[CI] Fix GLIBCXX_3.4.29 error

[vmoens]

cc @TroyGarden

This is a proble we had for the cpu py3.12 and py3.13 wheels (the glibcxx lib was too old) across tensordict and torchrec, upgrading in post-script solved it
cc @atalman @huydhn

EDIT
the error persists on pytorch 2.6.0 stable (here the wheels were built with 2.7 nightly)

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}10$. Worsened: $\large\color{#d91a1a}12$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	49.2820μs	20.7333μs	48.2317 KOps/s	48.7478 KOps/s	$\color{#d91a1a}-1.06\%$
test_plain_set_stack_nested	56.2550μs	20.9379μs	47.7602 KOps/s	48.3166 KOps/s	$\color{#d91a1a}-1.15\%$
test_plain_set_nested_inplace	58.7300μs	22.6388μs	44.1720 KOps/s	44.2580 KOps/s	$\color{#d91a1a}-0.19\%$
test_plain_set_stack_nested_inplace	58.6000μs	22.3419μs	44.7590 KOps/s	44.5123 KOps/s	$\color{#35bf28}+0.55\%$
test_items	22.1210μs	4.1609μs	240.3302 KOps/s	235.8005 KOps/s	$\color{#35bf28}+1.92\%$
test_items_nested	0.5422ms	0.4032ms	2.4805 KOps/s	2.4675 KOps/s	$\color{#35bf28}+0.52\%$
test_items_nested_locked	0.6882ms	0.4040ms	2.4755 KOps/s	2.4613 KOps/s	$\color{#35bf28}+0.57\%$
test_items_nested_leaf	0.1486ms	76.7801μs	13.0242 KOps/s	12.9783 KOps/s	$\color{#35bf28}+0.35\%$
test_items_stack_nested	0.8417ms	0.4071ms	2.4564 KOps/s	2.4497 KOps/s	$\color{#35bf28}+0.27\%$
test_items_stack_nested_leaf	0.1577ms	79.2677μs	12.6155 KOps/s	12.6196 KOps/s	$\color{#d91a1a}-0.03\%$
test_items_stack_nested_locked	0.4901ms	0.4050ms	2.4694 KOps/s	2.4524 KOps/s	$\color{#35bf28}+0.70\%$
test_keys	36.4580μs	3.5885μs	278.6661 KOps/s	273.6132 KOps/s	$\color{#35bf28}+1.85\%$
test_keys_nested	0.2864ms	0.1634ms	6.1216 KOps/s	6.0708 KOps/s	$\color{#35bf28}+0.84\%$
test_keys_nested_locked	1.6276ms	0.1692ms	5.9100 KOps/s	5.8496 KOps/s	$\color{#35bf28}+1.03\%$
test_keys_nested_leaf	0.2412ms	0.1427ms	7.0086 KOps/s	6.9695 KOps/s	$\color{#35bf28}+0.56\%$
test_keys_stack_nested	0.3074ms	0.1625ms	6.1527 KOps/s	6.0791 KOps/s	$\color{#35bf28}+1.21\%$
test_keys_stack_nested_leaf	0.2597ms	0.1412ms	7.0810 KOps/s	7.0055 KOps/s	$\color{#35bf28}+1.08\%$
test_keys_stack_nested_locked	0.2780ms	0.1678ms	5.9606 KOps/s	5.8977 KOps/s	$\color{#35bf28}+1.07\%$
test_values	4.7590μs	1.0392μs	962.2705 KOps/s	924.4633 KOps/s	$\color{#35bf28}+4.09\%$
test_values_nested	0.1123ms	62.0997μs	16.1031 KOps/s	16.0788 KOps/s	$\color{#35bf28}+0.15\%$
test_values_nested_locked	0.1197ms	62.3914μs	16.0279 KOps/s	16.0206 KOps/s	$\color{#35bf28}+0.05\%$
test_values_nested_leaf	0.1303ms	71.3591μs	14.0136 KOps/s	14.1794 KOps/s	$\color{#d91a1a}-1.17\%$
test_values_stack_nested	0.1493ms	63.7605μs	15.6837 KOps/s	15.8496 KOps/s	$\color{#d91a1a}-1.05\%$
test_values_stack_nested_leaf	0.1426ms	71.5327μs	13.9796 KOps/s	13.9870 KOps/s	$\color{#d91a1a}-0.05\%$
test_values_stack_nested_locked	0.1162ms	64.2341μs	15.5681 KOps/s	15.7803 KOps/s	$\color{#d91a1a}-1.35\%$
test_membership	2.1034μs	0.6820μs	1.4664 MOps/s	1.1497 MOps/s	$\textbf{\color{#35bf28}+27.54\%}$
test_membership_nested	22.4220μs	2.9257μs	341.7962 KOps/s	343.1184 KOps/s	$\color{#d91a1a}-0.39\%$
test_membership_nested_leaf	27.0410μs	2.9090μs	343.7634 KOps/s	342.6931 KOps/s	$\color{#35bf28}+0.31\%$
test_membership_stacked_nested	21.3300μs	2.8656μs	348.9619 KOps/s	345.9182 KOps/s	$\color{#35bf28}+0.88\%$
test_membership_stacked_nested_leaf	21.3100μs	2.9112μs	343.5001 KOps/s	346.5003 KOps/s	$\color{#d91a1a}-0.87\%$
test_membership_nested_last	29.2450μs	4.3198μs	231.4915 KOps/s	231.6239 KOps/s	$\color{#d91a1a}-0.06\%$
test_membership_nested_leaf_last	28.0630μs	4.2945μs	232.8539 KOps/s	230.6069 KOps/s	$\color{#35bf28}+0.97\%$
test_membership_stacked_nested_last	24.8660μs	5.0152μs	199.3945 KOps/s	227.7280 KOps/s	$\textbf{\color{#d91a1a}-12.44\%}$
test_membership_stacked_nested_leaf_last	37.1190μs	5.0714μs	197.1840 KOps/s	218.7767 KOps/s	$\textbf{\color{#d91a1a}-9.87\%}$
test_nested_getleaf	35.9680μs	10.5421μs	94.8581 KOps/s	94.9416 KOps/s	$\color{#d91a1a}-0.09\%$
test_nested_get	30.7170μs	9.9009μs	101.0011 KOps/s	97.7578 KOps/s	$\color{#35bf28}+3.32\%$
test_stacked_getleaf	30.1170μs	10.3568μs	96.5545 KOps/s	93.7717 KOps/s	$\color{#35bf28}+2.97\%$
test_stacked_get	33.1720μs	9.9665μs	100.3357 KOps/s	96.8819 KOps/s	$\color{#35bf28}+3.57\%$
test_nested_getitemleaf	31.7700μs	11.0428μs	90.5565 KOps/s	87.0474 KOps/s	$\color{#35bf28}+4.03\%$
test_nested_getitem	62.6580μs	10.4442μs	95.7473 KOps/s	91.7901 KOps/s	$\color{#35bf28}+4.31\%$
test_stacked_getitemleaf	35.9280μs	11.0176μs	90.7638 KOps/s	88.3442 KOps/s	$\color{#35bf28}+2.74\%$
test_stacked_getitem	52.5280μs	10.5063μs	95.1813 KOps/s	94.2801 KOps/s	$\color{#35bf28}+0.96\%$
test_lock_nested	0.7779ms	0.4097ms	2.4409 KOps/s	2.4563 KOps/s	$\color{#d91a1a}-0.63\%$
test_lock_stack_nested	0.6539ms	0.4191ms	2.3858 KOps/s	2.3751 KOps/s	$\color{#35bf28}+0.45\%$
test_unlock_nested	0.4944ms	0.3357ms	2.9790 KOps/s	3.0272 KOps/s	$\color{#d91a1a}-1.59\%$
test_unlock_stack_nested	0.6567ms	0.3376ms	2.9623 KOps/s	2.9402 KOps/s	$\color{#35bf28}+0.75\%$
test_flatten_speed	0.2436ms	99.2916μs	10.0713 KOps/s	10.0435 KOps/s	$\color{#35bf28}+0.28\%$
test_unflatten_speed	0.6501ms	0.5179ms	1.9308 KOps/s	1.8858 KOps/s	$\color{#35bf28}+2.39\%$
test_common_ops	7.3385ms	0.8002ms	1.2497 KOps/s	1.2309 KOps/s	$\color{#35bf28}+1.53\%$
test_creation	22.3520μs	2.5271μs	395.7077 KOps/s	395.2796 KOps/s	$\color{#35bf28}+0.11\%$
test_creation_empty	37.8920μs	12.1332μs	82.4188 KOps/s	81.4689 KOps/s	$\color{#35bf28}+1.17\%$
test_creation_nested_1	37.7110μs	14.9100μs	67.0691 KOps/s	65.8284 KOps/s	$\color{#35bf28}+1.88\%$
test_creation_nested_2	48.0710μs	19.7477μs	50.6387 KOps/s	50.7903 KOps/s	$\color{#d91a1a}-0.30\%$
test_clone	50.6350μs	13.7930μs	72.5007 KOps/s	74.9520 KOps/s	$\color{#d91a1a}-3.27\%$
test_getitem[int]	2.9895ms	12.9369μs	77.2984 KOps/s	79.4765 KOps/s	$\color{#d91a1a}-2.74\%$
test_getitem[slice_int]	0.1257ms	23.9566μs	41.7421 KOps/s	41.1636 KOps/s	$\color{#35bf28}+1.41\%$
test_getitem[range]	0.1577ms	48.7220μs	20.5246 KOps/s	20.5248 KOps/s	$-0.00\%$
test_getitem[tuple]	0.1222ms	20.4844μs	48.8177 KOps/s	49.8378 KOps/s	$\color{#d91a1a}-2.05\%$
test_getitem[list]	0.1586ms	45.5168μs	21.9699 KOps/s	22.7476 KOps/s	$\color{#d91a1a}-3.42\%$
test_setitem_dim[int]	50.0340μs	25.8278μs	38.7180 KOps/s	39.7044 KOps/s	$\color{#d91a1a}-2.48\%$
test_setitem_dim[slice_int]	95.2390μs	51.2376μs	19.5169 KOps/s	19.3832 KOps/s	$\color{#35bf28}+0.69\%$
test_setitem_dim[range]	0.1348ms	75.8827μs	13.1782 KOps/s	13.2510 KOps/s	$\color{#d91a1a}-0.55\%$
test_setitem_dim[tuple]	81.0620μs	40.5427μs	24.6654 KOps/s	23.1661 KOps/s	$\textbf{\color{#35bf28}+6.47\%}$
test_setitem	0.1058ms	21.3531μs	46.8317 KOps/s	48.1580 KOps/s	$\color{#d91a1a}-2.75\%$
test_set	57.5280μs	20.2944μs	49.2746 KOps/s	49.4679 KOps/s	$\color{#d91a1a}-0.39\%$
test_set_shared	4.0183ms	0.1779ms	5.6208 KOps/s	5.5597 KOps/s	$\color{#35bf28}+1.10\%$
test_update	0.1112ms	23.2357μs	43.0372 KOps/s	43.3703 KOps/s	$\color{#d91a1a}-0.77\%$
test_update_nested	79.6700μs	33.4622μs	29.8844 KOps/s	30.7303 KOps/s	$\color{#d91a1a}-2.75\%$
test_update__nested	0.4387ms	33.5090μs	29.8427 KOps/s	29.4335 KOps/s	$\color{#35bf28}+1.39\%$
test_set_nested	86.5730μs	22.5186μs	44.4078 KOps/s	45.2570 KOps/s	$\color{#d91a1a}-1.88\%$
test_set_nested_new	94.1260μs	27.6683μs	36.1424 KOps/s	37.6573 KOps/s	$\color{#d91a1a}-4.02\%$
test_select	94.6380μs	43.9432μs	22.7566 KOps/s	22.7040 KOps/s	$\color{#35bf28}+0.23\%$
test_select_nested	0.1281ms	65.5519μs	15.2551 KOps/s	15.7150 KOps/s	$\color{#d91a1a}-2.93\%$
test_exclude_nested	0.1774ms	80.8883μs	12.3627 KOps/s	11.7304 KOps/s	$\textbf{\color{#35bf28}+5.39\%}$
test_empty[True]	0.8301ms	0.4052ms	2.4680 KOps/s	2.4571 KOps/s	$\color{#35bf28}+0.45\%$
test_empty[False]	7.6945μs	1.3701μs	729.8972 KOps/s	737.9073 KOps/s	$\color{#d91a1a}-1.09\%$
test_unbind_speed	0.5764ms	0.2715ms	3.6837 KOps/s	3.7045 KOps/s	$\color{#d91a1a}-0.56\%$
test_unbind_speed_stack0	0.3273ms	0.2691ms	3.7166 KOps/s	3.7777 KOps/s	$\color{#d91a1a}-1.62\%$
test_unbind_speed_stack1	95.8348ms	0.7232ms	1.3828 KOps/s	1.2712 KOps/s	$\textbf{\color{#35bf28}+8.78\%}$
test_split	97.4921ms	1.7391ms	574.9999 Ops/s	568.7394 Ops/s	$\color{#35bf28}+1.10\%$
test_chunk	96.1941ms	1.7489ms	571.7771 Ops/s	624.6153 Ops/s	$\textbf{\color{#d91a1a}-8.46\%}$
test_consolidate_njt[False-None]	8.4351ms	8.1433ms	122.8005 Ops/s	112.9769 Ops/s	$\textbf{\color{#35bf28}+8.70\%}$
test_creation[device0]	0.2180ms	90.2003μs	11.0864 KOps/s	11.2690 KOps/s	$\color{#d91a1a}-1.62\%$
test_creation_from_tensor	3.2698ms	93.7367μs	10.6682 KOps/s	10.7412 KOps/s	$\color{#d91a1a}-0.68\%$
test_add_one[memmap_tensor0]	0.1351ms	5.0767μs	196.9778 KOps/s	209.4897 KOps/s	$\textbf{\color{#d91a1a}-5.97\%}$
test_contiguous[memmap_tensor0]	20.9490μs	0.5044μs	1.9824 MOps/s	1.9562 MOps/s	$\color{#35bf28}+1.34\%$
test_stack[memmap_tensor0]	21.0590μs	3.4137μs	292.9374 KOps/s	292.8087 KOps/s	$\color{#35bf28}+0.04\%$
test_memmaptd_index	0.3874ms	0.2270ms	4.4047 KOps/s	4.4383 KOps/s	$\color{#d91a1a}-0.76\%$
test_memmaptd_index_astensor	1.0286ms	0.3124ms	3.2010 KOps/s	3.2176 KOps/s	$\color{#d91a1a}-0.52\%$
test_memmaptd_index_op	0.7541ms	0.5867ms	1.7045 KOps/s	1.7491 KOps/s	$\color{#d91a1a}-2.55\%$
test_serialize_model	0.2166s	0.1297s	7.7074 Ops/s	8.7579 Ops/s	$\textbf{\color{#d91a1a}-12.00\%}$
test_serialize_model_pickle	0.5194s	0.4069s	2.4578 Ops/s	2.5385 Ops/s	$\color{#d91a1a}-3.18\%$
test_serialize_weights	0.1202s	0.1127s	8.8702 Ops/s	8.7278 Ops/s	$\color{#35bf28}+1.63\%$
test_serialize_weights_returnearly	0.1723s	0.1596s	6.2672 Ops/s	6.5868 Ops/s	$\color{#d91a1a}-4.85\%$
test_serialize_weights_pickle	1.1085s	0.7459s	1.3407 Ops/s	2.4633 Ops/s	$\textbf{\color{#d91a1a}-45.57\%}$
test_serialize_weights_filesystem	0.1557s	0.1450s	6.8958 Ops/s	6.4589 Ops/s	$\textbf{\color{#35bf28}+6.77\%}$
test_serialize_model_filesystem	0.2300s	0.1512s	6.6127 Ops/s	6.6613 Ops/s	$\color{#d91a1a}-0.73\%$
test_reshape_pytree	47.1590μs	25.9671μs	38.5103 KOps/s	38.1931 KOps/s	$\color{#35bf28}+0.83\%$
test_reshape_td	62.6980μs	32.7280μs	30.5549 KOps/s	30.8977 KOps/s	$\color{#d91a1a}-1.11\%$
test_view_pytree	73.9190μs	26.4013μs	37.8769 KOps/s	38.9745 KOps/s	$\color{#d91a1a}-2.82\%$
test_view_td	77.8260μs	38.3045μs	26.1066 KOps/s	26.6665 KOps/s	$\color{#d91a1a}-2.10\%$
test_unbind_pytree	60.2230μs	29.1455μs	34.3107 KOps/s	34.4918 KOps/s	$\color{#d91a1a}-0.53\%$
test_unbind_td	0.3294ms	39.8369μs	25.1024 KOps/s	24.8189 KOps/s	$\color{#35bf28}+1.14\%$
test_split_pytree	62.9690μs	28.5707μs	35.0009 KOps/s	34.9945 KOps/s	$\color{#35bf28}+0.02\%$
test_split_td	0.1979ms	45.6359μs	21.9126 KOps/s	22.2600 KOps/s	$\color{#d91a1a}-1.56\%$
test_add_pytree	73.4380μs	36.6542μs	27.2820 KOps/s	29.0805 KOps/s	$\textbf{\color{#d91a1a}-6.18\%}$
test_add_td	0.1172ms	57.7080μs	17.3286 KOps/s	18.6074 KOps/s	$\textbf{\color{#d91a1a}-6.87\%}$
test_compile_add_one_nested[tensordict-compile]	0.1318ms	68.5945μs	14.5784 KOps/s	15.0581 KOps/s	$\color{#d91a1a}-3.19\%$
test_compile_add_one_nested[tensordict-eager]	1.2619ms	0.1744ms	5.7332 KOps/s	5.8463 KOps/s	$\color{#d91a1a}-1.93\%$
test_compile_add_one_nested[pytree-compile]	95.6000μs	47.5137μs	21.0466 KOps/s	20.9524 KOps/s	$\color{#35bf28}+0.45\%$
test_compile_add_one_nested[pytree-eager]	0.1862ms	0.1198ms	8.3497 KOps/s	8.6059 KOps/s	$\color{#d91a1a}-2.98\%$
test_compile_copy_nested[tensordict-compile]	62.4670μs	29.3023μs	34.1270 KOps/s	35.4876 KOps/s	$\color{#d91a1a}-3.83\%$
test_compile_copy_nested[tensordict-eager]	0.1101ms	58.8709μs	16.9863 KOps/s	17.0579 KOps/s	$\color{#d91a1a}-0.42\%$
test_compile_copy_nested[pytree-compile]	0.1455ms	79.9989μs	12.5002 KOps/s	12.6352 KOps/s	$\color{#d91a1a}-1.07\%$
test_compile_copy_nested[pytree-eager]	0.1358ms	66.4142μs	15.0570 KOps/s	15.0720 KOps/s	$\color{#d91a1a}-0.10\%$
test_compile_add_one_flat[tensordict-compile]	0.2150ms	0.1095ms	9.1363 KOps/s	9.4650 KOps/s	$\color{#d91a1a}-3.47\%$
test_compile_add_one_flat[tensordict-eager]	0.3024ms	0.2165ms	4.6188 KOps/s	4.6642 KOps/s	$\color{#d91a1a}-0.98\%$
test_compile_add_one_flat[tensorclass-compile]	0.1020ms	48.9221μs	20.4406 KOps/s	22.1375 KOps/s	$\textbf{\color{#d91a1a}-7.67\%}$
test_compile_add_one_flat[tensorclass-eager]	0.5491ms	68.2925μs	14.6429 KOps/s	15.2490 KOps/s	$\color{#d91a1a}-3.97\%$
test_compile_add_one_flat[pytree-compile]	0.1767ms	0.1014ms	9.8653 KOps/s	10.0599 KOps/s	$\color{#d91a1a}-1.93\%$
test_compile_add_one_flat[pytree-eager]	0.3730ms	0.2007ms	4.9824 KOps/s	4.9220 KOps/s	$\color{#35bf28}+1.23\%$
test_compile_add_self_flat[tensordict-eager]	0.4574ms	0.2345ms	4.2642 KOps/s	4.3180 KOps/s	$\color{#d91a1a}-1.25\%$
test_compile_add_self_flat[tensordict-compile]	0.2207ms	0.1150ms	8.6988 KOps/s	9.3819 KOps/s	$\textbf{\color{#d91a1a}-7.28\%}$
test_compile_add_self_flat[tensorclass-eager]	0.1276ms	62.1190μs	16.0981 KOps/s	16.1298 KOps/s	$\color{#d91a1a}-0.20\%$
test_compile_add_self_flat[tensorclass-compile]	0.1113ms	49.0331μs	20.3944 KOps/s	21.1317 KOps/s	$\color{#d91a1a}-3.49\%$
test_compile_add_self_flat[pytree-eager]	0.3358ms	0.1568ms	6.3783 KOps/s	6.3255 KOps/s	$\color{#35bf28}+0.84\%$
test_compile_add_self_flat[pytree-compile]	0.1993ms	0.1007ms	9.9258 KOps/s	9.9287 KOps/s	$\color{#d91a1a}-0.03\%$
test_compile_copy_flat[tensordict-compile]	57.6290μs	22.4602μs	44.5232 KOps/s	47.3974 KOps/s	$\textbf{\color{#d91a1a}-6.06\%}$
test_compile_copy_flat[tensordict-eager]	0.1513ms	68.0958μs	14.6852 KOps/s	14.3872 KOps/s	$\color{#35bf28}+2.07\%$
test_compile_copy_flat[pytree-compile]	0.1553ms	81.5319μs	12.2651 KOps/s	12.2358 KOps/s	$\color{#35bf28}+0.24\%$
test_compile_copy_flat[pytree-eager]	0.1401ms	66.9934μs	14.9268 KOps/s	14.8593 KOps/s	$\color{#35bf28}+0.45\%$
test_compile_assign_and_add[tensordict-compile]	0.3516ms	0.2170ms	4.6080 KOps/s	4.6838 KOps/s	$\color{#d91a1a}-1.62\%$
test_compile_assign_and_add[tensordict-eager]	2.4793ms	1.3829ms	723.1246 Ops/s	726.4046 Ops/s	$\color{#d91a1a}-0.45\%$
test_compile_assign_and_add[pytree-compile]	0.3012ms	0.2127ms	4.7014 KOps/s	4.7652 KOps/s	$\color{#d91a1a}-1.34\%$
test_compile_assign_and_add[pytree-eager]	1.0603ms	0.8229ms	1.2152 KOps/s	1.2163 KOps/s	$\color{#d91a1a}-0.09\%$
test_compile_assign_and_add_stack[compile]	0.6460ms	0.4617ms	2.1661 KOps/s	2.1971 KOps/s	$\color{#d91a1a}-1.41\%$
test_compile_assign_and_add_stack[eager]	4.2136ms	2.6923ms	371.4355 Ops/s	364.7766 Ops/s	$\color{#35bf28}+1.83\%$
test_compile_indexing[tensor-tensordict-compile]	0.1032ms	40.2832μs	24.8243 KOps/s	25.8113 KOps/s	$\color{#d91a1a}-3.82\%$
test_compile_indexing[tensor-tensordict-eager]	0.5201ms	32.9299μs	30.3675 KOps/s	29.8991 KOps/s	$\color{#35bf28}+1.57\%$
test_compile_indexing[tensor-tensorclass-compile]	75.9430μs	31.8880μs	31.3598 KOps/s	31.7846 KOps/s	$\color{#d91a1a}-1.34\%$
test_compile_indexing[tensor-tensorclass-eager]	62.8480μs	22.7206μs	44.0129 KOps/s	43.6947 KOps/s	$\color{#35bf28}+0.73\%$
test_compile_indexing[tensor-pytree-compile]	73.5780μs	32.9076μs	30.3881 KOps/s	31.2276 KOps/s	$\color{#d91a1a}-2.69\%$
test_compile_indexing[tensor-pytree-eager]	64.4810μs	22.7529μs	43.9505 KOps/s	44.3787 KOps/s	$\color{#d91a1a}-0.96\%$
test_compile_indexing[slice-tensordict-compile]	0.1418ms	54.9295μs	18.2052 KOps/s	18.8628 KOps/s	$\color{#d91a1a}-3.49\%$
test_compile_indexing[slice-tensordict-eager]	0.3467ms	19.5423μs	51.1710 KOps/s	48.9260 KOps/s	$\color{#35bf28}+4.59\%$
test_compile_indexing[slice-tensorclass-compile]	0.1005ms	46.9839μs	21.2839 KOps/s	21.5092 KOps/s	$\color{#d91a1a}-1.05\%$
test_compile_indexing[slice-tensorclass-eager]	45.8060μs	18.4243μs	54.2762 KOps/s	54.2209 KOps/s	$\color{#35bf28}+0.10\%$
test_compile_indexing[slice-pytree-compile]	0.1410ms	47.2405μs	21.1683 KOps/s	21.1223 KOps/s	$\color{#35bf28}+0.22\%$
test_compile_indexing[slice-pytree-eager]	80.7600μs	18.2323μs	54.8477 KOps/s	54.9697 KOps/s	$\color{#d91a1a}-0.22\%$
test_compile_indexing[int-tensordict-compile]	0.1276ms	55.0445μs	18.1671 KOps/s	18.2388 KOps/s	$\color{#d91a1a}-0.39\%$
test_compile_indexing[int-tensordict-eager]	0.8525ms	19.6822μs	50.8074 KOps/s	50.3331 KOps/s	$\color{#35bf28}+0.94\%$
test_compile_indexing[int-tensorclass-compile]	0.1091ms	47.1428μs	21.2121 KOps/s	21.3211 KOps/s	$\color{#d91a1a}-0.51\%$
test_compile_indexing[int-tensorclass-eager]	50.4050μs	17.9868μs	55.5963 KOps/s	50.6522 KOps/s	$\textbf{\color{#35bf28}+9.76\%}$
test_compile_indexing[int-pytree-compile]	0.1207ms	46.8390μs	21.3497 KOps/s	21.2083 KOps/s	$\color{#35bf28}+0.67\%$
test_compile_indexing[int-pytree-eager]	56.1550μs	18.0580μs	55.3772 KOps/s	55.1721 KOps/s	$\color{#35bf28}+0.37\%$
test_mod_add[eager]	0.1209ms	34.5456μs	28.9473 KOps/s	28.4466 KOps/s	$\color{#35bf28}+1.76\%$
test_mod_add[compile]	0.1303ms	65.7265μs	15.2146 KOps/s	15.2814 KOps/s	$\color{#d91a1a}-0.44\%$
test_mod_add[compile-overhead]	0.1235ms	65.0756μs	15.3667 KOps/s	15.4211 KOps/s	$\color{#d91a1a}-0.35\%$
test_mod_wrap[eager]	0.3236ms	0.2198ms	4.5504 KOps/s	4.4518 KOps/s	$\color{#35bf28}+2.21\%$
test_mod_wrap[compile]	1.3671ms	0.2303ms	4.3421 KOps/s	4.3502 KOps/s	$\color{#d91a1a}-0.19\%$
test_mod_wrap[compile-overhead]	0.2965ms	0.2289ms	4.3696 KOps/s	4.4482 KOps/s	$\color{#d91a1a}-1.77\%$
test_mod_wrap_and_backward[eager]	12.6314ms	10.7773ms	92.7873 Ops/s	74.2573 Ops/s	$\textbf{\color{#35bf28}+24.95\%}$
test_mod_wrap_and_backward[compile]	12.4630ms	10.8007ms	92.5869 Ops/s	88.6104 Ops/s	$\color{#35bf28}+4.49\%$
test_mod_wrap_and_backward[compile-overhead]	14.3833ms	11.0325ms	90.6413 Ops/s	85.6911 Ops/s	$\textbf{\color{#35bf28}+5.78\%}$
test_seq_add[eager]	0.2707ms	0.1210ms	8.2628 KOps/s	8.5849 KOps/s	$\color{#d91a1a}-3.75\%$
test_seq_add[compile]	0.1543ms	79.0551μs	12.6494 KOps/s	12.9640 KOps/s	$\color{#d91a1a}-2.43\%$
test_seq_add[compile-overhead]	0.1568ms	75.5986μs	13.2278 KOps/s	13.2633 KOps/s	$\color{#d91a1a}-0.27\%$
test_seq_wrap[eager]	0.7570ms	0.4449ms	2.2479 KOps/s	2.1931 KOps/s	$\color{#35bf28}+2.50\%$
test_seq_wrap[compile]	0.3205ms	0.2445ms	4.0892 KOps/s	4.1031 KOps/s	$\color{#d91a1a}-0.34\%$
test_seq_wrap[compile-overhead]	0.4573ms	0.2452ms	4.0789 KOps/s	4.0888 KOps/s	$\color{#d91a1a}-0.24\%$
test_func_call_runtime[False-eager]	0.9125ms	0.5424ms	1.8436 KOps/s	1.8326 KOps/s	$\color{#35bf28}+0.60\%$
test_func_call_runtime[False-compile]	0.5998ms	0.4448ms	2.2480 KOps/s	2.2598 KOps/s	$\color{#d91a1a}-0.52\%$
test_func_call_runtime[False-compile-overhead]	0.5974ms	0.4430ms	2.2575 KOps/s	2.2597 KOps/s	$\color{#d91a1a}-0.10\%$
test_func_call_runtime[True-eager]	1.0085ms	0.7562ms	1.3224 KOps/s	1.3138 KOps/s	$\color{#35bf28}+0.66\%$
test_func_call_runtime[True-compile]	0.8359ms	0.4697ms	2.1292 KOps/s	2.1775 KOps/s	$\color{#d91a1a}-2.22\%$
test_func_call_runtime[True-compile-overhead]	0.5656ms	0.4625ms	2.1624 KOps/s	2.1699 KOps/s	$\color{#d91a1a}-0.35\%$
test_func_call_cm_runtime[False-eager]	0.7389ms	0.5326ms	1.8775 KOps/s	1.8555 KOps/s	$\color{#35bf28}+1.18\%$
test_func_call_cm_runtime[False-compile]	0.8284ms	0.4449ms	2.2477 KOps/s	2.2887 KOps/s	$\color{#d91a1a}-1.79\%$
test_func_call_cm_runtime[False-compile-overhead]	0.6233ms	0.4433ms	2.2558 KOps/s	2.2785 KOps/s	$\color{#d91a1a}-1.00\%$
test_func_call_cm_runtime[True-eager]	1.0343ms	0.9043ms	1.1058 KOps/s	1.1144 KOps/s	$\color{#d91a1a}-0.77\%$
test_func_call_cm_runtime[True-compile]	0.9326ms	0.7927ms	1.2615 KOps/s	1.2663 KOps/s	$\color{#d91a1a}-0.38\%$
test_func_call_cm_runtime[True-compile-overhead]	1.3922ms	0.8059ms	1.2409 KOps/s	1.2553 KOps/s	$\color{#d91a1a}-1.15\%$
test_vmap_func_call_cm_runtime[eager]	2.7016ms	1.8978ms	526.9291 Ops/s	528.6741 Ops/s	$\color{#d91a1a}-0.33\%$
test_vmap_func_call_cm_runtime[compile]	1.0482ms	0.5391ms	1.8551 KOps/s	1.8601 KOps/s	$\color{#d91a1a}-0.27\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.7710ms	0.5355ms	1.8675 KOps/s	1.8425 KOps/s	$\color{#35bf28}+1.36\%$
test_distributed	0.2790ms	0.1244ms	8.0396 KOps/s	7.8474 KOps/s	$\color{#35bf28}+2.45\%$
test_tdmodule	85.8920μs	25.8039μs	38.7538 KOps/s	36.9122 KOps/s	$\color{#35bf28}+4.99\%$
test_tdmodule_dispatch	82.0540μs	48.9785μs	20.4171 KOps/s	20.2819 KOps/s	$\color{#35bf28}+0.67\%$
test_tdseq	58.0890μs	29.4687μs	33.9343 KOps/s	33.7374 KOps/s	$\color{#35bf28}+0.58\%$
test_tdseq_dispatch	0.1131ms	53.8056μs	18.5854 KOps/s	18.3657 KOps/s	$\color{#35bf28}+1.20\%$
test_instantiation_functorch	1.7598ms	1.5444ms	647.5120 Ops/s	651.8681 Ops/s	$\color{#d91a1a}-0.67\%$
test_exec_functorch	0.4218ms	0.1817ms	5.5039 KOps/s	5.6924 KOps/s	$\color{#d91a1a}-3.31\%$
test_exec_functional_call	0.3028ms	0.1726ms	5.7942 KOps/s	5.8868 KOps/s	$\color{#d91a1a}-1.57\%$
test_exec_td_decorator	0.4854ms	0.2302ms	4.3442 KOps/s	4.2815 KOps/s	$\color{#35bf28}+1.46\%$
test_vmap_mlp_speed_decorator[True-True]	0.8904ms	0.6551ms	1.5266 KOps/s	1.5368 KOps/s	$\color{#d91a1a}-0.67\%$
test_vmap_mlp_speed_decorator[True-False]	1.6923ms	0.6794ms	1.4718 KOps/s	1.5267 KOps/s	$\color{#d91a1a}-3.59\%$
test_vmap_mlp_speed_decorator[False-True]	0.8882ms	0.5319ms	1.8801 KOps/s	1.9072 KOps/s	$\color{#d91a1a}-1.42\%$
test_vmap_mlp_speed_decorator[False-False]	0.8577ms	0.5310ms	1.8834 KOps/s	1.9102 KOps/s	$\color{#d91a1a}-1.40\%$
test_to_module_speed[True]	1.9130ms	1.3354ms	748.8608 Ops/s	747.1871 Ops/s	$\color{#35bf28}+0.22\%$
test_to_module_speed[False]	1.4996ms	1.2993ms	769.6725 Ops/s	769.4691 Ops/s	$\color{#35bf28}+0.03\%$
test_tc_init	88.2560μs	47.3795μs	21.1062 KOps/s	20.6814 KOps/s	$\color{#35bf28}+2.05\%$
test_tc_init_nested	0.1650ms	92.2361μs	10.8417 KOps/s	10.7115 KOps/s	$\color{#35bf28}+1.22\%$
test_tc_first_layer_tensor	26.6700μs	1.5625μs	639.9829 KOps/s	634.0867 KOps/s	$\color{#35bf28}+0.93\%$
test_tc_first_layer_nontensor	25.2270μs	4.7411μs	210.9228 KOps/s	210.6297 KOps/s	$\color{#35bf28}+0.14\%$
test_tc_second_layer_tensor	22.3420μs	2.9478μs	339.2334 KOps/s	334.0002 KOps/s	$\color{#35bf28}+1.57\%$
test_tc_second_layer_nontensor	43.7920μs	6.1358μs	162.9782 KOps/s	161.1169 KOps/s	$\color{#35bf28}+1.16\%$
test_unbind	0.2227s	12.3232ms	81.1480 Ops/s	71.6886 Ops/s	$\textbf{\color{#35bf28}+13.20\%}$
test_full_like	8.9734ms	7.0323ms	142.2017 Ops/s	141.0915 Ops/s	$\color{#35bf28}+0.79\%$
test_zeros_like	4.4257ms	2.7733ms	360.5762 Ops/s	366.4834 Ops/s	$\color{#d91a1a}-1.61\%$
test_ones_like	13.5551ms	3.2473ms	307.9512 Ops/s	327.8168 Ops/s	$\textbf{\color{#d91a1a}-6.06\%}$
test_clone	5.7871ms	4.8109ms	207.8622 Ops/s	208.5087 Ops/s	$\color{#d91a1a}-0.31\%$
test_squeeze	66.3450μs	12.0404μs	83.0535 KOps/s	80.5716 KOps/s	$\color{#35bf28}+3.08\%$
test_unsqueeze	0.2467ms	91.2581μs	10.9579 KOps/s	11.0868 KOps/s	$\color{#d91a1a}-1.16\%$
test_split	0.3135ms	0.1935ms	5.1676 KOps/s	5.1682 KOps/s	$\color{#d91a1a}-0.01\%$
test_permute	0.4331ms	0.1970ms	5.0758 KOps/s	5.0994 KOps/s	$\color{#d91a1a}-0.46\%$
test_stack	27.5876ms	23.1981ms	43.1069 Ops/s	42.1038 Ops/s	$\color{#35bf28}+2.38\%$
test_cat	30.9665ms	22.9417ms	43.5888 Ops/s	42.1958 Ops/s	$\color{#35bf28}+3.30\%$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}10$. Worsened: $\large\color{#d91a1a}10$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	49.9700μs	13.0636μs	76.5488 KOps/s	77.5885 KOps/s	$\color{#d91a1a}-1.34\%$
test_plain_set_stack_nested	34.9500μs	13.2822μs	75.2887 KOps/s	77.0200 KOps/s	$\color{#d91a1a}-2.25\%$
test_plain_set_nested_inplace	0.1787ms	14.0485μs	71.1821 KOps/s	70.8646 KOps/s	$\color{#35bf28}+0.45\%$
test_plain_set_stack_nested_inplace	45.1000μs	14.1723μs	70.5604 KOps/s	72.4430 KOps/s	$\color{#d91a1a}-2.60\%$
test_items	29.2410μs	2.8453μs	351.4553 KOps/s	345.8841 KOps/s	$\color{#35bf28}+1.61\%$
test_items_nested	0.4289ms	0.3748ms	2.6683 KOps/s	2.7100 KOps/s	$\color{#d91a1a}-1.54\%$
test_items_nested_locked	0.4165ms	0.3742ms	2.6725 KOps/s	2.7108 KOps/s	$\color{#d91a1a}-1.41\%$
test_items_nested_leaf	0.1318ms	58.6845μs	17.0403 KOps/s	17.0945 KOps/s	$\color{#d91a1a}-0.32\%$
test_items_stack_nested	0.5366ms	0.3710ms	2.6952 KOps/s	2.6827 KOps/s	$\color{#35bf28}+0.47\%$
test_items_stack_nested_leaf	0.2095ms	59.4818μs	16.8119 KOps/s	16.6829 KOps/s	$\color{#35bf28}+0.77\%$
test_items_stack_nested_locked	0.4158ms	0.3740ms	2.6735 KOps/s	2.6894 KOps/s	$\color{#d91a1a}-0.59\%$
test_keys	25.9300μs	3.4609μs	288.9400 KOps/s	285.0861 KOps/s	$\color{#35bf28}+1.35\%$
test_keys_nested	0.1196ms	89.0568μs	11.2288 KOps/s	11.3795 KOps/s	$\color{#d91a1a}-1.32\%$
test_keys_nested_locked	0.6896ms	95.7424μs	10.4447 KOps/s	10.6096 KOps/s	$\color{#d91a1a}-1.55\%$
test_keys_nested_leaf	0.1076ms	79.0203μs	12.6550 KOps/s	12.6889 KOps/s	$\color{#d91a1a}-0.27\%$
test_keys_stack_nested	0.1284ms	89.0856μs	11.2252 KOps/s	11.1925 KOps/s	$\color{#35bf28}+0.29\%$
test_keys_stack_nested_leaf	0.1102ms	79.6391μs	12.5566 KOps/s	12.4926 KOps/s	$\color{#35bf28}+0.51\%$
test_keys_stack_nested_locked	0.1304ms	95.8484μs	10.4331 KOps/s	10.5277 KOps/s	$\color{#d91a1a}-0.90\%$
test_values	7.7035μs	0.8463μs	1.1816 MOps/s	1.1725 MOps/s	$\color{#35bf28}+0.78\%$
test_values_nested	81.3710μs	37.7112μs	26.5173 KOps/s	26.8182 KOps/s	$\color{#d91a1a}-1.12\%$
test_values_nested_locked	67.9710μs	38.9921μs	25.6462 KOps/s	25.8264 KOps/s	$\color{#d91a1a}-0.70\%$
test_values_nested_leaf	85.5710μs	42.4846μs	23.5380 KOps/s	23.8615 KOps/s	$\color{#d91a1a}-1.36\%$
test_values_stack_nested	74.5510μs	38.0404μs	26.2879 KOps/s	26.1072 KOps/s	$\color{#35bf28}+0.69\%$
test_values_stack_nested_leaf	0.1113ms	42.8103μs	23.3589 KOps/s	23.6214 KOps/s	$\color{#d91a1a}-1.11\%$
test_values_stack_nested_locked	0.1011ms	39.7397μs	25.1638 KOps/s	25.0912 KOps/s	$\color{#35bf28}+0.29\%$
test_membership	1.8525μs	0.5090μs	1.9646 MOps/s	1.9666 MOps/s	$\color{#d91a1a}-0.10\%$
test_membership_nested	39.7910μs	2.0990μs	476.4209 KOps/s	479.6966 KOps/s	$\color{#d91a1a}-0.68\%$
test_membership_nested_leaf	18.5800μs	2.0267μs	493.4068 KOps/s	496.0386 KOps/s	$\color{#d91a1a}-0.53\%$
test_membership_stacked_nested	41.7700μs	2.1156μs	472.6760 KOps/s	480.6521 KOps/s	$\color{#d91a1a}-1.66\%$
test_membership_stacked_nested_leaf	25.0600μs	2.1072μs	474.5607 KOps/s	480.9197 KOps/s	$\color{#d91a1a}-1.32\%$
test_membership_nested_last	45.8300μs	3.0517μs	327.6891 KOps/s	319.9398 KOps/s	$\color{#35bf28}+2.42\%$
test_membership_nested_leaf_last	32.7500μs	3.0377μs	329.1978 KOps/s	322.6893 KOps/s	$\color{#35bf28}+2.02\%$
test_membership_stacked_nested_last	42.0110μs	8.3661μs	119.5298 KOps/s	238.5592 KOps/s	$\textbf{\color{#d91a1a}-49.90\%}$
test_membership_stacked_nested_leaf_last	45.3700μs	8.1576μs	122.5847 KOps/s	244.1783 KOps/s	$\textbf{\color{#d91a1a}-49.80\%}$
test_nested_getleaf	38.2700μs	6.1709μs	162.0512 KOps/s	161.0900 KOps/s	$\color{#35bf28}+0.60\%$
test_nested_get	34.7500μs	5.8482μs	170.9925 KOps/s	169.7108 KOps/s	$\color{#35bf28}+0.76\%$
test_stacked_getleaf	49.7810μs	6.2230μs	160.6942 KOps/s	161.6072 KOps/s	$\color{#d91a1a}-0.56\%$
test_stacked_get	25.0100μs	5.8863μs	169.8847 KOps/s	169.5212 KOps/s	$\color{#35bf28}+0.21\%$
test_nested_getitemleaf	57.6710μs	6.5030μs	153.7751 KOps/s	152.9794 KOps/s	$\color{#35bf28}+0.52\%$
test_nested_getitem	37.9810μs	6.1006μs	163.9183 KOps/s	163.3371 KOps/s	$\color{#35bf28}+0.36\%$
test_stacked_getitemleaf	41.4710μs	6.4622μs	154.7469 KOps/s	156.0059 KOps/s	$\color{#d91a1a}-0.81\%$
test_stacked_getitem	34.6500μs	6.1689μs	162.1038 KOps/s	165.7176 KOps/s	$\color{#d91a1a}-2.18\%$
test_lock_nested	10.1240ms	0.3525ms	2.8371 KOps/s	2.8511 KOps/s	$\color{#d91a1a}-0.49\%$
test_lock_stack_nested	0.3968ms	0.3399ms	2.9418 KOps/s	2.8741 KOps/s	$\color{#35bf28}+2.36\%$
test_unlock_nested	0.4101ms	0.2884ms	3.4676 KOps/s	3.5172 KOps/s	$\color{#d91a1a}-1.41\%$
test_unlock_stack_nested	0.4454ms	0.2791ms	3.5831 KOps/s	3.5334 KOps/s	$\color{#35bf28}+1.41\%$
test_flatten_speed	0.1846ms	75.3357μs	13.2739 KOps/s	13.4763 KOps/s	$\color{#d91a1a}-1.50\%$
test_unflatten_speed	0.3628ms	0.3212ms	3.1132 KOps/s	3.1169 KOps/s	$\color{#d91a1a}-0.12\%$
test_common_ops	0.7978ms	0.6459ms	1.5483 KOps/s	1.5680 KOps/s	$\color{#d91a1a}-1.26\%$
test_creation	73.9210μs	1.7464μs	572.6107 KOps/s	560.3060 KOps/s	$\color{#35bf28}+2.20\%$
test_creation_empty	32.3700μs	9.9235μs	100.7707 KOps/s	104.4790 KOps/s	$\color{#d91a1a}-3.55\%$
test_creation_nested_1	61.4610μs	11.5254μs	86.7651 KOps/s	89.0260 KOps/s	$\color{#d91a1a}-2.54\%$
test_creation_nested_2	44.4200μs	14.3061μs	69.9002 KOps/s	70.9862 KOps/s	$\color{#d91a1a}-1.53\%$
test_clone	45.9710μs	11.1917μs	89.3523 KOps/s	90.7848 KOps/s	$\color{#d91a1a}-1.58\%$
test_getitem[int]	1.2678ms	10.8985μs	91.7556 KOps/s	93.1024 KOps/s	$\color{#d91a1a}-1.45\%$
test_getitem[slice_int]	0.1088ms	22.0895μs	45.2703 KOps/s	48.4824 KOps/s	$\textbf{\color{#d91a1a}-6.63\%}$
test_getitem[range]	0.1406ms	37.1971μs	26.8838 KOps/s	27.4897 KOps/s	$\color{#d91a1a}-2.20\%$
test_getitem[tuple]	0.1116ms	18.3056μs	54.6281 KOps/s	54.5083 KOps/s	$\color{#35bf28}+0.22\%$
test_getitem[list]	0.1516ms	32.9794μs	30.3220 KOps/s	30.7196 KOps/s	$\color{#d91a1a}-1.29\%$
test_setitem_dim[int]	40.8210μs	19.2551μs	51.9343 KOps/s	50.9646 KOps/s	$\color{#35bf28}+1.90\%$
test_setitem_dim[slice_int]	75.5510μs	39.0147μs	25.6313 KOps/s	25.3844 KOps/s	$\color{#35bf28}+0.97\%$
test_setitem_dim[range]	0.1122ms	52.6771μs	18.9836 KOps/s	18.2510 KOps/s	$\color{#35bf28}+4.01\%$
test_setitem_dim[tuple]	91.7310μs	33.8530μs	29.5395 KOps/s	30.2776 KOps/s	$\color{#d91a1a}-2.44\%$
test_setitem	57.8310μs	16.5521μs	60.4152 KOps/s	63.0809 KOps/s	$\color{#d91a1a}-4.23\%$
test_set	43.3400μs	15.9039μs	62.8778 KOps/s	65.1288 KOps/s	$\color{#d91a1a}-3.46\%$
test_set_shared	0.5047ms	0.1593ms	6.2774 KOps/s	6.2848 KOps/s	$\color{#d91a1a}-0.12\%$
test_update	0.3110ms	19.3994μs	51.5481 KOps/s	53.2945 KOps/s	$\color{#d91a1a}-3.28\%$
test_update_nested	66.7510μs	25.5429μs	39.1498 KOps/s	40.7343 KOps/s	$\color{#d91a1a}-3.89\%$
test_update__nested	0.5724ms	25.9900μs	38.4763 KOps/s	39.5045 KOps/s	$\color{#d91a1a}-2.60\%$
test_set_nested	54.0100μs	17.5621μs	56.9407 KOps/s	59.8575 KOps/s	$\color{#d91a1a}-4.87\%$
test_set_nested_new	51.3510μs	19.3787μs	51.6031 KOps/s	52.1924 KOps/s	$\color{#d91a1a}-1.13\%$
test_select	0.1474ms	31.7808μs	31.4656 KOps/s	32.4120 KOps/s	$\color{#d91a1a}-2.92\%$
test_select_nested	0.1384ms	43.2643μs	23.1138 KOps/s	23.2488 KOps/s	$\color{#d91a1a}-0.58\%$
test_exclude_nested	0.1126ms	63.2622μs	15.8072 KOps/s	16.0947 KOps/s	$\color{#d91a1a}-1.79\%$
test_empty[True]	0.3398ms	0.3025ms	3.3060 KOps/s	3.4005 KOps/s	$\color{#d91a1a}-2.78\%$
test_empty[False]	3.3181μs	0.8348μs	1.1978 MOps/s	1.2243 MOps/s	$\color{#d91a1a}-2.16\%$
test_to	93.4710μs	59.3320μs	16.8543 KOps/s	17.5038 KOps/s	$\color{#d91a1a}-3.71\%$
test_to_nonblocking	0.9269ms	48.6566μs	20.5522 KOps/s	20.8811 KOps/s	$\color{#d91a1a}-1.57\%$
test_unbind_speed	0.2923ms	0.2452ms	4.0787 KOps/s	4.1518 KOps/s	$\color{#d91a1a}-1.76\%$
test_unbind_speed_stack0	0.2817ms	0.2411ms	4.1470 KOps/s	4.1485 KOps/s	$\color{#d91a1a}-0.04\%$
test_unbind_speed_stack1	0.1017s	0.7444ms	1.3433 KOps/s	1.3578 KOps/s	$\color{#d91a1a}-1.07\%$
test_split	96.6838ms	1.5948ms	627.0545 Ops/s	632.0985 Ops/s	$\color{#d91a1a}-0.80\%$
test_chunk	0.1060s	1.6218ms	616.6057 Ops/s	627.0834 Ops/s	$\color{#d91a1a}-1.67\%$
test_consolidate[False-None]	2.8353ms	2.6773ms	373.5130 Ops/s	377.4876 Ops/s	$\color{#d91a1a}-1.05\%$
test_consolidate[default-None]	1.9304ms	1.6944ms	590.1779 Ops/s	592.4699 Ops/s	$\color{#d91a1a}-0.39\%$
test_consolidate[reduce-overhead-None]	1.8701ms	1.7279ms	578.7465 Ops/s	577.2857 Ops/s	$\color{#35bf28}+0.25\%$
test_consolidate_njt[False-None]	6.7309ms	6.4993ms	153.8628 Ops/s	154.7559 Ops/s	$\color{#d91a1a}-0.58\%$
test_to[False-False-None]	1.9401ms	1.7694ms	565.1513 Ops/s	580.1092 Ops/s	$\color{#d91a1a}-2.58\%$
test_to[True-False-None]	1.5955ms	1.3265ms	753.8685 Ops/s	762.9780 Ops/s	$\color{#d91a1a}-1.19\%$
test_to[within-False-None]	4.3001ms	4.0679ms	245.8242 Ops/s	243.5414 Ops/s	$\color{#35bf28}+0.94\%$
test_to[True-default-None]	5.4935ms	5.1997ms	192.3177 Ops/s	195.6121 Ops/s	$\color{#d91a1a}-1.68\%$
test_to_njt[False-False-None]	7.1244ms	6.8776ms	145.4005 Ops/s	147.0732 Ops/s	$\color{#d91a1a}-1.14\%$
test_to_njt[True-False-None]	5.6326ms	5.4266ms	184.2765 Ops/s	187.9848 Ops/s	$\color{#d91a1a}-1.97\%$
test_to_njt[within-False-None]	12.5253ms	11.8330ms	84.5092 Ops/s	85.3612 Ops/s	$\color{#d91a1a}-1.00\%$
test_creation[device0]	0.5426ms	80.2164μs	12.4663 KOps/s	12.5177 KOps/s	$\color{#d91a1a}-0.41\%$
test_creation_from_tensor	0.5188ms	88.0377μs	11.3588 KOps/s	11.8919 KOps/s	$\color{#d91a1a}-4.48\%$
test_add_one[memmap_tensor0]	0.4977ms	7.0881μs	141.0816 KOps/s	147.8929 KOps/s	$\color{#d91a1a}-4.61\%$
test_contiguous[memmap_tensor0]	1.8910μs	0.4038μs	2.4764 MOps/s	2.4725 MOps/s	$\color{#35bf28}+0.16\%$
test_stack[memmap_tensor0]	38.3010μs	4.5449μs	220.0284 KOps/s	224.1590 KOps/s	$\color{#d91a1a}-1.84\%$
test_memmaptd_index	0.4453ms	0.2424ms	4.1254 KOps/s	4.2229 KOps/s	$\color{#d91a1a}-2.31\%$
test_memmaptd_index_astensor	0.4293ms	0.3037ms	3.2926 KOps/s	3.3634 KOps/s	$\color{#d91a1a}-2.10\%$
test_memmaptd_index_op	0.7379ms	0.6086ms	1.6431 KOps/s	1.6975 KOps/s	$\color{#d91a1a}-3.21\%$
test_serialize_model	0.1323s	0.1306s	7.6586 Ops/s	7.6956 Ops/s	$\color{#d91a1a}-0.48\%$
test_serialize_model_pickle	1.3490s	1.2154s	0.8227 Ops/s	0.8227 Ops/s	$+0.00\%$
test_serialize_weights	0.1313s	0.1301s	7.6861 Ops/s	7.7028 Ops/s	$\color{#d91a1a}-0.22\%$
test_serialize_weights_returnearly	48.9304ms	42.2214ms	23.6847 Ops/s	15.1498 Ops/s	$\textbf{\color{#35bf28}+56.34\%}$
test_serialize_weights_pickle	1.3542s	1.2184s	0.8207 Ops/s	0.8208 Ops/s	$-0.01\%$
test_reshape_pytree	0.1454ms	23.1101μs	43.2711 KOps/s	44.8624 KOps/s	$\color{#d91a1a}-3.55\%$
test_reshape_td	0.1626ms	26.4808μs	37.7631 KOps/s	36.6452 KOps/s	$\color{#35bf28}+3.05\%$
test_view_pytree	0.1635ms	23.2193μs	43.0677 KOps/s	45.3624 KOps/s	$\textbf{\color{#d91a1a}-5.06\%}$
test_view_td	0.1525ms	32.3834μs	30.8800 KOps/s	30.6579 KOps/s	$\color{#35bf28}+0.72\%$
test_unbind_pytree	67.8410μs	28.3986μs	35.2130 KOps/s	35.3652 KOps/s	$\color{#d91a1a}-0.43\%$
test_unbind_td	0.9166ms	37.6652μs	26.5497 KOps/s	27.1455 KOps/s	$\color{#d91a1a}-2.19\%$
test_split_pytree	66.5510μs	29.5045μs	33.8931 KOps/s	32.7003 KOps/s	$\color{#35bf28}+3.65\%$
test_split_td	0.7610ms	38.0513μs	26.2803 KOps/s	25.1299 KOps/s	$\color{#35bf28}+4.58\%$
test_add_pytree	0.1218ms	35.9726μs	27.7989 KOps/s	27.9782 KOps/s	$\color{#d91a1a}-0.64\%$
test_add_td	0.1834ms	50.9517μs	19.6264 KOps/s	19.4759 KOps/s	$\color{#35bf28}+0.77\%$
test_compile_add_one_nested[tensordict-compile]	0.2516ms	0.1232ms	8.1174 KOps/s	7.7978 KOps/s	$\color{#35bf28}+4.10\%$
test_compile_add_one_nested[tensordict-eager]	0.2809ms	0.1322ms	7.5670 KOps/s	7.5218 KOps/s	$\color{#35bf28}+0.60\%$
test_compile_add_one_nested[pytree-compile]	0.2479ms	96.4848μs	10.3643 KOps/s	10.2314 KOps/s	$\color{#35bf28}+1.30\%$
test_compile_add_one_nested[pytree-eager]	1.3373ms	0.1554ms	6.4361 KOps/s	6.5399 KOps/s	$\color{#d91a1a}-1.59\%$
test_compile_copy_nested[tensordict-compile]	0.1552ms	23.8166μs	41.9875 KOps/s	42.2976 KOps/s	$\color{#d91a1a}-0.73\%$
test_compile_copy_nested[tensordict-eager]	0.1548ms	29.4165μs	33.9945 KOps/s	33.6793 KOps/s	$\color{#35bf28}+0.94\%$
test_compile_copy_nested[pytree-compile]	0.3924ms	64.9658μs	15.3927 KOps/s	15.2464 KOps/s	$\color{#35bf28}+0.96\%$
test_compile_copy_nested[pytree-eager]	0.2255ms	49.5485μs	20.1823 KOps/s	19.9986 KOps/s	$\color{#35bf28}+0.92\%$
test_compile_add_one_flat[tensordict-compile]	0.2775ms	0.1421ms	7.0368 KOps/s	7.1196 KOps/s	$\color{#d91a1a}-1.16\%$
test_compile_add_one_flat[tensordict-eager]	0.3690ms	0.2199ms	4.5470 KOps/s	4.5896 KOps/s	$\color{#d91a1a}-0.93\%$
test_compile_add_one_flat[tensorclass-compile]	0.2421ms	97.5298μs	10.2533 KOps/s	10.1447 KOps/s	$\color{#35bf28}+1.07\%$
test_compile_add_one_flat[tensorclass-eager]	0.1982ms	57.0812μs	17.5189 KOps/s	17.9031 KOps/s	$\color{#d91a1a}-2.15\%$
test_compile_add_one_flat[pytree-compile]	0.2251ms	0.1393ms	7.1813 KOps/s	7.3971 KOps/s	$\color{#d91a1a}-2.92\%$
test_compile_add_one_flat[pytree-eager]	0.6668ms	0.5107ms	1.9579 KOps/s	2.0584 KOps/s	$\color{#d91a1a}-4.88\%$
test_compile_add_self_flat[tensordict-eager]	0.3876ms	0.2606ms	3.8379 KOps/s	3.8195 KOps/s	$\color{#35bf28}+0.48\%$
test_compile_add_self_flat[tensordict-compile]	0.2840ms	0.1432ms	6.9811 KOps/s	7.1376 KOps/s	$\color{#d91a1a}-2.19\%$
test_compile_add_self_flat[tensorclass-eager]	0.2175ms	69.2772μs	14.4348 KOps/s	14.5813 KOps/s	$\color{#d91a1a}-1.01\%$
test_compile_add_self_flat[tensorclass-compile]	0.2525ms	0.1045ms	9.5724 KOps/s	10.2214 KOps/s	$\textbf{\color{#d91a1a}-6.35\%}$
test_compile_add_self_flat[pytree-eager]	0.5825ms	0.4248ms	2.3542 KOps/s	2.4525 KOps/s	$\color{#d91a1a}-4.01\%$
test_compile_add_self_flat[pytree-compile]	0.2865ms	0.1387ms	7.2106 KOps/s	7.5302 KOps/s	$\color{#d91a1a}-4.24\%$
test_compile_copy_flat[tensordict-compile]	0.1602ms	18.3243μs	54.5725 KOps/s	57.3184 KOps/s	$\color{#d91a1a}-4.79\%$
test_compile_copy_flat[tensordict-eager]	64.4610μs	30.7972μs	32.4705 KOps/s	31.6990 KOps/s	$\color{#35bf28}+2.43\%$
test_compile_copy_flat[pytree-compile]	0.1073ms	69.7460μs	14.3377 KOps/s	14.1388 KOps/s	$\color{#35bf28}+1.41\%$
test_compile_copy_flat[pytree-eager]	0.1421ms	51.1341μs	19.5564 KOps/s	19.3564 KOps/s	$\color{#35bf28}+1.03\%$
test_compile_assign_and_add[tensordict-compile]	1.6273ms	0.4416ms	2.2643 KOps/s	2.1465 KOps/s	$\textbf{\color{#35bf28}+5.49\%}$
test_compile_assign_and_add[tensordict-eager]	2.8924ms	2.6604ms	375.8848 Ops/s	369.7919 Ops/s	$\color{#35bf28}+1.65\%$
test_compile_assign_and_add[pytree-compile]	1.5856ms	0.4286ms	2.3334 KOps/s	2.2995 KOps/s	$\color{#35bf28}+1.47\%$
test_compile_assign_and_add[pytree-eager]	2.9602ms	2.7196ms	367.7071 Ops/s	376.9254 Ops/s	$\color{#d91a1a}-2.45\%$
test_compile_indexing[tensor-tensordict-compile]	0.2738ms	0.1113ms	8.9835 KOps/s	8.8343 KOps/s	$\color{#35bf28}+1.69\%$
test_compile_indexing[tensor-tensordict-eager]	0.5424ms	79.3697μs	12.5993 KOps/s	12.2400 KOps/s	$\color{#35bf28}+2.93\%$
test_compile_indexing[tensor-tensorclass-compile]	0.3514ms	0.1047ms	9.5484 KOps/s	9.5712 KOps/s	$\color{#d91a1a}-0.24\%$
test_compile_indexing[tensor-tensorclass-eager]	0.2217ms	68.5577μs	14.5862 KOps/s	13.5065 KOps/s	$\textbf{\color{#35bf28}+7.99\%}$
test_compile_indexing[tensor-pytree-compile]	0.2528ms	0.1098ms	9.1093 KOps/s	8.9392 KOps/s	$\color{#35bf28}+1.90\%$
test_compile_indexing[tensor-pytree-eager]	0.2268ms	69.1156μs	14.4685 KOps/s	13.6809 KOps/s	$\textbf{\color{#35bf28}+5.76\%}$
test_compile_indexing[slice-tensordict-compile]	0.2576ms	99.6623μs	10.0339 KOps/s	9.7929 KOps/s	$\color{#35bf28}+2.46\%$
test_compile_indexing[slice-tensordict-eager]	0.2055ms	20.8964μs	47.8551 KOps/s	55.9729 KOps/s	$\textbf{\color{#d91a1a}-14.50\%}$
test_compile_indexing[slice-tensorclass-compile]	0.2424ms	95.0751μs	10.5180 KOps/s	10.2842 KOps/s	$\color{#35bf28}+2.27\%$
test_compile_indexing[slice-tensorclass-eager]	0.1465ms	16.0427μs	62.3335 KOps/s	62.5046 KOps/s	$\color{#d91a1a}-0.27\%$
test_compile_indexing[slice-pytree-compile]	0.2415ms	96.1920μs	10.3959 KOps/s	10.2723 KOps/s	$\color{#35bf28}+1.20\%$
test_compile_indexing[slice-pytree-eager]	0.1646ms	16.2972μs	61.3603 KOps/s	62.5436 KOps/s	$\color{#d91a1a}-1.89\%$
test_compile_indexing[int-tensordict-compile]	0.2684ms	0.1006ms	9.9413 KOps/s	9.9183 KOps/s	$\color{#35bf28}+0.23\%$
test_compile_indexing[int-tensordict-eager]	0.5762ms	17.3100μs	57.7701 KOps/s	57.2456 KOps/s	$\color{#35bf28}+0.92\%$
test_compile_indexing[int-tensorclass-compile]	0.2782ms	96.0248μs	10.4140 KOps/s	10.2952 KOps/s	$\color{#35bf28}+1.15\%$
test_compile_indexing[int-tensorclass-eager]	0.1723ms	16.0569μs	62.2784 KOps/s	62.9506 KOps/s	$\color{#d91a1a}-1.07\%$
test_compile_indexing[int-pytree-compile]	0.2443ms	0.1011ms	9.8933 KOps/s	10.2725 KOps/s	$\color{#d91a1a}-3.69\%$
test_compile_indexing[int-pytree-eager]	62.9710μs	16.0020μs	62.4922 KOps/s	62.7459 KOps/s	$\color{#d91a1a}-0.40\%$
test_mod_add[eager]	0.1844ms	39.7373μs	25.1653 KOps/s	25.2209 KOps/s	$\color{#d91a1a}-0.22\%$
test_mod_add[compile]	0.3388ms	78.8963μs	12.6749 KOps/s	12.0891 KOps/s	$\color{#35bf28}+4.85\%$
test_mod_add[compile-overhead]	0.3334ms	0.1667ms	6.0004 KOps/s	5.6904 KOps/s	$\textbf{\color{#35bf28}+5.45\%}$
test_mod_wrap[eager]	0.4239ms	0.2537ms	3.9411 KOps/s	3.7780 KOps/s	$\color{#35bf28}+4.32\%$
test_mod_wrap[compile]	0.7476ms	0.2868ms	3.4871 KOps/s	3.5391 KOps/s	$\color{#d91a1a}-1.47\%$
test_mod_wrap[compile-overhead]	7.2178ms	3.7687ms	265.3456 Ops/s	287.1147 Ops/s	$\textbf{\color{#d91a1a}-7.58\%}$
test_mod_wrap_and_backward[eager]	1.6703ms	1.3688ms	730.5785 Ops/s	685.2185 Ops/s	$\textbf{\color{#35bf28}+6.62\%}$
test_mod_wrap_and_backward[compile]	2.0429ms	1.3734ms	728.1376 Ops/s	724.7582 Ops/s	$\color{#35bf28}+0.47\%$
test_mod_wrap_and_backward[compile-overhead]	1.7047ms	1.0677ms	936.6039 Ops/s	934.6645 Ops/s	$\color{#35bf28}+0.21\%$
test_seq_add[eager]	0.2639ms	0.1186ms	8.4291 KOps/s	8.4934 KOps/s	$\color{#d91a1a}-0.76\%$
test_seq_add[compile]	0.2038ms	87.9268μs	11.3731 KOps/s	11.6340 KOps/s	$\color{#d91a1a}-2.24\%$
test_seq_add[compile-overhead]	0.2819ms	0.1271ms	7.8696 KOps/s	7.3930 KOps/s	$\textbf{\color{#35bf28}+6.45\%}$
test_seq_wrap[eager]	0.5781ms	0.4227ms	2.3659 KOps/s	2.2534 KOps/s	$\color{#35bf28}+4.99\%$
test_seq_wrap[compile]	0.4335ms	0.3010ms	3.3227 KOps/s	3.2070 KOps/s	$\color{#35bf28}+3.61\%$
test_seq_wrap[compile-overhead]	0.3508ms	0.2261ms	4.4222 KOps/s	4.3022 KOps/s	$\color{#35bf28}+2.79\%$
test_func_call_runtime[False-eager]	0.8935ms	0.7386ms	1.3539 KOps/s	1.3254 KOps/s	$\color{#35bf28}+2.15\%$
test_func_call_runtime[False-compile]	0.9154ms	0.7419ms	1.3479 KOps/s	1.3574 KOps/s	$\color{#d91a1a}-0.70\%$
test_func_call_runtime[False-compile-overhead]	0.7728ms	0.3580ms	2.7934 KOps/s	2.7494 KOps/s	$\color{#35bf28}+1.60\%$
test_func_call_runtime[True-eager]	1.3062ms	0.8930ms	1.1198 KOps/s	1.0596 KOps/s	$\textbf{\color{#35bf28}+5.68\%}$
test_func_call_runtime[True-compile]	0.9443ms	0.7524ms	1.3290 KOps/s	1.3060 KOps/s	$\color{#35bf28}+1.76\%$
test_func_call_runtime[True-compile-overhead]	0.5213ms	0.3807ms	2.6268 KOps/s	2.6061 KOps/s	$\color{#35bf28}+0.79\%$
test_func_call_cm_runtime[False-eager]	0.9043ms	0.7269ms	1.3758 KOps/s	1.3694 KOps/s	$\color{#35bf28}+0.47\%$
test_func_call_cm_runtime[False-compile]	0.8757ms	0.7300ms	1.3699 KOps/s	1.3448 KOps/s	$\color{#35bf28}+1.87\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4728ms	0.3587ms	2.7879 KOps/s	2.7560 KOps/s	$\color{#35bf28}+1.16\%$
test_func_call_cm_runtime[True-eager]	1.4043ms	0.9995ms	1.0005 KOps/s	988.0984 Ops/s	$\color{#35bf28}+1.26\%$
test_func_call_cm_runtime[True-compile]	1.4818ms	1.0028ms	997.2375 Ops/s	1.0058 KOps/s	$\color{#d91a1a}-0.85\%$
test_func_call_cm_runtime[True-compile-overhead]	1.1583ms	0.9873ms	1.0129 KOps/s	1.0096 KOps/s	$\color{#35bf28}+0.32\%$
test_vmap_func_call_cm_runtime[eager]	2.5298ms	2.1047ms	475.1202 Ops/s	472.7464 Ops/s	$\color{#35bf28}+0.50\%$
test_vmap_func_call_cm_runtime[compile]	0.9728ms	0.8031ms	1.2452 KOps/s	1.2374 KOps/s	$\color{#35bf28}+0.63\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.5625ms	0.4120ms	2.4269 KOps/s	2.4114 KOps/s	$\color{#35bf28}+0.64\%$
test_distributed	4.7657ms	0.2111ms	4.7378 KOps/s	8.6295 KOps/s	$\textbf{\color{#d91a1a}-45.10\%}$
test_tdmodule	0.1867ms	20.7103μs	48.2851 KOps/s	48.1349 KOps/s	$\color{#35bf28}+0.31\%$
test_tdmodule_dispatch	82.1510μs	37.0766μs	26.9712 KOps/s	26.7315 KOps/s	$\color{#35bf28}+0.90\%$
test_tdseq	49.7000μs	21.3807μs	46.7711 KOps/s	46.7995 KOps/s	$\color{#d91a1a}-0.06\%$
test_tdseq_dispatch	71.9510μs	40.8537μs	24.4776 KOps/s	24.6976 KOps/s	$\color{#d91a1a}-0.89\%$
test_instantiation_functorch	1.6965ms	1.5479ms	646.0510 Ops/s	643.5854 Ops/s	$\color{#35bf28}+0.38\%$
test_exec_functorch	0.2733ms	0.1472ms	6.7939 KOps/s	6.8394 KOps/s	$\color{#d91a1a}-0.66\%$
test_exec_functional_call	0.2723ms	0.1395ms	7.1661 KOps/s	7.2945 KOps/s	$\color{#d91a1a}-1.76\%$
test_exec_td_decorator	0.3883ms	0.1891ms	5.2892 KOps/s	5.2859 KOps/s	$\color{#35bf28}+0.06\%$
test_vmap_mlp_speed_decorator[True-True]	0.8654ms	0.6886ms	1.4523 KOps/s	1.4507 KOps/s	$\color{#35bf28}+0.11\%$
test_vmap_mlp_speed_decorator[True-False]	0.8499ms	0.6893ms	1.4508 KOps/s	1.4546 KOps/s	$\color{#d91a1a}-0.26\%$
test_vmap_mlp_speed_decorator[False-True]	0.7594ms	0.5968ms	1.6757 KOps/s	1.6764 KOps/s	$\color{#d91a1a}-0.04\%$
test_vmap_mlp_speed_decorator[False-False]	0.7839ms	0.5980ms	1.6723 KOps/s	1.6711 KOps/s	$\color{#35bf28}+0.07\%$
test_vmap_transformer_speed_decorator[True-True]	20.3037ms	19.2637ms	51.9110 Ops/s	51.9153 Ops/s	$-0.01\%$
test_vmap_transformer_speed_decorator[True-False]	19.4412ms	19.2574ms	51.9280 Ops/s	51.9930 Ops/s	$\color{#d91a1a}-0.13\%$
test_vmap_transformer_speed_decorator[False-True]	19.3071ms	19.0711ms	52.4354 Ops/s	52.0389 Ops/s	$\color{#35bf28}+0.76\%$
test_vmap_transformer_speed_decorator[False-False]	19.2818ms	19.0925ms	52.3765 Ops/s	52.2806 Ops/s	$\color{#35bf28}+0.18\%$
test_to_module_speed[True]	1.4909ms	0.9482ms	1.0546 KOps/s	1.0374 KOps/s	$\color{#35bf28}+1.66\%$
test_to_module_speed[False]	1.0065ms	0.9377ms	1.0665 KOps/s	1.0579 KOps/s	$\color{#35bf28}+0.82\%$
test_tc_init	62.7610μs	37.1819μs	26.8948 KOps/s	26.5389 KOps/s	$\color{#35bf28}+1.34\%$
test_tc_init_nested	0.1140ms	74.1923μs	13.4785 KOps/s	13.2684 KOps/s	$\color{#35bf28}+1.58\%$
test_tc_first_layer_tensor	19.4400μs	0.8156μs	1.2261 MOps/s	1.4444 MOps/s	$\textbf{\color{#d91a1a}-15.12\%}$
test_tc_first_layer_nontensor	23.9110μs	2.2990μs	434.9635 KOps/s	444.9515 KOps/s	$\color{#d91a1a}-2.24\%$
test_tc_second_layer_tensor	9.1750μs	1.4485μs	690.3456 KOps/s	695.9883 KOps/s	$\color{#d91a1a}-0.81\%$
test_tc_second_layer_nontensor	30.8710μs	3.0241μs	330.6758 KOps/s	332.5816 KOps/s	$\color{#d91a1a}-0.57\%$
test_unbind	0.2269s	12.3772ms	80.7939 Ops/s	143.6561 Ops/s	$\textbf{\color{#d91a1a}-43.76\%}$
test_full_like	11.5574ms	10.2644ms	97.4238 Ops/s	97.0159 Ops/s	$\color{#35bf28}+0.42\%$
test_zeros_like	5.4659ms	4.5093ms	221.7617 Ops/s	219.8583 Ops/s	$\color{#35bf28}+0.87\%$
test_ones_like	9.8684ms	7.5337ms	132.7365 Ops/s	133.1455 Ops/s	$\color{#d91a1a}-0.31\%$
test_clone	8.0364ms	7.1513ms	139.8338 Ops/s	136.2384 Ops/s	$\color{#35bf28}+2.64\%$
test_squeeze	0.1519ms	9.2895μs	107.6487 KOps/s	104.4279 KOps/s	$\color{#35bf28}+3.08\%$
test_unsqueeze	0.1793ms	69.4429μs	14.4003 KOps/s	13.2715 KOps/s	$\textbf{\color{#35bf28}+8.51\%}$
test_split	0.3711ms	0.1542ms	6.4864 KOps/s	6.2077 KOps/s	$\color{#35bf28}+4.49\%$
test_permute	0.4978ms	0.1737ms	5.7571 KOps/s	5.4515 KOps/s	$\textbf{\color{#35bf28}+5.61\%}$
test_stack	53.2199ms	51.9389ms	19.2534 Ops/s	18.8068 Ops/s	$\color{#35bf28}+2.37\%$
test_cat	53.3621ms	52.0530ms	19.2112 Ops/s	19.1668 Ops/s	$\color{#35bf28}+0.23\%$