_add[pytree-eager]	2.9309ms	2.7566ms	362.7699 Ops/s	370.4736 Ops/s	$\color{#d91a1a}-2.08\%$
test_compile_indexing[tensor-tensordict-compile]	0.2805ms	0.1184ms	8.4433 KOps/s	8.8273 KOps/s	$\color{#d91a1a}-4.35\%$
test_compile_indexing[tensor-tensordict-eager]	0.5951ms	84.4303μs	11.8441 KOps/s	12.5207 KOps/s	$\textbf{\color{#d91a1a}-5.40\%}$
test_compile_indexing[tensor-tensorclass-compile]	0.5202ms	0.1083ms	9.2348 KOps/s	9.5374 KOps/s	$\color{#d91a1a}-3.17\%$
test_compile_indexing[tensor-tensorclass-eager]	0.2195ms	70.6851μs	14.1472 KOps/s	14.5306 KOps/s	$\color{#d91a1a}-2.64\%$
test_compile_indexing[tensor-pytree-compile]	0.2559ms	0.1123ms	8.9031 KOps/s	9.4459 KOps/s	$\textbf{\color{#d91a1a}-5.75\%}$
test_compile_indexing[tensor-pytree-eager]	0.2457ms	72.2568μs	13.8395 KOps/s	13.8863 KOps/s	$\color{#d91a1a}-0.34\%$
test_compile_indexing[slice-tensordict-compile]	0.1501ms	0.1045ms	9.5693 KOps/s	9.9149 KOps/s	$\color{#d91a1a}-3.49\%$
test_compile_indexing[slice-tensordict-eager]	0.1455ms	17.3978μs	57.4784 KOps/s	55.5521 KOps/s	$\color{#35bf28}+3.47\%$
test_compile_indexing[slice-tensorclass-compile]	0.2464ms	98.6358μs	10.1383 KOps/s	10.2301 KOps/s	$\color{#d91a1a}-0.90\%$
test_compile_indexing[slice-tensorclass-eager]	70.1610μs	15.9613μs	62.6515 KOps/s	60.9104 KOps/s	$\color{#35bf28}+2.86\%$
test_compile_indexing[slice-pytree-compile]	0.1518ms	97.0835μs	10.3004 KOps/s	10.2305 KOps/s	$\color{#35bf28}+0.68\%$
test_compile_indexing[slice-pytree-eager]	53.3910μs	16.0626μs	62.2564 KOps/s	61.1954 KOps/s	$\color{#35bf28}+1.73\%$
test_compile_indexing[int-tensordict-compile]	0.2686ms	0.1031ms	9.7001 KOps/s	9.8546 KOps/s	$\color{#d91a1a}-1.57\%$
test_compile_indexing[int-tensordict-eager]	0.5634ms	17.2879μs	57.8441 KOps/s	55.6115 KOps/s	$\color{#35bf28}+4.01\%$
test_compile_indexing[int-tensorclass-compile]	0.1787ms	0.1011ms	9.8958 KOps/s	10.2352 KOps/s	$\color{#d91a1a}-3.32\%$
test_compile_indexing[int-tensorclass-eager]	57.5610μs	15.8046μs	63.2725 KOps/s	61.3751 KOps/s	$\color{#35bf28}+3.09\%$
test_compile_indexing[int-pytree-compile]	0.7500ms	96.6981μs	10.3415 KOps/s	10.2056 KOps/s	$\color{#35bf28}+1.33\%$
test_compile_indexing[int-pytree-eager]	43.4900μs	15.9492μs	62.6991 KOps/s	60.8192 KOps/s	$\color{#35bf28}+3.09\%$
test_mod_add[eager]	0.1824ms	36.2730μs	27.5687 KOps/s	25.4112 KOps/s	$\textbf{\color{#35bf28}+8.49\%}$
test_mod_add[compile]	0.4072ms	80.3317μs	12.4484 KOps/s	11.6498 KOps/s	$\textbf{\color{#35bf28}+6.85\%}$
test_mod_add[compile-overhead]	0.3207ms	0.1668ms	5.9964 KOps/s	5.7439 KOps/s	$\color{#35bf28}+4.39\%$
test_mod_wrap[eager]	0.3781ms	0.2486ms	4.0218 KOps/s	3.9008 KOps/s	$\color{#35bf28}+3.10\%$
test_mod_wrap[compile]	0.6709ms	0.2819ms	3.5480 KOps/s	3.4689 KOps/s	$\color{#35bf28}+2.28\%$
test_mod_wrap[compile-overhead]	7.1434ms	3.6915ms	270.8922 Ops/s	269.4441 Ops/s	$\color{#35bf28}+0.54\%$
test_mod_wrap_and_backward[eager]	1.4858ms	1.3599ms	735.3359 Ops/s	683.4156 Ops/s	$\textbf{\color{#35bf28}+7.60\%}$
test_mod_wrap_and_backward[compile]	1.3923ms	1.2768ms	783.1807 Ops/s	718.4075 Ops/s	$\textbf{\color{#35bf28}+9.02\%}$
test_mod_wrap_and_backward[compile-overhead]	1.3660ms	0.9155ms	1.0923 KOps/s	959.7846 Ops/s	$\textbf{\color{#35bf28}+13.81\%}$
test_seq_add[eager]	0.2636ms	0.1129ms	8.8566 KOps/s	8.2701 KOps/s	$\textbf{\color{#35bf28}+7.09\%}$
test_seq_add[compile]	0.1335ms	88.5698μs	11.2905 KOps/s	11.3892 KOps/s	$\color{#d91a1a}-0.87\%$
test_seq_add[compile-overhead]	0.2857ms	0.1299ms	7.7012 KOps/s	7.6687 KOps/s	$\color{#35bf28}+0.42\%$
test_seq_wrap[eager]	0.5609ms	0.4126ms	2.4237 KOps/s	2.3039 KOps/s	$\textbf{\color{#35bf28}+5.20\%}$
test_seq_wrap[compile]	0.4141ms	0.2994ms	3.3396 KOps/s	3.2875 KOps/s	$\color{#35bf28}+1.58\%$
test_seq_wrap[compile-overhead]	0.3148ms	0.2253ms	4.4392 KOps/s	4.3991 KOps/s	$\color{#35bf28}+0.91\%$
test_func_call_runtime[False-eager]	0.9019ms	0.7435ms	1.3449 KOps/s	1.3174 KOps/s	$\color{#35bf28}+2.09\%$
test_func_call_runtime[False-compile]	0.9109ms	0.7429ms	1.3460 KOps/s	1.3327 KOps/s	$\color{#35bf28}+1.00\%$
test_func_call_runtime[False-compile-overhead]	0.4119ms	0.3627ms	2.7571 KOps/s	2.7363 KOps/s	$\color{#35bf28}+0.76\%$
test_func_call_runtime[True-eager]	1.5152ms	0.9238ms	1.0825 KOps/s	1.0895 KOps/s	$\color{#d91a1a}-0.64\%$
test_func_call_runtime[True-compile]	0.9533ms	0.7631ms	1.3104 KOps/s	1.3016 KOps/s	$\color{#35bf28}+0.68\%$
test_func_call_runtime[True-compile-overhead]	0.5674ms	0.3814ms	2.6220 KOps/s	2.5865 KOps/s	$\color{#35bf28}+1.37\%$
test_func_call_cm_runtime[False-eager]	0.8716ms	0.7567ms	1.3215 KOps/s	1.3328 KOps/s	$\color{#d91a1a}-0.85\%$
test_func_call_cm_runtime[False-compile]	0.9045ms	0.7480ms	1.3369 KOps/s	1.3269 KOps/s	$\color{#35bf28}+0.75\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4294ms	0.3639ms	2.7478 KOps/s	2.7267 KOps/s	$\color{#35bf28}+0.77\%$
test_func_call_cm_runtime[True-eager]	1.1614ms	1.0083ms	991.7947 Ops/s	969.7468 Ops/s	$\color{#35bf28}+2.27\%$
test_func_call_cm_runtime[True-compile]	0.9431ms	0.7928ms	1.2613 KOps/s	1.2520 KOps/s	$\color{#35bf28}+0.74\%$
test_func_call_cm_runtime[True-compile-overhead]	0.4939ms	0.4094ms	2.4426 KOps/s	2.4177 KOps/s	$\color{#35bf28}+1.03\%$
test_vmap_func_call_cm_runtime[eager]	2.5426ms	2.0989ms	476.4384 Ops/s	470.7993 Ops/s	$\color{#35bf28}+1.20\%$
test_vmap_func_call_cm_runtime[compile]	1.2214ms	0.8038ms	1.2440 KOps/s	1.2234 KOps/s	$\color{#35bf28}+1.68\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.4929ms	0.4111ms	2.4324 KOps/s	2.4102 KOps/s	$\color{#35bf28}+0.92\%$
test_distributed	0.8303ms	0.1195ms	8.3699 KOps/s	8.4086 KOps/s	$\color{#d91a1a}-0.46\%$
test_tdmodule	0.7934ms	19.4353μs	51.4529 KOps/s	48.6925 KOps/s	$\textbf{\color{#35bf28}+5.67\%}$
test_tdmodule_dispatch	53.9810μs	32.9995μs	30.3035 KOps/s	26.7338 KOps/s	$\textbf{\color{#35bf28}+13.35\%}$
test_tdseq	49.8010μs	19.3137μs	51.7768 KOps/s	45.6183 KOps/s	$\textbf{\color{#35bf28}+13.50\%}$
test_tdseq_dispatch	70.4210μs	35.9407μs	27.8236 KOps/s	24.4911 KOps/s	$\textbf{\color{#35bf28}+13.61\%}$
test_instantiation_functorch	1.7914ms	1.5888ms	629.4130 Ops/s	625.3872 Ops/s	$\color{#35bf28}+0.64\%$
test_exec_functorch	0.2105ms	0.1485ms	6.7359 KOps/s	6.8090 KOps/s	$\color{#d91a1a}-1.07\%$
test_exec_functional_call	0.2491ms	0.1408ms	7.1001 KOps/s	6.9973 KOps/s	$\color{#35bf28}+1.47\%$
test_exec_td_decorator	0.3889ms	0.1904ms	5.2531 KOps/s	5.2594 KOps/s	$\color{#d91a1a}-0.12\%$
test_vmap_mlp_speed_decorator[True-True]	0.8283ms	0.6860ms	1.4577 KOps/s	1.4360 KOps/s	$\color{#35bf28}+1.51\%$
test_vmap_mlp_speed_decorator[True-False]	1.0623ms	0.6834ms	1.4632 KOps/s	1.4342 KOps/s	$\color{#35bf28}+2.02\%$
test_vmap_mlp_speed_decorator[False-True]	0.9809ms	0.5981ms	1.6720 KOps/s	1.6437 KOps/s	$\color{#35bf28}+1.73\%$
test_vmap_mlp_speed_decorator[False-False]	1.0259ms	0.6005ms	1.6654 KOps/s	1.6483 KOps/s	$\color{#35bf28}+1.03\%$
test_vmap_transformer_speed_decorator[True-True]	19.6190ms	19.2550ms	51.9346 Ops/s	51.0573 Ops/s	$\color{#35bf28}+1.72\%$
test_vmap_transformer_speed_decorator[True-False]	20.0185ms	19.3035ms	51.8042 Ops/s	51.5558 Ops/s	$\color{#35bf28}+0.48\%$
test_vmap_transformer_speed_decorator[False-True]	19.5492ms	19.1751ms	52.1510 Ops/s	51.9297 Ops/s	$\color{#35bf28}+0.43\%$
test_vmap_transformer_speed_decorator[False-False]	19.5156ms	19.1583ms	52.1966 Ops/s	51.9352 Ops/s	$\color{#35bf28}+0.50\%$
test_to_module_speed[True]	1.1323ms	0.9837ms	1.0166 KOps/s	1.0228 KOps/s	$\color{#d91a1a}-0.60\%$
test_to_module_speed[False]	1.3677ms	0.9806ms	1.0197 KOps/s	1.0416 KOps/s	$\color{#d91a1a}-2.10\%$
test_tc_init	55.5810μs	34.2965μs	29.1575 KOps/s	24.9484 KOps/s	$\textbf{\color{#35bf28}+16.87\%}$
test_tc_init_nested	99.5620μs	69.6505μs	14.3574 KOps/s	12.4842 KOps/s	$\textbf{\color{#35bf28}+15.00\%}$
test_tc_first_layer_tensor	55.1781μs	0.7150μs	1.3986 MOps/s	1.4245 MOps/s	$\color{#d91a1a}-1.82\%$
test_tc_first_layer_nontensor	0.3876ms	2.3843μs	419.4181 KOps/s	427.5639 KOps/s	$\color{#d91a1a}-1.91\%$
test_tc_second_layer_tensor	10.6103μs	1.4345μs	697.1001 KOps/s	698.0607 KOps/s	$\color{#d91a1a}-0.14\%$
test_tc_second_layer_nontensor	27.3510μs	3.0845μs	324.2029 KOps/s	325.9427 KOps/s	$\color{#d91a1a}-0.53\%$
test_unbind	0.2210s	11.8379ms	84.4743 Ops/s	143.4648 Ops/s	$\textbf{\color{#d91a1a}-41.12\%}$
test_full_like	9.7238ms	9.2195ms	108.4663 Ops/s	104.2675 Ops/s	$\color{#35bf28}+4.03\%$
test_zeros_like	4.9286ms	4.3261ms	231.1525 Ops/s	114.0217 Ops/s	$\textbf{\color{#35bf28}+102.73\%}$
test_ones_like	4.5497ms	4.3320ms	230.8419 Ops/s	230.6300 Ops/s	$\color{#35bf28}+0.09\%$
test_clone	6.9640ms	6.5014ms	153.8121 Ops/s	153.0906 Ops/s	$\color{#35bf28}+0.47\%$
test_squeeze	0.3954ms	9.4507μs	105.8125 KOps/s	102.9337 KOps/s	$\color{#35bf28}+2.80\%$
test_unsqueeze	0.1219ms	72.9322μs	13.7114 KOps/s	13.6304 KOps/s	$\color{#35bf28}+0.59\%$
test_split	0.5396ms	0.1589ms	6.2941 KOps/s	6.1078 KOps/s	$\color{#35bf28}+3.05\%$
test_permute	0.2290ms	0.1850ms	5.4047 KOps/s	5.4091 KOps/s	$\color{#d91a1a}-0.08\%$
test_stack	51.7324ms	51.0009ms	19.6075 Ops/s	19.5575 Ops/s	$\color{#35bf28}+0.26\%$
test_cat	51.4680ms	50.6931ms	19.7266 Ops/s	19.7601 Ops/s	$\color{#d91a1a}-0.17\%$