[Feature] super() calls within TensorClass subclasses

[vmoens]

Stack from ghstack (oldest at bottom):

• -> [Feature] super() calls within TensorClass subclasses #1133
• [Feature] NonTensorStack.data #1132

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}8$. Worsened: $\large\color{#d91a1a}17$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	47.2590μs	18.0872μs	55.2876 KOps/s	57.5528 KOps/s	$\color{#d91a1a}-3.94\%$
test_plain_set_stack_nested	45.4150μs	18.2586μs	54.7686 KOps/s	56.4604 KOps/s	$\color{#d91a1a}-3.00\%$
test_plain_set_nested_inplace	56.2950μs	19.8954μs	50.2629 KOps/s	51.9612 KOps/s	$\color{#d91a1a}-3.27\%$
test_plain_set_stack_nested_inplace	50.4940μs	19.9453μs	50.1372 KOps/s	52.2642 KOps/s	$\color{#d91a1a}-4.07\%$
test_items	20.3780μs	4.1600μs	240.3875 KOps/s	237.6886 KOps/s	$\color{#35bf28}+1.14\%$
test_items_nested	0.6964ms	0.4046ms	2.4713 KOps/s	2.3953 KOps/s	$\color{#35bf28}+3.17\%$
test_items_nested_locked	0.5958ms	0.4042ms	2.4741 KOps/s	2.4108 KOps/s	$\color{#35bf28}+2.63\%$
test_items_nested_leaf	0.1458ms	70.6108μs	14.1621 KOps/s	14.2285 KOps/s	$\color{#d91a1a}-0.47\%$
test_items_stack_nested	0.8407ms	0.4047ms	2.4709 KOps/s	2.4036 KOps/s	$\color{#35bf28}+2.80\%$
test_items_stack_nested_leaf	0.1268ms	71.4616μs	13.9935 KOps/s	13.7004 KOps/s	$\color{#35bf28}+2.14\%$
test_items_stack_nested_locked	0.7013ms	0.4033ms	2.4796 KOps/s	2.3828 KOps/s	$\color{#35bf28}+4.06\%$
test_keys	25.4980μs	3.4966μs	285.9941 KOps/s	282.6369 KOps/s	$\color{#35bf28}+1.19\%$
test_keys_nested	0.2256ms	0.1391ms	7.1907 KOps/s	7.4211 KOps/s	$\color{#d91a1a}-3.10\%$
test_keys_nested_locked	1.8289ms	0.1439ms	6.9504 KOps/s	7.1120 KOps/s	$\color{#d91a1a}-2.27\%$
test_keys_nested_leaf	0.2123ms	0.1203ms	8.3125 KOps/s	8.6625 KOps/s	$\color{#d91a1a}-4.04\%$
test_keys_stack_nested	0.2681ms	0.1391ms	7.1907 KOps/s	7.4342 KOps/s	$\color{#d91a1a}-3.28\%$
test_keys_stack_nested_leaf	0.2692ms	0.1200ms	8.3348 KOps/s	8.6709 KOps/s	$\color{#d91a1a}-3.88\%$
test_keys_stack_nested_locked	0.2454ms	0.1444ms	6.9244 KOps/s	7.0321 KOps/s	$\color{#d91a1a}-1.53\%$
test_values	6.9550μs	1.0397μs	961.7856 KOps/s	966.8221 KOps/s	$\color{#d91a1a}-0.52\%$
test_values_nested	99.8470μs	55.3160μs	18.0779 KOps/s	18.2299 KOps/s	$\color{#d91a1a}-0.83\%$
test_values_nested_locked	98.2540μs	55.7812μs	17.9272 KOps/s	17.8651 KOps/s	$\color{#35bf28}+0.35\%$
test_values_nested_leaf	0.1071ms	60.4180μs	16.5514 KOps/s	14.8077 KOps/s	$\textbf{\color{#35bf28}+11.78\%}$
test_values_stack_nested	0.1071ms	55.0717μs	18.1581 KOps/s	17.9294 KOps/s	$\color{#35bf28}+1.28\%$
test_values_stack_nested_leaf	0.1082ms	59.9498μs	16.6806 KOps/s	16.5984 KOps/s	$\color{#35bf28}+0.50\%$
test_values_stack_nested_locked	0.1109ms	55.7453μs	17.9387 KOps/s	17.8359 KOps/s	$\color{#35bf28}+0.58\%$
test_membership	19.7970μs	0.8649μs	1.1562 MOps/s	1.3678 MOps/s	$\textbf{\color{#d91a1a}-15.47\%}$
test_membership_nested	35.6570μs	2.9454μs	339.5125 KOps/s	337.2617 KOps/s	$\color{#35bf28}+0.67\%$
test_membership_nested_leaf	60.7430μs	2.9439μs	339.6820 KOps/s	333.1118 KOps/s	$\color{#35bf28}+1.97\%$
test_membership_stacked_nested	32.3110μs	2.8866μs	346.4224 KOps/s	343.0138 KOps/s	$\color{#35bf28}+0.99\%$
test_membership_stacked_nested_leaf	22.9630μs	2.9189μs	342.6000 KOps/s	338.3451 KOps/s	$\color{#35bf28}+1.26\%$
test_membership_nested_last	38.9430μs	4.2530μs	235.1257 KOps/s	238.1784 KOps/s	$\color{#d91a1a}-1.28\%$
test_membership_nested_leaf_last	28.1520μs	4.3100μs	232.0211 KOps/s	238.0551 KOps/s	$\color{#d91a1a}-2.53\%$
test_membership_stacked_nested_last	43.3010μs	4.2461μs	235.5088 KOps/s	240.3159 KOps/s	$\color{#d91a1a}-2.00\%$
test_membership_stacked_nested_leaf_last	38.4430μs	4.2553μs	234.9990 KOps/s	237.2472 KOps/s	$\color{#d91a1a}-0.95\%$
test_nested_getleaf	32.2300μs	10.9197μs	91.5772 KOps/s	93.2582 KOps/s	$\color{#d91a1a}-1.80\%$
test_nested_get	0.2437ms	10.2257μs	97.7924 KOps/s	96.4844 KOps/s	$\color{#35bf28}+1.36\%$
test_stacked_getleaf	0.2105ms	11.6435μs	85.8845 KOps/s	93.9364 KOps/s	$\textbf{\color{#d91a1a}-8.57\%}$
test_stacked_get	56.4560μs	10.3400μs	96.7117 KOps/s	98.1226 KOps/s	$\color{#d91a1a}-1.44\%$
test_nested_getitemleaf	40.4160μs	11.2644μs	88.7755 KOps/s	89.8884 KOps/s	$\color{#d91a1a}-1.24\%$
test_nested_getitem	49.1020μs	10.5119μs	95.1301 KOps/s	97.4704 KOps/s	$\color{#d91a1a}-2.40\%$
test_stacked_getitemleaf	43.5710μs	11.1933μs	89.3394 KOps/s	90.5485 KOps/s	$\color{#d91a1a}-1.34\%$
test_stacked_getitem	55.3730μs	10.4433μs	95.7550 KOps/s	96.7409 KOps/s	$\color{#d91a1a}-1.02\%$
test_lock_nested	4.7801ms	0.4559ms	2.1933 KOps/s	2.2183 KOps/s	$\color{#d91a1a}-1.13\%$
test_lock_stack_nested	1.1426ms	0.4215ms	2.3725 KOps/s	2.4169 KOps/s	$\color{#d91a1a}-1.84\%$
test_unlock_nested	1.7758ms	0.3793ms	2.6367 KOps/s	2.7269 KOps/s	$\color{#d91a1a}-3.31\%$
test_unlock_stack_nested	0.5199ms	0.3393ms	2.9473 KOps/s	2.9851 KOps/s	$\color{#d91a1a}-1.26\%$
test_flatten_speed	0.1887ms	94.2946μs	10.6051 KOps/s	10.5416 KOps/s	$\color{#35bf28}+0.60\%$
test_unflatten_speed	1.0751ms	0.4983ms	2.0067 KOps/s	2.0022 KOps/s	$\color{#35bf28}+0.22\%$
test_common_ops	3.8546ms	0.7866ms	1.2712 KOps/s	1.2905 KOps/s	$\color{#d91a1a}-1.49\%$
test_creation	25.2670μs	2.1622μs	462.4998 KOps/s	480.3181 KOps/s	$\color{#d91a1a}-3.71\%$
test_creation_empty	54.0720μs	11.3397μs	88.1855 KOps/s	98.2380 KOps/s	$\textbf{\color{#d91a1a}-10.23\%}$
test_creation_nested_1	1.4166ms	14.0891μs	70.9771 KOps/s	76.4004 KOps/s	$\textbf{\color{#d91a1a}-7.10\%}$
test_creation_nested_2	62.5770μs	18.2335μs	54.8440 KOps/s	57.7416 KOps/s	$\textbf{\color{#d91a1a}-5.02\%}$
test_clone	81.6230μs	13.3265μs	75.0384 KOps/s	78.1359 KOps/s	$\color{#d91a1a}-3.96\%$
test_getitem[int]	0.2687ms	12.5668μs	79.5750 KOps/s	79.8701 KOps/s	$\color{#d91a1a}-0.37\%$
test_getitem[slice_int]	0.1612ms	24.3024μs	41.1483 KOps/s	40.5537 KOps/s	$\color{#35bf28}+1.47\%$
test_getitem[range]	0.2784ms	49.1345μs	20.3523 KOps/s	20.9604 KOps/s	$\color{#d91a1a}-2.90\%$
test_getitem[tuple]	0.1349ms	20.4205μs	48.9704 KOps/s	49.0052 KOps/s	$\color{#d91a1a}-0.07\%$
test_getitem[list]	0.2205ms	43.8641μs	22.7977 KOps/s	23.2562 KOps/s	$\color{#d91a1a}-1.97\%$
test_setitem_dim[int]	57.6170μs	25.5809μs	39.0917 KOps/s	39.1768 KOps/s	$\color{#d91a1a}-0.22\%$
test_setitem_dim[slice_int]	92.1020μs	52.6572μs	18.9908 KOps/s	18.8869 KOps/s	$\color{#35bf28}+0.55\%$
test_setitem_dim[range]	0.1243ms	74.3244μs	13.4545 KOps/s	13.6568 KOps/s	$\color{#d91a1a}-1.48\%$
test_setitem_dim[tuple]	63.8090μs	43.0857μs	23.2096 KOps/s	23.6000 KOps/s	$\color{#d91a1a}-1.65\%$
test_setitem	0.1351ms	20.8191μs	48.0329 KOps/s	51.7683 KOps/s	$\textbf{\color{#d91a1a}-7.22\%}$
test_set	0.1322ms	20.4620μs	48.8710 KOps/s	52.4579 KOps/s	$\textbf{\color{#d91a1a}-6.84\%}$
test_set_shared	5.7226ms	0.1698ms	5.8887 KOps/s	5.9152 KOps/s	$\color{#d91a1a}-0.45\%$
test_update	0.1758ms	23.3581μs	42.8117 KOps/s	46.3555 KOps/s	$\textbf{\color{#d91a1a}-7.64\%}$
test_update_nested	0.1297ms	34.5354μs	28.9558 KOps/s	31.2959 KOps/s	$\textbf{\color{#d91a1a}-7.48\%}$
test_update__nested	1.0160ms	33.8525μs	29.5400 KOps/s	31.4546 KOps/s	$\textbf{\color{#d91a1a}-6.09\%}$
test_set_nested	0.1046ms	23.3989μs	42.7371 KOps/s	48.1069 KOps/s	$\textbf{\color{#d91a1a}-11.16\%}$
test_set_nested_new	0.1182ms	28.1936μs	35.4690 KOps/s	39.1660 KOps/s	$\textbf{\color{#d91a1a}-9.44\%}$
test_select	0.1920ms	44.5386μs	22.4524 KOps/s	24.0281 KOps/s	$\textbf{\color{#d91a1a}-6.56\%}$
test_select_nested	0.1252ms	60.3866μs	16.5600 KOps/s	16.8918 KOps/s	$\color{#d91a1a}-1.96\%$
test_exclude_nested	0.1925ms	79.6314μs	12.5579 KOps/s	12.7992 KOps/s	$\color{#d91a1a}-1.89\%$
test_empty[True]	0.5947ms	0.3882ms	2.5759 KOps/s	2.5847 KOps/s	$\color{#d91a1a}-0.34\%$
test_empty[False]	11.9423μs	1.2710μs	786.7844 KOps/s	815.9154 KOps/s	$\color{#d91a1a}-3.57\%$
test_unbind_speed	0.3955ms	0.2676ms	3.7374 KOps/s	3.7655 KOps/s	$\color{#d91a1a}-0.75\%$
test_unbind_speed_stack0	0.4554ms	0.2655ms	3.7669 KOps/s	3.8933 KOps/s	$\color{#d91a1a}-3.25\%$
test_unbind_speed_stack1	0.1143s	0.7963ms	1.2557 KOps/s	1.4307 KOps/s	$\textbf{\color{#d91a1a}-12.23\%}$
test_split	0.1169s	1.7447ms	573.1796 Ops/s	585.0297 Ops/s	$\color{#d91a1a}-2.03\%$
test_chunk	0.1051s	1.7370ms	575.7023 Ops/s	585.7254 Ops/s	$\color{#d91a1a}-1.71\%$
test_consolidate_njt[False-None]	8.3411ms	8.1092ms	123.3172 Ops/s	121.5396 Ops/s	$\color{#35bf28}+1.46\%$
test_creation[device0]	0.2514ms	90.1905μs	11.0876 KOps/s	10.5927 KOps/s	$\color{#35bf28}+4.67\%$
test_creation_from_tensor	3.8366ms	95.8417μs	10.4339 KOps/s	10.5279 KOps/s	$\color{#d91a1a}-0.89\%$
test_add_one[memmap_tensor0]	95.6790μs	4.6679μs	214.2310 KOps/s	210.8647 KOps/s	$\color{#35bf28}+1.60\%$
test_contiguous[memmap_tensor0]	23.6540μs	0.5240μs	1.9083 MOps/s	1.8821 MOps/s	$\color{#35bf28}+1.40\%$
test_stack[memmap_tensor0]	27.2820μs	3.3033μs	302.7247 KOps/s	298.2389 KOps/s	$\color{#35bf28}+1.50\%$
test_memmaptd_index	1.0821ms	0.2291ms	4.3652 KOps/s	4.2616 KOps/s	$\color{#35bf28}+2.43\%$
test_memmaptd_index_astensor	0.5876ms	0.3066ms	3.2611 KOps/s	3.1919 KOps/s	$\color{#35bf28}+2.17\%$
test_memmaptd_index_op	1.0468ms	0.5765ms	1.7346 KOps/s	1.7473 KOps/s	$\color{#d91a1a}-0.73\%$
test_serialize_model	0.1331s	0.1171s	8.5388 Ops/s	7.3802 Ops/s	$\textbf{\color{#35bf28}+15.70\%}$
test_serialize_model_pickle	0.4952s	0.3974s	2.5164 Ops/s	2.5521 Ops/s	$\color{#d91a1a}-1.40\%$
test_serialize_weights	0.2257s	0.1318s	7.5881 Ops/s	8.7803 Ops/s	$\textbf{\color{#d91a1a}-13.58\%}$
test_serialize_weights_returnearly	0.1675s	0.1595s	6.2694 Ops/s	6.3988 Ops/s	$\color{#d91a1a}-2.02\%$
test_serialize_weights_pickle	1.2461s	0.7114s	1.4056 Ops/s	2.2529 Ops/s	$\textbf{\color{#d91a1a}-37.61\%}$
test_serialize_weights_filesystem	0.1528s	0.1425s	7.0159 Ops/s	6.4316 Ops/s	$\textbf{\color{#35bf28}+9.08\%}$
test_serialize_model_filesystem	0.2469s	0.1587s	6.3029 Ops/s	6.8491 Ops/s	$\textbf{\color{#d91a1a}-7.97\%}$
test_reshape_pytree	71.9440μs	26.9120μs	37.1581 KOps/s	36.6930 KOps/s	$\color{#35bf28}+1.27\%$
test_reshape_td	82.9050μs	32.4876μs	30.7810 KOps/s	29.4769 KOps/s	$\color{#35bf28}+4.42\%$
test_view_pytree	68.3780μs	26.6703μs	37.4949 KOps/s	36.1233 KOps/s	$\color{#35bf28}+3.80\%$
test_view_td	0.1159ms	37.1670μs	26.9056 KOps/s	25.8179 KOps/s	$\color{#35bf28}+4.21\%$
test_unbind_pytree	66.2940μs	30.1300μs	33.1896 KOps/s	33.1293 KOps/s	$\color{#35bf28}+0.18\%$
test_unbind_td	0.3669ms	39.1761μs	25.5258 KOps/s	25.6128 KOps/s	$\color{#d91a1a}-0.34\%$
test_split_pytree	89.4380μs	30.1406μs	33.1779 KOps/s	33.4164 KOps/s	$\color{#d91a1a}-0.71\%$
test_split_td	0.4957ms	44.0752μs	22.6885 KOps/s	22.7538 KOps/s	$\color{#d91a1a}-0.29\%$
test_add_pytree	75.3810μs	35.9061μs	27.8504 KOps/s	27.4481 KOps/s	$\color{#35bf28}+1.47\%$
test_add_td	0.1287ms	55.2843μs	18.0883 KOps/s	18.8841 KOps/s	$\color{#d91a1a}-4.21\%$
test_compile_add_one_nested[tensordict-compile]	0.1454ms	61.9533μs	16.1412 KOps/s	16.0163 KOps/s	$\color{#35bf28}+0.78\%$
test_compile_add_one_nested[tensordict-eager]	1.4410ms	0.1617ms	6.1824 KOps/s	6.2061 KOps/s	$\color{#d91a1a}-0.38\%$
test_compile_add_one_nested[pytree-compile]	0.1293ms	46.2200μs	21.6357 KOps/s	22.4297 KOps/s	$\color{#d91a1a}-3.54\%$
test_compile_add_one_nested[pytree-eager]	0.2193ms	0.1181ms	8.4685 KOps/s	8.3450 KOps/s	$\color{#35bf28}+1.48\%$
test_compile_copy_nested[tensordict-compile]	75.8620μs	26.1247μs	38.2779 KOps/s	38.8624 KOps/s	$\color{#d91a1a}-1.50\%$
test_compile_copy_nested[tensordict-eager]	0.1448ms	53.4036μs	18.7253 KOps/s	18.8678 KOps/s	$\color{#d91a1a}-0.75\%$
test_compile_copy_nested[pytree-compile]	0.3752ms	80.0004μs	12.4999 KOps/s	12.5817 KOps/s	$\color{#d91a1a}-0.65\%$
test_compile_copy_nested[pytree-eager]	0.2404ms	68.1395μs	14.6758 KOps/s	14.7772 KOps/s	$\color{#d91a1a}-0.69\%$
test_compile_add_one_flat[tensordict-compile]	0.1833ms	0.1049ms	9.5331 KOps/s	9.4668 KOps/s	$\color{#35bf28}+0.70\%$
test_compile_add_one_flat[tensordict-eager]	0.4113ms	0.2000ms	5.0008 KOps/s	4.9739 KOps/s	$\color{#35bf28}+0.54\%$
test_compile_add_one_flat[tensorclass-compile]	0.1063ms	45.1069μs	22.1696 KOps/s	22.7602 KOps/s	$\color{#d91a1a}-2.59\%$
test_compile_add_one_flat[tensorclass-eager]	0.4988ms	63.6589μs	15.7087 KOps/s	15.9758 KOps/s	$\color{#d91a1a}-1.67\%$
test_compile_add_one_flat[pytree-compile]	0.2194ms	0.1043ms	9.5896 KOps/s	9.7925 KOps/s	$\color{#d91a1a}-2.07\%$
test_compile_add_one_flat[pytree-eager]	0.3166ms	0.2010ms	4.9755 KOps/s	4.9929 KOps/s	$\color{#d91a1a}-0.35\%$
test_compile_add_self_flat[tensordict-eager]	0.4256ms	0.2114ms	4.7305 KOps/s	4.7214 KOps/s	$\color{#35bf28}+0.19\%$
test_compile_add_self_flat[tensordict-compile]	0.3058ms	0.1088ms	9.1908 KOps/s	9.4901 KOps/s	$\color{#d91a1a}-3.15\%$
test_compile_add_self_flat[tensorclass-eager]	0.2488ms	55.2594μs	18.0965 KOps/s	18.1645 KOps/s	$\color{#d91a1a}-0.37\%$
test_compile_add_self_flat[tensorclass-compile]	0.3779ms	46.5310μs	21.4911 KOps/s	21.8502 KOps/s	$\color{#d91a1a}-1.64\%$
test_compile_add_self_flat[pytree-eager]	0.6689ms	0.1597ms	6.2605 KOps/s	6.3120 KOps/s	$\color{#d91a1a}-0.82\%$
test_compile_add_self_flat[pytree-compile]	0.1961ms	0.1020ms	9.8064 KOps/s	9.6687 KOps/s	$\color{#35bf28}+1.42\%$
test_compile_copy_flat[tensordict-compile]	91.2110μs	21.7049μs	46.0725 KOps/s	45.5424 KOps/s	$\color{#35bf28}+1.16\%$
test_compile_copy_flat[tensordict-eager]	0.4173ms	58.6243μs	17.0578 KOps/s	17.0330 KOps/s	$\color{#35bf28}+0.15\%$
test_compile_copy_flat[pytree-compile]	0.1645ms	80.3106μs	12.4517 KOps/s	12.3042 KOps/s	$\color{#35bf28}+1.20\%$
test_compile_copy_flat[pytree-eager]	0.1413ms	68.7162μs	14.5526 KOps/s	14.3618 KOps/s	$\color{#35bf28}+1.33\%$
test_compile_assign_and_add[tensordict-compile]	0.3042ms	0.2080ms	4.8085 KOps/s	4.8051 KOps/s	$\color{#35bf28}+0.07\%$
test_compile_assign_and_add[tensordict-eager]	2.8313ms	1.2883ms	776.2249 Ops/s	769.4625 Ops/s	$\color{#35bf28}+0.88\%$
test_compile_assign_and_add[pytree-compile]	0.2981ms	0.2026ms	4.9348 KOps/s	4.9458 KOps/s	$\color{#d91a1a}-0.22\%$
test_compile_assign_and_add[pytree-eager]	0.8875ms	0.7635ms	1.3097 KOps/s	1.2727 KOps/s	$\color{#35bf28}+2.91\%$
test_compile_assign_and_add_stack[compile]	0.8370ms	0.4594ms	2.1768 KOps/s	2.1914 KOps/s	$\color{#d91a1a}-0.67\%$
test_compile_assign_and_add_stack[eager]	3.5904ms	2.6679ms	374.8262 Ops/s	375.4216 Ops/s	$\color{#d91a1a}-0.16\%$
test_compile_indexing[tensor-tensordict-compile]	96.3610μs	35.9565μs	27.8114 KOps/s	28.1952 KOps/s	$\color{#d91a1a}-1.36\%$
test_compile_indexing[tensor-tensordict-eager]	0.5502ms	32.9973μs	30.3055 KOps/s	29.8740 KOps/s	$\color{#35bf28}+1.44\%$
test_compile_indexing[tensor-tensorclass-compile]	70.3220μs	28.8733μs	34.6341 KOps/s	34.3413 KOps/s	$\color{#35bf28}+0.85\%$
test_compile_indexing[tensor-tensorclass-eager]	94.6870μs	23.8174μs	41.9861 KOps/s	42.0622 KOps/s	$\color{#d91a1a}-0.18\%$
test_compile_indexing[tensor-pytree-compile]	97.3330μs	29.7435μs	33.6208 KOps/s	33.9973 KOps/s	$\color{#d91a1a}-1.11\%$
test_compile_indexing[tensor-pytree-eager]	70.8130μs	23.6729μs	42.2424 KOps/s	42.4596 KOps/s	$\color{#d91a1a}-0.51\%$
test_compile_indexing[slice-tensordict-compile]	99.9870μs	51.3065μs	19.4907 KOps/s	19.4938 KOps/s	$\color{#d91a1a}-0.02\%$
test_compile_indexing[slice-tensordict-eager]	0.4227ms	20.0840μs	49.7909 KOps/s	48.9511 KOps/s	$\color{#35bf28}+1.72\%$
test_compile_indexing[slice-tensorclass-compile]	0.1581ms	44.1440μs	22.6531 KOps/s	22.3204 KOps/s	$\color{#35bf28}+1.49\%$
test_compile_indexing[slice-tensorclass-eager]	61.5460μs	18.6696μs	53.5631 KOps/s	51.8724 KOps/s	$\color{#35bf28}+3.26\%$
test_compile_indexing[slice-pytree-compile]	0.1238ms	44.4358μs	22.5044 KOps/s	22.2442 KOps/s	$\color{#35bf28}+1.17\%$
test_compile_indexing[slice-pytree-eager]	66.3950μs	18.6490μs	53.6221 KOps/s	51.5038 KOps/s	$\color{#35bf28}+4.11\%$
test_compile_indexing[int-tensordict-compile]	0.1206ms	52.8423μs	18.9242 KOps/s	18.6944 KOps/s	$\color{#35bf28}+1.23\%$
test_compile_indexing[int-tensordict-eager]	1.0010ms	20.0870μs	49.7835 KOps/s	49.4191 KOps/s	$\color{#35bf28}+0.74\%$
test_compile_indexing[int-tensorclass-compile]	0.1248ms	44.8959μs	22.2738 KOps/s	22.2013 KOps/s	$\color{#35bf28}+0.33\%$
test_compile_indexing[int-tensorclass-eager]	76.4430μs	18.7140μs	53.4360 KOps/s	52.2159 KOps/s	$\color{#35bf28}+2.34\%$
test_compile_indexing[int-pytree-compile]	92.7040μs	44.6053μs	22.4189 KOps/s	22.2318 KOps/s	$\color{#35bf28}+0.84\%$
test_compile_indexing[int-pytree-eager]	59.4320μs	18.6533μs	53.6100 KOps/s	52.7237 KOps/s	$\color{#35bf28}+1.68\%$
test_mod_add[eager]	76.8740μs	34.4243μs	29.0493 KOps/s	29.0791 KOps/s	$\color{#d91a1a}-0.10\%$
test_mod_add[compile]	93.8460μs	47.1563μs	21.2061 KOps/s	20.9461 KOps/s	$\color{#35bf28}+1.24\%$
test_mod_add[compile-overhead]	0.1093ms	47.1694μs	21.2002 KOps/s	21.1077 KOps/s	$\color{#35bf28}+0.44\%$
test_mod_wrap[eager]	0.4104ms	0.2212ms	4.5201 KOps/s	4.2302 KOps/s	$\textbf{\color{#35bf28}+6.85\%}$
test_mod_wrap[compile]	0.3384ms	0.2032ms	4.9204 KOps/s	4.6969 KOps/s	$\color{#35bf28}+4.76\%$
test_mod_wrap[compile-overhead]	0.8396ms	0.2057ms	4.8622 KOps/s	4.7295 KOps/s	$\color{#35bf28}+2.81\%$
test_mod_wrap_and_backward[eager]	15.7409ms	12.2194ms	81.8370 Ops/s	80.9821 Ops/s	$\color{#35bf28}+1.06\%$
test_mod_wrap_and_backward[compile]	13.9449ms	11.4670ms	87.2070 Ops/s	85.2607 Ops/s	$\color{#35bf28}+2.28\%$
test_mod_wrap_and_backward[compile-overhead]	21.3785ms	13.5275ms	73.9233 Ops/s	76.3951 Ops/s	$\color{#d91a1a}-3.24\%$
test_seq_add[eager]	0.1957ms	0.1109ms	9.0154 KOps/s	8.8463 KOps/s	$\color{#35bf28}+1.91\%$
test_seq_add[compile]	0.1239ms	62.5709μs	15.9819 KOps/s	16.1352 KOps/s	$\color{#d91a1a}-0.95\%$
test_seq_add[compile-overhead]	0.1178ms	59.4822μs	16.8118 KOps/s	16.6147 KOps/s	$\color{#35bf28}+1.19\%$
test_seq_wrap[eager]	1.0575ms	0.4332ms	2.3083 KOps/s	2.2583 KOps/s	$\color{#35bf28}+2.21\%$
test_seq_wrap[compile]	0.4419ms	0.2268ms	4.4098 KOps/s	4.2629 KOps/s	$\color{#35bf28}+3.45\%$
test_seq_wrap[compile-overhead]	0.3033ms	0.2261ms	4.4224 KOps/s	4.3516 KOps/s	$\color{#35bf28}+1.63\%$
test_func_call_runtime[False-eager]	0.8208ms	0.5417ms	1.8459 KOps/s	1.7697 KOps/s	$\color{#35bf28}+4.31\%$
test_func_call_runtime[False-compile]	0.9216ms	0.4247ms	2.3544 KOps/s	2.2964 KOps/s	$\color{#35bf28}+2.52\%$
test_func_call_runtime[False-compile-overhead]	0.8214ms	0.4247ms	2.3547 KOps/s	2.2896 KOps/s	$\color{#35bf28}+2.84\%$
test_func_call_runtime[True-eager]	1.2477ms	0.7517ms	1.3303 KOps/s	1.3001 KOps/s	$\color{#35bf28}+2.33\%$
test_func_call_runtime[True-compile]	1.2212ms	0.4646ms	2.1522 KOps/s	2.1192 KOps/s	$\color{#35bf28}+1.55\%$
test_func_call_runtime[True-compile-overhead]	0.6864ms	0.4645ms	2.1527 KOps/s	2.1214 KOps/s	$\color{#35bf28}+1.48\%$
test_func_call_cm_runtime[False-eager]	0.6956ms	0.5317ms	1.8808 KOps/s	1.7806 KOps/s	$\textbf{\color{#35bf28}+5.63\%}$
test_func_call_cm_runtime[False-compile]	0.5283ms	0.4209ms	2.3761 KOps/s	2.2978 KOps/s	$\color{#35bf28}+3.41\%$
test_func_call_cm_runtime[False-compile-overhead]	0.7978ms	0.4261ms	2.3471 KOps/s	2.3298 KOps/s	$\color{#35bf28}+0.74\%$
test_func_call_cm_runtime[True-eager]	1.0484ms	0.8832ms	1.1323 KOps/s	1.1078 KOps/s	$\color{#35bf28}+2.21\%$
test_func_call_cm_runtime[True-compile]	0.8362ms	0.4911ms	2.0363 KOps/s	2.0000 KOps/s	$\color{#35bf28}+1.82\%$
test_func_call_cm_runtime[True-compile-overhead]	0.9485ms	0.4897ms	2.0420 KOps/s	2.0138 KOps/s	$\color{#35bf28}+1.40\%$
test_vmap_func_call_cm_runtime[eager]	2.7609ms	1.8813ms	531.5449 Ops/s	526.0654 Ops/s	$\color{#35bf28}+1.04\%$
test_vmap_func_call_cm_runtime[compile]	0.8243ms	0.5160ms	1.9381 KOps/s	1.9184 KOps/s	$\color{#35bf28}+1.03\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.9627ms	0.5212ms	1.9187 KOps/s	1.9126 KOps/s	$\color{#35bf28}+0.32\%$
test_distributed	0.2575ms	0.1257ms	7.9575 KOps/s	7.7277 KOps/s	$\color{#35bf28}+2.97\%$
test_tdmodule	81.3320μs	25.5773μs	39.0971 KOps/s	38.0127 KOps/s	$\color{#35bf28}+2.85\%$
test_tdmodule_dispatch	99.7460μs	46.3866μs	21.5579 KOps/s	20.4662 KOps/s	$\textbf{\color{#35bf28}+5.33\%}$
test_tdseq	48.3600μs	25.8029μs	38.7554 KOps/s	37.5081 KOps/s	$\color{#35bf28}+3.33\%$
test_tdseq_dispatch	77.5650μs	49.3124μs	20.2789 KOps/s	19.5781 KOps/s	$\color{#35bf28}+3.58\%$
test_instantiation_functorch	1.6614ms	1.5333ms	652.1987 Ops/s	627.8208 Ops/s	$\color{#35bf28}+3.88\%$
test_exec_functorch	0.4152ms	0.1769ms	5.6515 KOps/s	5.3796 KOps/s	$\textbf{\color{#35bf28}+5.05\%}$
test_exec_functional_call	0.3231ms	0.1699ms	5.8871 KOps/s	5.6533 KOps/s	$\color{#35bf28}+4.14\%$
test_exec_td_decorator	0.4668ms	0.2291ms	4.3644 KOps/s	4.2987 KOps/s	$\color{#35bf28}+1.53\%$
test_vmap_mlp_speed_decorator[True-True]	0.9737ms	0.6393ms	1.5643 KOps/s	1.5092 KOps/s	$\color{#35bf28}+3.65\%$
test_vmap_mlp_speed_decorator[True-False]	1.0259ms	0.6415ms	1.5588 KOps/s	1.4856 KOps/s	$\color{#35bf28}+4.93\%$
test_vmap_mlp_speed_decorator[False-True]	1.1841ms	0.5215ms	1.9177 KOps/s	1.8820 KOps/s	$\color{#35bf28}+1.90\%$
test_vmap_mlp_speed_decorator[False-False]	0.7074ms	0.5161ms	1.9377 KOps/s	1.8820 KOps/s	$\color{#35bf28}+2.96\%$
test_to_module_speed[True]	2.0305ms	1.2941ms	772.7099 Ops/s	772.5685 Ops/s	$\color{#35bf28}+0.02\%$
test_to_module_speed[False]	1.6892ms	1.2481ms	801.2287 Ops/s	781.5993 Ops/s	$\color{#35bf28}+2.51\%$
test_tc_init	0.1069ms	45.5815μs	21.9387 KOps/s	21.3191 KOps/s	$\color{#35bf28}+2.91\%$
test_tc_init_nested	0.1366ms	91.9269μs	10.8782 KOps/s	10.6402 KOps/s	$\color{#35bf28}+2.24\%$
test_tc_first_layer_tensor	21.7800μs	1.5180μs	658.7702 KOps/s	655.5865 KOps/s	$\color{#35bf28}+0.49\%$
test_tc_first_layer_nontensor	27.1820μs	4.6289μs	216.0335 KOps/s	216.1939 KOps/s	$\color{#d91a1a}-0.07\%$
test_tc_second_layer_tensor	18.0540μs	2.7663μs	361.4900 KOps/s	354.8956 KOps/s	$\color{#35bf28}+1.86\%$
test_tc_second_layer_nontensor	46.7870μs	5.9075μs	169.2753 KOps/s	169.7088 KOps/s	$\color{#d91a1a}-0.26\%$
test_unbind	0.2308s	12.8100ms	78.0637 Ops/s	77.8240 Ops/s	$\color{#35bf28}+0.31\%$
test_full_like	16.0881ms	11.8621ms	84.3023 Ops/s	78.8646 Ops/s	$\textbf{\color{#35bf28}+6.89\%}$
test_zeros_like	16.1665ms	7.9189ms	126.2800 Ops/s	127.3233 Ops/s	$\color{#d91a1a}-0.82\%$
test_ones_like	11.7972ms	8.0539ms	124.1637 Ops/s	127.1372 Ops/s	$\color{#d91a1a}-2.34\%$
test_clone	15.7320ms	9.7706ms	102.3474 Ops/s	103.4004 Ops/s	$\color{#d91a1a}-1.02\%$
test_squeeze	64.5610μs	12.4798μs	80.1293 KOps/s	83.8164 KOps/s	$\color{#d91a1a}-4.40\%$
test_unsqueeze	0.1882ms	91.7797μs	10.8957 KOps/s	11.1370 KOps/s	$\color{#d91a1a}-2.17\%$
test_split	0.4789ms	0.1989ms	5.0264 KOps/s	5.0757 KOps/s	$\color{#d91a1a}-0.97\%$
test_permute	0.2974ms	0.2087ms	4.7921 KOps/s	4.7766 KOps/s	$\color{#35bf28}+0.32\%$
test_stack	31.8243ms	25.4619ms	39.2744 Ops/s	38.5942 Ops/s	$\color{#35bf28}+1.76\%$
test_cat	29.1785ms	25.1535ms	39.7559 Ops/s	38.7972 Ops/s	$\color{#35bf28}+2.47\%$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}30$. Worsened: $\large\color{#d91a1a}19$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	0.1895ms	11.2900μs	88.5736 KOps/s	95.7276 KOps/s	$\textbf{\color{#d91a1a}-7.47\%}$
test_plain_set_stack_nested	0.1787ms	11.3319μs	88.2461 KOps/s	94.8101 KOps/s	$\textbf{\color{#d91a1a}-6.92\%}$
test_plain_set_nested_inplace	43.2810μs	12.3753μs	80.8064 KOps/s	88.2620 KOps/s	$\textbf{\color{#d91a1a}-8.45\%}$
test_plain_set_stack_nested_inplace	0.1977ms	12.2467μs	81.6549 KOps/s	88.0480 KOps/s	$\textbf{\color{#d91a1a}-7.26\%}$
test_items	0.1582ms	2.8542μs	350.3602 KOps/s	344.1711 KOps/s	$\color{#35bf28}+1.80\%$
test_items_nested	0.5397ms	0.3515ms	2.8452 KOps/s	2.8756 KOps/s	$\color{#d91a1a}-1.06\%$
test_items_nested_locked	0.5620ms	0.3532ms	2.8309 KOps/s	2.8595 KOps/s	$\color{#d91a1a}-1.00\%$
test_items_nested_leaf	0.1429ms	57.8291μs	17.2923 KOps/s	17.2020 KOps/s	$\color{#35bf28}+0.53\%$
test_items_stack_nested	0.4028ms	0.3540ms	2.8245 KOps/s	2.8435 KOps/s	$\color{#d91a1a}-0.67\%$
test_items_stack_nested_leaf	0.1389ms	59.2109μs	16.8888 KOps/s	16.8645 KOps/s	$\color{#35bf28}+0.14\%$
test_items_stack_nested_locked	0.4015ms	0.3533ms	2.8303 KOps/s	2.8529 KOps/s	$\color{#d91a1a}-0.79\%$
test_keys	31.1700μs	3.4372μs	290.9335 KOps/s	289.2130 KOps/s	$\color{#35bf28}+0.59\%$
test_keys_nested	0.2187ms	71.6956μs	13.9479 KOps/s	14.2297 KOps/s	$\color{#d91a1a}-1.98\%$
test_keys_nested_locked	0.8339ms	75.6405μs	13.2204 KOps/s	13.1823 KOps/s	$\color{#35bf28}+0.29\%$
test_keys_nested_leaf	92.9020μs	61.2760μs	16.3196 KOps/s	16.2559 KOps/s	$\color{#35bf28}+0.39\%$
test_keys_stack_nested	0.1067ms	70.8402μs	14.1163 KOps/s	14.0098 KOps/s	$\color{#35bf28}+0.76\%$
test_keys_stack_nested_leaf	0.1459ms	61.4979μs	16.2607 KOps/s	16.0471 KOps/s	$\color{#35bf28}+1.33\%$
test_keys_stack_nested_locked	0.1168ms	76.6270μs	13.0502 KOps/s	12.9784 KOps/s	$\color{#35bf28}+0.55\%$
test_values	6.8218μs	0.8425μs	1.1869 MOps/s	1.1659 MOps/s	$\color{#35bf28}+1.81\%$
test_values_nested	64.3010μs	31.2412μs	32.0090 KOps/s	32.0677 KOps/s	$\color{#d91a1a}-0.18\%$
test_values_nested_locked	67.2610μs	32.8718μs	30.4212 KOps/s	30.7484 KOps/s	$\color{#d91a1a}-1.06\%$
test_values_nested_leaf	65.5410μs	33.9948μs	29.4163 KOps/s	29.8804 KOps/s	$\color{#d91a1a}-1.55\%$
test_values_stack_nested	0.1534ms	31.8650μs	31.3824 KOps/s	31.4055 KOps/s	$\color{#d91a1a}-0.07\%$
test_values_stack_nested_leaf	90.5820μs	34.2539μs	29.1937 KOps/s	29.2088 KOps/s	$\color{#d91a1a}-0.05\%$
test_values_stack_nested_locked	0.2261ms	33.3729μs	29.9644 KOps/s	29.9308 KOps/s	$\color{#35bf28}+0.11\%$
test_membership	9.9231μs	0.5151μs	1.9412 MOps/s	1.9561 MOps/s	$\color{#d91a1a}-0.76\%$
test_membership_nested	32.8255μs	1.9714μs	507.2532 KOps/s	467.3980 KOps/s	$\textbf{\color{#35bf28}+8.53\%}$
test_membership_nested_leaf	14.6755μs	2.0092μs	497.7179 KOps/s	484.8599 KOps/s	$\color{#35bf28}+2.65\%$
test_membership_stacked_nested	30.9000μs	2.0503μs	487.7447 KOps/s	462.4525 KOps/s	$\textbf{\color{#35bf28}+5.47\%}$
test_membership_stacked_nested_leaf	24.3210μs	2.0256μs	493.6867 KOps/s	461.3329 KOps/s	$\textbf{\color{#35bf28}+7.01\%}$
test_membership_nested_last	29.0100μs	2.9152μs	343.0329 KOps/s	329.3776 KOps/s	$\color{#35bf28}+4.15\%$
test_membership_nested_leaf_last	37.7400μs	2.9330μs	340.9422 KOps/s	327.4491 KOps/s	$\color{#35bf28}+4.12\%$
test_membership_stacked_nested_last	35.7210μs	3.3167μs	301.5074 KOps/s	326.0011 KOps/s	$\textbf{\color{#d91a1a}-7.51\%}$
test_membership_stacked_nested_leaf_last	33.5310μs	3.2935μs	303.6311 KOps/s	331.3821 KOps/s	$\textbf{\color{#d91a1a}-8.37\%}$
test_nested_getleaf	34.7710μs	6.1203μs	163.3916 KOps/s	161.1386 KOps/s	$\color{#35bf28}+1.40\%$
test_nested_get	47.3610μs	5.7963μs	172.5250 KOps/s	169.8428 KOps/s	$\color{#35bf28}+1.58\%$
test_stacked_getleaf	36.6310μs	6.0581μs	165.0674 KOps/s	162.8708 KOps/s	$\color{#35bf28}+1.35\%$
test_stacked_get	27.9510μs	5.7840μs	172.8917 KOps/s	171.9088 KOps/s	$\color{#35bf28}+0.57\%$
test_nested_getitemleaf	29.1600μs	6.1940μs	161.4457 KOps/s	159.2827 KOps/s	$\color{#35bf28}+1.36\%$
test_nested_getitem	24.6900μs	5.8969μs	169.5813 KOps/s	167.6815 KOps/s	$\color{#35bf28}+1.13\%$
test_stacked_getitemleaf	62.9310μs	6.1777μs	161.8719 KOps/s	158.7577 KOps/s	$\color{#35bf28}+1.96\%$
test_stacked_getitem	33.5210μs	5.8689μs	170.3899 KOps/s	169.0698 KOps/s	$\color{#35bf28}+0.78\%$
test_lock_nested	0.7555ms	0.3619ms	2.7631 KOps/s	2.6742 KOps/s	$\color{#35bf28}+3.32\%$
test_lock_stack_nested	0.3838ms	0.3338ms	2.9959 KOps/s	2.9673 KOps/s	$\color{#35bf28}+0.96\%$
test_unlock_nested	0.6810ms	0.3039ms	3.2906 KOps/s	3.2855 KOps/s	$\color{#35bf28}+0.15\%$
test_unlock_stack_nested	0.4470ms	0.2740ms	3.6492 KOps/s	3.6202 KOps/s	$\color{#35bf28}+0.80\%$
test_flatten_speed	0.1127ms	74.4340μs	13.4347 KOps/s	13.4829 KOps/s	$\color{#d91a1a}-0.36\%$
test_unflatten_speed	0.3339ms	0.3019ms	3.3120 KOps/s	3.2384 KOps/s	$\color{#35bf28}+2.27\%$
test_common_ops	1.6366ms	0.6096ms	1.6404 KOps/s	1.7006 KOps/s	$\color{#d91a1a}-3.54\%$
test_creation	0.1050ms	1.4267μs	700.9222 KOps/s	674.7110 KOps/s	$\color{#35bf28}+3.88\%$
test_creation_empty	37.6910μs	8.8955μs	112.4166 KOps/s	142.1158 KOps/s	$\textbf{\color{#d91a1a}-20.90\%}$
test_creation_nested_1	34.1200μs	10.3643μs	96.4849 KOps/s	117.6515 KOps/s	$\textbf{\color{#d91a1a}-17.99\%}$
test_creation_nested_2	36.3200μs	12.8931μs	77.5610 KOps/s	90.8306 KOps/s	$\textbf{\color{#d91a1a}-14.61\%}$
test_clone	1.9944ms	10.4888μs	95.3394 KOps/s	89.0996 KOps/s	$\textbf{\color{#35bf28}+7.00\%}$
test_getitem[int]	1.2893ms	10.3598μs	96.5269 KOps/s	91.8507 KOps/s	$\textbf{\color{#35bf28}+5.09\%}$
test_getitem[slice_int]	0.1394ms	20.2721μs	49.3290 KOps/s	46.4053 KOps/s	$\textbf{\color{#35bf28}+6.30\%}$
test_getitem[range]	0.1816ms	37.5523μs	26.6295 KOps/s	26.5948 KOps/s	$\color{#35bf28}+0.13\%$
test_getitem[tuple]	0.1031ms	17.6557μs	56.6389 KOps/s	53.7456 KOps/s	$\textbf{\color{#35bf28}+5.38\%}$
test_getitem[list]	0.2390ms	32.2427μs	31.0148 KOps/s	30.2998 KOps/s	$\color{#35bf28}+2.36\%$
test_setitem_dim[int]	38.6910μs	18.4655μs	54.1551 KOps/s	52.2457 KOps/s	$\color{#35bf28}+3.65\%$
test_setitem_dim[slice_int]	0.1389ms	37.2150μs	26.8709 KOps/s	25.8580 KOps/s	$\color{#35bf28}+3.92\%$
test_setitem_dim[range]	0.1081ms	52.9973μs	18.8689 KOps/s	18.7873 KOps/s	$\color{#35bf28}+0.43\%$
test_setitem_dim[tuple]	0.1334ms	31.6733μs	31.5723 KOps/s	30.6378 KOps/s	$\color{#35bf28}+3.05\%$
test_setitem	99.9020μs	14.9715μs	66.7937 KOps/s	65.1240 KOps/s	$\color{#35bf28}+2.56\%$
test_set	84.8210μs	14.6228μs	68.3862 KOps/s	67.2419 KOps/s	$\color{#35bf28}+1.70\%$
test_set_shared	1.6763ms	0.1467ms	6.8155 KOps/s	6.7585 KOps/s	$\color{#35bf28}+0.84\%$
test_update	1.0419ms	17.9018μs	55.8602 KOps/s	58.2953 KOps/s	$\color{#d91a1a}-4.18\%$
test_update_nested	0.1005ms	23.2828μs	42.9502 KOps/s	44.6779 KOps/s	$\color{#d91a1a}-3.87\%$
test_update__nested	0.1398ms	23.9757μs	41.7089 KOps/s	40.4493 KOps/s	$\color{#35bf28}+3.11\%$
test_set_nested	0.1013ms	16.1898μs	61.7673 KOps/s	62.2926 KOps/s	$\color{#d91a1a}-0.84\%$
test_set_nested_new	90.2220μs	18.2610μs	54.7614 KOps/s	53.8232 KOps/s	$\color{#35bf28}+1.74\%$
test_select	0.1499ms	30.5054μs	32.7811 KOps/s	32.4727 KOps/s	$\color{#35bf28}+0.95\%$
test_select_nested	0.1871ms	41.5376μs	24.0746 KOps/s	23.8102 KOps/s	$\color{#35bf28}+1.11\%$
test_exclude_nested	0.1642ms	60.7684μs	16.4559 KOps/s	16.0994 KOps/s	$\color{#35bf28}+2.21\%$
test_empty[True]	0.3745ms	0.2711ms	3.6884 KOps/s	3.6421 KOps/s	$\color{#35bf28}+1.27\%$
test_empty[False]	2.9300μs	0.7354μs	1.3597 MOps/s	1.3536 MOps/s	$\color{#35bf28}+0.46\%$
test_to	94.9010μs	55.8181μs	17.9153 KOps/s	17.5624 KOps/s	$\color{#35bf28}+2.01\%$
test_to_nonblocking	0.1933ms	45.4285μs	22.0126 KOps/s	20.8826 KOps/s	$\textbf{\color{#35bf28}+5.41\%}$
test_unbind_speed	1.7304ms	0.2288ms	4.3712 KOps/s	4.3307 KOps/s	$\color{#35bf28}+0.94\%$
test_unbind_speed_stack0	0.3086ms	0.2292ms	4.3634 KOps/s	4.3563 KOps/s	$\color{#35bf28}+0.16\%$
test_unbind_speed_stack1	93.6656ms	0.6413ms	1.5594 KOps/s	1.5621 KOps/s	$\color{#d91a1a}-0.17\%$
test_split	93.6531ms	1.5523ms	644.1928 Ops/s	569.2642 Ops/s	$\textbf{\color{#35bf28}+13.16\%}$
test_chunk	95.8361ms	1.6949ms	589.9934 Ops/s	679.2126 Ops/s	$\textbf{\color{#d91a1a}-13.14\%}$
test_consolidate[False-None]	2.7326ms	2.6142ms	382.5218 Ops/s	351.2761 Ops/s	$\textbf{\color{#35bf28}+8.89\%}$
test_consolidate[default-None]	1.8081ms	1.6382ms	610.4227 Ops/s	586.9493 Ops/s	$\color{#35bf28}+4.00\%$
test_consolidate[reduce-overhead-None]	2.0347ms	1.7524ms	570.6462 Ops/s	574.1384 Ops/s	$\color{#d91a1a}-0.61\%$
test_consolidate_njt[False-None]	6.8527ms	6.5893ms	151.7614 Ops/s	152.5511 Ops/s	$\color{#d91a1a}-0.52\%$
test_to[False-False-None]	1.9421ms	1.6633ms	601.2229 Ops/s	587.9804 Ops/s	$\color{#35bf28}+2.25\%$
test_to[True-False-None]	1.4958ms	1.2604ms	793.3739 Ops/s	762.7244 Ops/s	$\color{#35bf28}+4.02\%$
test_to[within-False-None]	4.2461ms	3.9870ms	250.8153 Ops/s	245.7898 Ops/s	$\color{#35bf28}+2.04\%$
test_to[True-default-None]	5.5826ms	5.2027ms	192.2090 Ops/s	194.9959 Ops/s	$\color{#d91a1a}-1.43\%$
test_to_njt[False-False-None]	7.6171ms	7.1929ms	139.0254 Ops/s	142.5446 Ops/s	$\color{#d91a1a}-2.47\%$
test_to_njt[True-False-None]	6.0042ms	5.6136ms	178.1376 Ops/s	177.2072 Ops/s	$\color{#35bf28}+0.53\%$
test_to_njt[within-False-None]	12.8793ms	12.0844ms	82.7513 Ops/s	80.8741 Ops/s	$\color{#35bf28}+2.32\%$
test_creation[device0]	0.4653ms	81.9980μs	12.1954 KOps/s	12.4973 KOps/s	$\color{#d91a1a}-2.42\%$
test_creation_from_tensor	0.5115ms	85.9170μs	11.6391 KOps/s	12.0456 KOps/s	$\color{#d91a1a}-3.37\%$
test_add_one[memmap_tensor0]	0.4040ms	6.8615μs	145.7406 KOps/s	143.5782 KOps/s	$\color{#35bf28}+1.51\%$
test_contiguous[memmap_tensor0]	2.0645μs	0.4041μs	2.4744 MOps/s	2.4349 MOps/s	$\color{#35bf28}+1.62\%$
test_stack[memmap_tensor0]	0.1536ms	4.3404μs	230.3962 KOps/s	212.9352 KOps/s	$\textbf{\color{#35bf28}+8.20\%}$
test_memmaptd_index	0.5663ms	0.2498ms	4.0033 KOps/s	3.9751 KOps/s	$\color{#35bf28}+0.71\%$
test_memmaptd_index_astensor	0.5912ms	0.3078ms	3.2484 KOps/s	3.2371 KOps/s	$\color{#35bf28}+0.35\%$
test_memmaptd_index_op	1.0501ms	0.6025ms	1.6598 KOps/s	1.7379 KOps/s	$\color{#d91a1a}-4.49\%$
test_serialize_model	0.4174s	0.1715s	5.8320 Ops/s	7.6576 Ops/s	$\textbf{\color{#d91a1a}-23.84\%}$
test_serialize_model_pickle	1.3470s	1.1861s	0.8431 Ops/s	0.8232 Ops/s	$\color{#35bf28}+2.42\%$
test_serialize_weights	0.1329s	0.1306s	7.6561 Ops/s	7.6813 Ops/s	$\color{#d91a1a}-0.33\%$
test_serialize_weights_returnearly	0.3209s	53.6413ms	18.6424 Ops/s	15.0136 Ops/s	$\textbf{\color{#35bf28}+24.17\%}$
test_serialize_weights_pickle	1.3803s	1.1907s	0.8399 Ops/s	0.8230 Ops/s	$\color{#35bf28}+2.05\%$
test_reshape_pytree	0.1671ms	22.2048μs	45.0353 KOps/s	43.7238 KOps/s	$\color{#35bf28}+3.00\%$
test_reshape_td	60.4610μs	26.6004μs	37.5934 KOps/s	36.6522 KOps/s	$\color{#35bf28}+2.57\%$
test_view_pytree	0.1545ms	22.2542μs	44.9353 KOps/s	43.4452 KOps/s	$\color{#35bf28}+3.43\%$
test_view_td	0.2294ms	31.6002μs	31.6454 KOps/s	31.1606 KOps/s	$\color{#35bf28}+1.56\%$
test_unbind_pytree	0.2057ms	27.8035μs	35.9667 KOps/s	34.9500 KOps/s	$\color{#35bf28}+2.91\%$
test_unbind_td	0.7709ms	35.3700μs	28.2725 KOps/s	27.8764 KOps/s	$\color{#35bf28}+1.42\%$
test_split_pytree	0.2212ms	29.4286μs	33.9805 KOps/s	32.7070 KOps/s	$\color{#35bf28}+3.89\%$
test_split_td	0.9713ms	37.5597μs	26.6243 KOps/s	24.6203 KOps/s	$\textbf{\color{#35bf28}+8.14\%}$
test_add_pytree	0.1534ms	34.2374μs	29.2078 KOps/s	27.1789 KOps/s	$\textbf{\color{#35bf28}+7.47\%}$
test_add_td	0.1938ms	48.1822μs	20.7546 KOps/s	19.6228 KOps/s	$\textbf{\color{#35bf28}+5.77\%}$
test_compile_add_one_nested[tensordict-compile]	0.2976ms	0.1230ms	8.1294 KOps/s	7.8856 KOps/s	$\color{#35bf28}+3.09\%$
test_compile_add_one_nested[tensordict-eager]	0.2949ms	0.1254ms	7.9713 KOps/s	7.8203 KOps/s	$\color{#35bf28}+1.93\%$
test_compile_add_one_nested[pytree-compile]	0.2509ms	96.6197μs	10.3499 KOps/s	10.0982 KOps/s	$\color{#35bf28}+2.49\%$
test_compile_add_one_nested[pytree-eager]	3.0755ms	0.1482ms	6.7477 KOps/s	6.4798 KOps/s	$\color{#35bf28}+4.13\%$
test_compile_copy_nested[tensordict-compile]	0.2183ms	31.3836μs	31.8638 KOps/s	42.0391 KOps/s	$\textbf{\color{#d91a1a}-24.20\%}$
test_compile_copy_nested[tensordict-eager]	0.1472ms	26.0198μs	38.4323 KOps/s	36.9704 KOps/s	$\color{#35bf28}+3.95\%$
test_compile_copy_nested[pytree-compile]	0.2934ms	62.2955μs	16.0525 KOps/s	15.2257 KOps/s	$\textbf{\color{#35bf28}+5.43\%}$
test_compile_copy_nested[pytree-eager]	0.1641ms	48.9565μs	20.4263 KOps/s	20.1402 KOps/s	$\color{#35bf28}+1.42\%$
test_compile_add_one_flat[tensordict-compile]	0.2820ms	0.1447ms	6.9109 KOps/s	6.9930 KOps/s	$\color{#d91a1a}-1.17\%$
test_compile_add_one_flat[tensordict-eager]	0.3618ms	0.2068ms	4.8366 KOps/s	4.8044 KOps/s	$\color{#35bf28}+0.67\%$
test_compile_add_one_flat[tensorclass-compile]	0.2647ms	0.1015ms	9.8558 KOps/s	9.3707 KOps/s	$\textbf{\color{#35bf28}+5.18\%}$
test_compile_add_one_flat[tensorclass-eager]	0.2293ms	53.9267μs	18.5437 KOps/s	17.7689 KOps/s	$\color{#35bf28}+4.36\%$
test_compile_add_one_flat[pytree-compile]	0.3199ms	0.1442ms	6.9326 KOps/s	6.8386 KOps/s	$\color{#35bf28}+1.38\%$
test_compile_add_one_flat[pytree-eager]	0.6716ms	0.4785ms	2.0899 KOps/s	1.9644 KOps/s	$\textbf{\color{#35bf28}+6.39\%}$
test_compile_add_self_flat[tensordict-eager]	0.3923ms	0.2460ms	4.0644 KOps/s	3.9361 KOps/s	$\color{#35bf28}+3.26\%$
test_compile_add_self_flat[tensordict-compile]	0.3295ms	0.1466ms	6.8190 KOps/s	6.5189 KOps/s	$\color{#35bf28}+4.60\%$
test_compile_add_self_flat[tensorclass-eager]	0.2170ms	62.0808μs	16.1080 KOps/s	15.6240 KOps/s	$\color{#35bf28}+3.10\%$
test_compile_add_self_flat[tensorclass-compile]	0.3091ms	0.1009ms	9.9095 KOps/s	9.4271 KOps/s	$\textbf{\color{#35bf28}+5.12\%}$
test_compile_add_self_flat[pytree-eager]	0.5666ms	0.4042ms	2.4743 KOps/s	2.3637 KOps/s	$\color{#35bf28}+4.68\%$
test_compile_add_self_flat[pytree-compile]	0.2715ms	0.1388ms	7.2039 KOps/s	6.8300 KOps/s	$\textbf{\color{#35bf28}+5.47\%}$
test_compile_copy_flat[tensordict-compile]	0.1628ms	19.9565μs	50.1091 KOps/s	51.1607 KOps/s	$\color{#d91a1a}-2.06\%$
test_compile_copy_flat[tensordict-eager]	0.1150ms	26.4322μs	37.8327 KOps/s	37.4781 KOps/s	$\color{#35bf28}+0.95\%$
test_compile_copy_flat[pytree-compile]	0.1713ms	70.1567μs	14.2538 KOps/s	14.2464 KOps/s	$\color{#35bf28}+0.05\%$
test_compile_copy_flat[pytree-eager]	95.8520μs	51.1718μs	19.5420 KOps/s	19.3172 KOps/s	$\color{#35bf28}+1.16\%$
test_compile_assign_and_add[tensordict-compile]	1.6322ms	0.3931ms	2.5442 KOps/s	2.2348 KOps/s	$\textbf{\color{#35bf28}+13.85\%}$
test_compile_assign_and_add[tensordict-eager]	2.9310ms	2.5504ms	392.0894 Ops/s	375.5018 Ops/s	$\color{#35bf28}+4.42\%$
test_compile_assign_and_add[pytree-compile]	1.5763ms	0.4301ms	2.3250 KOps/s	2.2850 KOps/s	$\color{#35bf28}+1.75\%$
test_compile_assign_and_add[pytree-eager]	2.8723ms	2.5939ms	385.5186 Ops/s	372.5845 Ops/s	$\color{#35bf28}+3.47\%$
test_compile_indexing[tensor-tensordict-compile]	0.5940ms	0.1138ms	8.7881 KOps/s	8.8650 KOps/s	$\color{#d91a1a}-0.87\%$
test_compile_indexing[tensor-tensordict-eager]	0.5823ms	83.1121μs	12.0319 KOps/s	12.5096 KOps/s	$\color{#d91a1a}-3.82\%$
test_compile_indexing[tensor-tensorclass-compile]	0.2908ms	0.1112ms	8.9955 KOps/s	9.5300 KOps/s	$\textbf{\color{#d91a1a}-5.61\%}$
test_compile_indexing[tensor-tensorclass-eager]	0.2554ms	69.2635μs	14.4376 KOps/s	14.7773 KOps/s	$\color{#d91a1a}-2.30\%$
test_compile_indexing[tensor-pytree-compile]	0.2979ms	0.1116ms	8.9598 KOps/s	9.4155 KOps/s	$\color{#d91a1a}-4.84\%$
test_compile_indexing[tensor-pytree-eager]	0.2209ms	67.2402μs	14.8721 KOps/s	14.7720 KOps/s	$\color{#35bf28}+0.68\%$
test_compile_indexing[slice-tensordict-compile]	0.2937ms	0.1019ms	9.8167 KOps/s	9.9047 KOps/s	$\color{#d91a1a}-0.89\%$
test_compile_indexing[slice-tensordict-eager]	0.1835ms	16.8026μs	59.5144 KOps/s	55.0634 KOps/s	$\textbf{\color{#35bf28}+8.08\%}$
test_compile_indexing[slice-tensorclass-compile]	0.2544ms	96.6518μs	10.3464 KOps/s	10.2542 KOps/s	$\color{#35bf28}+0.90\%$
test_compile_indexing[slice-tensorclass-eager]	99.3810μs	15.6778μs	63.7843 KOps/s	62.0289 KOps/s	$\color{#35bf28}+2.83\%$
test_compile_indexing[slice-pytree-compile]	0.2518ms	96.6253μs	10.3493 KOps/s	10.2301 KOps/s	$\color{#35bf28}+1.16\%$
test_compile_indexing[slice-pytree-eager]	0.1546ms	15.6794μs	63.7780 KOps/s	62.2519 KOps/s	$\color{#35bf28}+2.45\%$
test_compile_indexing[int-tensordict-compile]	0.3170ms	0.1059ms	9.4445 KOps/s	9.7780 KOps/s	$\color{#d91a1a}-3.41\%$
test_compile_indexing[int-tensordict-eager]	0.6163ms	16.5954μs	60.2576 KOps/s	55.5919 KOps/s	$\textbf{\color{#35bf28}+8.39\%}$
test_compile_indexing[int-tensorclass-compile]	0.2865ms	98.8945μs	10.1118 KOps/s	10.1663 KOps/s	$\color{#d91a1a}-0.54\%$
test_compile_indexing[int-tensorclass-eager]	0.1902ms	15.7368μs	63.5453 KOps/s	63.4350 KOps/s	$\color{#35bf28}+0.17\%$
test_compile_indexing[int-pytree-compile]	0.2975ms	96.8797μs	10.3221 KOps/s	10.2243 KOps/s	$\color{#35bf28}+0.96\%$
test_compile_indexing[int-pytree-eager]	0.2170ms	15.6446μs	63.9199 KOps/s	62.8533 KOps/s	$\color{#35bf28}+1.70\%$
test_mod_add[eager]	0.2055ms	37.7189μs	26.5119 KOps/s	26.8068 KOps/s	$\color{#d91a1a}-1.10\%$
test_mod_add[compile]	0.3248ms	82.7195μs	12.0890 KOps/s	12.1836 KOps/s	$\color{#d91a1a}-0.78\%$
test_mod_add[compile-overhead]	0.3361ms	0.1753ms	5.7058 KOps/s	5.6614 KOps/s	$\color{#35bf28}+0.78\%$
test_mod_wrap[eager]	0.4327ms	0.2498ms	4.0026 KOps/s	3.9508 KOps/s	$\color{#35bf28}+1.31\%$
test_mod_wrap[compile]	0.4283ms	0.2826ms	3.5383 KOps/s	3.4445 KOps/s	$\color{#35bf28}+2.72\%$
test_mod_wrap[compile-overhead]	7.4812ms	3.7467ms	266.9047 Ops/s	265.5282 Ops/s	$\color{#35bf28}+0.52\%$
test_mod_wrap_and_backward[eager]	1.6514ms	1.3670ms	731.5147 Ops/s	682.5495 Ops/s	$\textbf{\color{#35bf28}+7.17\%}$
test_mod_wrap_and_backward[compile]	1.5832ms	1.2739ms	785.0169 Ops/s	717.9488 Ops/s	$\textbf{\color{#35bf28}+9.34\%}$
test_mod_wrap_and_backward[compile-overhead]	1.3633ms	0.9140ms	1.0941 KOps/s	892.3581 Ops/s	$\textbf{\color{#35bf28}+22.61\%}$
test_seq_add[eager]	0.2654ms	0.1130ms	8.8504 KOps/s	8.7639 KOps/s	$\color{#35bf28}+0.99\%$
test_seq_add[compile]	0.3881ms	89.5084μs	11.1721 KOps/s	11.0925 KOps/s	$\color{#35bf28}+0.72\%$
test_seq_add[compile-overhead]	0.2756ms	0.1294ms	7.7278 KOps/s	7.7141 KOps/s	$\color{#35bf28}+0.18\%$
test_seq_wrap[eager]	0.5948ms	0.4144ms	2.4130 KOps/s	2.3946 KOps/s	$\color{#35bf28}+0.77\%$
test_seq_wrap[compile]	0.4641ms	0.3021ms	3.3100 KOps/s	3.3154 KOps/s	$\color{#d91a1a}-0.16\%$
test_seq_wrap[compile-overhead]	0.3682ms	0.2229ms	4.4858 KOps/s	4.4141 KOps/s	$\color{#35bf28}+1.62\%$
test_func_call_runtime[False-eager]	0.9236ms	0.7447ms	1.3428 KOps/s	1.2294 KOps/s	$\textbf{\color{#35bf28}+9.23\%}$
test_func_call_runtime[False-compile]	1.3959ms	0.7454ms	1.3415 KOps/s	1.3355 KOps/s	$\color{#35bf28}+0.45\%$
test_func_call_runtime[False-compile-overhead]	0.5827ms	0.3586ms	2.7887 KOps/s	2.7749 KOps/s	$\color{#35bf28}+0.50\%$
test_func_call_runtime[True-eager]	1.0548ms	0.8963ms	1.1157 KOps/s	1.0915 KOps/s	$\color{#35bf28}+2.21\%$
test_func_call_runtime[True-compile]	0.9637ms	0.7667ms	1.3042 KOps/s	1.2954 KOps/s	$\color{#35bf28}+0.68\%$
test_func_call_runtime[True-compile-overhead]	0.5285ms	0.3816ms	2.6206 KOps/s	2.6155 KOps/s	$\color{#35bf28}+0.20\%$
test_func_call_cm_runtime[False-eager]	0.8853ms	0.7298ms	1.3703 KOps/s	1.3279 KOps/s	$\color{#35bf28}+3.20\%$
test_func_call_cm_runtime[False-compile]	0.9073ms	0.7513ms	1.3310 KOps/s	1.2889 KOps/s	$\color{#35bf28}+3.27\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4929ms	0.3607ms	2.7723 KOps/s	2.7559 KOps/s	$\color{#35bf28}+0.59\%$
test_func_call_cm_runtime[True-eager]	1.1493ms	0.9973ms	1.0027 KOps/s	976.7860 Ops/s	$\color{#35bf28}+2.66\%$
test_func_call_cm_runtime[True-compile]	0.9776ms	0.8013ms	1.2480 KOps/s	1.2423 KOps/s	$\color{#35bf28}+0.46\%$
test_func_call_cm_runtime[True-compile-overhead]	0.5955ms	0.4093ms	2.4434 KOps/s	2.4388 KOps/s	$\color{#35bf28}+0.19\%$
test_vmap_func_call_cm_runtime[eager]	2.5695ms	2.0783ms	481.1666 Ops/s	474.4585 Ops/s	$\color{#35bf28}+1.41\%$
test_vmap_func_call_cm_runtime[compile]	0.9923ms	0.8060ms	1.2406 KOps/s	1.2111 KOps/s	$\color{#35bf28}+2.43\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.5636ms	0.4105ms	2.4360 KOps/s	2.4179 KOps/s	$\color{#35bf28}+0.75\%$
test_distributed	0.8308ms	0.1198ms	8.3485 KOps/s	8.7078 KOps/s	$\color{#d91a1a}-4.13\%$
test_tdmodule	28.7110μs	19.2473μs	51.9554 KOps/s	52.3165 KOps/s	$\color{#d91a1a}-0.69\%$
test_tdmodule_dispatch	0.1670ms	35.2521μs	28.3671 KOps/s	29.9030 KOps/s	$\textbf{\color{#d91a1a}-5.14\%}$
test_tdseq	60.2310μs	19.2789μs	51.8701 KOps/s	54.3231 KOps/s	$\color{#d91a1a}-4.52\%$
test_tdseq_dispatch	57.1510μs	37.0131μs	27.0175 KOps/s	28.4437 KOps/s	$\textbf{\color{#d91a1a}-5.01\%}$
test_instantiation_functorch	1.6845ms	1.5507ms	644.8763 Ops/s	636.3122 Ops/s	$\color{#35bf28}+1.35\%$
test_exec_functorch	0.2226ms	0.1410ms	7.0925 KOps/s	6.7508 KOps/s	$\textbf{\color{#35bf28}+5.06\%}$
test_exec_functional_call	0.2555ms	0.1351ms	7.4016 KOps/s	7.1127 KOps/s	$\color{#35bf28}+4.06\%$
test_exec_td_decorator	0.3685ms	0.1818ms	5.5020 KOps/s	5.3060 KOps/s	$\color{#35bf28}+3.69\%$
test_vmap_mlp_speed_decorator[True-True]	0.8862ms	0.6889ms	1.4517 KOps/s	1.4476 KOps/s	$\color{#35bf28}+0.28\%$
test_vmap_mlp_speed_decorator[True-False]	0.8712ms	0.6800ms	1.4706 KOps/s	1.4087 KOps/s	$\color{#35bf28}+4.40\%$
test_vmap_mlp_speed_decorator[False-True]	0.8242ms	0.5876ms	1.7018 KOps/s	1.6528 KOps/s	$\color{#35bf28}+2.97\%$
test_vmap_mlp_speed_decorator[False-False]	0.8051ms	0.5902ms	1.6943 KOps/s	1.6517 KOps/s	$\color{#35bf28}+2.58\%$
test_vmap_transformer_speed_decorator[True-True]	19.2902ms	19.0103ms	52.6030 Ops/s	51.6152 Ops/s	$\color{#35bf28}+1.91\%$
test_vmap_transformer_speed_decorator[True-False]	19.3910ms	19.0725ms	52.4316 Ops/s	51.6196 Ops/s	$\color{#35bf28}+1.57\%$
test_vmap_transformer_speed_decorator[False-True]	19.2631ms	18.9314ms	52.8223 Ops/s	52.1573 Ops/s	$\color{#35bf28}+1.28\%$
test_vmap_transformer_speed_decorator[False-False]	19.1557ms	18.8994ms	52.9116 Ops/s	51.8050 Ops/s	$\color{#35bf28}+2.14\%$
test_to_module_speed[True]	1.0755ms	0.9400ms	1.0638 KOps/s	1.0493 KOps/s	$\color{#35bf28}+1.39\%$
test_to_module_speed[False]	1.3804ms	0.9273ms	1.0784 KOps/s	1.0725 KOps/s	$\color{#35bf28}+0.55\%$
test_tc_init	75.5620μs	35.2611μs	28.3599 KOps/s	28.1904 KOps/s	$\color{#35bf28}+0.60\%$
test_tc_init_nested	0.1076ms	74.8230μs	13.3649 KOps/s	13.5736 KOps/s	$\color{#d91a1a}-1.54\%$
test_tc_first_layer_tensor	6.2350μs	0.7796μs	1.2826 MOps/s	1.4250 MOps/s	$\textbf{\color{#d91a1a}-9.99\%}$
test_tc_first_layer_nontensor	27.0300μs	2.3204μs	430.9581 KOps/s	433.2853 KOps/s	$\color{#d91a1a}-0.54\%$
test_tc_second_layer_tensor	10.3367μs	1.4951μs	668.8503 KOps/s	707.8226 KOps/s	$\textbf{\color{#d91a1a}-5.51\%}$
test_tc_second_layer_nontensor	29.0600μs	3.0608μs	326.7072 KOps/s	328.0698 KOps/s	$\color{#d91a1a}-0.42\%$
test_unbind	0.2210s	9.8330ms	101.6986 Ops/s	150.8023 Ops/s	$\textbf{\color{#d91a1a}-32.56\%}$
test_full_like	10.1299ms	9.1981ms	108.7179 Ops/s	108.9718 Ops/s	$\color{#d91a1a}-0.23\%$
test_zeros_like	9.4550ms	7.2739ms	137.4771 Ops/s	114.4071 Ops/s	$\textbf{\color{#35bf28}+20.16\%}$
test_ones_like	4.8546ms	4.3371ms	230.5697 Ops/s	230.0998 Ops/s	$\color{#35bf28}+0.20\%$
test_clone	11.5878ms	9.1488ms	109.3034 Ops/s	156.2292 Ops/s	$\textbf{\color{#d91a1a}-30.04\%}$
test_squeeze	56.7310μs	9.1634μs	109.1304 KOps/s	109.4073 KOps/s	$\color{#d91a1a}-0.25\%$
test_unsqueeze	0.2222ms	72.0884μs	13.8719 KOps/s	13.8533 KOps/s	$\color{#35bf28}+0.13\%$
test_split	0.3820ms	0.1566ms	6.3841 KOps/s	5.9241 KOps/s	$\textbf{\color{#35bf28}+7.76\%}$
test_permute	0.3627ms	0.1777ms	5.6285 KOps/s	5.4831 KOps/s	$\color{#35bf28}+2.65\%$
test_stack	51.0922ms	50.7275ms	19.7132 Ops/s	19.5386 Ops/s	$\color{#35bf28}+0.89\%$
test_cat	51.0531ms	50.5895ms	19.7670 Ops/s	19.6117 Ops/s	$\color{#35bf28}+0.79\%$