[BE] Check ordering and exclusivity of tensorclass registers

[vmoens]

Stack from ghstack (oldest at bottom):

• -> [BE] Check ordering and exclusivity of tensorclass registers #1176
• [BE] tensorclass method registration check #1175
• [BE] TensorClass stub method check #1174

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}34$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	54.7620μs	19.4248μs	51.4807 KOps/s	48.0400 KOps/s	$\textbf{\color{#35bf28}+7.16\%}$
test_plain_set_stack_nested	56.1450μs	19.8050μs	50.4922 KOps/s	48.9251 KOps/s	$\color{#35bf28}+3.20\%$
test_plain_set_nested_inplace	54.5310μs	21.4805μs	46.5538 KOps/s	45.1850 KOps/s	$\color{#35bf28}+3.03\%$
test_plain_set_stack_nested_inplace	74.8690μs	21.4846μs	46.5450 KOps/s	45.0766 KOps/s	$\color{#35bf28}+3.26\%$
test_items	29.4340μs	4.2079μs	237.6473 KOps/s	236.0073 KOps/s	$\color{#35bf28}+0.69\%$
test_items_nested	0.5559ms	0.3950ms	2.5317 KOps/s	2.5063 KOps/s	$\color{#35bf28}+1.02\%$
test_items_nested_locked	0.7328ms	0.3945ms	2.5351 KOps/s	2.4860 KOps/s	$\color{#35bf28}+1.98\%$
test_items_nested_leaf	0.1416ms	76.8484μs	13.0126 KOps/s	13.0030 KOps/s	$\color{#35bf28}+0.07\%$
test_items_stack_nested	0.7398ms	0.3996ms	2.5024 KOps/s	2.4972 KOps/s	$\color{#35bf28}+0.21\%$
test_items_stack_nested_leaf	0.1406ms	78.4820μs	12.7418 KOps/s	12.8805 KOps/s	$\color{#d91a1a}-1.08\%$
test_items_stack_nested_locked	0.7213ms	0.3984ms	2.5101 KOps/s	2.5127 KOps/s	$\color{#d91a1a}-0.11\%$
test_keys	21.4900μs	3.4658μs	288.5308 KOps/s	286.0355 KOps/s	$\color{#35bf28}+0.87\%$
test_keys_nested	0.2776ms	0.1619ms	6.1780 KOps/s	6.0922 KOps/s	$\color{#35bf28}+1.41\%$
test_keys_nested_locked	1.8484ms	0.1684ms	5.9392 KOps/s	5.8781 KOps/s	$\color{#35bf28}+1.04\%$
test_keys_nested_leaf	0.2365ms	0.1425ms	7.0159 KOps/s	6.9852 KOps/s	$\color{#35bf28}+0.44\%$
test_keys_stack_nested	0.3210ms	0.1628ms	6.1439 KOps/s	6.1125 KOps/s	$\color{#35bf28}+0.51\%$
test_keys_stack_nested_leaf	0.2112ms	0.1420ms	7.0434 KOps/s	6.9734 KOps/s	$\color{#35bf28}+1.00\%$
test_keys_stack_nested_locked	0.2829ms	0.1672ms	5.9803 KOps/s	5.8736 KOps/s	$\color{#35bf28}+1.82\%$
test_values	9.0930μs	1.0201μs	980.2554 KOps/s	951.2370 KOps/s	$\color{#35bf28}+3.05\%$
test_values_nested	0.1212ms	61.0647μs	16.3761 KOps/s	16.4123 KOps/s	$\color{#d91a1a}-0.22\%$
test_values_nested_locked	0.1161ms	60.6627μs	16.4846 KOps/s	16.4107 KOps/s	$\color{#35bf28}+0.45\%$
test_values_nested_leaf	0.1287ms	70.8258μs	14.1192 KOps/s	14.2948 KOps/s	$\color{#d91a1a}-1.23\%$
test_values_stack_nested	0.1153ms	62.8105μs	15.9209 KOps/s	15.6565 KOps/s	$\color{#35bf28}+1.69\%$
test_values_stack_nested_leaf	0.1355ms	71.8629μs	13.9154 KOps/s	14.1702 KOps/s	$\color{#d91a1a}-1.80\%$
test_values_stack_nested_locked	0.1215ms	62.0067μs	16.1273 KOps/s	16.2749 KOps/s	$\color{#d91a1a}-0.91\%$
test_membership	17.1720μs	0.8570μs	1.1669 MOps/s	1.0899 MOps/s	$\textbf{\color{#35bf28}+7.07\%}$
test_membership_nested	30.8770μs	2.8428μs	351.7608 KOps/s	349.7284 KOps/s	$\color{#35bf28}+0.58\%$
test_membership_nested_leaf	34.2740μs	2.8768μs	347.6036 KOps/s	346.8572 KOps/s	$\color{#35bf28}+0.22\%$
test_membership_stacked_nested	30.8480μs	2.8486μs	351.0542 KOps/s	345.5118 KOps/s	$\color{#35bf28}+1.60\%$
test_membership_stacked_nested_leaf	22.5620μs	2.8806μs	347.1535 KOps/s	348.3026 KOps/s	$\color{#d91a1a}-0.33\%$
test_membership_nested_last	27.8120μs	4.3301μs	230.9400 KOps/s	229.1739 KOps/s	$\color{#35bf28}+0.77\%$
test_membership_nested_leaf_last	33.1120μs	4.3570μs	229.5155 KOps/s	229.6677 KOps/s	$\color{#d91a1a}-0.07\%$
test_membership_stacked_nested_last	39.6240μs	5.0562μs	197.7761 KOps/s	232.4124 KOps/s	$\textbf{\color{#d91a1a}-14.90\%}$
test_membership_stacked_nested_leaf_last	45.4040μs	5.1191μs	195.3473 KOps/s	232.2795 KOps/s	$\textbf{\color{#d91a1a}-15.90\%}$
test_nested_getleaf	33.3420μs	10.6620μs	93.7913 KOps/s	90.7682 KOps/s	$\color{#35bf28}+3.33\%$
test_nested_get	31.7990μs	10.1802μs	98.2301 KOps/s	94.6745 KOps/s	$\color{#35bf28}+3.76\%$
test_stacked_getleaf	49.0720μs	10.5269μs	94.9944 KOps/s	91.0536 KOps/s	$\color{#35bf28}+4.33\%$
test_stacked_get	40.4450μs	10.0250μs	99.7506 KOps/s	94.7431 KOps/s	$\textbf{\color{#35bf28}+5.29\%}$
test_nested_getitemleaf	40.8360μs	11.0536μs	90.4681 KOps/s	86.7230 KOps/s	$\color{#35bf28}+4.32\%$
test_nested_getitem	39.7540μs	10.1660μs	98.3675 KOps/s	93.3932 KOps/s	$\textbf{\color{#35bf28}+5.33\%}$
test_stacked_getitemleaf	32.4300μs	11.0352μs	90.6194 KOps/s	87.4269 KOps/s	$\color{#35bf28}+3.65\%$
test_stacked_getitem	41.1570μs	10.3308μs	96.7983 KOps/s	91.5146 KOps/s	$\textbf{\color{#35bf28}+5.77\%}$
test_lock_nested	1.9599ms	0.4545ms	2.2000 KOps/s	1.7534 KOps/s	$\textbf{\color{#35bf28}+25.47\%}$
test_lock_stack_nested	0.6522ms	0.4228ms	2.3653 KOps/s	2.3144 KOps/s	$\color{#35bf28}+2.20\%$
test_unlock_nested	0.9900ms	0.3769ms	2.6531 KOps/s	2.6169 KOps/s	$\color{#35bf28}+1.38\%$
test_unlock_stack_nested	0.5973ms	0.3445ms	2.9030 KOps/s	2.8730 KOps/s	$\color{#35bf28}+1.05\%$
test_flatten_speed	0.1937ms	0.1014ms	9.8574 KOps/s	9.9604 KOps/s	$\color{#d91a1a}-1.03\%$
test_unflatten_speed	0.6480ms	0.5267ms	1.8985 KOps/s	1.9448 KOps/s	$\color{#d91a1a}-2.38\%$
test_common_ops	3.8609ms	0.7774ms	1.2863 KOps/s	1.2761 KOps/s	$\color{#35bf28}+0.80\%$
test_creation	31.8400μs	2.4905μs	401.5184 KOps/s	400.3112 KOps/s	$\color{#35bf28}+0.30\%$
test_creation_empty	38.7620μs	10.7092μs	93.3773 KOps/s	84.9365 KOps/s	$\textbf{\color{#35bf28}+9.94\%}$
test_creation_nested_1	44.9440μs	13.6420μs	73.3031 KOps/s	67.4952 KOps/s	$\textbf{\color{#35bf28}+8.60\%}$
test_creation_nested_2	51.4760μs	18.1513μs	55.0923 KOps/s	51.1236 KOps/s	$\textbf{\color{#35bf28}+7.76\%}$
test_clone	0.1843ms	13.3722μs	74.7821 KOps/s	73.1551 KOps/s	$\color{#35bf28}+2.22\%$
test_getitem[int]	1.4817ms	12.7830μs	78.2291 KOps/s	76.7820 KOps/s	$\color{#35bf28}+1.88\%$
test_getitem[slice_int]	0.1501ms	24.9765μs	40.0377 KOps/s	40.7874 KOps/s	$\color{#d91a1a}-1.84\%$
test_getitem[range]	0.3639ms	48.9096μs	20.4459 KOps/s	20.2574 KOps/s	$\color{#35bf28}+0.93\%$
test_getitem[tuple]	0.1487ms	20.1981μs	49.5095 KOps/s	48.6375 KOps/s	$\color{#35bf28}+1.79\%$
test_getitem[list]	0.3037ms	42.9339μs	23.2916 KOps/s	22.3961 KOps/s	$\color{#35bf28}+4.00\%$
test_setitem_dim[int]	42.3890μs	24.1323μs	41.4383 KOps/s	40.5518 KOps/s	$\color{#35bf28}+2.19\%$
test_setitem_dim[slice_int]	77.1940μs	49.6650μs	20.1349 KOps/s	20.1166 KOps/s	$\color{#35bf28}+0.09\%$
test_setitem_dim[range]	0.1142ms	71.7291μs	13.9413 KOps/s	13.4022 KOps/s	$\color{#35bf28}+4.02\%$
test_setitem_dim[tuple]	70.2000μs	39.5537μs	25.2821 KOps/s	25.2102 KOps/s	$\color{#35bf28}+0.29\%$
test_setitem	94.3760μs	19.6112μs	50.9913 KOps/s	47.9041 KOps/s	$\textbf{\color{#35bf28}+6.44\%}$
test_set	0.1270ms	19.3818μs	51.5948 KOps/s	49.9816 KOps/s	$\color{#35bf28}+3.23\%$
test_set_shared	1.2552ms	0.1681ms	5.9502 KOps/s	5.7641 KOps/s	$\color{#35bf28}+3.23\%$
test_update	0.1433ms	21.7929μs	45.8864 KOps/s	43.3987 KOps/s	$\textbf{\color{#35bf28}+5.73\%}$
test_update_nested	0.1818ms	32.6711μs	30.6081 KOps/s	30.0898 KOps/s	$\color{#35bf28}+1.72\%$
test_update__nested	1.0320ms	34.3185μs	29.1388 KOps/s	29.4737 KOps/s	$\color{#d91a1a}-1.14\%$
test_set_nested	0.2052ms	21.5536μs	46.3959 KOps/s	44.6746 KOps/s	$\color{#35bf28}+3.85\%$
test_set_nested_new	0.2470ms	25.8434μs	38.6947 KOps/s	36.7607 KOps/s	$\textbf{\color{#35bf28}+5.26\%}$
test_select	0.2221ms	43.4654μs	23.0068 KOps/s	22.9874 KOps/s	$\color{#35bf28}+0.08\%$
test_select_nested	0.1287ms	63.5821μs	15.7277 KOps/s	15.6108 KOps/s	$\color{#35bf28}+0.75\%$
test_exclude_nested	0.1671ms	82.5170μs	12.1187 KOps/s	12.0680 KOps/s	$\color{#35bf28}+0.42\%$
test_empty[True]	0.5586ms	0.4059ms	2.4639 KOps/s	2.4596 KOps/s	$\color{#35bf28}+0.17\%$
test_empty[False]	10.4520μs	1.3720μs	728.8519 KOps/s	706.1274 KOps/s	$\color{#35bf28}+3.22\%$
test_unbind_speed	0.3043ms	0.2686ms	3.7223 KOps/s	3.6677 KOps/s	$\color{#35bf28}+1.49\%$
test_unbind_speed_stack0	0.5695ms	0.2703ms	3.7000 KOps/s	3.6912 KOps/s	$\color{#35bf28}+0.24\%$
test_unbind_speed_stack1	0.1176s	0.8134ms	1.2294 KOps/s	1.3157 KOps/s	$\textbf{\color{#d91a1a}-6.56\%}$
test_split	0.1077s	1.7827ms	560.9328 Ops/s	549.8060 Ops/s	$\color{#35bf28}+2.02\%$
test_chunk	1.8136ms	1.6094ms	621.3616 Ops/s	550.4559 Ops/s	$\textbf{\color{#35bf28}+12.88\%}$
test_consolidate_njt[False-None]	0.1261s	9.3641ms	106.7903 Ops/s	120.0754 Ops/s	$\textbf{\color{#d91a1a}-11.06\%}$
test_creation[device0]	3.6294ms	93.3787μs	10.7091 KOps/s	10.0209 KOps/s	$\textbf{\color{#35bf28}+6.87\%}$
test_creation_from_tensor	0.2805ms	94.9532μs	10.5315 KOps/s	10.2644 KOps/s	$\color{#35bf28}+2.60\%$
test_add_one[memmap_tensor0]	0.1964ms	4.8302μs	207.0303 KOps/s	212.2068 KOps/s	$\color{#d91a1a}-2.44\%$
test_contiguous[memmap_tensor0]	22.0720μs	0.5120μs	1.9531 MOps/s	1.9270 MOps/s	$\color{#35bf28}+1.35\%$
test_stack[memmap_tensor0]	59.1900μs	3.3575μs	297.8390 KOps/s	288.1245 KOps/s	$\color{#35bf28}+3.37\%$
test_memmaptd_index	1.0808ms	0.2335ms	4.2821 KOps/s	4.1405 KOps/s	$\color{#35bf28}+3.42\%$
test_memmaptd_index_astensor	0.6501ms	0.3207ms	3.1182 KOps/s	3.0561 KOps/s	$\color{#35bf28}+2.03\%$
test_memmaptd_index_op	0.9569ms	0.5585ms	1.7905 KOps/s	1.6653 KOps/s	$\textbf{\color{#35bf28}+7.52\%}$
test_serialize_model	0.1464s	0.1283s	7.7923 Ops/s	8.1656 Ops/s	$\color{#d91a1a}-4.57\%$
test_serialize_model_pickle	0.4596s	0.3933s	2.5424 Ops/s	2.4417 Ops/s	$\color{#35bf28}+4.12\%$
test_serialize_weights	0.1343s	0.1230s	8.1308 Ops/s	8.4042 Ops/s	$\color{#d91a1a}-3.25\%$
test_serialize_weights_returnearly	0.1703s	0.1618s	6.1801 Ops/s	6.3418 Ops/s	$\color{#d91a1a}-2.55\%$
test_serialize_weights_pickle	0.4997s	0.4156s	2.4060 Ops/s	2.4932 Ops/s	$\color{#d91a1a}-3.50\%$
test_serialize_weights_filesystem	0.1588s	0.1472s	6.7915 Ops/s	6.9546 Ops/s	$\color{#d91a1a}-2.35\%$
test_serialize_model_filesystem	0.1637s	0.1562s	6.4014 Ops/s	5.7896 Ops/s	$\textbf{\color{#35bf28}+10.57\%}$
test_reshape_pytree	65.9330μs	25.8439μs	38.6939 KOps/s	36.8670 KOps/s	$\color{#35bf28}+4.96\%$
test_reshape_td	0.1018ms	32.3354μs	30.9258 KOps/s	29.6126 KOps/s	$\color{#35bf28}+4.43\%$
test_view_pytree	62.7570μs	25.5131μs	39.1955 KOps/s	37.1649 KOps/s	$\textbf{\color{#35bf28}+5.46\%}$
test_view_td	90.8490μs	37.5350μs	26.6418 KOps/s	25.7036 KOps/s	$\color{#35bf28}+3.65\%$
test_unbind_pytree	89.5770μs	28.7616μs	34.7685 KOps/s	33.9803 KOps/s	$\color{#35bf28}+2.32\%$
test_unbind_td	0.3082ms	39.3542μs	25.4102 KOps/s	25.0184 KOps/s	$\color{#35bf28}+1.57\%$
test_split_pytree	0.1194ms	28.7202μs	34.8187 KOps/s	34.0035 KOps/s	$\color{#35bf28}+2.40\%$
test_split_td	0.5282ms	44.6377μs	22.4026 KOps/s	20.1491 KOps/s	$\textbf{\color{#35bf28}+11.18\%}$
test_add_pytree	0.1032ms	34.3508μs	29.1114 KOps/s	28.9500 KOps/s	$\color{#35bf28}+0.56\%$
test_add_td	0.1592ms	52.7873μs	18.9440 KOps/s	16.9843 KOps/s	$\textbf{\color{#35bf28}+11.54\%}$
test_compile_add_one_nested[tensordict-compile]	0.1646ms	62.4700μs	16.0077 KOps/s	15.9041 KOps/s	$\color{#35bf28}+0.65\%$
test_compile_add_one_nested[tensordict-eager]	1.5091ms	0.1708ms	5.8545 KOps/s	5.7621 KOps/s	$\color{#35bf28}+1.60\%$
test_compile_add_one_nested[pytree-compile]	0.2007ms	46.2929μs	21.6016 KOps/s	21.9505 KOps/s	$\color{#d91a1a}-1.59\%$
test_compile_add_one_nested[pytree-eager]	0.2917ms	0.1171ms	8.5361 KOps/s	8.5879 KOps/s	$\color{#d91a1a}-0.60\%$
test_compile_copy_nested[tensordict-compile]	0.1023ms	25.7096μs	38.8959 KOps/s	38.6767 KOps/s	$\color{#35bf28}+0.57\%$
test_compile_copy_nested[tensordict-eager]	0.1387ms	59.2987μs	16.8638 KOps/s	16.7652 KOps/s	$\color{#35bf28}+0.59\%$
test_compile_copy_nested[pytree-compile]	0.1575ms	77.0236μs	12.9830 KOps/s	12.7491 KOps/s	$\color{#35bf28}+1.83\%$
test_compile_copy_nested[pytree-eager]	0.1755ms	66.3868μs	15.0632 KOps/s	14.7949 KOps/s	$\color{#35bf28}+1.81\%$
test_compile_add_one_flat[tensordict-compile]	0.1909ms	0.1041ms	9.6022 KOps/s	9.7183 KOps/s	$\color{#d91a1a}-1.19\%$
test_compile_add_one_flat[tensordict-eager]	0.4072ms	0.2140ms	4.6726 KOps/s	4.7129 KOps/s	$\color{#d91a1a}-0.86\%$
test_compile_add_one_flat[tensorclass-compile]	0.1461ms	45.3148μs	22.0678 KOps/s	22.4143 KOps/s	$\color{#d91a1a}-1.55\%$
test_compile_add_one_flat[tensorclass-eager]	0.5403ms	65.8115μs	15.1949 KOps/s	15.1712 KOps/s	$\color{#35bf28}+0.16\%$
test_compile_add_one_flat[pytree-compile]	0.2383ms	0.1030ms	9.7072 KOps/s	9.7889 KOps/s	$\color{#d91a1a}-0.83\%$
test_compile_add_one_flat[pytree-eager]	0.3765ms	0.2006ms	4.9852 KOps/s	5.0177 KOps/s	$\color{#d91a1a}-0.65\%$
test_compile_add_self_flat[tensordict-eager]	0.4665ms	0.2354ms	4.2489 KOps/s	4.3068 KOps/s	$\color{#d91a1a}-1.34\%$
test_compile_add_self_flat[tensordict-compile]	0.2041ms	0.1057ms	9.4639 KOps/s	9.5402 KOps/s	$\color{#d91a1a}-0.80\%$
test_compile_add_self_flat[tensorclass-eager]	0.1281ms	60.8350μs	16.4379 KOps/s	15.9012 KOps/s	$\color{#35bf28}+3.38\%$
test_compile_add_self_flat[tensorclass-compile]	0.1458ms	46.2047μs	21.6428 KOps/s	21.6089 KOps/s	$\color{#35bf28}+0.16\%$
test_compile_add_self_flat[pytree-eager]	0.6499ms	0.1570ms	6.3713 KOps/s	6.4030 KOps/s	$\color{#d91a1a}-0.49\%$
test_compile_add_self_flat[pytree-compile]	0.1928ms	0.1029ms	9.7163 KOps/s	9.3187 KOps/s	$\color{#35bf28}+4.27\%$
test_compile_copy_flat[tensordict-compile]	87.7530μs	20.9748μs	47.6763 KOps/s	48.2282 KOps/s	$\color{#d91a1a}-1.14\%$
test_compile_copy_flat[tensordict-eager]	0.1287ms	66.3090μs	15.0809 KOps/s	15.1531 KOps/s	$\color{#d91a1a}-0.48\%$
test_compile_copy_flat[pytree-compile]	0.1473ms	78.2027μs	12.7873 KOps/s	12.6973 KOps/s	$\color{#35bf28}+0.71\%$
test_compile_copy_flat[pytree-eager]	0.1673ms	66.8924μs	14.9494 KOps/s	14.7611 KOps/s	$\color{#35bf28}+1.28\%$
test_compile_assign_and_add[tensordict-compile]	0.3055ms	0.2083ms	4.8002 KOps/s	4.6957 KOps/s	$\color{#35bf28}+2.23\%$
test_compile_assign_and_add[tensordict-eager]	2.3631ms	1.3163ms	759.7144 Ops/s	767.7911 Ops/s	$\color{#d91a1a}-1.05\%$
test_compile_assign_and_add[pytree-compile]	0.2890ms	0.2056ms	4.8630 KOps/s	4.9067 KOps/s	$\color{#d91a1a}-0.89\%$
test_compile_assign_and_add[pytree-eager]	1.1909ms	0.7713ms	1.2965 KOps/s	1.2909 KOps/s	$\color{#35bf28}+0.43\%$
test_compile_assign_and_add_stack[compile]	0.6535ms	0.4519ms	2.2127 KOps/s	2.2090 KOps/s	$\color{#35bf28}+0.17\%$
test_compile_assign_and_add_stack[eager]	2.8436ms	2.5975ms	384.9790 Ops/s	374.2965 Ops/s	$\color{#35bf28}+2.85\%$
test_compile_indexing[tensor-tensordict-compile]	0.1169ms	35.9023μs	27.8534 KOps/s	28.1065 KOps/s	$\color{#d91a1a}-0.90\%$
test_compile_indexing[tensor-tensordict-eager]	0.5251ms	32.2964μs	30.9632 KOps/s	29.0969 KOps/s	$\textbf{\color{#35bf28}+6.41\%}$
test_compile_indexing[tensor-tensorclass-compile]	0.1307ms	29.6855μs	33.6865 KOps/s	33.2463 KOps/s	$\color{#35bf28}+1.32\%$
test_compile_indexing[tensor-tensorclass-eager]	73.7270μs	22.3672μs	44.7084 KOps/s	43.2460 KOps/s	$\color{#35bf28}+3.38\%$
test_compile_indexing[tensor-pytree-compile]	93.1330μs	30.4032μs	32.8913 KOps/s	32.6048 KOps/s	$\color{#35bf28}+0.88\%$
test_compile_indexing[tensor-pytree-eager]	73.1260μs	22.3576μs	44.7276 KOps/s	42.5712 KOps/s	$\textbf{\color{#35bf28}+5.07\%}$
test_compile_indexing[slice-tensordict-compile]	0.1026ms	51.2203μs	19.5235 KOps/s	19.4614 KOps/s	$\color{#35bf28}+0.32\%$
test_compile_indexing[slice-tensordict-eager]	0.5827ms	19.7261μs	50.6942 KOps/s	47.7039 KOps/s	$\textbf{\color{#35bf28}+6.27\%}$
test_compile_indexing[slice-tensorclass-compile]	0.1019ms	43.6701μs	22.8989 KOps/s	22.5654 KOps/s	$\color{#35bf28}+1.48\%$
test_compile_indexing[slice-tensorclass-eager]	98.8740μs	18.5486μs	53.9126 KOps/s	52.7511 KOps/s	$\color{#35bf28}+2.20\%$
test_compile_indexing[slice-pytree-compile]	0.1363ms	44.8507μs	22.2962 KOps/s	22.0379 KOps/s	$\color{#35bf28}+1.17\%$
test_compile_indexing[slice-pytree-eager]	67.5560μs	18.0994μs	55.2504 KOps/s	53.5151 KOps/s	$\color{#35bf28}+3.24\%$
test_compile_indexing[int-tensordict-compile]	0.1120ms	52.1012μs	19.1934 KOps/s	18.5390 KOps/s	$\color{#35bf28}+3.53\%$
test_compile_indexing[int-tensordict-eager]	0.9249ms	19.4714μs	51.3575 KOps/s	48.5175 KOps/s	$\textbf{\color{#35bf28}+5.85\%}$
test_compile_indexing[int-tensorclass-compile]	0.1329ms	44.3730μs	22.5362 KOps/s	22.1159 KOps/s	$\color{#35bf28}+1.90\%$
test_compile_indexing[int-tensorclass-eager]	76.1920μs	18.4325μs	54.2520 KOps/s	53.2617 KOps/s	$\color{#35bf28}+1.86\%$
test_compile_indexing[int-pytree-compile]	0.1064ms	45.0142μs	22.2152 KOps/s	22.2926 KOps/s	$\color{#d91a1a}-0.35\%$
test_compile_indexing[int-pytree-eager]	84.5580μs	18.2690μs	54.7376 KOps/s	53.3525 KOps/s	$\color{#35bf28}+2.60\%$
test_mod_add[eager]	0.1187ms	33.0840μs	30.2261 KOps/s	27.7240 KOps/s	$\textbf{\color{#35bf28}+9.03\%}$
test_mod_add[compile]	0.1178ms	46.7190μs	21.4046 KOps/s	20.8114 KOps/s	$\color{#35bf28}+2.85\%$
test_mod_add[compile-overhead]	0.1409ms	46.7526μs	21.3892 KOps/s	20.3300 KOps/s	$\textbf{\color{#35bf28}+5.21\%}$
test_mod_wrap[eager]	0.6285ms	0.2215ms	4.5154 KOps/s	4.4322 KOps/s	$\color{#35bf28}+1.88\%$
test_mod_wrap[compile]	0.3521ms	0.2079ms	4.8089 KOps/s	4.7776 KOps/s	$\color{#35bf28}+0.65\%$
test_mod_wrap[compile-overhead]	0.4574ms	0.2085ms	4.7969 KOps/s	4.8806 KOps/s	$\color{#d91a1a}-1.71\%$
test_mod_wrap_and_backward[eager]	13.1373ms	11.4155ms	87.6006 Ops/s	82.8039 Ops/s	$\textbf{\color{#35bf28}+5.79\%}$
test_mod_wrap_and_backward[compile]	19.3935ms	13.7711ms	72.6160 Ops/s	76.0631 Ops/s	$\color{#d91a1a}-4.53\%$
test_mod_wrap_and_backward[compile-overhead]	14.5705ms	11.8970ms	84.0545 Ops/s	72.4828 Ops/s	$\textbf{\color{#35bf28}+15.96\%}$
test_seq_add[eager]	0.2238ms	0.1161ms	8.6107 KOps/s	8.1546 KOps/s	$\textbf{\color{#35bf28}+5.59\%}$
test_seq_add[compile]	0.1278ms	62.9335μs	15.8898 KOps/s	15.5478 KOps/s	$\color{#35bf28}+2.20\%$
test_seq_add[compile-overhead]	0.1226ms	60.2806μs	16.5891 KOps/s	16.0974 KOps/s	$\color{#35bf28}+3.05\%$
test_seq_wrap[eager]	0.7158ms	0.4422ms	2.2612 KOps/s	2.2180 KOps/s	$\color{#35bf28}+1.95\%$
test_seq_wrap[compile]	0.3633ms	0.2301ms	4.3455 KOps/s	4.1844 KOps/s	$\color{#35bf28}+3.85\%$
test_seq_wrap[compile-overhead]	0.4203ms	0.2266ms	4.4127 KOps/s	4.2837 KOps/s	$\color{#35bf28}+3.01\%$
test_func_call_runtime[False-eager]	0.9537ms	0.5254ms	1.9034 KOps/s	1.8214 KOps/s	$\color{#35bf28}+4.51\%$
test_func_call_runtime[False-compile]	0.6127ms	0.4232ms	2.3628 KOps/s	2.3311 KOps/s	$\color{#35bf28}+1.36\%$
test_func_call_runtime[False-compile-overhead]	0.6689ms	0.4183ms	2.3909 KOps/s	2.3159 KOps/s	$\color{#35bf28}+3.24\%$
test_func_call_runtime[True-eager]	0.9659ms	0.7376ms	1.3558 KOps/s	1.3253 KOps/s	$\color{#35bf28}+2.30\%$
test_func_call_runtime[True-compile]	0.6402ms	0.4574ms	2.1865 KOps/s	2.1194 KOps/s	$\color{#35bf28}+3.17\%$
test_func_call_runtime[True-compile-overhead]	0.5817ms	0.4600ms	2.1740 KOps/s	2.1420 KOps/s	$\color{#35bf28}+1.49\%$
test_func_call_cm_runtime[False-eager]	0.9157ms	0.5298ms	1.8877 KOps/s	1.8377 KOps/s	$\color{#35bf28}+2.72\%$
test_func_call_cm_runtime[False-compile]	0.5428ms	0.4170ms	2.3979 KOps/s	2.3298 KOps/s	$\color{#35bf28}+2.92\%$
test_func_call_cm_runtime[False-compile-overhead]	0.5969ms	0.4224ms	2.3673 KOps/s	2.3191 KOps/s	$\color{#35bf28}+2.08\%$
test_func_call_cm_runtime[True-eager]	1.0661ms	0.8738ms	1.1444 KOps/s	1.0958 KOps/s	$\color{#35bf28}+4.44\%$
test_func_call_cm_runtime[True-compile]	0.6774ms	0.4848ms	2.0627 KOps/s	2.0208 KOps/s	$\color{#35bf28}+2.08\%$
test_func_call_cm_runtime[True-compile-overhead]	0.6059ms	0.4780ms	2.0920 KOps/s	2.0125 KOps/s	$\color{#35bf28}+3.95\%$
test_vmap_func_call_cm_runtime[eager]	2.4202ms	1.8582ms	538.1515 Ops/s	515.2188 Ops/s	$\color{#35bf28}+4.45\%$
test_vmap_func_call_cm_runtime[compile]	0.9201ms	0.5099ms	1.9614 KOps/s	1.9133 KOps/s	$\color{#35bf28}+2.51\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.7302ms	0.5118ms	1.9539 KOps/s	1.8821 KOps/s	$\color{#35bf28}+3.81\%$
test_distributed	0.2585ms	0.1277ms	7.8288 KOps/s	7.7390 KOps/s	$\color{#35bf28}+1.16\%$
test_tdmodule	45.7250μs	25.5754μs	39.1001 KOps/s	36.6378 KOps/s	$\textbf{\color{#35bf28}+6.72\%}$
test_tdmodule_dispatch	77.4740μs	47.2120μs	21.1810 KOps/s	20.4683 KOps/s	$\color{#35bf28}+3.48\%$
test_tdseq	85.5090μs	28.2194μs	35.4366 KOps/s	34.0617 KOps/s	$\color{#35bf28}+4.04\%$
test_tdseq_dispatch	0.1061ms	52.5097μs	19.0441 KOps/s	18.3932 KOps/s	$\color{#35bf28}+3.54\%$
test_instantiation_functorch	2.0432ms	1.5293ms	653.9004 Ops/s	645.3348 Ops/s	$\color{#35bf28}+1.33\%$
test_exec_functorch	0.2822ms	0.1771ms	5.6466 KOps/s	5.5125 KOps/s	$\color{#35bf28}+2.43\%$
test_exec_functional_call	0.3282ms	0.1675ms	5.9689 KOps/s	5.7210 KOps/s	$\color{#35bf28}+4.33\%$
test_exec_td_decorator	0.4398ms	0.2256ms	4.4326 KOps/s	4.2121 KOps/s	$\textbf{\color{#35bf28}+5.24\%}$
test_vmap_mlp_speed_decorator[True-True]	0.9897ms	0.6350ms	1.5749 KOps/s	1.5198 KOps/s	$\color{#35bf28}+3.63\%$
test_vmap_mlp_speed_decorator[True-False]	1.1536ms	0.6453ms	1.5497 KOps/s	1.5170 KOps/s	$\color{#35bf28}+2.15\%$
test_vmap_mlp_speed_decorator[False-True]	0.8226ms	0.5155ms	1.9398 KOps/s	1.8739 KOps/s	$\color{#35bf28}+3.52\%$
test_vmap_mlp_speed_decorator[False-False]	0.7658ms	0.5102ms	1.9600 KOps/s	1.8727 KOps/s	$\color{#35bf28}+4.66\%$
test_to_module_speed[True]	2.1447ms	1.3232ms	755.7179 Ops/s	738.4412 Ops/s	$\color{#35bf28}+2.34\%$
test_to_module_speed[False]	1.8135ms	1.2888ms	775.9351 Ops/s	751.6171 Ops/s	$\color{#35bf28}+3.24\%$
test_tc_init	0.1044ms	44.6762μs	22.3833 KOps/s	21.4696 KOps/s	$\color{#35bf28}+4.26\%$
test_tc_init_nested	0.1824ms	90.9243μs	10.9982 KOps/s	10.5825 KOps/s	$\color{#35bf28}+3.93\%$
test_tc_first_layer_tensor	37.4400μs	1.5971μs	626.1387 KOps/s	631.7277 KOps/s	$\color{#d91a1a}-0.88\%$
test_tc_first_layer_nontensor	52.3170μs	4.7495μs	210.5467 KOps/s	209.9907 KOps/s	$\color{#35bf28}+0.26\%$
test_tc_second_layer_tensor	20.4480μs	2.9146μs	343.1050 KOps/s	338.9775 KOps/s	$\color{#35bf28}+1.22\%$
test_tc_second_layer_nontensor	54.9920μs	6.1097μs	163.6740 KOps/s	163.3025 KOps/s	$\color{#35bf28}+0.23\%$
test_unbind	0.2338s	14.3300ms	69.7837 Ops/s	51.8048 Ops/s	$\textbf{\color{#35bf28}+34.71\%}$
test_full_like	22.4481ms	13.2025ms	75.7433 Ops/s	66.2307 Ops/s	$\textbf{\color{#35bf28}+14.36\%}$
test_zeros_like	11.0524ms	7.6458ms	130.7909 Ops/s	122.6328 Ops/s	$\textbf{\color{#35bf28}+6.65\%}$
test_ones_like	16.4116ms	8.7094ms	114.8191 Ops/s	120.7504 Ops/s	$\color{#d91a1a}-4.91\%$
test_clone	16.8358ms	10.5000ms	95.2384 Ops/s	98.7465 Ops/s	$\color{#d91a1a}-3.55\%$
test_squeeze	72.3540μs	11.8802μs	84.1739 KOps/s	82.0337 KOps/s	$\color{#35bf28}+2.61\%$
test_unsqueeze	0.1734ms	91.0365μs	10.9846 KOps/s	10.5571 KOps/s	$\color{#35bf28}+4.05\%$
test_split	0.4625ms	0.1948ms	5.1342 KOps/s	5.1418 KOps/s	$\color{#d91a1a}-0.15\%$
test_permute	0.2786ms	0.1972ms	5.0699 KOps/s	4.9903 KOps/s	$\color{#35bf28}+1.59\%$
test_stack	32.5656ms	26.5870ms	37.6124 Ops/s	35.4172 Ops/s	$\textbf{\color{#35bf28}+6.20\%}$
test_cat	30.0284ms	27.4630ms	36.4126 Ops/s	37.1215 Ops/s	$\color{#d91a1a}-1.91\%$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}35$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	30.0000μs	11.5129μs	86.8588 KOps/s	73.9307 KOps/s	$\textbf{\color{#35bf28}+17.49\%}$
test_plain_set_stack_nested	68.0810μs	11.6496μs	85.8401 KOps/s	73.9489 KOps/s	$\textbf{\color{#35bf28}+16.08\%}$
test_plain_set_nested_inplace	37.5210μs	12.6382μs	79.1253 KOps/s	70.2571 KOps/s	$\textbf{\color{#35bf28}+12.62\%}$
test_plain_set_stack_nested_inplace	64.1810μs	12.6749μs	78.8959 KOps/s	68.9032 KOps/s	$\textbf{\color{#35bf28}+14.50\%}$
test_items	26.2200μs	2.9270μs	341.6495 KOps/s	341.6512 KOps/s	$-0.00\%$
test_items_nested	0.7474ms	0.3618ms	2.7637 KOps/s	2.7671 KOps/s	$\color{#d91a1a}-0.12\%$
test_items_nested_locked	0.4278ms	0.3693ms	2.7076 KOps/s	2.7442 KOps/s	$\color{#d91a1a}-1.34\%$
test_items_nested_leaf	0.4627ms	58.6905μs	17.0385 KOps/s	17.1661 KOps/s	$\color{#d91a1a}-0.74\%$
test_items_stack_nested	0.7940ms	0.3718ms	2.6896 KOps/s	2.7485 KOps/s	$\color{#d91a1a}-2.15\%$
test_items_stack_nested_leaf	0.4606ms	59.2637μs	16.8737 KOps/s	16.8525 KOps/s	$\color{#35bf28}+0.13\%$
test_items_stack_nested_locked	0.4964ms	0.3667ms	2.7269 KOps/s	2.7733 KOps/s	$\color{#d91a1a}-1.68\%$
test_keys	47.3910μs	3.4573μs	289.2449 KOps/s	291.4545 KOps/s	$\color{#d91a1a}-0.76\%$
test_keys_nested	0.1719ms	80.2920μs	12.4545 KOps/s	12.1601 KOps/s	$\color{#35bf28}+2.42\%$
test_keys_nested_locked	2.1763ms	87.6296μs	11.4117 KOps/s	11.2531 KOps/s	$\color{#35bf28}+1.41\%$
test_keys_nested_leaf	0.1136ms	72.1891μs	13.8525 KOps/s	13.6772 KOps/s	$\color{#35bf28}+1.28\%$
test_keys_stack_nested	0.1221ms	82.8535μs	12.0695 KOps/s	12.0657 KOps/s	$\color{#35bf28}+0.03\%$
test_keys_stack_nested_leaf	0.1108ms	74.1948μs	13.4780 KOps/s	13.5702 KOps/s	$\color{#d91a1a}-0.68\%$
test_keys_stack_nested_locked	0.1468ms	88.3874μs	11.3138 KOps/s	11.3763 KOps/s	$\color{#d91a1a}-0.55\%$
test_values	7.3383μs	0.8498μs	1.1767 MOps/s	1.1825 MOps/s	$\color{#d91a1a}-0.49\%$
test_values_nested	82.4010μs	35.1083μs	28.4833 KOps/s	28.9893 KOps/s	$\color{#d91a1a}-1.75\%$
test_values_nested_locked	61.8610μs	36.0734μs	27.7213 KOps/s	27.6091 KOps/s	$\color{#35bf28}+0.41\%$
test_values_nested_leaf	62.2810μs	39.4514μs	25.3476 KOps/s	25.3943 KOps/s	$\color{#d91a1a}-0.18\%$
test_values_stack_nested	67.6310μs	35.0749μs	28.5104 KOps/s	28.8722 KOps/s	$\color{#d91a1a}-1.25\%$
test_values_stack_nested_leaf	68.6110μs	39.9201μs	25.0501 KOps/s	25.0861 KOps/s	$\color{#d91a1a}-0.14\%$
test_values_stack_nested_locked	77.5520μs	36.1707μs	27.6467 KOps/s	27.4989 KOps/s	$\color{#35bf28}+0.54\%$
test_membership	2.0725μs	0.5094μs	1.9633 MOps/s	1.9499 MOps/s	$\color{#35bf28}+0.69\%$
test_membership_nested	14.8005μs	2.0260μs	493.5739 KOps/s	481.3812 KOps/s	$\color{#35bf28}+2.53\%$
test_membership_nested_leaf	18.5950μs	2.0262μs	493.5326 KOps/s	484.8382 KOps/s	$\color{#35bf28}+1.79\%$
test_membership_stacked_nested	25.0710μs	2.1329μs	468.8417 KOps/s	464.1155 KOps/s	$\color{#35bf28}+1.02\%$
test_membership_stacked_nested_leaf	26.9910μs	2.0746μs	482.0320 KOps/s	465.5049 KOps/s	$\color{#35bf28}+3.55\%$
test_membership_nested_last	41.5200μs	3.1493μs	317.5276 KOps/s	312.5144 KOps/s	$\color{#35bf28}+1.60\%$
test_membership_nested_leaf_last	53.1710μs	3.0982μs	322.7656 KOps/s	310.1237 KOps/s	$\color{#35bf28}+4.08\%$
test_membership_stacked_nested_last	41.9110μs	3.1073μs	321.8267 KOps/s	315.3481 KOps/s	$\color{#35bf28}+2.05\%$
test_membership_stacked_nested_leaf_last	44.1410μs	3.0705μs	325.6785 KOps/s	313.6990 KOps/s	$\color{#35bf28}+3.82\%$
test_nested_getleaf	46.9010μs	6.0894μs	164.2191 KOps/s	162.7030 KOps/s	$\color{#35bf28}+0.93\%$
test_nested_get	37.2600μs	5.8295μs	171.5406 KOps/s	170.9232 KOps/s	$\color{#35bf28}+0.36\%$
test_stacked_getleaf	37.3010μs	6.1210μs	163.3723 KOps/s	162.7394 KOps/s	$\color{#35bf28}+0.39\%$
test_stacked_get	38.2410μs	5.8532μs	170.8468 KOps/s	172.1421 KOps/s	$\color{#d91a1a}-0.75\%$
test_nested_getitemleaf	41.0100μs	6.2241μs	160.6668 KOps/s	159.0792 KOps/s	$\color{#35bf28}+1.00\%$
test_nested_getitem	44.3610μs	5.8387μs	171.2715 KOps/s	164.8467 KOps/s	$\color{#35bf28}+3.90\%$
test_stacked_getitemleaf	29.2000μs	6.1785μs	161.8522 KOps/s	160.5066 KOps/s	$\color{#35bf28}+0.84\%$
test_stacked_getitem	28.9000μs	5.9113μs	169.1679 KOps/s	168.5025 KOps/s	$\color{#35bf28}+0.39\%$
test_lock_nested	4.1853ms	0.3850ms	2.5976 KOps/s	2.5994 KOps/s	$\color{#d91a1a}-0.07\%$
test_lock_stack_nested	0.3931ms	0.3503ms	2.8543 KOps/s	2.8279 KOps/s	$\color{#35bf28}+0.93\%$
test_unlock_nested	0.8118ms	0.3234ms	3.0920 KOps/s	3.0909 KOps/s	$\color{#35bf28}+0.03\%$
test_unlock_stack_nested	0.3354ms	0.2895ms	3.4545 KOps/s	3.4143 KOps/s	$\color{#35bf28}+1.18\%$
test_flatten_speed	0.1012ms	76.1894μs	13.1252 KOps/s	13.5277 KOps/s	$\color{#d91a1a}-2.98\%$
test_unflatten_speed	0.3757ms	0.3233ms	3.0930 KOps/s	3.1340 KOps/s	$\color{#d91a1a}-1.31\%$
test_common_ops	1.6596ms	0.5946ms	1.6819 KOps/s	1.5034 KOps/s	$\textbf{\color{#35bf28}+11.87\%}$
test_creation	21.4400μs	1.7687μs	565.3808 KOps/s	565.1167 KOps/s	$\color{#35bf28}+0.05\%$
test_creation_empty	25.1010μs	6.9574μs	143.7313 KOps/s	95.6863 KOps/s	$\textbf{\color{#35bf28}+50.21\%}$
test_creation_nested_1	1.7011ms	8.7066μs	114.8549 KOps/s	82.6962 KOps/s	$\textbf{\color{#35bf28}+38.89\%}$
test_creation_nested_2	43.4810μs	11.5775μs	86.3748 KOps/s	65.7038 KOps/s	$\textbf{\color{#35bf28}+31.46\%}$
test_clone	98.6810μs	11.0898μs	90.1727 KOps/s	87.1010 KOps/s	$\color{#35bf28}+3.53\%$
test_getitem[int]	1.2992ms	11.0835μs	90.2244 KOps/s	89.6182 KOps/s	$\color{#35bf28}+0.68\%$
test_getitem[slice_int]	0.1118ms	21.1791μs	47.2164 KOps/s	46.3501 KOps/s	$\color{#35bf28}+1.87\%$
test_getitem[range]	0.2496ms	37.9303μs	26.3642 KOps/s	26.1076 KOps/s	$\color{#35bf28}+0.98\%$
test_getitem[tuple]	0.1046ms	18.7349μs	53.3765 KOps/s	53.1935 KOps/s	$\color{#35bf28}+0.34\%$
test_getitem[list]	0.3208ms	34.2336μs	29.2111 KOps/s	28.9437 KOps/s	$\color{#35bf28}+0.92\%$
test_setitem_dim[int]	48.5110μs	19.1424μs	52.2399 KOps/s	50.7427 KOps/s	$\color{#35bf28}+2.95\%$
test_setitem_dim[slice_int]	76.5120μs	38.7101μs	25.8330 KOps/s	25.6953 KOps/s	$\color{#35bf28}+0.54\%$
test_setitem_dim[range]	75.9610μs	52.3246μs	19.1115 KOps/s	18.8831 KOps/s	$\color{#35bf28}+1.21\%$
test_setitem_dim[tuple]	54.1700μs	32.9728μs	30.3280 KOps/s	30.1481 KOps/s	$\color{#35bf28}+0.60\%$
test_setitem	0.1121ms	14.9962μs	66.6835 KOps/s	58.5374 KOps/s	$\textbf{\color{#35bf28}+13.92\%}$
test_set	94.6520μs	14.4758μs	69.0807 KOps/s	59.8895 KOps/s	$\textbf{\color{#35bf28}+15.35\%}$
test_set_shared	1.6262ms	0.1519ms	6.5829 KOps/s	6.5375 KOps/s	$\color{#35bf28}+0.69\%$
test_update	0.5288ms	16.6507μs	60.0576 KOps/s	48.7053 KOps/s	$\textbf{\color{#35bf28}+23.31\%}$
test_update_nested	0.1196ms	22.6692μs	44.1127 KOps/s	37.0743 KOps/s	$\textbf{\color{#35bf28}+18.98\%}$
test_update__nested	0.4512ms	25.7421μs	38.8469 KOps/s	37.5294 KOps/s	$\color{#35bf28}+3.51\%$
test_set_nested	0.1217ms	15.8894μs	62.9351 KOps/s	54.7433 KOps/s	$\textbf{\color{#35bf28}+14.96\%}$
test_set_nested_new	0.1072ms	18.2903μs	54.6738 KOps/s	48.3014 KOps/s	$\textbf{\color{#35bf28}+13.19\%}$
test_select	0.2279ms	29.9769μs	33.3590 KOps/s	30.6104 KOps/s	$\textbf{\color{#35bf28}+8.98\%}$
test_select_nested	75.9710μs	43.6563μs	22.9062 KOps/s	22.8376 KOps/s	$\color{#35bf28}+0.30\%$
test_exclude_nested	94.6110μs	64.3115μs	15.5493 KOps/s	15.5724 KOps/s	$\color{#d91a1a}-0.15\%$
test_empty[True]	0.4590ms	0.2937ms	3.4044 KOps/s	3.4702 KOps/s	$\color{#d91a1a}-1.90\%$
test_empty[False]	5.7581μs	0.8151μs	1.2269 MOps/s	1.1962 MOps/s	$\color{#35bf28}+2.56\%$
test_to	87.1210μs	56.4937μs	17.7011 KOps/s	17.5339 KOps/s	$\color{#35bf28}+0.95\%$
test_to_nonblocking	96.4220μs	47.8165μs	20.9133 KOps/s	20.5817 KOps/s	$\color{#35bf28}+1.61\%$
test_unbind_speed	1.7017ms	0.2420ms	4.1324 KOps/s	4.1124 KOps/s	$\color{#35bf28}+0.49\%$
test_unbind_speed_stack0	0.2941ms	0.2423ms	4.1274 KOps/s	4.1252 KOps/s	$\color{#35bf28}+0.05\%$
test_unbind_speed_stack1	92.5265ms	0.6814ms	1.4676 KOps/s	1.4621 KOps/s	$\color{#35bf28}+0.38\%$
test_split	93.7482ms	1.6073ms	622.1539 Ops/s	561.1765 Ops/s	$\textbf{\color{#35bf28}+10.87\%}$
test_chunk	93.8907ms	1.6123ms	620.2264 Ops/s	674.9045 Ops/s	$\textbf{\color{#d91a1a}-8.10\%}$
test_consolidate[False-None]	96.3742ms	2.9545ms	338.4628 Ops/s	339.1137 Ops/s	$\color{#d91a1a}-0.19\%$
test_consolidate[default-None]	1.7543ms	1.6614ms	601.8855 Ops/s	591.5835 Ops/s	$\color{#35bf28}+1.74\%$
test_consolidate[reduce-overhead-None]	1.7894ms	1.6956ms	589.7630 Ops/s	580.1800 Ops/s	$\color{#35bf28}+1.65\%$
test_consolidate_njt[False-None]	6.8312ms	6.5335ms	153.0574 Ops/s	153.4038 Ops/s	$\color{#d91a1a}-0.23\%$
test_to[False-False-None]	1.8602ms	1.7303ms	577.9489 Ops/s	582.4117 Ops/s	$\color{#d91a1a}-0.77\%$
test_to[True-False-None]	0.2928s	1.6746ms	597.1653 Ops/s	749.6204 Ops/s	$\textbf{\color{#d91a1a}-20.34\%}$
test_to[within-False-None]	4.1793ms	4.0362ms	247.7562 Ops/s	240.7521 Ops/s	$\color{#35bf28}+2.91\%$
test_to[True-default-None]	5.4630ms	5.2683ms	189.8138 Ops/s	189.9690 Ops/s	$\color{#d91a1a}-0.08\%$
test_to_njt[False-False-None]	7.0829ms	6.9134ms	144.6475 Ops/s	144.5904 Ops/s	$\color{#35bf28}+0.04\%$
test_to_njt[True-False-None]	5.8909ms	5.4791ms	182.5133 Ops/s	186.1233 Ops/s	$\color{#d91a1a}-1.94\%$
test_to_njt[within-False-None]	12.3272ms	12.1497ms	82.3065 Ops/s	83.4535 Ops/s	$\color{#d91a1a}-1.37\%$
test_creation[device0]	0.3763ms	80.6429μs	12.4003 KOps/s	12.2613 KOps/s	$\color{#35bf28}+1.13\%$
test_creation_from_tensor	0.5318ms	83.7400μs	11.9417 KOps/s	11.8689 KOps/s	$\color{#35bf28}+0.61\%$
test_add_one[memmap_tensor0]	0.4839ms	6.7084μs	149.0660 KOps/s	143.6716 KOps/s	$\color{#35bf28}+3.75\%$
test_contiguous[memmap_tensor0]	1.8616μs	0.4176μs	2.3948 MOps/s	2.4391 MOps/s	$\color{#d91a1a}-1.82\%$
test_stack[memmap_tensor0]	26.2300μs	4.4837μs	223.0312 KOps/s	217.5753 KOps/s	$\color{#35bf28}+2.51\%$
test_memmaptd_index	1.8877ms	0.2538ms	3.9406 KOps/s	3.8709 KOps/s	$\color{#35bf28}+1.80\%$
test_memmaptd_index_astensor	0.9392ms	0.3144ms	3.1810 KOps/s	3.1044 KOps/s	$\color{#35bf28}+2.47\%$
test_memmaptd_index_op	1.0267ms	0.5704ms	1.7532 KOps/s	1.5343 KOps/s	$\textbf{\color{#35bf28}+14.27\%}$
test_serialize_model	0.1310s	0.1302s	7.6815 Ops/s	7.6264 Ops/s	$\color{#35bf28}+0.72\%$
test_serialize_model_pickle	1.3654s	1.2154s	0.8228 Ops/s	0.8208 Ops/s	$\color{#35bf28}+0.24\%$
test_serialize_weights	0.2780s	0.1522s	6.5716 Ops/s	7.6210 Ops/s	$\textbf{\color{#d91a1a}-13.77\%}$
test_serialize_weights_returnearly	0.3256s	53.8819ms	18.5591 Ops/s	15.3233 Ops/s	$\textbf{\color{#35bf28}+21.12\%}$
test_serialize_weights_pickle	1.3759s	1.2162s	0.8222 Ops/s	0.8219 Ops/s	$\color{#35bf28}+0.04\%$
test_reshape_pytree	55.1200μs	22.1741μs	45.0978 KOps/s	44.2615 KOps/s	$\color{#35bf28}+1.89\%$
test_reshape_td	77.1810μs	26.5676μs	37.6398 KOps/s	36.8838 KOps/s	$\color{#35bf28}+2.05\%$
test_view_pytree	56.4010μs	21.8604μs	45.7447 KOps/s	44.8899 KOps/s	$\color{#35bf28}+1.90\%$
test_view_td	73.9210μs	30.6430μs	32.6339 KOps/s	31.7377 KOps/s	$\color{#35bf28}+2.82\%$
test_unbind_pytree	70.1110μs	27.8530μs	35.9028 KOps/s	34.9177 KOps/s	$\color{#35bf28}+2.82\%$
test_unbind_td	0.6162ms	36.7660μs	27.1990 KOps/s	26.4975 KOps/s	$\color{#35bf28}+2.65\%$
test_split_pytree	79.6110μs	30.0782μs	33.2467 KOps/s	32.8086 KOps/s	$\color{#35bf28}+1.34\%$
test_split_td	0.7934ms	38.7910μs	25.7792 KOps/s	25.1658 KOps/s	$\color{#35bf28}+2.44\%$
test_add_pytree	70.9710μs	34.3213μs	29.1364 KOps/s	28.0053 KOps/s	$\color{#35bf28}+4.04\%$
test_add_td	0.1210ms	48.7633μs	20.5072 KOps/s	18.6130 KOps/s	$\textbf{\color{#35bf28}+10.18\%}$
test_compile_add_one_nested[tensordict-compile]	0.1725ms	0.1197ms	8.3518 KOps/s	8.0670 KOps/s	$\color{#35bf28}+3.53\%$
test_compile_add_one_nested[tensordict-eager]	0.2236ms	0.1328ms	7.5309 KOps/s	7.5414 KOps/s	$\color{#d91a1a}-0.14\%$
test_compile_add_one_nested[pytree-compile]	0.1948ms	96.6037μs	10.3516 KOps/s	10.3172 KOps/s	$\color{#35bf28}+0.33\%$
test_compile_add_one_nested[pytree-eager]	1.0679ms	0.1520ms	6.5807 KOps/s	6.5324 KOps/s	$\color{#35bf28}+0.74\%$
test_compile_copy_nested[tensordict-compile]	58.8510μs	22.8686μs	43.7281 KOps/s	43.6667 KOps/s	$\color{#35bf28}+0.14\%$
test_compile_copy_nested[tensordict-eager]	62.4510μs	29.4876μs	33.9125 KOps/s	33.8876 KOps/s	$\color{#35bf28}+0.07\%$
test_compile_copy_nested[pytree-compile]	0.3913ms	63.9966μs	15.6258 KOps/s	15.6062 KOps/s	$\color{#35bf28}+0.13\%$
test_compile_copy_nested[pytree-eager]	84.9220μs	48.8070μs	20.4889 KOps/s	20.3847 KOps/s	$\color{#35bf28}+0.51\%$
test_compile_add_one_flat[tensordict-compile]	0.2184ms	0.1421ms	7.0361 KOps/s	6.6975 KOps/s	$\textbf{\color{#35bf28}+5.06\%}$
test_compile_add_one_flat[tensordict-eager]	0.3123ms	0.2182ms	4.5826 KOps/s	4.5625 KOps/s	$\color{#35bf28}+0.44\%$
test_compile_add_one_flat[tensorclass-compile]	0.1454ms	0.1018ms	9.8250 KOps/s	9.8162 KOps/s	$\color{#35bf28}+0.09\%$
test_compile_add_one_flat[tensorclass-eager]	0.1236ms	57.8554μs	17.2845 KOps/s	17.7865 KOps/s	$\color{#d91a1a}-2.82\%$
test_compile_add_one_flat[pytree-compile]	0.2626ms	0.1365ms	7.3241 KOps/s	7.3683 KOps/s	$\color{#d91a1a}-0.60\%$
test_compile_add_one_flat[pytree-eager]	0.5540ms	0.4920ms	2.0326 KOps/s	2.0385 KOps/s	$\color{#d91a1a}-0.29\%$
test_compile_add_self_flat[tensordict-eager]	0.3761ms	0.2606ms	3.8374 KOps/s	3.8147 KOps/s	$\color{#35bf28}+0.60\%$
test_compile_add_self_flat[tensordict-compile]	0.2101ms	0.1475ms	6.7791 KOps/s	6.6790 KOps/s	$\color{#35bf28}+1.50\%$
test_compile_add_self_flat[tensorclass-eager]	0.1711ms	67.9658μs	14.7133 KOps/s	14.1621 KOps/s	$\color{#35bf28}+3.89\%$
test_compile_add_self_flat[tensorclass-compile]	0.1464ms	99.0128μs	10.0997 KOps/s	9.6508 KOps/s	$\color{#35bf28}+4.65\%$
test_compile_add_self_flat[pytree-eager]	0.5210ms	0.4155ms	2.4068 KOps/s	2.4159 KOps/s	$\color{#d91a1a}-0.38\%$
test_compile_add_self_flat[pytree-compile]	0.1801ms	0.1358ms	7.3637 KOps/s	7.0534 KOps/s	$\color{#35bf28}+4.40\%$
test_compile_copy_flat[tensordict-compile]	55.4510μs	18.6404μs	53.6470 KOps/s	53.0184 KOps/s	$\color{#35bf28}+1.19\%$
test_compile_copy_flat[tensordict-eager]	76.7520μs	31.0953μs	32.1592 KOps/s	32.0775 KOps/s	$\color{#35bf28}+0.25\%$
test_compile_copy_flat[pytree-compile]	0.1150ms	70.2451μs	14.2359 KOps/s	14.2461 KOps/s	$\color{#d91a1a}-0.07\%$
test_compile_copy_flat[pytree-eager]	92.5710μs	51.5612μs	19.3944 KOps/s	19.4282 KOps/s	$\color{#d91a1a}-0.17\%$
test_compile_assign_and_add[tensordict-compile]	1.6218ms	0.3918ms	2.5522 KOps/s	2.2185 KOps/s	$\textbf{\color{#35bf28}+15.04\%}$
test_compile_assign_and_add[tensordict-eager]	2.8293ms	2.6673ms	374.9131 Ops/s	370.4603 Ops/s	$\color{#35bf28}+1.20\%$
test_compile_assign_and_add[pytree-compile]	1.5550ms	0.4255ms	2.3502 KOps/s	2.2875 KOps/s	$\color{#35bf28}+2.74\%$
test_compile_assign_and_add[pytree-eager]	3.0361ms	2.7538ms	363.1348 Ops/s	371.0586 Ops/s	$\color{#d91a1a}-2.14\%$
test_compile_indexing[tensor-tensordict-compile]	0.2710ms	0.1209ms	8.2746 KOps/s	8.4304 KOps/s	$\color{#d91a1a}-1.85\%$
test_compile_indexing[tensor-tensordict-eager]	0.6076ms	84.5960μs	11.8209 KOps/s	11.8915 KOps/s	$\color{#d91a1a}-0.59\%$
test_compile_indexing[tensor-tensorclass-compile]	0.2319ms	0.1142ms	8.7572 KOps/s	9.3722 KOps/s	$\textbf{\color{#d91a1a}-6.56\%}$
test_compile_indexing[tensor-tensorclass-eager]	0.1913ms	72.8564μs	13.7256 KOps/s	13.8165 KOps/s	$\color{#d91a1a}-0.66\%$
test_compile_indexing[tensor-pytree-compile]	0.2385ms	0.1143ms	8.7521 KOps/s	8.8103 KOps/s	$\color{#d91a1a}-0.66\%$
test_compile_indexing[tensor-pytree-eager]	0.1712ms	73.1667μs	13.6674 KOps/s	13.5501 KOps/s	$\color{#35bf28}+0.87\%$
test_compile_indexing[slice-tensordict-compile]	0.2120ms	0.1055ms	9.4767 KOps/s	9.9617 KOps/s	$\color{#d91a1a}-4.87\%$
test_compile_indexing[slice-tensordict-eager]	0.1716ms	17.4468μs	57.3171 KOps/s	55.9925 KOps/s	$\color{#35bf28}+2.37\%$
test_compile_indexing[slice-tensorclass-compile]	0.2367ms	99.6772μs	10.0324 KOps/s	10.3548 KOps/s	$\color{#d91a1a}-3.11\%$
test_compile_indexing[slice-tensorclass-eager]	0.1212ms	16.6442μs	60.0811 KOps/s	61.8628 KOps/s	$\color{#d91a1a}-2.88\%$
test_compile_indexing[slice-pytree-compile]	0.2245ms	0.1005ms	9.9530 KOps/s	10.2845 KOps/s	$\color{#d91a1a}-3.22\%$
test_compile_indexing[slice-pytree-eager]	95.7820μs	15.8652μs	63.0311 KOps/s	61.4168 KOps/s	$\color{#35bf28}+2.63\%$
test_compile_indexing[int-tensordict-compile]	0.1653ms	0.1062ms	9.4170 KOps/s	9.8547 KOps/s	$\color{#d91a1a}-4.44\%$
test_compile_indexing[int-tensordict-eager]	0.5812ms	17.6958μs	56.5105 KOps/s	57.3179 KOps/s	$\color{#d91a1a}-1.41\%$
test_compile_indexing[int-tensorclass-compile]	0.2244ms	0.1022ms	9.7832 KOps/s	10.3048 KOps/s	$\textbf{\color{#d91a1a}-5.06\%}$
test_compile_indexing[int-tensorclass-eager]	0.1099ms	17.3336μs	57.6914 KOps/s	61.6523 KOps/s	$\textbf{\color{#d91a1a}-6.42\%}$
test_compile_indexing[int-pytree-compile]	0.2557ms	0.1015ms	9.8515 KOps/s	10.2987 KOps/s	$\color{#d91a1a}-4.34\%$
test_compile_indexing[int-pytree-eager]	57.2600μs	15.8803μs	62.9710 KOps/s	62.3849 KOps/s	$\color{#35bf28}+0.94\%$
test_mod_add[eager]	0.1356ms	37.3097μs	26.8027 KOps/s	24.3321 KOps/s	$\textbf{\color{#35bf28}+10.15\%}$
test_mod_add[compile]	0.1274ms	81.2398μs	12.3092 KOps/s	11.9919 KOps/s	$\color{#35bf28}+2.65\%$
test_mod_add[compile-overhead]	0.3224ms	0.1688ms	5.9241 KOps/s	5.4578 KOps/s	$\textbf{\color{#35bf28}+8.54\%}$
test_mod_wrap[eager]	0.3292ms	0.2459ms	4.0665 KOps/s	3.7408 KOps/s	$\textbf{\color{#35bf28}+8.71\%}$
test_mod_wrap[compile]	0.3597ms	0.2873ms	3.4802 KOps/s	3.4781 KOps/s	$\color{#35bf28}+0.06\%$
test_mod_wrap[compile-overhead]	7.0505ms	3.6885ms	271.1141 Ops/s	273.1975 Ops/s	$\color{#d91a1a}-0.76\%$
test_mod_wrap_and_backward[eager]	1.5010ms	1.3534ms	738.8821 Ops/s	675.0393 Ops/s	$\textbf{\color{#35bf28}+9.46\%}$
test_mod_wrap_and_backward[compile]	1.3491ms	1.2627ms	791.9770 Ops/s	720.9761 Ops/s	$\textbf{\color{#35bf28}+9.85\%}$
test_mod_wrap_and_backward[compile-overhead]	1.3736ms	0.9209ms	1.0859 KOps/s	963.9797 Ops/s	$\textbf{\color{#35bf28}+12.65\%}$
test_seq_add[eager]	0.1732ms	0.1130ms	8.8522 KOps/s	8.1258 KOps/s	$\textbf{\color{#35bf28}+8.94\%}$
test_seq_add[compile]	0.1381ms	90.3172μs	11.0721 KOps/s	11.1990 KOps/s	$\color{#d91a1a}-1.13\%$
test_seq_add[compile-overhead]	0.1771ms	0.1304ms	7.6663 KOps/s	7.6994 KOps/s	$\color{#d91a1a}-0.43\%$
test_seq_wrap[eager]	0.5013ms	0.4295ms	2.3282 KOps/s	2.2919 KOps/s	$\color{#35bf28}+1.58\%$
test_seq_wrap[compile]	0.3703ms	0.2954ms	3.3851 KOps/s	3.2782 KOps/s	$\color{#35bf28}+3.26\%$
test_seq_wrap[compile-overhead]	0.3014ms	0.2237ms	4.4711 KOps/s	4.4597 KOps/s	$\color{#35bf28}+0.26\%$
test_func_call_runtime[False-eager]	0.9067ms	0.7503ms	1.3328 KOps/s	1.3229 KOps/s	$\color{#35bf28}+0.74\%$
test_func_call_runtime[False-compile]	0.7943ms	0.7381ms	1.3548 KOps/s	1.3280 KOps/s	$\color{#35bf28}+2.02\%$
test_func_call_runtime[False-compile-overhead]	0.4372ms	0.3608ms	2.7719 KOps/s	2.7626 KOps/s	$\color{#35bf28}+0.34\%$
test_func_call_runtime[True-eager]	1.0398ms	0.9006ms	1.1104 KOps/s	1.0811 KOps/s	$\color{#35bf28}+2.71\%$
test_func_call_runtime[True-compile]	0.8217ms	0.7609ms	1.3142 KOps/s	1.2964 KOps/s	$\color{#35bf28}+1.37\%$
test_func_call_runtime[True-compile-overhead]	0.4680ms	0.3831ms	2.6102 KOps/s	2.6224 KOps/s	$\color{#d91a1a}-0.46\%$
test_func_call_cm_runtime[False-eager]	0.8201ms	0.7291ms	1.3716 KOps/s	1.3237 KOps/s	$\color{#35bf28}+3.61\%$
test_func_call_cm_runtime[False-compile]	0.8140ms	0.7471ms	1.3384 KOps/s	1.3211 KOps/s	$\color{#35bf28}+1.31\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4101ms	0.3640ms	2.7476 KOps/s	2.7480 KOps/s	$\color{#d91a1a}-0.01\%$
test_func_call_cm_runtime[True-eager]	1.1470ms	1.0065ms	993.5591 Ops/s	977.4628 Ops/s	$\color{#35bf28}+1.65\%$
test_func_call_cm_runtime[True-compile]	0.8754ms	0.7926ms	1.2617 KOps/s	1.2507 KOps/s	$\color{#35bf28}+0.88\%$
test_func_call_cm_runtime[True-compile-overhead]	0.4588ms	0.4081ms	2.4504 KOps/s	2.4472 KOps/s	$\color{#35bf28}+0.13\%$
test_vmap_func_call_cm_runtime[eager]	2.5369ms	2.0684ms	483.4555 Ops/s	475.0127 Ops/s	$\color{#35bf28}+1.78\%$
test_vmap_func_call_cm_runtime[compile]	0.8749ms	0.8038ms	1.2440 KOps/s	1.2200 KOps/s	$\color{#35bf28}+1.97\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.4758ms	0.4131ms	2.4206 KOps/s	2.4306 KOps/s	$\color{#d91a1a}-0.41\%$
test_distributed	2.5882ms	0.3058ms	3.2699 KOps/s	8.4242 KOps/s	$\textbf{\color{#d91a1a}-61.18\%}$
test_tdmodule	43.4500μs	18.7557μs	53.3172 KOps/s	47.8732 KOps/s	$\textbf{\color{#35bf28}+11.37\%}$
test_tdmodule_dispatch	72.1520μs	33.3626μs	29.9737 KOps/s	26.4672 KOps/s	$\textbf{\color{#35bf28}+13.25\%}$
test_tdseq	40.1510μs	19.7995μs	50.5062 KOps/s	44.4245 KOps/s	$\textbf{\color{#35bf28}+13.69\%}$
test_tdseq_dispatch	57.4410μs	36.9670μs	27.0512 KOps/s	24.1438 KOps/s	$\textbf{\color{#35bf28}+12.04\%}$
test_instantiation_functorch	1.6428ms	1.5493ms	645.4732 Ops/s	629.6777 Ops/s	$\color{#35bf28}+2.51\%$
test_exec_functorch	0.1930ms	0.1489ms	6.7152 KOps/s	6.7874 KOps/s	$\color{#d91a1a}-1.06\%$
test_exec_functional_call	0.1883ms	0.1398ms	7.1508 KOps/s	7.3068 KOps/s	$\color{#d91a1a}-2.13\%$
test_exec_td_decorator	0.3956ms	0.1890ms	5.2910 KOps/s	5.3737 KOps/s	$\color{#d91a1a}-1.54\%$
test_vmap_mlp_speed_decorator[True-True]	0.8160ms	0.6936ms	1.4417 KOps/s	1.4389 KOps/s	$\color{#35bf28}+0.20\%$
test_vmap_mlp_speed_decorator[True-False]	0.8077ms	0.6879ms	1.4536 KOps/s	1.4359 KOps/s	$\color{#35bf28}+1.23\%$
test_vmap_mlp_speed_decorator[False-True]	0.7076ms	0.5949ms	1.6809 KOps/s	1.6607 KOps/s	$\color{#35bf28}+1.22\%$
test_vmap_mlp_speed_decorator[False-False]	0.7230ms	0.5942ms	1.6830 KOps/s	1.6546 KOps/s	$\color{#35bf28}+1.72\%$
test_vmap_transformer_speed_decorator[True-True]	19.9904ms	19.2505ms	51.9466 Ops/s	51.5647 Ops/s	$\color{#35bf28}+0.74\%$
test_vmap_transformer_speed_decorator[True-False]	19.3417ms	19.2482ms	51.9528 Ops/s	51.6776 Ops/s	$\color{#35bf28}+0.53\%$
test_vmap_transformer_speed_decorator[False-True]	19.8815ms	19.3256ms	51.7449 Ops/s	52.0274 Ops/s	$\color{#d91a1a}-0.54\%$
test_vmap_transformer_speed_decorator[False-False]	19.8818ms	19.1535ms	52.2098 Ops/s	51.9873 Ops/s	$\color{#35bf28}+0.43\%$
test_to_module_speed[True]	2.2559ms	0.9820ms	1.0184 KOps/s	1.0263 KOps/s	$\color{#d91a1a}-0.78\%$
test_to_module_speed[False]	1.0551ms	0.9703ms	1.0306 KOps/s	1.0512 KOps/s	$\color{#d91a1a}-1.97\%$
test_tc_init	72.1110μs	34.4792μs	29.0030 KOps/s	25.3328 KOps/s	$\textbf{\color{#35bf28}+14.49\%}$
test_tc_init_nested	0.1081ms	67.9759μs	14.7111 KOps/s	12.9092 KOps/s	$\textbf{\color{#35bf28}+13.96\%}$
test_tc_first_layer_tensor	4.2371μs	0.7123μs	1.4040 MOps/s	1.2137 MOps/s	$\textbf{\color{#35bf28}+15.68\%}$
test_tc_first_layer_nontensor	96.3520μs	2.2439μs	445.6504 KOps/s	436.3911 KOps/s	$\color{#35bf28}+2.12\%$
test_tc_second_layer_tensor	6.9177μs	1.4271μs	700.7049 KOps/s	699.8813 KOps/s	$\color{#35bf28}+0.12\%$
test_tc_second_layer_nontensor	26.8210μs	3.0382μs	329.1416 KOps/s	330.1855 KOps/s	$\color{#d91a1a}-0.32\%$
test_unbind	0.2163s	12.2500ms	81.6325 Ops/s	142.8104 Ops/s	$\textbf{\color{#d91a1a}-42.84\%}$
test_full_like	9.7054ms	9.1421ms	109.3846 Ops/s	105.9083 Ops/s	$\color{#35bf28}+3.28\%$
test_zeros_like	4.7943ms	4.1833ms	239.0453 Ops/s	230.3417 Ops/s	$\color{#35bf28}+3.78\%$
test_ones_like	9.2583ms	7.2549ms	137.8387 Ops/s	233.6981 Ops/s	$\textbf{\color{#d91a1a}-41.02\%}$
test_clone	6.7980ms	6.3961ms	156.3457 Ops/s	156.6513 Ops/s	$\color{#d91a1a}-0.20\%$
test_squeeze	59.5510μs	9.7470μs	102.5957 KOps/s	106.6082 KOps/s	$\color{#d91a1a}-3.76\%$
test_unsqueeze	0.1219ms	73.6081μs	13.5855 KOps/s	13.6617 KOps/s	$\color{#d91a1a}-0.56\%$
test_split	0.3984ms	0.1646ms	6.0753 KOps/s	6.1512 KOps/s	$\color{#d91a1a}-1.23\%$
test_permute	0.2454ms	0.1800ms	5.5560 KOps/s	5.6088 KOps/s	$\color{#d91a1a}-0.94\%$
test_stack	50.7325ms	50.2111ms	19.9159 Ops/s	19.8706 Ops/s	$\color{#35bf28}+0.23\%$
test_cat	50.5565ms	50.2251ms	19.9103 Ops/s	19.8447 Ops/s	$\color{#35bf28}+0.33\%$