[Feature] Fix type assertion in Seq build

[vmoens]

Stack from ghstack (oldest at bottom):

• [Feature] Plotting TensorDictSequential graphs #1144
• -> [Feature] Fix type assertion in Seq build #1143
• [Feature] OrderedDict for TensorDictSequential #1142

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}15$. Worsened: $\large\color{#d91a1a}29$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	47.7890μs	21.5059μs	46.4989 KOps/s	49.9190 KOps/s	$\textbf{\color{#d91a1a}-6.85\%}$
test_plain_set_stack_nested	59.9620μs	21.3078μs	46.9312 KOps/s	49.2152 KOps/s	$\color{#d91a1a}-4.64\%$
test_plain_set_nested_inplace	91.0100μs	23.0281μs	43.4252 KOps/s	45.5892 KOps/s	$\color{#d91a1a}-4.75\%$
test_plain_set_stack_nested_inplace	86.9930μs	23.2109μs	43.0833 KOps/s	45.4356 KOps/s	$\textbf{\color{#d91a1a}-5.18\%}$
test_items	34.4340μs	4.1455μs	241.2255 KOps/s	244.4773 KOps/s	$\color{#d91a1a}-1.33\%$
test_items_nested	0.5993ms	0.3981ms	2.5121 KOps/s	2.4822 KOps/s	$\color{#35bf28}+1.20\%$
test_items_nested_locked	0.5423ms	0.3994ms	2.5040 KOps/s	2.5064 KOps/s	$\color{#d91a1a}-0.10\%$
test_items_nested_leaf	0.1551ms	76.1973μs	13.1238 KOps/s	12.9066 KOps/s	$\color{#35bf28}+1.68\%$
test_items_stack_nested	0.5303ms	0.4043ms	2.4737 KOps/s	2.4997 KOps/s	$\color{#d91a1a}-1.04\%$
test_items_stack_nested_leaf	0.1661ms	78.9406μs	12.6678 KOps/s	12.6418 KOps/s	$\color{#35bf28}+0.21\%$
test_items_stack_nested_locked	0.6864ms	0.4026ms	2.4841 KOps/s	2.4706 KOps/s	$\color{#35bf28}+0.55\%$
test_keys	25.0870μs	3.5337μs	282.9897 KOps/s	279.0355 KOps/s	$\color{#35bf28}+1.42\%$
test_keys_nested	0.2540ms	0.1647ms	6.0728 KOps/s	5.9782 KOps/s	$\color{#35bf28}+1.58\%$
test_keys_nested_locked	1.9563ms	0.1712ms	5.8412 KOps/s	5.7699 KOps/s	$\color{#35bf28}+1.24\%$
test_keys_nested_leaf	0.2719ms	0.1430ms	6.9910 KOps/s	6.9221 KOps/s	$\color{#35bf28}+1.00\%$
test_keys_stack_nested	0.2722ms	0.1650ms	6.0589 KOps/s	6.0468 KOps/s	$\color{#35bf28}+0.20\%$
test_keys_stack_nested_leaf	0.2647ms	0.1434ms	6.9758 KOps/s	6.9421 KOps/s	$\color{#35bf28}+0.49\%$
test_keys_stack_nested_locked	0.3078ms	0.1700ms	5.8824 KOps/s	5.7730 KOps/s	$\color{#35bf28}+1.90\%$
test_values	8.9306μs	1.0413μs	960.3059 KOps/s	958.1990 KOps/s	$\color{#35bf28}+0.22\%$
test_values_nested	0.1329ms	62.2398μs	16.0669 KOps/s	16.2037 KOps/s	$\color{#d91a1a}-0.84\%$
test_values_nested_locked	0.1149ms	62.9402μs	15.8881 KOps/s	15.7028 KOps/s	$\color{#35bf28}+1.18\%$
test_values_nested_leaf	0.1279ms	71.2166μs	14.0417 KOps/s	13.9574 KOps/s	$\color{#35bf28}+0.60\%$
test_values_stack_nested	0.1259ms	63.3705μs	15.7802 KOps/s	15.7517 KOps/s	$\color{#35bf28}+0.18\%$
test_values_stack_nested_leaf	0.1285ms	71.4722μs	13.9915 KOps/s	13.8151 KOps/s	$\color{#35bf28}+1.28\%$
test_values_stack_nested_locked	0.1196ms	63.4657μs	15.7565 KOps/s	15.8452 KOps/s	$\color{#d91a1a}-0.56\%$
test_membership	15.8700μs	0.8496μs	1.1770 MOps/s	1.1183 MOps/s	$\textbf{\color{#35bf28}+5.25\%}$
test_membership_nested	44.7430μs	2.9807μs	335.4879 KOps/s	328.5789 KOps/s	$\color{#35bf28}+2.10\%$
test_membership_nested_leaf	28.1920μs	3.0069μs	332.5690 KOps/s	320.5255 KOps/s	$\color{#35bf28}+3.76\%$
test_membership_stacked_nested	45.2540μs	2.9654μs	337.2244 KOps/s	326.9707 KOps/s	$\color{#35bf28}+3.14\%$
test_membership_stacked_nested_leaf	29.8860μs	2.9741μs	336.2364 KOps/s	325.3161 KOps/s	$\color{#35bf28}+3.36\%$
test_membership_nested_last	46.6670μs	4.4230μs	226.0902 KOps/s	220.9525 KOps/s	$\color{#35bf28}+2.33\%$
test_membership_nested_leaf_last	30.5570μs	4.4117μs	226.6705 KOps/s	222.2556 KOps/s	$\color{#35bf28}+1.99\%$
test_membership_stacked_nested_last	50.3630μs	4.3757μs	228.5341 KOps/s	190.1681 KOps/s	$\textbf{\color{#35bf28}+20.17\%}$
test_membership_stacked_nested_leaf_last	23.2230μs	4.3922μs	227.6786 KOps/s	187.3546 KOps/s	$\textbf{\color{#35bf28}+21.52\%}$
test_nested_getleaf	54.9320μs	10.9252μs	91.5314 KOps/s	93.4145 KOps/s	$\color{#d91a1a}-2.02\%$
test_nested_get	39.2430μs	10.3789μs	96.3495 KOps/s	99.4204 KOps/s	$\color{#d91a1a}-3.09\%$
test_stacked_getleaf	36.0670μs	10.8904μs	91.8236 KOps/s	94.5899 KOps/s	$\color{#d91a1a}-2.92\%$
test_stacked_get	55.5930μs	10.4602μs	95.6001 KOps/s	98.8746 KOps/s	$\color{#d91a1a}-3.31\%$
test_nested_getitemleaf	38.1610μs	11.3378μs	88.2007 KOps/s	90.1691 KOps/s	$\color{#d91a1a}-2.18\%$
test_nested_getitem	58.5160μs	10.5107μs	95.1409 KOps/s	95.3423 KOps/s	$\color{#d91a1a}-0.21\%$
test_stacked_getitemleaf	35.4460μs	11.2744μs	88.6968 KOps/s	89.4900 KOps/s	$\color{#d91a1a}-0.89\%$
test_stacked_getitem	32.1990μs	10.4513μs	95.6819 KOps/s	95.2316 KOps/s	$\color{#35bf28}+0.47\%$
test_lock_nested	4.4843ms	0.4588ms	2.1794 KOps/s	2.2076 KOps/s	$\color{#d91a1a}-1.28\%$
test_lock_stack_nested	0.6691ms	0.4299ms	2.3261 KOps/s	2.3398 KOps/s	$\color{#d91a1a}-0.59\%$
test_unlock_nested	0.8235ms	0.3762ms	2.6584 KOps/s	2.6533 KOps/s	$\color{#35bf28}+0.19\%$
test_unlock_stack_nested	0.5315ms	0.3479ms	2.8741 KOps/s	2.8731 KOps/s	$\color{#35bf28}+0.04\%$
test_flatten_speed	0.1825ms	99.1774μs	10.0829 KOps/s	9.8254 KOps/s	$\color{#35bf28}+2.62\%$
test_unflatten_speed	0.9217ms	0.5232ms	1.9113 KOps/s	1.9045 KOps/s	$\color{#35bf28}+0.35\%$
test_common_ops	1.6566ms	0.8194ms	1.2203 KOps/s	1.2979 KOps/s	$\textbf{\color{#d91a1a}-5.97\%}$
test_creation	44.1820μs	2.5526μs	391.7600 KOps/s	378.9265 KOps/s	$\color{#35bf28}+3.39\%$
test_creation_empty	36.0570μs	13.3152μs	75.1021 KOps/s	96.8051 KOps/s	$\textbf{\color{#d91a1a}-22.42\%}$
test_creation_nested_1	53.8800μs	16.3376μs	61.2086 KOps/s	74.8284 KOps/s	$\textbf{\color{#d91a1a}-18.20\%}$
test_creation_nested_2	66.6170μs	21.1296μs	47.3269 KOps/s	54.9547 KOps/s	$\textbf{\color{#d91a1a}-13.88\%}$
test_clone	67.7160μs	13.5903μs	73.5819 KOps/s	71.4493 KOps/s	$\color{#35bf28}+2.98\%$
test_getitem[int]	1.1724ms	12.6273μs	79.1937 KOps/s	78.2290 KOps/s	$\color{#35bf28}+1.23\%$
test_getitem[slice_int]	0.1405ms	24.8053μs	40.3139 KOps/s	41.2706 KOps/s	$\color{#d91a1a}-2.32\%$
test_getitem[range]	0.2249ms	49.2033μs	20.3238 KOps/s	20.8211 KOps/s	$\color{#d91a1a}-2.39\%$
test_getitem[tuple]	0.1319ms	20.1897μs	49.5303 KOps/s	49.7207 KOps/s	$\color{#d91a1a}-0.38\%$
test_getitem[list]	0.1717ms	44.5250μs	22.4593 KOps/s	23.1135 KOps/s	$\color{#d91a1a}-2.83\%$
test_setitem_dim[int]	59.8110μs	25.3824μs	39.3975 KOps/s	41.5765 KOps/s	$\textbf{\color{#d91a1a}-5.24\%}$
test_setitem_dim[slice_int]	0.1193ms	51.1324μs	19.5571 KOps/s	20.1424 KOps/s	$\color{#d91a1a}-2.91\%$
test_setitem_dim[range]	0.1281ms	73.0532μs	13.6887 KOps/s	13.9109 KOps/s	$\color{#d91a1a}-1.60\%$
test_setitem_dim[tuple]	60.9830μs	40.3506μs	24.7828 KOps/s	25.5191 KOps/s	$\color{#d91a1a}-2.89\%$
test_setitem	81.2710μs	22.1077μs	45.2331 KOps/s	50.2658 KOps/s	$\textbf{\color{#d91a1a}-10.01\%}$
test_set	78.7670μs	21.7071μs	46.0680 KOps/s	51.7980 KOps/s	$\textbf{\color{#d91a1a}-11.06\%}$
test_set_shared	4.6228ms	0.1688ms	5.9254 KOps/s	5.9156 KOps/s	$\color{#35bf28}+0.17\%$
test_update	0.1290ms	25.8077μs	38.7481 KOps/s	47.0906 KOps/s	$\textbf{\color{#d91a1a}-17.72\%}$
test_update_nested	85.1690μs	35.5604μs	28.1212 KOps/s	31.1650 KOps/s	$\textbf{\color{#d91a1a}-9.77\%}$
test_update__nested	0.7440ms	34.7050μs	28.8143 KOps/s	29.0831 KOps/s	$\color{#d91a1a}-0.92\%$
test_set_nested	70.4410μs	23.7919μs	42.0311 KOps/s	45.8072 KOps/s	$\textbf{\color{#d91a1a}-8.24\%}$
test_set_nested_new	93.2530μs	28.6632μs	34.8880 KOps/s	38.2204 KOps/s	$\textbf{\color{#d91a1a}-8.72\%}$
test_select	89.5770μs	45.2765μs	22.0865 KOps/s	23.3993 KOps/s	$\textbf{\color{#d91a1a}-5.61\%}$
test_select_nested	0.1275ms	62.9811μs	15.8778 KOps/s	15.7089 KOps/s	$\color{#35bf28}+1.08\%$
test_exclude_nested	0.1561ms	81.1791μs	12.3184 KOps/s	12.0578 KOps/s	$\color{#35bf28}+2.16\%$
test_empty[True]	0.7056ms	0.4168ms	2.3995 KOps/s	2.3753 KOps/s	$\color{#35bf28}+1.02\%$
test_empty[False]	11.6768μs	1.3956μs	716.5451 KOps/s	695.7539 KOps/s	$\color{#35bf28}+2.99\%$
test_unbind_speed	0.3958ms	0.2724ms	3.6706 KOps/s	3.6446 KOps/s	$\color{#35bf28}+0.71\%$
test_unbind_speed_stack0	0.4063ms	0.2701ms	3.7027 KOps/s	3.7517 KOps/s	$\color{#d91a1a}-1.31\%$
test_unbind_speed_stack1	0.1082s	0.8290ms	1.2063 KOps/s	1.3713 KOps/s	$\textbf{\color{#d91a1a}-12.03\%}$
test_split	2.4459ms	1.5792ms	633.2316 Ops/s	559.8547 Ops/s	$\textbf{\color{#35bf28}+13.11\%}$
test_chunk	0.1055s	1.8944ms	527.8672 Ops/s	560.0845 Ops/s	$\textbf{\color{#d91a1a}-5.75\%}$
test_consolidate_njt[False-None]	9.2102ms	8.1245ms	123.0850 Ops/s	122.4022 Ops/s	$\color{#35bf28}+0.56\%$
test_creation[device0]	4.6937ms	93.5674μs	10.6875 KOps/s	10.9892 KOps/s	$\color{#d91a1a}-2.75\%$
test_creation_from_tensor	0.3014ms	95.3325μs	10.4896 KOps/s	10.6564 KOps/s	$\color{#d91a1a}-1.57\%$
test_add_one[memmap_tensor0]	0.1172ms	4.5853μs	218.0870 KOps/s	200.3032 KOps/s	$\textbf{\color{#35bf28}+8.88\%}$
test_contiguous[memmap_tensor0]	19.0150μs	0.5117μs	1.9542 MOps/s	1.9156 MOps/s	$\color{#35bf28}+2.01\%$
test_stack[memmap_tensor0]	28.5630μs	3.3646μs	297.2109 KOps/s	287.2690 KOps/s	$\color{#35bf28}+3.46\%$
test_memmaptd_index	1.0515ms	0.2397ms	4.1711 KOps/s	4.1692 KOps/s	$\color{#35bf28}+0.05\%$
test_memmaptd_index_astensor	0.5687ms	0.3275ms	3.0533 KOps/s	3.0282 KOps/s	$\color{#35bf28}+0.83\%$
test_memmaptd_index_op	0.9735ms	0.6348ms	1.5754 KOps/s	1.7479 KOps/s	$\textbf{\color{#d91a1a}-9.87\%}$
test_serialize_model	0.1256s	0.1157s	8.6453 Ops/s	8.5987 Ops/s	$\color{#35bf28}+0.54\%$
test_serialize_model_pickle	0.4311s	0.3923s	2.5494 Ops/s	2.5804 Ops/s	$\color{#d91a1a}-1.20\%$
test_serialize_weights	0.1233s	0.1155s	8.6613 Ops/s	8.6100 Ops/s	$\color{#35bf28}+0.60\%$
test_serialize_weights_returnearly	0.2536s	0.1728s	5.7886 Ops/s	6.4250 Ops/s	$\textbf{\color{#d91a1a}-9.90\%}$
test_serialize_weights_pickle	0.5546s	0.4559s	2.1935 Ops/s	2.4034 Ops/s	$\textbf{\color{#d91a1a}-8.73\%}$
test_serialize_weights_filesystem	0.1481s	0.1410s	7.0901 Ops/s	7.0569 Ops/s	$\color{#35bf28}+0.47\%$
test_serialize_model_filesystem	0.1554s	0.1471s	6.7965 Ops/s	5.8084 Ops/s	$\textbf{\color{#35bf28}+17.01\%}$
test_reshape_pytree	52.7380μs	26.3366μs	37.9700 KOps/s	36.0292 KOps/s	$\textbf{\color{#35bf28}+5.39\%}$
test_reshape_td	88.0240μs	33.6125μs	29.7509 KOps/s	30.5052 KOps/s	$\color{#d91a1a}-2.47\%$
test_view_pytree	82.2000μs	26.4274μs	37.8395 KOps/s	37.1514 KOps/s	$\color{#35bf28}+1.85\%$
test_view_td	89.4060μs	38.3475μs	26.0773 KOps/s	26.0564 KOps/s	$\color{#35bf28}+0.08\%$
test_unbind_pytree	75.7510μs	29.2872μs	34.1446 KOps/s	33.6318 KOps/s	$\color{#35bf28}+1.52\%$
test_unbind_td	0.3714ms	40.2090μs	24.8700 KOps/s	24.8312 KOps/s	$\color{#35bf28}+0.16\%$
test_split_pytree	74.6390μs	29.1414μs	34.3154 KOps/s	33.9005 KOps/s	$\color{#35bf28}+1.22\%$
test_split_td	0.1014s	53.4701μs	18.7020 KOps/s	21.6343 KOps/s	$\textbf{\color{#d91a1a}-13.55\%}$
test_add_pytree	86.2410μs	35.2093μs	28.4016 KOps/s	27.7907 KOps/s	$\color{#35bf28}+2.20\%$
test_add_td	0.1610ms	60.5379μs	16.5186 KOps/s	18.4674 KOps/s	$\textbf{\color{#d91a1a}-10.55\%}$
test_compile_add_one_nested[tensordict-compile]	0.1383ms	62.6310μs	15.9665 KOps/s	15.8526 KOps/s	$\color{#35bf28}+0.72\%$
test_compile_add_one_nested[tensordict-eager]	0.3653ms	0.1704ms	5.8671 KOps/s	5.8494 KOps/s	$\color{#35bf28}+0.30\%$
test_compile_add_one_nested[pytree-compile]	0.1119ms	45.8005μs	21.8338 KOps/s	21.9699 KOps/s	$\color{#d91a1a}-0.62\%$
test_compile_add_one_nested[pytree-eager]	0.2896ms	0.1201ms	8.3254 KOps/s	8.3660 KOps/s	$\color{#d91a1a}-0.49\%$
test_compile_copy_nested[tensordict-compile]	88.3340μs	26.4191μs	37.8513 KOps/s	38.5142 KOps/s	$\color{#d91a1a}-1.72\%$
test_compile_copy_nested[tensordict-eager]	0.1160ms	59.3971μs	16.8358 KOps/s	16.7194 KOps/s	$\color{#35bf28}+0.70\%$
test_compile_copy_nested[pytree-compile]	0.1709ms	79.1660μs	12.6317 KOps/s	12.5742 KOps/s	$\color{#35bf28}+0.46\%$
test_compile_copy_nested[pytree-eager]	0.1392ms	67.8960μs	14.7284 KOps/s	14.6668 KOps/s	$\color{#35bf28}+0.42\%$
test_compile_add_one_flat[tensordict-compile]	0.2148ms	0.1058ms	9.4531 KOps/s	9.5422 KOps/s	$\color{#d91a1a}-0.93\%$
test_compile_add_one_flat[tensordict-eager]	0.4816ms	0.2168ms	4.6123 KOps/s	4.5907 KOps/s	$\color{#35bf28}+0.47\%$
test_compile_add_one_flat[tensorclass-compile]	0.1089ms	44.7255μs	22.3586 KOps/s	22.2206 KOps/s	$\color{#35bf28}+0.62\%$
test_compile_add_one_flat[tensorclass-eager]	0.4984ms	66.0459μs	15.1410 KOps/s	15.4997 KOps/s	$\color{#d91a1a}-2.31\%$
test_compile_add_one_flat[pytree-compile]	0.2096ms	0.1026ms	9.7434 KOps/s	9.6773 KOps/s	$\color{#35bf28}+0.68\%$
test_compile_add_one_flat[pytree-eager]	0.3720ms	0.1995ms	5.0115 KOps/s	4.9287 KOps/s	$\color{#35bf28}+1.68\%$
test_compile_add_self_flat[tensordict-eager]	0.4064ms	0.2318ms	4.3137 KOps/s	4.2692 KOps/s	$\color{#35bf28}+1.04\%$
test_compile_add_self_flat[tensordict-compile]	0.1969ms	0.1055ms	9.4810 KOps/s	9.6511 KOps/s	$\color{#d91a1a}-1.76\%$
test_compile_add_self_flat[tensorclass-eager]	0.1382ms	61.6237μs	16.2275 KOps/s	17.2521 KOps/s	$\textbf{\color{#d91a1a}-5.94\%}$
test_compile_add_self_flat[tensorclass-compile]	0.1175ms	47.0265μs	21.2646 KOps/s	21.9601 KOps/s	$\color{#d91a1a}-3.17\%$
test_compile_add_self_flat[pytree-eager]	0.6442ms	0.1580ms	6.3290 KOps/s	6.3111 KOps/s	$\color{#35bf28}+0.28\%$
test_compile_add_self_flat[pytree-compile]	0.2080ms	0.1050ms	9.5251 KOps/s	9.8528 KOps/s	$\color{#d91a1a}-3.33\%$
test_compile_copy_flat[tensordict-compile]	52.8490μs	20.9648μs	47.6990 KOps/s	44.7735 KOps/s	$\textbf{\color{#35bf28}+6.53\%}$
test_compile_copy_flat[tensordict-eager]	0.1291ms	64.1630μs	15.5853 KOps/s	14.6573 KOps/s	$\textbf{\color{#35bf28}+6.33\%}$
test_compile_copy_flat[pytree-compile]	0.1515ms	80.0668μs	12.4896 KOps/s	12.2976 KOps/s	$\color{#35bf28}+1.56\%$
test_compile_copy_flat[pytree-eager]	0.1414ms	68.1198μs	14.6800 KOps/s	14.4562 KOps/s	$\color{#35bf28}+1.55\%$
test_compile_assign_and_add[tensordict-compile]	0.3020ms	0.2115ms	4.7281 KOps/s	4.7484 KOps/s	$\color{#d91a1a}-0.43\%$
test_compile_assign_and_add[tensordict-eager]	1.5059ms	1.2982ms	770.2902 Ops/s	765.7462 Ops/s	$\color{#35bf28}+0.59\%$
test_compile_assign_and_add[pytree-compile]	0.4038ms	0.2061ms	4.8513 KOps/s	4.7734 KOps/s	$\color{#35bf28}+1.63\%$
test_compile_assign_and_add[pytree-eager]	0.9674ms	0.7693ms	1.2999 KOps/s	1.2870 KOps/s	$\color{#35bf28}+1.00\%$
test_compile_assign_and_add_stack[compile]	0.5665ms	0.4666ms	2.1431 KOps/s	2.1746 KOps/s	$\color{#d91a1a}-1.45\%$
test_compile_assign_and_add_stack[eager]	4.3036ms	2.7804ms	359.6620 Ops/s	381.3326 Ops/s	$\textbf{\color{#d91a1a}-5.68\%}$
test_compile_indexing[tensor-tensordict-compile]	98.8750μs	36.3749μs	27.4915 KOps/s	27.5813 KOps/s	$\color{#d91a1a}-0.33\%$
test_compile_indexing[tensor-tensordict-eager]	0.4790ms	32.2581μs	30.9999 KOps/s	30.0607 KOps/s	$\color{#35bf28}+3.12\%$
test_compile_indexing[tensor-tensorclass-compile]	0.1057ms	28.9664μs	34.5228 KOps/s	33.1941 KOps/s	$\color{#35bf28}+4.00\%$
test_compile_indexing[tensor-tensorclass-eager]	74.3790μs	22.7093μs	44.0348 KOps/s	42.2762 KOps/s	$\color{#35bf28}+4.16\%$
test_compile_indexing[tensor-pytree-compile]	0.1241ms	30.4727μs	32.8163 KOps/s	32.8437 KOps/s	$\color{#d91a1a}-0.08\%$
test_compile_indexing[tensor-pytree-eager]	86.4440μs	22.6782μs	44.0951 KOps/s	42.0892 KOps/s	$\color{#35bf28}+4.77\%$
test_compile_indexing[slice-tensordict-compile]	0.1236ms	51.9324μs	19.2558 KOps/s	19.0181 KOps/s	$\color{#35bf28}+1.25\%$
test_compile_indexing[slice-tensordict-eager]	0.5166ms	19.2624μs	51.9145 KOps/s	48.4481 KOps/s	$\textbf{\color{#35bf28}+7.15\%}$
test_compile_indexing[slice-tensorclass-compile]	0.3173ms	45.2493μs	22.0998 KOps/s	22.2123 KOps/s	$\color{#d91a1a}-0.51\%$
test_compile_indexing[slice-tensorclass-eager]	0.2316ms	18.8879μs	52.9440 KOps/s	53.0635 KOps/s	$\color{#d91a1a}-0.23\%$
test_compile_indexing[slice-pytree-compile]	0.1215ms	45.5337μs	21.9617 KOps/s	21.9450 KOps/s	$\color{#35bf28}+0.08\%$
test_compile_indexing[slice-pytree-eager]	65.8250μs	18.5398μs	53.9380 KOps/s	53.2883 KOps/s	$\color{#35bf28}+1.22\%$
test_compile_indexing[int-tensordict-compile]	0.1114ms	54.2556μs	18.4313 KOps/s	18.6548 KOps/s	$\color{#d91a1a}-1.20\%$
test_compile_indexing[int-tensordict-eager]	1.0088ms	19.2278μs	52.0080 KOps/s	48.4590 KOps/s	$\textbf{\color{#35bf28}+7.32\%}$
test_compile_indexing[int-tensorclass-compile]	0.1037ms	45.6886μs	21.8873 KOps/s	22.2625 KOps/s	$\color{#d91a1a}-1.69\%$
test_compile_indexing[int-tensorclass-eager]	64.6500μs	18.0115μs	55.5201 KOps/s	52.8842 KOps/s	$\color{#35bf28}+4.98\%$
test_compile_indexing[int-pytree-compile]	96.4200μs	45.3798μs	22.0362 KOps/s	22.0650 KOps/s	$\color{#d91a1a}-0.13\%$
test_compile_indexing[int-pytree-eager]	55.1930μs	18.1506μs	55.0945 KOps/s	53.0878 KOps/s	$\color{#35bf28}+3.78\%$
test_mod_add[eager]	0.1278ms	35.3404μs	28.2962 KOps/s	28.7959 KOps/s	$\color{#d91a1a}-1.74\%$
test_mod_add[compile]	0.1323ms	49.1472μs	20.3471 KOps/s	20.1541 KOps/s	$\color{#35bf28}+0.96\%$
test_mod_add[compile-overhead]	0.1752ms	50.5899μs	19.7668 KOps/s	20.2411 KOps/s	$\color{#d91a1a}-2.34\%$
test_mod_wrap[eager]	0.3559ms	0.2258ms	4.4295 KOps/s	4.5351 KOps/s	$\color{#d91a1a}-2.33\%$
test_mod_wrap[compile]	0.3868ms	0.2105ms	4.7501 KOps/s	4.8005 KOps/s	$\color{#d91a1a}-1.05\%$
test_mod_wrap[compile-overhead]	0.3947ms	0.2041ms	4.8988 KOps/s	4.8296 KOps/s	$\color{#35bf28}+1.43\%$
test_mod_wrap_and_backward[eager]	14.7641ms	12.9667ms	77.1206 Ops/s	88.0142 Ops/s	$\textbf{\color{#d91a1a}-12.38\%}$
test_mod_wrap_and_backward[compile]	15.9159ms	13.5458ms	73.8234 Ops/s	83.6756 Ops/s	$\textbf{\color{#d91a1a}-11.77\%}$
test_mod_wrap_and_backward[compile-overhead]	16.0968ms	14.0173ms	71.3402 Ops/s	74.5056 Ops/s	$\color{#d91a1a}-4.25\%$
test_seq_add[eager]	0.2288ms	0.1175ms	8.5101 KOps/s	8.5478 KOps/s	$\color{#d91a1a}-0.44\%$
test_seq_add[compile]	0.1306ms	63.1559μs	15.8338 KOps/s	15.6267 KOps/s	$\color{#35bf28}+1.33\%$
test_seq_add[compile-overhead]	0.1188ms	61.3649μs	16.2960 KOps/s	16.1583 KOps/s	$\color{#35bf28}+0.85\%$
test_seq_wrap[eager]	0.5456ms	0.4486ms	2.2291 KOps/s	2.2392 KOps/s	$\color{#d91a1a}-0.45\%$
test_seq_wrap[compile]	0.3600ms	0.2292ms	4.3634 KOps/s	4.2815 KOps/s	$\color{#35bf28}+1.91\%$
test_seq_wrap[compile-overhead]	0.3334ms	0.2272ms	4.4010 KOps/s	4.2892 KOps/s	$\color{#35bf28}+2.61\%$
test_func_call_runtime[False-eager]	0.7962ms	0.5448ms	1.8356 KOps/s	1.8368 KOps/s	$\color{#d91a1a}-0.07\%$
test_func_call_runtime[False-compile]	0.8105ms	0.4350ms	2.2988 KOps/s	2.3237 KOps/s	$\color{#d91a1a}-1.07\%$
test_func_call_runtime[False-compile-overhead]	0.8169ms	0.4331ms	2.3088 KOps/s	2.3345 KOps/s	$\color{#d91a1a}-1.10\%$
test_func_call_runtime[True-eager]	0.9494ms	0.7573ms	1.3205 KOps/s	1.3132 KOps/s	$\color{#35bf28}+0.56\%$
test_func_call_runtime[True-compile]	0.9219ms	0.4745ms	2.1076 KOps/s	2.1092 KOps/s	$\color{#d91a1a}-0.08\%$
test_func_call_runtime[True-compile-overhead]	0.6534ms	0.4736ms	2.1116 KOps/s	2.1202 KOps/s	$\color{#d91a1a}-0.40\%$
test_func_call_cm_runtime[False-eager]	0.7568ms	0.5433ms	1.8407 KOps/s	1.8555 KOps/s	$\color{#d91a1a}-0.80\%$
test_func_call_cm_runtime[False-compile]	0.5515ms	0.4314ms	2.3181 KOps/s	2.3420 KOps/s	$\color{#d91a1a}-1.02\%$
test_func_call_cm_runtime[False-compile-overhead]	0.5217ms	0.4302ms	2.3247 KOps/s	2.3383 KOps/s	$\color{#d91a1a}-0.58\%$
test_func_call_cm_runtime[True-eager]	1.0354ms	0.9095ms	1.0995 KOps/s	1.1126 KOps/s	$\color{#d91a1a}-1.17\%$
test_func_call_cm_runtime[True-compile]	0.7055ms	0.4979ms	2.0085 KOps/s	2.0022 KOps/s	$\color{#35bf28}+0.32\%$
test_func_call_cm_runtime[True-compile-overhead]	0.5971ms	0.4986ms	2.0055 KOps/s	2.0266 KOps/s	$\color{#d91a1a}-1.04\%$
test_vmap_func_call_cm_runtime[eager]	2.8172ms	1.8910ms	528.8067 Ops/s	523.9026 Ops/s	$\color{#35bf28}+0.94\%$
test_vmap_func_call_cm_runtime[compile]	0.7640ms	0.5176ms	1.9320 KOps/s	1.9110 KOps/s	$\color{#35bf28}+1.10\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.8822ms	0.5286ms	1.8917 KOps/s	1.8857 KOps/s	$\color{#35bf28}+0.32\%$
test_distributed	0.3506ms	0.1249ms	8.0043 KOps/s	7.6983 KOps/s	$\color{#35bf28}+3.98\%$
test_tdmodule	87.6840μs	27.7480μs	36.0386 KOps/s	39.3394 KOps/s	$\textbf{\color{#d91a1a}-8.39\%}$
test_tdmodule_dispatch	85.5690μs	51.0441μs	19.5909 KOps/s	21.2136 KOps/s	$\textbf{\color{#d91a1a}-7.65\%}$
test_tdseq	54.2320μs	31.0672μs	32.1883 KOps/s	35.4732 KOps/s	$\textbf{\color{#d91a1a}-9.26\%}$
test_tdseq_dispatch	92.5230μs	57.3849μs	17.4262 KOps/s	19.0649 KOps/s	$\textbf{\color{#d91a1a}-8.60\%}$
test_instantiation_functorch	1.6766ms	1.5430ms	648.1007 Ops/s	647.3676 Ops/s	$\color{#35bf28}+0.11\%$
test_exec_functorch	0.4002ms	0.1798ms	5.5614 KOps/s	5.5576 KOps/s	$\color{#35bf28}+0.07\%$
test_exec_functional_call	0.2993ms	0.1698ms	5.8891 KOps/s	5.7901 KOps/s	$\color{#35bf28}+1.71\%$
test_exec_td_decorator	0.4604ms	0.2309ms	4.3306 KOps/s	4.2687 KOps/s	$\color{#35bf28}+1.45\%$
test_vmap_mlp_speed_decorator[True-True]	0.9588ms	0.6558ms	1.5248 KOps/s	1.5298 KOps/s	$\color{#d91a1a}-0.33\%$
test_vmap_mlp_speed_decorator[True-False]	1.0232ms	0.6650ms	1.5037 KOps/s	1.5258 KOps/s	$\color{#d91a1a}-1.45\%$
test_vmap_mlp_speed_decorator[False-True]	0.7644ms	0.5276ms	1.8953 KOps/s	1.8822 KOps/s	$\color{#35bf28}+0.69\%$
test_vmap_mlp_speed_decorator[False-False]	0.9908ms	0.5300ms	1.8869 KOps/s	1.8937 KOps/s	$\color{#d91a1a}-0.36\%$
test_to_module_speed[True]	2.1367ms	1.3552ms	737.8772 Ops/s	735.6328 Ops/s	$\color{#35bf28}+0.31\%$
test_to_module_speed[False]	1.8680ms	1.3050ms	766.2951 Ops/s	755.3887 Ops/s	$\color{#35bf28}+1.44\%$
test_tc_init	78.4260μs	48.1931μs	20.7499 KOps/s	21.0080 KOps/s	$\color{#d91a1a}-1.23\%$
test_tc_init_nested	0.2062ms	96.9936μs	10.3100 KOps/s	10.5852 KOps/s	$\color{#d91a1a}-2.60\%$
test_tc_first_layer_tensor	19.5170μs	1.4960μs	668.4379 KOps/s	664.7539 KOps/s	$\color{#35bf28}+0.55\%$
test_tc_first_layer_nontensor	56.2280μs	4.5991μs	217.4335 KOps/s	216.2035 KOps/s	$\color{#35bf28}+0.57\%$
test_tc_second_layer_tensor	26.6490μs	2.8256μs	353.9100 KOps/s	348.2270 KOps/s	$\color{#35bf28}+1.63\%$
test_tc_second_layer_nontensor	33.2110μs	6.0382μs	165.6115 KOps/s	166.7328 KOps/s	$\color{#d91a1a}-0.67\%$
test_unbind	0.2256s	13.5186ms	73.9723 Ops/s	74.4842 Ops/s	$\color{#d91a1a}-0.69\%$
test_full_like	8.7752ms	7.4975ms	133.3775 Ops/s	77.5345 Ops/s	$\textbf{\color{#35bf28}+72.02\%}$
test_zeros_like	3.3098ms	2.8127ms	355.5352 Ops/s	133.1422 Ops/s	$\textbf{\color{#35bf28}+167.03\%}$
test_ones_like	3.9439ms	3.3192ms	301.2732 Ops/s	129.1386 Ops/s	$\textbf{\color{#35bf28}+133.29\%}$
test_clone	5.5596ms	5.1178ms	195.3980 Ops/s	108.2378 Ops/s	$\textbf{\color{#35bf28}+80.53\%}$
test_squeeze	69.5900μs	12.3341μs	81.0758 KOps/s	82.3877 KOps/s	$\color{#d91a1a}-1.59\%$
test_unsqueeze	0.4779ms	91.2210μs	10.9624 KOps/s	10.6166 KOps/s	$\color{#35bf28}+3.26\%$
test_split	0.3646ms	0.1933ms	5.1738 KOps/s	5.0829 KOps/s	$\color{#35bf28}+1.79\%$
test_permute	0.3279ms	0.2094ms	4.7754 KOps/s	4.9231 KOps/s	$\color{#d91a1a}-3.00\%$
test_stack	29.5587ms	25.6816ms	38.9385 Ops/s	39.8134 Ops/s	$\color{#d91a1a}-2.20\%$
test_cat	31.1958ms	25.5176ms	39.1887 Ops/s	40.5116 Ops/s	$\color{#d91a1a}-3.27\%$

[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: $\large\color{#d91a1a}9$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	55.9230μs	11.8442μs	84.4295 KOps/s	77.2659 KOps/s	$\textbf{\color{#35bf28}+9.27\%}$
test_plain_set_stack_nested	37.9820μs	11.5507μs	86.5751 KOps/s	76.1515 KOps/s	$\textbf{\color{#35bf28}+13.69\%}$
test_plain_set_nested_inplace	38.2620μs	12.5478μs	79.6955 KOps/s	70.4397 KOps/s	$\textbf{\color{#35bf28}+13.14\%}$
test_plain_set_stack_nested_inplace	42.9720μs	12.5677μs	79.5693 KOps/s	71.3065 KOps/s	$\textbf{\color{#35bf28}+11.59\%}$
test_items	32.8920μs	2.9458μs	339.4609 KOps/s	329.6168 KOps/s	$\color{#35bf28}+2.99\%$
test_items_nested	0.4114ms	0.3574ms	2.7979 KOps/s	2.7810 KOps/s	$\color{#35bf28}+0.61\%$
test_items_nested_locked	0.4081ms	0.3566ms	2.8044 KOps/s	2.7769 KOps/s	$\color{#35bf28}+0.99\%$
test_items_nested_leaf	0.1003ms	58.6790μs	17.0419 KOps/s	17.1030 KOps/s	$\color{#d91a1a}-0.36\%$
test_items_stack_nested	0.4136ms	0.3575ms	2.7972 KOps/s	2.7494 KOps/s	$\color{#35bf28}+1.74\%$
test_items_stack_nested_leaf	95.3540μs	59.6739μs	16.7577 KOps/s	16.3244 KOps/s	$\color{#35bf28}+2.65\%$
test_items_stack_nested_locked	0.4049ms	0.3594ms	2.7827 KOps/s	2.7282 KOps/s	$\color{#35bf28}+2.00\%$
test_keys	25.3810μs	3.4542μs	289.4991 KOps/s	288.2230 KOps/s	$\color{#35bf28}+0.44\%$
test_keys_nested	0.1151ms	81.2530μs	12.3072 KOps/s	12.1248 KOps/s	$\color{#35bf28}+1.50\%$
test_keys_nested_locked	0.7953ms	87.1378μs	11.4761 KOps/s	11.3288 KOps/s	$\color{#35bf28}+1.30\%$
test_keys_nested_leaf	0.1010ms	72.2783μs	13.8354 KOps/s	13.6624 KOps/s	$\color{#35bf28}+1.27\%$
test_keys_stack_nested	0.1177ms	82.8867μs	12.0647 KOps/s	11.9673 KOps/s	$\color{#35bf28}+0.81\%$
test_keys_stack_nested_leaf	0.1060ms	73.5792μs	13.5908 KOps/s	13.2239 KOps/s	$\color{#35bf28}+2.77\%$
test_keys_stack_nested_locked	0.1261ms	88.5177μs	11.2972 KOps/s	11.2337 KOps/s	$\color{#35bf28}+0.57\%$
test_values	6.3185μs	0.8487μs	1.1783 MOps/s	1.1778 MOps/s	$\color{#35bf28}+0.05\%$
test_values_nested	68.2630μs	34.8715μs	28.6767 KOps/s	28.8075 KOps/s	$\color{#d91a1a}-0.45\%$
test_values_nested_locked	68.1230μs	36.7324μs	27.2239 KOps/s	27.4359 KOps/s	$\color{#d91a1a}-0.77\%$
test_values_nested_leaf	71.1340μs	39.2087μs	25.5046 KOps/s	25.5398 KOps/s	$\color{#d91a1a}-0.14\%$
test_values_stack_nested	64.7630μs	35.2740μs	28.3495 KOps/s	28.5713 KOps/s	$\color{#d91a1a}-0.78\%$
test_values_stack_nested_leaf	73.1630μs	39.6612μs	25.2136 KOps/s	24.9783 KOps/s	$\color{#35bf28}+0.94\%$
test_values_stack_nested_locked	66.1030μs	36.9813μs	27.0407 KOps/s	27.1037 KOps/s	$\color{#d91a1a}-0.23\%$
test_membership	1.9136μs	0.5053μs	1.9790 MOps/s	1.9613 MOps/s	$\color{#35bf28}+0.90\%$
test_membership_nested	33.2220μs	2.0651μs	484.2284 KOps/s	489.3407 KOps/s	$\color{#d91a1a}-1.04\%$
test_membership_nested_leaf	14.4005μs	1.9882μs	502.9732 KOps/s	487.5556 KOps/s	$\color{#35bf28}+3.16\%$
test_membership_stacked_nested	45.1520μs	2.0924μs	477.9253 KOps/s	473.2531 KOps/s	$\color{#35bf28}+0.99\%$
test_membership_stacked_nested_leaf	43.6720μs	2.1009μs	475.9976 KOps/s	477.7572 KOps/s	$\color{#d91a1a}-0.37\%$
test_membership_nested_last	36.2410μs	3.1227μs	320.2366 KOps/s	321.6279 KOps/s	$\color{#d91a1a}-0.43\%$
test_membership_nested_leaf_last	26.1710μs	3.1600μs	316.4545 KOps/s	323.6410 KOps/s	$\color{#d91a1a}-2.22\%$
test_membership_stacked_nested_last	42.0720μs	3.1224μs	320.2658 KOps/s	192.2122 KOps/s	$\textbf{\color{#35bf28}+66.62\%}$
test_membership_stacked_nested_leaf_last	36.0610μs	3.1395μs	318.5203 KOps/s	190.9872 KOps/s	$\textbf{\color{#35bf28}+66.78\%}$
test_nested_getleaf	42.2720μs	6.2603μs	159.7358 KOps/s	161.5620 KOps/s	$\color{#d91a1a}-1.13\%$
test_nested_get	34.1920μs	5.8377μs	171.2992 KOps/s	168.2032 KOps/s	$\color{#35bf28}+1.84\%$
test_stacked_getleaf	29.8610μs	6.2021μs	161.2345 KOps/s	161.5852 KOps/s	$\color{#d91a1a}-0.22\%$
test_stacked_get	33.2420μs	5.8930μs	169.6939 KOps/s	172.0031 KOps/s	$\color{#d91a1a}-1.34\%$
test_nested_getitemleaf	33.8110μs	6.2418μs	160.2105 KOps/s	160.3220 KOps/s	$\color{#d91a1a}-0.07\%$
test_nested_getitem	29.6720μs	5.9548μs	167.9316 KOps/s	165.9038 KOps/s	$\color{#35bf28}+1.22\%$
test_stacked_getitemleaf	36.1110μs	6.2708μs	159.4700 KOps/s	158.6620 KOps/s	$\color{#35bf28}+0.51\%$
test_stacked_getitem	34.2720μs	6.0200μs	166.1124 KOps/s	168.3457 KOps/s	$\color{#d91a1a}-1.33\%$
test_lock_nested	9.5225ms	0.3900ms	2.5638 KOps/s	2.5535 KOps/s	$\color{#35bf28}+0.40\%$
test_lock_stack_nested	0.3943ms	0.3496ms	2.8605 KOps/s	2.8571 KOps/s	$\color{#35bf28}+0.12\%$
test_unlock_nested	0.6125ms	0.3176ms	3.1484 KOps/s	3.0756 KOps/s	$\color{#35bf28}+2.37\%$
test_unlock_stack_nested	0.3284ms	0.2873ms	3.4805 KOps/s	3.4677 KOps/s	$\color{#35bf28}+0.37\%$
test_flatten_speed	0.1410ms	76.5846μs	13.0575 KOps/s	13.0628 KOps/s	$\color{#d91a1a}-0.04\%$
test_unflatten_speed	0.3884ms	0.3255ms	3.0719 KOps/s	3.0605 KOps/s	$\color{#35bf28}+0.37\%$
test_common_ops	1.6943ms	0.5794ms	1.7260 KOps/s	1.5538 KOps/s	$\textbf{\color{#35bf28}+11.08\%}$
test_creation	0.1658ms	1.7772μs	562.6815 KOps/s	558.9314 KOps/s	$\color{#35bf28}+0.67\%$
test_creation_empty	32.7920μs	6.5473μs	152.7357 KOps/s	109.4430 KOps/s	$\textbf{\color{#35bf28}+39.56\%}$
test_creation_nested_1	52.4330μs	8.1656μs	122.4653 KOps/s	92.5464 KOps/s	$\textbf{\color{#35bf28}+32.33\%}$
test_creation_nested_2	41.4820μs	10.9482μs	91.3396 KOps/s	73.5950 KOps/s	$\textbf{\color{#35bf28}+24.11\%}$
test_clone	65.5530μs	10.6907μs	93.5394 KOps/s	87.6295 KOps/s	$\textbf{\color{#35bf28}+6.74\%}$
test_getitem[int]	1.8596ms	10.9417μs	91.3935 KOps/s	88.0540 KOps/s	$\color{#35bf28}+3.79\%$
test_getitem[slice_int]	92.5196ms	29.6577μs	33.7181 KOps/s	45.5562 KOps/s	$\textbf{\color{#d91a1a}-25.99\%}$
test_getitem[range]	0.1270ms	38.3356μs	26.0854 KOps/s	25.4177 KOps/s	$\color{#35bf28}+2.63\%$
test_getitem[tuple]	0.1053ms	18.2743μs	54.7215 KOps/s	53.0820 KOps/s	$\color{#35bf28}+3.09\%$
test_getitem[list]	0.2406ms	33.3399μs	29.9941 KOps/s	28.7578 KOps/s	$\color{#35bf28}+4.30\%$
test_setitem_dim[int]	38.8710μs	19.1595μs	52.1935 KOps/s	48.7041 KOps/s	$\textbf{\color{#35bf28}+7.16\%}$
test_setitem_dim[slice_int]	66.2630μs	38.8652μs	25.7299 KOps/s	25.2685 KOps/s	$\color{#35bf28}+1.83\%$
test_setitem_dim[range]	85.2740μs	54.1017μs	18.4837 KOps/s	18.1798 KOps/s	$\color{#35bf28}+1.67\%$
test_setitem_dim[tuple]	59.8130μs	32.9895μs	30.3127 KOps/s	30.6657 KOps/s	$\color{#d91a1a}-1.15\%$
test_setitem	90.3640μs	14.2126μs	70.3600 KOps/s	61.0037 KOps/s	$\textbf{\color{#35bf28}+15.34\%}$
test_set	98.1350μs	13.6290μs	73.3728 KOps/s	62.8471 KOps/s	$\textbf{\color{#35bf28}+16.75\%}$
test_set_shared	1.7114ms	0.1503ms	6.6546 KOps/s	6.5752 KOps/s	$\color{#35bf28}+1.21\%$
test_update	0.5075ms	15.6683μs	63.8233 KOps/s	52.7659 KOps/s	$\textbf{\color{#35bf28}+20.96\%}$
test_update_nested	89.8150μs	20.9284μs	47.7820 KOps/s	40.5328 KOps/s	$\textbf{\color{#35bf28}+17.88\%}$
test_update__nested	1.1373ms	25.8751μs	38.6472 KOps/s	37.4408 KOps/s	$\color{#35bf28}+3.22\%$
test_set_nested	90.2750μs	15.0953μs	66.2458 KOps/s	57.6678 KOps/s	$\textbf{\color{#35bf28}+14.87\%}$
test_set_nested_new	96.3750μs	17.3937μs	57.4921 KOps/s	46.9451 KOps/s	$\textbf{\color{#35bf28}+22.47\%}$
test_select	98.1640μs	29.0698μs	34.4000 KOps/s	31.8353 KOps/s	$\textbf{\color{#35bf28}+8.06\%}$
test_select_nested	0.1011ms	43.9360μs	22.7604 KOps/s	22.4969 KOps/s	$\color{#35bf28}+1.17\%$
test_exclude_nested	0.3654ms	63.2214μs	15.8174 KOps/s	15.6764 KOps/s	$\color{#35bf28}+0.90\%$
test_empty[True]	0.3372ms	0.2915ms	3.4310 KOps/s	3.3428 KOps/s	$\color{#35bf28}+2.64\%$
test_empty[False]	3.2931μs	0.8390μs	1.1919 MOps/s	1.1848 MOps/s	$\color{#35bf28}+0.60\%$
test_to	89.1840μs	57.3614μs	17.4333 KOps/s	17.3594 KOps/s	$\color{#35bf28}+0.43\%$
test_to_nonblocking	94.4150μs	48.4185μs	20.6533 KOps/s	20.5283 KOps/s	$\color{#35bf28}+0.61\%$
test_unbind_speed	1.5752ms	0.2402ms	4.1631 KOps/s	4.0831 KOps/s	$\color{#35bf28}+1.96\%$
test_unbind_speed_stack0	0.3462ms	0.2426ms	4.1213 KOps/s	4.1486 KOps/s	$\color{#d91a1a}-0.66\%$
test_unbind_speed_stack1	92.2622ms	0.6774ms	1.4762 KOps/s	1.4637 KOps/s	$\color{#35bf28}+0.85\%$
test_split	93.4879ms	1.6000ms	624.9839 Ops/s	618.0519 Ops/s	$\color{#35bf28}+1.12\%$
test_chunk	95.5987ms	1.5969ms	626.2197 Ops/s	611.1953 Ops/s	$\color{#35bf28}+2.46\%$
test_consolidate[False-None]	3.0467ms	2.7442ms	364.4053 Ops/s	333.6729 Ops/s	$\textbf{\color{#35bf28}+9.21\%}$
test_consolidate[default-None]	1.8341ms	1.7421ms	574.0251 Ops/s	576.2903 Ops/s	$\color{#d91a1a}-0.39\%$
test_consolidate[reduce-overhead-None]	1.9073ms	1.7978ms	556.2240 Ops/s	562.6862 Ops/s	$\color{#d91a1a}-1.15\%$
test_consolidate_njt[False-None]	6.8759ms	6.7720ms	147.6659 Ops/s	150.4629 Ops/s	$\color{#d91a1a}-1.86\%$
test_to[False-False-None]	1.8189ms	1.7106ms	584.5871 Ops/s	578.7292 Ops/s	$\color{#35bf28}+1.01\%$
test_to[True-False-None]	1.5712ms	1.3599ms	735.3275 Ops/s	714.6530 Ops/s	$\color{#35bf28}+2.89\%$
test_to[within-False-None]	4.4217ms	4.2022ms	237.9702 Ops/s	234.1992 Ops/s	$\color{#35bf28}+1.61\%$
test_to[True-default-None]	5.6363ms	5.4457ms	183.6302 Ops/s	190.0264 Ops/s	$\color{#d91a1a}-3.37\%$
test_to_njt[False-False-None]	7.4890ms	7.2104ms	138.6894 Ops/s	144.5584 Ops/s	$\color{#d91a1a}-4.06\%$
test_to_njt[True-False-None]	5.9117ms	5.7293ms	174.5418 Ops/s	183.3496 Ops/s	$\color{#d91a1a}-4.80\%$
test_to_njt[within-False-None]	0.3237s	15.7937ms	63.3164 Ops/s	83.4418 Ops/s	$\textbf{\color{#d91a1a}-24.12\%}$
test_creation[device0]	0.4658ms	79.3763μs	12.5982 KOps/s	12.2363 KOps/s	$\color{#35bf28}+2.96\%$
test_creation_from_tensor	0.5141ms	84.2750μs	11.8659 KOps/s	11.6878 KOps/s	$\color{#35bf28}+1.52\%$
test_add_one[memmap_tensor0]	0.3995ms	6.6909μs	149.4565 KOps/s	140.3904 KOps/s	$\textbf{\color{#35bf28}+6.46\%}$
test_contiguous[memmap_tensor0]	5.1658μs	0.4303μs	2.3240 MOps/s	2.2669 MOps/s	$\color{#35bf28}+2.52\%$
test_stack[memmap_tensor0]	33.0510μs	4.4639μs	224.0173 KOps/s	218.1435 KOps/s	$\color{#35bf28}+2.69\%$
test_memmaptd_index	1.4826ms	0.2505ms	3.9915 KOps/s	3.8544 KOps/s	$\color{#35bf28}+3.56\%$
test_memmaptd_index_astensor	0.5760ms	0.3114ms	3.2108 KOps/s	3.1100 KOps/s	$\color{#35bf28}+3.24\%$
test_memmaptd_index_op	0.9614ms	0.5523ms	1.8107 KOps/s	1.6069 KOps/s	$\textbf{\color{#35bf28}+12.68\%}$
test_serialize_model	0.1307s	0.1299s	7.6975 Ops/s	7.6992 Ops/s	$\color{#d91a1a}-0.02\%$
test_serialize_model_pickle	1.3470s	1.1881s	0.8417 Ops/s	0.8237 Ops/s	$\color{#35bf28}+2.18\%$
test_serialize_weights	0.1304s	0.1292s	7.7394 Ops/s	7.7513 Ops/s	$\color{#d91a1a}-0.15\%$
test_serialize_weights_returnearly	0.3258s	53.7160ms	18.6164 Ops/s	15.7836 Ops/s	$\textbf{\color{#35bf28}+17.95\%}$
test_serialize_weights_pickle	1.4138s	1.2299s	0.8131 Ops/s	0.8226 Ops/s	$\color{#d91a1a}-1.16\%$
test_reshape_pytree	63.1730μs	22.2997μs	44.8437 KOps/s	45.1602 KOps/s	$\color{#d91a1a}-0.70\%$
test_reshape_td	60.5130μs	26.9976μs	37.0403 KOps/s	36.7535 KOps/s	$\color{#35bf28}+0.78\%$
test_view_pytree	53.8930μs	22.0725μs	45.3052 KOps/s	45.6051 KOps/s	$\color{#d91a1a}-0.66\%$
test_view_td	70.4230μs	29.7542μs	33.6087 KOps/s	32.1572 KOps/s	$\color{#35bf28}+4.51\%$
test_unbind_pytree	66.1430μs	28.0429μs	35.6596 KOps/s	35.3960 KOps/s	$\color{#35bf28}+0.74\%$
test_unbind_td	0.5751ms	36.7750μs	27.1924 KOps/s	26.6095 KOps/s	$\color{#35bf28}+2.19\%$
test_split_pytree	83.6640μs	30.0914μs	33.2321 KOps/s	33.1820 KOps/s	$\color{#35bf28}+0.15\%$
test_split_td	0.7366ms	37.8797μs	26.3994 KOps/s	25.0764 KOps/s	$\textbf{\color{#35bf28}+5.28\%}$
test_add_pytree	73.9740μs	35.3267μs	28.3072 KOps/s	27.9619 KOps/s	$\color{#35bf28}+1.24\%$
test_add_td	0.1027ms	50.8393μs	19.6698 KOps/s	19.8017 KOps/s	$\color{#d91a1a}-0.67\%$
test_compile_add_one_nested[tensordict-compile]	0.1824ms	0.1233ms	8.1098 KOps/s	8.0937 KOps/s	$\color{#35bf28}+0.20\%$
test_compile_add_one_nested[tensordict-eager]	0.3028ms	0.1351ms	7.4035 KOps/s	7.8318 KOps/s	$\textbf{\color{#d91a1a}-5.47\%}$
test_compile_add_one_nested[pytree-compile]	0.1483ms	0.1007ms	9.9293 KOps/s	10.2824 KOps/s	$\color{#d91a1a}-3.43\%$
test_compile_add_one_nested[pytree-eager]	1.2130ms	0.1476ms	6.7759 KOps/s	6.5289 KOps/s	$\color{#35bf28}+3.78\%$
test_compile_copy_nested[tensordict-compile]	62.1630μs	23.1849μs	43.1316 KOps/s	47.4178 KOps/s	$\textbf{\color{#d91a1a}-9.04\%}$
test_compile_copy_nested[tensordict-eager]	60.0830μs	29.5709μs	33.8171 KOps/s	33.5207 KOps/s	$\color{#35bf28}+0.88\%$
test_compile_copy_nested[pytree-compile]	0.2896ms	64.8950μs	15.4095 KOps/s	15.2462 KOps/s	$\color{#35bf28}+1.07\%$
test_compile_copy_nested[pytree-eager]	0.1055ms	48.6141μs	20.5702 KOps/s	20.3431 KOps/s	$\color{#35bf28}+1.12\%$
test_compile_add_one_flat[tensordict-compile]	0.2015ms	0.1429ms	6.9973 KOps/s	6.9685 KOps/s	$\color{#35bf28}+0.41\%$
test_compile_add_one_flat[tensordict-eager]	0.3097ms	0.2170ms	4.6078 KOps/s	4.6956 KOps/s	$\color{#d91a1a}-1.87\%$
test_compile_add_one_flat[tensorclass-compile]	0.1485ms	98.3950μs	10.1631 KOps/s	9.9657 KOps/s	$\color{#35bf28}+1.98\%$
test_compile_add_one_flat[tensorclass-eager]	0.1092ms	54.4517μs	18.3649 KOps/s	17.9188 KOps/s	$\color{#35bf28}+2.49\%$
test_compile_add_one_flat[pytree-compile]	0.1972ms	0.1357ms	7.3704 KOps/s	7.2966 KOps/s	$\color{#35bf28}+1.01\%$
test_compile_add_one_flat[pytree-eager]	0.5453ms	0.4792ms	2.0870 KOps/s	1.9895 KOps/s	$\color{#35bf28}+4.90\%$
test_compile_add_self_flat[tensordict-eager]	0.3742ms	0.2586ms	3.8666 KOps/s	3.8262 KOps/s	$\color{#35bf28}+1.06\%$
test_compile_add_self_flat[tensordict-compile]	0.1926ms	0.1418ms	7.0500 KOps/s	6.9626 KOps/s	$\color{#35bf28}+1.25\%$
test_compile_add_self_flat[tensorclass-eager]	0.1682ms	63.7524μs	15.6857 KOps/s	15.4105 KOps/s	$\color{#35bf28}+1.79\%$
test_compile_add_self_flat[tensorclass-compile]	0.1653ms	98.2164μs	10.1816 KOps/s	10.0443 KOps/s	$\color{#35bf28}+1.37\%$
test_compile_add_self_flat[pytree-eager]	0.5269ms	0.4076ms	2.4535 KOps/s	2.4102 KOps/s	$\color{#35bf28}+1.79\%$
test_compile_add_self_flat[pytree-compile]	0.2039ms	0.1385ms	7.2214 KOps/s	7.2814 KOps/s	$\color{#d91a1a}-0.82\%$
test_compile_copy_flat[tensordict-compile]	0.1132ms	17.4226μs	57.3967 KOps/s	57.6422 KOps/s	$\color{#d91a1a}-0.43\%$
test_compile_copy_flat[tensordict-eager]	62.0730μs	31.5014μs	31.7446 KOps/s	32.0507 KOps/s	$\color{#d91a1a}-0.96\%$
test_compile_copy_flat[pytree-compile]	0.1719ms	69.8470μs	14.3170 KOps/s	14.4036 KOps/s	$\color{#d91a1a}-0.60\%$
test_compile_copy_flat[pytree-eager]	0.1271ms	51.3155μs	19.4873 KOps/s	19.6169 KOps/s	$\color{#d91a1a}-0.66\%$
test_compile_assign_and_add[tensordict-compile]	1.6276ms	0.3913ms	2.5556 KOps/s	2.2091 KOps/s	$\textbf{\color{#35bf28}+15.69\%}$
test_compile_assign_and_add[tensordict-eager]	2.7630ms	2.6330ms	379.7929 Ops/s	385.5393 Ops/s	$\color{#d91a1a}-1.49\%$
test_compile_assign_and_add[pytree-compile]	1.6388ms	0.4404ms	2.2707 KOps/s	2.2516 KOps/s	$\color{#35bf28}+0.85\%$
test_compile_assign_and_add[pytree-eager]	2.9337ms	2.7210ms	367.5149 Ops/s	373.0145 Ops/s	$\color{#d91a1a}-1.47\%$
test_compile_indexing[tensor-tensordict-compile]	0.6065ms	0.1199ms	8.3419 KOps/s	8.8135 KOps/s	$\textbf{\color{#d91a1a}-5.35\%}$
test_compile_indexing[tensor-tensordict-eager]	0.5734ms	85.4993μs	11.6960 KOps/s	12.4874 KOps/s	$\textbf{\color{#d91a1a}-6.34\%}$
test_compile_indexing[tensor-tensorclass-compile]	0.3818ms	0.1114ms	8.9771 KOps/s	9.1347 KOps/s	$\color{#d91a1a}-1.72\%$
test_compile_indexing[tensor-tensorclass-eager]	0.1277ms	74.5897μs	13.4067 KOps/s	14.5489 KOps/s	$\textbf{\color{#d91a1a}-7.85\%}$
test_compile_indexing[tensor-pytree-compile]	0.2181ms	0.1139ms	8.7806 KOps/s	8.9724 KOps/s	$\color{#d91a1a}-2.14\%$
test_compile_indexing[tensor-pytree-eager]	0.1397ms	74.4564μs	13.4307 KOps/s	14.5710 KOps/s	$\textbf{\color{#d91a1a}-7.83\%}$
test_compile_indexing[slice-tensordict-compile]	0.1546ms	0.1058ms	9.4481 KOps/s	9.7926 KOps/s	$\color{#d91a1a}-3.52\%$
test_compile_indexing[slice-tensordict-eager]	0.1431ms	17.0948μs	58.4972 KOps/s	55.0804 KOps/s	$\textbf{\color{#35bf28}+6.20\%}$
test_compile_indexing[slice-tensorclass-compile]	0.1395ms	97.3578μs	10.2714 KOps/s	10.1966 KOps/s	$\color{#35bf28}+0.73\%$
test_compile_indexing[slice-tensorclass-eager]	75.7730μs	15.7296μs	63.5744 KOps/s	61.2080 KOps/s	$\color{#35bf28}+3.87\%$
test_compile_indexing[slice-pytree-compile]	0.1598ms	98.2687μs	10.1762 KOps/s	10.1289 KOps/s	$\color{#35bf28}+0.47\%$
test_compile_indexing[slice-pytree-eager]	68.8330μs	15.7182μs	63.6205 KOps/s	61.9115 KOps/s	$\color{#35bf28}+2.76\%$
test_compile_indexing[int-tensordict-compile]	0.1511ms	0.1026ms	9.7425 KOps/s	9.5507 KOps/s	$\color{#35bf28}+2.01\%$
test_compile_indexing[int-tensordict-eager]	0.5733ms	17.0261μs	58.7335 KOps/s	56.0998 KOps/s	$\color{#35bf28}+4.69\%$
test_compile_indexing[int-tensorclass-compile]	0.1505ms	0.1026ms	9.7462 KOps/s	10.1145 KOps/s	$\color{#d91a1a}-3.64\%$
test_compile_indexing[int-tensorclass-eager]	60.5930μs	15.6772μs	63.7870 KOps/s	61.8620 KOps/s	$\color{#35bf28}+3.11\%$
test_compile_indexing[int-pytree-compile]	0.2700ms	97.7010μs	10.2353 KOps/s	10.1818 KOps/s	$\color{#35bf28}+0.53\%$
test_compile_indexing[int-pytree-eager]	49.8530μs	15.7919μs	63.3235 KOps/s	61.8952 KOps/s	$\color{#35bf28}+2.31\%$
test_mod_add[eager]	0.1018ms	36.3415μs	27.5167 KOps/s	26.2757 KOps/s	$\color{#35bf28}+4.72\%$
test_mod_add[compile]	0.3627ms	81.2125μs	12.3134 KOps/s	12.4467 KOps/s	$\color{#d91a1a}-1.07\%$
test_mod_add[compile-overhead]	0.3272ms	0.1678ms	5.9580 KOps/s	5.6337 KOps/s	$\textbf{\color{#35bf28}+5.76\%}$
test_mod_wrap[eager]	0.3476ms	0.2528ms	3.9551 KOps/s	3.8850 KOps/s	$\color{#35bf28}+1.80\%$
test_mod_wrap[compile]	0.5309ms	0.2921ms	3.4234 KOps/s	3.4477 KOps/s	$\color{#d91a1a}-0.71\%$
test_mod_wrap[compile-overhead]	7.1891ms	3.8077ms	262.6269 Ops/s	267.1338 Ops/s	$\color{#d91a1a}-1.69\%$
test_mod_wrap_and_backward[eager]	1.5201ms	1.3707ms	729.5595 Ops/s	677.4140 Ops/s	$\textbf{\color{#35bf28}+7.70\%}$
test_mod_wrap_and_backward[compile]	1.3941ms	1.2721ms	786.1002 Ops/s	717.2833 Ops/s	$\textbf{\color{#35bf28}+9.59\%}$
test_mod_wrap_and_backward[compile-overhead]	1.3818ms	0.9215ms	1.0852 KOps/s	935.5978 Ops/s	$\textbf{\color{#35bf28}+15.99\%}$
test_seq_add[eager]	0.1647ms	0.1094ms	9.1413 KOps/s	8.2003 KOps/s	$\textbf{\color{#35bf28}+11.48\%}$
test_seq_add[compile]	0.2732ms	87.8220μs	11.3867 KOps/s	10.7761 KOps/s	$\textbf{\color{#35bf28}+5.67\%}$
test_seq_add[compile-overhead]	0.1720ms	0.1290ms	7.7519 KOps/s	7.2732 KOps/s	$\textbf{\color{#35bf28}+6.58\%}$
test_seq_wrap[eager]	0.5668ms	0.4088ms	2.4462 KOps/s	2.2127 KOps/s	$\textbf{\color{#35bf28}+10.55\%}$
test_seq_wrap[compile]	0.3624ms	0.3005ms	3.3276 KOps/s	3.1709 KOps/s	$\color{#35bf28}+4.94\%$
test_seq_wrap[compile-overhead]	0.3275ms	0.2270ms	4.4051 KOps/s	4.2309 KOps/s	$\color{#35bf28}+4.12\%$
test_func_call_runtime[False-eager]	0.9364ms	0.7661ms	1.3053 KOps/s	1.3340 KOps/s	$\color{#d91a1a}-2.15\%$
test_func_call_runtime[False-compile]	0.8786ms	0.7704ms	1.2980 KOps/s	1.3329 KOps/s	$\color{#d91a1a}-2.61\%$
test_func_call_runtime[False-compile-overhead]	0.4167ms	0.3681ms	2.7164 KOps/s	2.7372 KOps/s	$\color{#d91a1a}-0.76\%$
test_func_call_runtime[True-eager]	1.0120ms	0.9041ms	1.1061 KOps/s	1.0835 KOps/s	$\color{#35bf28}+2.09\%$
test_func_call_runtime[True-compile]	0.8568ms	0.7696ms	1.2993 KOps/s	1.2964 KOps/s	$\color{#35bf28}+0.22\%$
test_func_call_runtime[True-compile-overhead]	0.4468ms	0.3912ms	2.5563 KOps/s	2.5807 KOps/s	$\color{#d91a1a}-0.95\%$
test_func_call_cm_runtime[False-eager]	0.8434ms	0.7357ms	1.3592 KOps/s	1.2818 KOps/s	$\textbf{\color{#35bf28}+6.04\%}$
test_func_call_cm_runtime[False-compile]	0.8316ms	0.7449ms	1.3424 KOps/s	1.3288 KOps/s	$\color{#35bf28}+1.02\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4220ms	0.3713ms	2.6931 KOps/s	2.7176 KOps/s	$\color{#d91a1a}-0.90\%$
test_func_call_cm_runtime[True-eager]	1.1301ms	1.0078ms	992.2369 Ops/s	981.2217 Ops/s	$\color{#35bf28}+1.12\%$
test_func_call_cm_runtime[True-compile]	0.8482ms	0.7937ms	1.2600 KOps/s	1.2176 KOps/s	$\color{#35bf28}+3.48\%$
test_func_call_cm_runtime[True-compile-overhead]	0.4661ms	0.4192ms	2.3857 KOps/s	2.4043 KOps/s	$\color{#d91a1a}-0.77\%$
test_vmap_func_call_cm_runtime[eager]	2.5500ms	2.1064ms	474.7507 Ops/s	468.7180 Ops/s	$\color{#35bf28}+1.29\%$
test_vmap_func_call_cm_runtime[compile]	0.9308ms	0.8108ms	1.2334 KOps/s	1.2162 KOps/s	$\color{#35bf28}+1.42\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.4969ms	0.4181ms	2.3919 KOps/s	2.3740 KOps/s	$\color{#35bf28}+0.75\%$
test_distributed	0.8664ms	0.1214ms	8.2392 KOps/s	8.1789 KOps/s	$\color{#35bf28}+0.74\%$
test_tdmodule	0.1095ms	17.7923μs	56.2042 KOps/s	47.6218 KOps/s	$\textbf{\color{#35bf28}+18.02\%}$
test_tdmodule_dispatch	65.7040μs	31.5826μs	31.6630 KOps/s	27.8621 KOps/s	$\textbf{\color{#35bf28}+13.64\%}$
test_tdseq	45.3520μs	18.9280μs	52.8317 KOps/s	47.8748 KOps/s	$\textbf{\color{#35bf28}+10.35\%}$
test_tdseq_dispatch	70.6330μs	34.9979μs	28.5732 KOps/s	25.3988 KOps/s	$\textbf{\color{#35bf28}+12.50\%}$
test_instantiation_functorch	1.6407ms	1.5564ms	642.5027 Ops/s	618.0826 Ops/s	$\color{#35bf28}+3.95\%$
test_exec_functorch	0.1963ms	0.1434ms	6.9758 KOps/s	6.6586 KOps/s	$\color{#35bf28}+4.76\%$
test_exec_functional_call	0.1829ms	0.1363ms	7.3381 KOps/s	7.0577 KOps/s	$\color{#35bf28}+3.97\%$
test_exec_td_decorator	0.3827ms	0.1856ms	5.3877 KOps/s	5.2150 KOps/s	$\color{#35bf28}+3.31\%$
test_vmap_mlp_speed_decorator[True-True]	0.8315ms	0.6825ms	1.4652 KOps/s	1.4366 KOps/s	$\color{#35bf28}+1.99\%$
test_vmap_mlp_speed_decorator[True-False]	0.8281ms	0.6802ms	1.4702 KOps/s	1.4380 KOps/s	$\color{#35bf28}+2.24\%$
test_vmap_mlp_speed_decorator[False-True]	0.7064ms	0.6001ms	1.6663 KOps/s	1.6581 KOps/s	$\color{#35bf28}+0.49\%$
test_vmap_mlp_speed_decorator[False-False]	0.7196ms	0.6003ms	1.6659 KOps/s	1.6404 KOps/s	$\color{#35bf28}+1.56\%$
test_vmap_transformer_speed_decorator[True-True]	19.5277ms	19.3939ms	51.5626 Ops/s	51.2238 Ops/s	$\color{#35bf28}+0.66\%$
test_vmap_transformer_speed_decorator[True-False]	20.1527ms	19.3798ms	51.6001 Ops/s	51.3030 Ops/s	$\color{#35bf28}+0.58\%$
test_vmap_transformer_speed_decorator[False-True]	19.4047ms	19.2701ms	51.8938 Ops/s	51.8895 Ops/s	$+0.01\%$
test_vmap_transformer_speed_decorator[False-False]	19.4053ms	19.2478ms	51.9539 Ops/s	51.7999 Ops/s	$\color{#35bf28}+0.30\%$
test_to_module_speed[True]	1.0678ms	0.9586ms	1.0432 KOps/s	1.0288 KOps/s	$\color{#35bf28}+1.39\%$
test_to_module_speed[False]	1.0403ms	0.9482ms	1.0547 KOps/s	1.0455 KOps/s	$\color{#35bf28}+0.88\%$
test_tc_init	59.9930μs	33.6802μs	29.6910 KOps/s	26.5861 KOps/s	$\textbf{\color{#35bf28}+11.68\%}$
test_tc_init_nested	0.1060ms	67.1630μs	14.8892 KOps/s	13.1680 KOps/s	$\textbf{\color{#35bf28}+13.07\%}$
test_tc_first_layer_tensor	5.2831μs	0.7161μs	1.3964 MOps/s	1.4071 MOps/s	$\color{#d91a1a}-0.76\%$
test_tc_first_layer_nontensor	24.4210μs	2.3796μs	420.2358 KOps/s	429.7391 KOps/s	$\color{#d91a1a}-2.21\%$
test_tc_second_layer_tensor	10.8203μs	1.4413μs	693.8258 KOps/s	693.2755 KOps/s	$\color{#35bf28}+0.08\%$
test_tc_second_layer_nontensor	31.0420μs	3.1340μs	319.0785 KOps/s	324.4051 KOps/s	$\color{#d91a1a}-1.64\%$
test_unbind	0.2229s	10.4147ms	96.0179 Ops/s	140.3513 Ops/s	$\textbf{\color{#d91a1a}-31.59\%}$
test_full_like	9.7556ms	9.3379ms	107.0910 Ops/s	106.0877 Ops/s	$\color{#35bf28}+0.95\%$
test_zeros_like	5.2407ms	4.3514ms	229.8105 Ops/s	233.9259 Ops/s	$\color{#d91a1a}-1.76\%$
test_ones_like	4.9760ms	4.3521ms	229.7730 Ops/s	230.3114 Ops/s	$\color{#d91a1a}-0.23\%$
test_clone	6.9929ms	6.5732ms	152.1328 Ops/s	107.8015 Ops/s	$\textbf{\color{#35bf28}+41.12\%}$
test_squeeze	57.1630μs	9.4551μs	105.7634 KOps/s	108.3551 KOps/s	$\color{#d91a1a}-2.39\%$
test_unsqueeze	0.1220ms	70.5002μs	14.1844 KOps/s	14.0558 KOps/s	$\color{#35bf28}+0.91\%$
test_split	0.4082ms	0.1543ms	6.4819 KOps/s	6.3465 KOps/s	$\color{#35bf28}+2.13\%$
test_permute	0.2256ms	0.1742ms	5.7399 KOps/s	5.7100 KOps/s	$\color{#35bf28}+0.52\%$
test_stack	53.2960ms	51.0154ms	19.6019 Ops/s	19.5023 Ops/s	$\color{#35bf28}+0.51\%$
test_cat	51.2929ms	50.8109ms	19.6808 Ops/s	19.4443 Ops/s	$\color{#35bf28}+1.22\%$