[Feature] from_dataclass with dest_cls arg

[vmoens]

Stack from ghstack (oldest at bottom):

• -> [Feature] from_dataclass with dest_cls arg #1250
• [BugFix] Fix tensordict.get in TDModule tensor retrieval for NonTensorData #1249

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}27$. Worsened: $\large\color{#d91a1a}7$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	40.5750μs	20.7606μs	48.1683 KOps/s	48.0171 KOps/s	$\color{#35bf28}+0.31\%$
test_plain_set_stack_nested	46.4060μs	20.8546μs	47.9510 KOps/s	47.7608 KOps/s	$\color{#35bf28}+0.40\%$
test_plain_set_nested_inplace	68.6380μs	22.6499μs	44.1503 KOps/s	43.8413 KOps/s	$\color{#35bf28}+0.70\%$
test_plain_set_stack_nested_inplace	59.4510μs	22.6018μs	44.2443 KOps/s	43.8127 KOps/s	$\color{#35bf28}+0.99\%$
test_items	41.2880μs	4.2082μs	237.6334 KOps/s	241.2324 KOps/s	$\color{#d91a1a}-1.49\%$
test_items_nested	0.5439ms	0.4090ms	2.4450 KOps/s	2.4182 KOps/s	$\color{#35bf28}+1.11\%$
test_items_nested_locked	0.5486ms	0.4083ms	2.4492 KOps/s	2.4064 KOps/s	$\color{#35bf28}+1.78\%$
test_items_nested_leaf	0.1503ms	76.9189μs	13.0007 KOps/s	12.9700 KOps/s	$\color{#35bf28}+0.24\%$
test_items_stack_nested	0.8367ms	0.4151ms	2.4093 KOps/s	2.3702 KOps/s	$\color{#35bf28}+1.65\%$
test_items_stack_nested_leaf	0.1524ms	76.7000μs	13.0378 KOps/s	12.9484 KOps/s	$\color{#35bf28}+0.69\%$
test_items_stack_nested_locked	0.5913ms	0.4090ms	2.4450 KOps/s	2.3757 KOps/s	$\color{#35bf28}+2.91\%$
test_keys	43.6510μs	3.4558μs	289.3716 KOps/s	286.3559 KOps/s	$\color{#35bf28}+1.05\%$
test_keys_nested	0.2874ms	0.1670ms	5.9869 KOps/s	5.9940 KOps/s	$\color{#d91a1a}-0.12\%$
test_keys_nested_locked	0.7025ms	0.1733ms	5.7693 KOps/s	5.7863 KOps/s	$\color{#d91a1a}-0.29\%$
test_keys_nested_leaf	0.2588ms	0.1470ms	6.8034 KOps/s	6.7884 KOps/s	$\color{#35bf28}+0.22\%$
test_keys_stack_nested	0.2780ms	0.1693ms	5.9066 KOps/s	5.9405 KOps/s	$\color{#d91a1a}-0.57\%$
test_keys_stack_nested_leaf	0.2620ms	0.1465ms	6.8241 KOps/s	6.7647 KOps/s	$\color{#35bf28}+0.88\%$
test_keys_stack_nested_locked	0.2333ms	0.1732ms	5.7753 KOps/s	5.7616 KOps/s	$\color{#35bf28}+0.24\%$
test_values	9.5238μs	1.0545μs	948.3264 KOps/s	900.5473 KOps/s	$\textbf{\color{#35bf28}+5.31\%}$
test_values_nested	0.1154ms	63.1789μs	15.8281 KOps/s	15.8478 KOps/s	$\color{#d91a1a}-0.12\%$
test_values_nested_locked	0.1187ms	62.7351μs	15.9400 KOps/s	15.8765 KOps/s	$\color{#35bf28}+0.40\%$
test_values_nested_leaf	0.1260ms	72.1113μs	13.8675 KOps/s	13.7902 KOps/s	$\color{#35bf28}+0.56\%$
test_values_stack_nested	0.1153ms	62.2975μs	16.0520 KOps/s	16.0598 KOps/s	$\color{#d91a1a}-0.05\%$
test_values_stack_nested_leaf	0.1372ms	72.2708μs	13.8369 KOps/s	13.4061 KOps/s	$\color{#35bf28}+3.21\%$
test_values_stack_nested_locked	0.1225ms	63.2144μs	15.8192 KOps/s	15.9577 KOps/s	$\color{#d91a1a}-0.87\%$
test_membership	2.0333μs	0.6919μs	1.4453 MOps/s	1.4469 MOps/s	$\color{#d91a1a}-0.11\%$
test_membership_nested	20.7190μs	2.8978μs	345.0848 KOps/s	344.1723 KOps/s	$\color{#35bf28}+0.27\%$
test_membership_nested_leaf	45.5450μs	2.8994μs	344.9009 KOps/s	345.1008 KOps/s	$\color{#d91a1a}-0.06\%$
test_membership_stacked_nested	22.9120μs	2.8972μs	345.1590 KOps/s	344.2580 KOps/s	$\color{#35bf28}+0.26\%$
test_membership_stacked_nested_leaf	47.3380μs	2.9173μs	342.7787 KOps/s	346.1410 KOps/s	$\color{#d91a1a}-0.97\%$
test_membership_nested_last	28.0920μs	4.3222μs	231.3652 KOps/s	229.7165 KOps/s	$\color{#35bf28}+0.72\%$
test_membership_nested_leaf_last	46.8370μs	4.3690μs	228.8858 KOps/s	232.8407 KOps/s	$\color{#d91a1a}-1.70\%$
test_membership_stacked_nested_last	27.7010μs	4.3853μs	228.0371 KOps/s	231.7050 KOps/s	$\color{#d91a1a}-1.58\%$
test_membership_stacked_nested_leaf_last	25.9980μs	4.3354μs	230.6592 KOps/s	233.0949 KOps/s	$\color{#d91a1a}-1.04\%$
test_nested_getleaf	35.8770μs	10.6878μs	93.5644 KOps/s	93.6143 KOps/s	$\color{#d91a1a}-0.05\%$
test_nested_get	54.9820μs	10.1156μs	98.8571 KOps/s	99.2710 KOps/s	$\color{#d91a1a}-0.42\%$
test_stacked_getleaf	54.2710μs	10.5659μs	94.6445 KOps/s	96.1913 KOps/s	$\color{#d91a1a}-1.61\%$
test_stacked_get	54.3110μs	10.1072μs	98.9391 KOps/s	98.8315 KOps/s	$\color{#35bf28}+0.11\%$
test_nested_getitemleaf	60.2320μs	11.2314μs	89.0364 KOps/s	89.3209 KOps/s	$\color{#d91a1a}-0.32\%$
test_nested_getitem	53.1490μs	10.6438μs	93.9512 KOps/s	93.3433 KOps/s	$\color{#35bf28}+0.65\%$
test_stacked_getitemleaf	41.5080μs	11.2036μs	89.2572 KOps/s	88.5391 KOps/s	$\color{#35bf28}+0.81\%$
test_stacked_getitem	52.5290μs	10.7611μs	92.9276 KOps/s	94.4259 KOps/s	$\color{#d91a1a}-1.59\%$
test_lock_nested	0.6276ms	0.4039ms	2.4757 KOps/s	2.4286 KOps/s	$\color{#35bf28}+1.94\%$
test_lock_stack_nested	0.6467ms	0.4170ms	2.3979 KOps/s	2.3528 KOps/s	$\color{#35bf28}+1.92\%$
test_unlock_nested	0.5490ms	0.3339ms	2.9949 KOps/s	2.9692 KOps/s	$\color{#35bf28}+0.86\%$
test_unlock_stack_nested	0.4997ms	0.3371ms	2.9664 KOps/s	2.9005 KOps/s	$\color{#35bf28}+2.27\%$
test_flatten_speed	0.2019ms	99.8683μs	10.0132 KOps/s	9.9765 KOps/s	$\color{#35bf28}+0.37\%$
test_unflatten_speed	0.7419ms	0.5278ms	1.8948 KOps/s	1.9043 KOps/s	$\color{#d91a1a}-0.50\%$
test_common_ops	6.2712ms	0.7965ms	1.2554 KOps/s	1.1834 KOps/s	$\textbf{\color{#35bf28}+6.09\%}$
test_creation	24.0040μs	2.5163μs	397.4018 KOps/s	398.5103 KOps/s	$\color{#d91a1a}-0.28\%$
test_creation_empty	60.4030μs	11.5904μs	86.2783 KOps/s	79.8977 KOps/s	$\textbf{\color{#35bf28}+7.99\%}$
test_creation_nested_1	40.8660μs	14.4484μs	69.2120 KOps/s	64.3728 KOps/s	$\textbf{\color{#35bf28}+7.52\%}$
test_creation_nested_2	69.7000μs	19.0555μs	52.4782 KOps/s	49.5360 KOps/s	$\textbf{\color{#35bf28}+5.94\%}$
test_clone	34.4440μs	13.2359μs	75.5522 KOps/s	72.9165 KOps/s	$\color{#35bf28}+3.61\%$
test_getitem[int]	0.8563ms	12.5929μs	79.4095 KOps/s	78.2263 KOps/s	$\color{#35bf28}+1.51\%$
test_getitem[slice_int]	0.1684ms	24.4153μs	40.9580 KOps/s	38.5239 KOps/s	$\textbf{\color{#35bf28}+6.32\%}$
test_getitem[range]	0.1783ms	49.4971μs	20.2032 KOps/s	19.7463 KOps/s	$\color{#35bf28}+2.31\%$
test_getitem[tuple]	0.1236ms	19.9462μs	50.1349 KOps/s	49.5966 KOps/s	$\color{#35bf28}+1.09\%$
test_getitem[list]	0.1635ms	45.0366μs	22.2042 KOps/s	21.6098 KOps/s	$\color{#35bf28}+2.75\%$
test_setitem_dim[int]	51.0550μs	25.3128μs	39.5057 KOps/s	38.9238 KOps/s	$\color{#35bf28}+1.49\%$
test_setitem_dim[slice_int]	96.4300μs	51.5984μs	19.3804 KOps/s	18.9278 KOps/s	$\color{#35bf28}+2.39\%$
test_setitem_dim[range]	0.1044ms	76.0653μs	13.1466 KOps/s	13.0704 KOps/s	$\color{#35bf28}+0.58\%$
test_setitem_dim[tuple]	83.7860μs	40.5610μs	24.6542 KOps/s	23.8912 KOps/s	$\color{#35bf28}+3.19\%$
test_setitem	79.6890μs	19.8286μs	50.4321 KOps/s	47.0548 KOps/s	$\textbf{\color{#35bf28}+7.18\%}$
test_set	88.0540μs	19.4483μs	51.4185 KOps/s	48.5489 KOps/s	$\textbf{\color{#35bf28}+5.91\%}$
test_set_shared	0.3233ms	0.1795ms	5.5721 KOps/s	5.4543 KOps/s	$\color{#35bf28}+2.16\%$
test_update	0.2017ms	25.1045μs	39.8335 KOps/s	36.9885 KOps/s	$\textbf{\color{#35bf28}+7.69\%}$
test_update_nested	0.4410ms	40.6891μs	24.5766 KOps/s	23.3636 KOps/s	$\textbf{\color{#35bf28}+5.19\%}$
test_update__nested	97.5420μs	33.3316μs	30.0016 KOps/s	28.6732 KOps/s	$\color{#35bf28}+4.63\%$
test_set_nested	0.1047ms	21.4802μs	46.5546 KOps/s	42.6588 KOps/s	$\textbf{\color{#35bf28}+9.13\%}$
test_set_nested_new	0.1050ms	26.2523μs	38.0919 KOps/s	35.6260 KOps/s	$\textbf{\color{#35bf28}+6.92\%}$
test_select	0.1365ms	42.8456μs	23.3396 KOps/s	22.5940 KOps/s	$\color{#35bf28}+3.30\%$
test_select_nested	0.1374ms	63.1917μs	15.8249 KOps/s	15.6619 KOps/s	$\color{#35bf28}+1.04\%$
test_exclude_nested	0.1651ms	80.8371μs	12.3706 KOps/s	12.2088 KOps/s	$\color{#35bf28}+1.32\%$
test_empty[True]	0.7391ms	0.4129ms	2.4219 KOps/s	2.4072 KOps/s	$\color{#35bf28}+0.61\%$
test_empty[False]	12.8162μs	1.3639μs	733.1932 KOps/s	707.0360 KOps/s	$\color{#35bf28}+3.70\%$
test_unbind_speed	0.6290ms	0.2732ms	3.6604 KOps/s	3.6400 KOps/s	$\color{#35bf28}+0.56\%$
test_unbind_speed_stack0	0.5514ms	0.2690ms	3.7175 KOps/s	3.6626 KOps/s	$\color{#35bf28}+1.50\%$
test_unbind_speed_stack1	0.1105s	0.7386ms	1.3538 KOps/s	1.1778 KOps/s	$\textbf{\color{#35bf28}+14.95\%}$
test_split	0.1170s	1.7662ms	566.1718 Ops/s	559.1399 Ops/s	$\color{#35bf28}+1.26\%$
test_chunk	0.1102s	1.7690ms	565.2822 Ops/s	620.1914 Ops/s	$\textbf{\color{#d91a1a}-8.85\%}$
test_consolidate_njt[False-None]	8.3464ms	8.1010ms	123.4418 Ops/s	107.4907 Ops/s	$\textbf{\color{#35bf28}+14.84\%}$
test_creation[device0]	0.1934ms	91.6681μs	10.9089 KOps/s	10.5445 KOps/s	$\color{#35bf28}+3.46\%$
test_creation_from_tensor	3.1719ms	96.2867μs	10.3857 KOps/s	10.5419 KOps/s	$\color{#d91a1a}-1.48\%$
test_add_one[memmap_tensor0]	0.1085ms	4.8566μs	205.9048 KOps/s	199.6840 KOps/s	$\color{#35bf28}+3.12\%$
test_contiguous[memmap_tensor0]	21.4400μs	0.5161μs	1.9376 MOps/s	1.9714 MOps/s	$\color{#d91a1a}-1.72\%$
test_stack[memmap_tensor0]	32.5500μs	3.2566μs	307.0727 KOps/s	304.6447 KOps/s	$\color{#35bf28}+0.80\%$
test_memmaptd_index	1.3059ms	0.2332ms	4.2875 KOps/s	4.3862 KOps/s	$\color{#d91a1a}-2.25\%$
test_memmaptd_index_astensor	0.6725ms	0.3198ms	3.1267 KOps/s	3.1399 KOps/s	$\color{#d91a1a}-0.42\%$
test_memmaptd_index_op	1.0441ms	0.5739ms	1.7426 KOps/s	1.6817 KOps/s	$\color{#35bf28}+3.62\%$
test_serialize_model	0.2311s	0.1340s	7.4636 Ops/s	8.4716 Ops/s	$\textbf{\color{#d91a1a}-11.90\%}$
test_serialize_model_pickle	0.4697s	0.3931s	2.5439 Ops/s	2.5257 Ops/s	$\color{#35bf28}+0.72\%$
test_serialize_weights	0.1288s	0.1156s	8.6521 Ops/s	8.5029 Ops/s	$\color{#35bf28}+1.75\%$
test_serialize_weights_returnearly	0.1843s	0.1611s	6.2067 Ops/s	5.5792 Ops/s	$\textbf{\color{#35bf28}+11.25\%}$
test_serialize_weights_pickle	0.4942s	0.4476s	2.2343 Ops/s	2.5564 Ops/s	$\textbf{\color{#d91a1a}-12.60\%}$
test_serialize_weights_filesystem	0.2680s	0.1593s	6.2777 Ops/s	6.9367 Ops/s	$\textbf{\color{#d91a1a}-9.50\%}$
test_serialize_model_filesystem	0.1573s	0.1498s	6.6766 Ops/s	6.5144 Ops/s	$\color{#35bf28}+2.49\%$
test_reshape_pytree	63.2480μs	26.1375μs	38.2592 KOps/s	37.1505 KOps/s	$\color{#35bf28}+2.98\%$
test_reshape_td	73.4270μs	32.4424μs	30.8239 KOps/s	29.9784 KOps/s	$\color{#35bf28}+2.82\%$
test_view_pytree	75.7520μs	26.1134μs	38.2945 KOps/s	37.7776 KOps/s	$\color{#35bf28}+1.37\%$
test_view_td	89.0170μs	40.0573μs	24.9642 KOps/s	24.0392 KOps/s	$\color{#35bf28}+3.85\%$
test_unbind_pytree	71.3230μs	28.9814μs	34.5049 KOps/s	33.0655 KOps/s	$\color{#35bf28}+4.35\%$
test_unbind_td	0.3383ms	39.9941μs	25.0037 KOps/s	24.6108 KOps/s	$\color{#35bf28}+1.60\%$
test_split_pytree	64.4800μs	28.9929μs	34.4913 KOps/s	32.9212 KOps/s	$\color{#35bf28}+4.77\%$
test_split_td	0.5225ms	46.3074μs	21.5948 KOps/s	21.9544 KOps/s	$\color{#d91a1a}-1.64\%$
test_add_pytree	73.3360μs	35.6919μs	28.0176 KOps/s	27.1857 KOps/s	$\color{#35bf28}+3.06\%$
test_add_td	0.1097ms	55.0903μs	18.1520 KOps/s	17.4371 KOps/s	$\color{#35bf28}+4.10\%$
test_compile_add_one_nested[tensordict-compile]	0.1436ms	65.7592μs	15.2070 KOps/s	14.9625 KOps/s	$\color{#35bf28}+1.63\%$
test_compile_add_one_nested[tensordict-eager]	0.5368ms	0.1726ms	5.7941 KOps/s	5.7587 KOps/s	$\color{#35bf28}+0.62\%$
test_compile_add_one_nested[pytree-compile]	0.1124ms	45.6227μs	21.9189 KOps/s	21.9285 KOps/s	$\color{#d91a1a}-0.04\%$
test_compile_add_one_nested[pytree-eager]	0.2877ms	0.1182ms	8.4607 KOps/s	8.2553 KOps/s	$\color{#35bf28}+2.49\%$
test_compile_copy_nested[tensordict-compile]	85.3800μs	28.3905μs	35.2231 KOps/s	35.1768 KOps/s	$\color{#35bf28}+0.13\%$
test_compile_copy_nested[tensordict-eager]	0.1113ms	59.5516μs	16.7922 KOps/s	16.4548 KOps/s	$\color{#35bf28}+2.05\%$
test_compile_copy_nested[pytree-compile]	0.1888ms	78.8443μs	12.6832 KOps/s	12.2894 KOps/s	$\color{#35bf28}+3.20\%$
test_compile_copy_nested[pytree-eager]	0.1516ms	67.0326μs	14.9181 KOps/s	14.7533 KOps/s	$\color{#35bf28}+1.12\%$
test_compile_add_one_flat[tensordict-compile]	0.2038ms	0.1070ms	9.3486 KOps/s	9.2958 KOps/s	$\color{#35bf28}+0.57\%$
test_compile_add_one_flat[tensordict-eager]	0.4668ms	0.2168ms	4.6131 KOps/s	4.6401 KOps/s	$\color{#d91a1a}-0.58\%$
test_compile_add_one_flat[tensorclass-compile]	0.1549ms	46.3268μs	21.5858 KOps/s	21.6539 KOps/s	$\color{#d91a1a}-0.31\%$
test_compile_add_one_flat[tensorclass-eager]	0.1917ms	67.4929μs	14.8164 KOps/s	14.9660 KOps/s	$\color{#d91a1a}-1.00\%$
test_compile_add_one_flat[pytree-compile]	0.1791ms	99.8767μs	10.0123 KOps/s	10.1023 KOps/s	$\color{#d91a1a}-0.89\%$
test_compile_add_one_flat[pytree-eager]	0.3626ms	0.1995ms	5.0117 KOps/s	4.9607 KOps/s	$\color{#35bf28}+1.03\%$
test_compile_add_self_flat[tensordict-eager]	0.3919ms	0.2313ms	4.3237 KOps/s	4.3105 KOps/s	$\color{#35bf28}+0.31\%$
test_compile_add_self_flat[tensordict-compile]	0.1825ms	0.1072ms	9.3283 KOps/s	9.3179 KOps/s	$\color{#35bf28}+0.11\%$
test_compile_add_self_flat[tensorclass-eager]	0.3394ms	65.5951μs	15.2450 KOps/s	16.0638 KOps/s	$\textbf{\color{#d91a1a}-5.10\%}$
test_compile_add_self_flat[tensorclass-compile]	0.4323ms	49.1160μs	20.3600 KOps/s	20.7042 KOps/s	$\color{#d91a1a}-1.66\%$
test_compile_add_self_flat[pytree-eager]	0.2732ms	0.1571ms	6.3671 KOps/s	6.3358 KOps/s	$\color{#35bf28}+0.49\%$
test_compile_add_self_flat[pytree-compile]	0.1767ms	99.4348μs	10.0568 KOps/s	10.0226 KOps/s	$\color{#35bf28}+0.34\%$
test_compile_copy_flat[tensordict-compile]	80.8310μs	21.1323μs	47.3209 KOps/s	45.1897 KOps/s	$\color{#35bf28}+4.72\%$
test_compile_copy_flat[tensordict-eager]	0.1662ms	68.9571μs	14.5018 KOps/s	14.8102 KOps/s	$\color{#d91a1a}-2.08\%$
test_compile_copy_flat[pytree-compile]	0.1580ms	80.2138μs	12.4667 KOps/s	12.1538 KOps/s	$\color{#35bf28}+2.57\%$
test_compile_copy_flat[pytree-eager]	0.1266ms	67.0998μs	14.9032 KOps/s	14.7363 KOps/s	$\color{#35bf28}+1.13\%$
test_compile_assign_and_add[tensordict-compile]	0.2856ms	0.2143ms	4.6654 KOps/s	4.6911 KOps/s	$\color{#d91a1a}-0.55\%$
test_compile_assign_and_add[tensordict-eager]	1.5340ms	1.3900ms	719.4369 Ops/s	718.4855 Ops/s	$\color{#35bf28}+0.13\%$
test_compile_assign_and_add[pytree-compile]	0.3258ms	0.2094ms	4.7751 KOps/s	4.7345 KOps/s	$\color{#35bf28}+0.86\%$
test_compile_assign_and_add[pytree-eager]	1.0406ms	0.8280ms	1.2077 KOps/s	1.2202 KOps/s	$\color{#d91a1a}-1.02\%$
test_compile_assign_and_add_stack[compile]	0.7051ms	0.4616ms	2.1663 KOps/s	2.2064 KOps/s	$\color{#d91a1a}-1.82\%$
test_compile_assign_and_add_stack[eager]	2.9551ms	2.6576ms	376.2789 Ops/s	360.9779 Ops/s	$\color{#35bf28}+4.24\%$
test_compile_indexing[tensor-tensordict-compile]	93.1730μs	38.9464μs	25.6763 KOps/s	26.3739 KOps/s	$\color{#d91a1a}-2.64\%$
test_compile_indexing[tensor-tensordict-eager]	0.5800ms	32.6493μs	30.6286 KOps/s	30.8601 KOps/s	$\color{#d91a1a}-0.75\%$
test_compile_indexing[tensor-tensorclass-compile]	80.3200μs	30.3454μs	32.9539 KOps/s	32.4716 KOps/s	$\color{#35bf28}+1.49\%$
test_compile_indexing[tensor-tensorclass-eager]	68.4480μs	23.0346μs	43.4130 KOps/s	43.5505 KOps/s	$\color{#d91a1a}-0.32\%$
test_compile_indexing[tensor-pytree-compile]	71.1520μs	31.9966μs	31.2534 KOps/s	31.2695 KOps/s	$\color{#d91a1a}-0.05\%$
test_compile_indexing[tensor-pytree-eager]	94.8470μs	22.6779μs	44.0958 KOps/s	43.1772 KOps/s	$\color{#35bf28}+2.13\%$
test_compile_indexing[slice-tensordict-compile]	0.1311ms	53.9486μs	18.5362 KOps/s	18.6499 KOps/s	$\color{#d91a1a}-0.61\%$
test_compile_indexing[slice-tensordict-eager]	0.3625ms	19.9386μs	50.1539 KOps/s	48.1874 KOps/s	$\color{#35bf28}+4.08\%$
test_compile_indexing[slice-tensorclass-compile]	0.1491ms	45.9235μs	21.7754 KOps/s	21.3557 KOps/s	$\color{#35bf28}+1.97\%$
test_compile_indexing[slice-tensorclass-eager]	51.3360μs	18.5130μs	54.0160 KOps/s	53.4094 KOps/s	$\color{#35bf28}+1.14\%$
test_compile_indexing[slice-pytree-compile]	0.1014ms	47.0027μs	21.2754 KOps/s	20.7722 KOps/s	$\color{#35bf28}+2.42\%$
test_compile_indexing[slice-pytree-eager]	0.1033ms	19.2697μs	51.8950 KOps/s	53.4230 KOps/s	$\color{#d91a1a}-2.86\%$
test_compile_indexing[int-tensordict-compile]	0.1265ms	55.0194μs	18.1754 KOps/s	18.1635 KOps/s	$\color{#35bf28}+0.07\%$
test_compile_indexing[int-tensordict-eager]	0.9055ms	19.7639μs	50.5972 KOps/s	48.5296 KOps/s	$\color{#35bf28}+4.26\%$
test_compile_indexing[int-tensorclass-compile]	0.1335ms	47.6798μs	20.9732 KOps/s	20.7587 KOps/s	$\color{#35bf28}+1.03\%$
test_compile_indexing[int-tensorclass-eager]	63.7590μs	18.6748μs	53.5481 KOps/s	53.8684 KOps/s	$\color{#d91a1a}-0.59\%$
test_compile_indexing[int-pytree-compile]	0.1166ms	47.4281μs	21.0845 KOps/s	20.9517 KOps/s	$\color{#35bf28}+0.63\%$
test_compile_indexing[int-pytree-eager]	68.8880μs	18.6564μs	53.6008 KOps/s	53.8840 KOps/s	$\color{#d91a1a}-0.53\%$
test_mod_add[eager]	92.3720μs	37.2341μs	26.8571 KOps/s	26.6750 KOps/s	$\color{#35bf28}+0.68\%$
test_mod_add[compile]	0.1434ms	67.4380μs	14.8284 KOps/s	15.1898 KOps/s	$\color{#d91a1a}-2.38\%$
test_mod_add[compile-overhead]	0.1342ms	66.4209μs	15.0555 KOps/s	15.4614 KOps/s	$\color{#d91a1a}-2.63\%$
test_mod_wrap[eager]	0.4569ms	0.2224ms	4.4960 KOps/s	4.2904 KOps/s	$\color{#35bf28}+4.79\%$
test_mod_wrap[compile]	1.8192ms	0.2306ms	4.3357 KOps/s	4.2786 KOps/s	$\color{#35bf28}+1.34\%$
test_mod_wrap[compile-overhead]	0.4071ms	0.2253ms	4.4391 KOps/s	4.3331 KOps/s	$\color{#35bf28}+2.45\%$
test_mod_wrap_and_backward[eager]	17.3828ms	12.6656ms	78.9538 Ops/s	73.3056 Ops/s	$\textbf{\color{#35bf28}+7.71\%}$
test_mod_wrap_and_backward[compile]	16.9148ms	13.6171ms	73.4369 Ops/s	83.3490 Ops/s	$\textbf{\color{#d91a1a}-11.89\%}$
test_mod_wrap_and_backward[compile-overhead]	15.4097ms	13.1962ms	75.7791 Ops/s	85.7164 Ops/s	$\textbf{\color{#d91a1a}-11.59\%}$
test_seq_add[eager]	0.2033ms	0.1205ms	8.2960 KOps/s	8.3400 KOps/s	$\color{#d91a1a}-0.53\%$
test_seq_add[compile]	0.1483ms	78.6919μs	12.7078 KOps/s	12.6091 KOps/s	$\color{#35bf28}+0.78\%$
test_seq_add[compile-overhead]	0.1457ms	78.2465μs	12.7801 KOps/s	13.1106 KOps/s	$\color{#d91a1a}-2.52\%$
test_seq_wrap[eager]	0.6833ms	0.4514ms	2.2153 KOps/s	2.1462 KOps/s	$\color{#35bf28}+3.22\%$
test_seq_wrap[compile]	0.4167ms	0.2445ms	4.0907 KOps/s	3.9955 KOps/s	$\color{#35bf28}+2.38\%$
test_seq_wrap[compile-overhead]	0.3790ms	0.2442ms	4.0953 KOps/s	4.0823 KOps/s	$\color{#35bf28}+0.32\%$
test_func_call_runtime[False-eager]	0.7353ms	0.5292ms	1.8897 KOps/s	1.7483 KOps/s	$\textbf{\color{#35bf28}+8.09\%}$
test_func_call_runtime[False-compile]	0.5795ms	0.4488ms	2.2279 KOps/s	2.2068 KOps/s	$\color{#35bf28}+0.96\%$
test_func_call_runtime[False-compile-overhead]	0.5818ms	0.4480ms	2.2320 KOps/s	2.1996 KOps/s	$\color{#35bf28}+1.47\%$
test_func_call_runtime[True-eager]	1.0771ms	0.7387ms	1.3538 KOps/s	1.2713 KOps/s	$\textbf{\color{#35bf28}+6.49\%}$
test_func_call_runtime[True-compile]	0.5740ms	0.4699ms	2.1281 KOps/s	2.1008 KOps/s	$\color{#35bf28}+1.30\%$
test_func_call_runtime[True-compile-overhead]	0.5839ms	0.4718ms	2.1197 KOps/s	2.0966 KOps/s	$\color{#35bf28}+1.10\%$
test_func_call_cm_runtime[False-eager]	0.7514ms	0.5253ms	1.9038 KOps/s	1.7565 KOps/s	$\textbf{\color{#35bf28}+8.38\%}$
test_func_call_cm_runtime[False-compile]	0.5568ms	0.4475ms	2.2348 KOps/s	2.2042 KOps/s	$\color{#35bf28}+1.39\%$
test_func_call_cm_runtime[False-compile-overhead]	0.7534ms	0.4492ms	2.2263 KOps/s	2.2043 KOps/s	$\color{#35bf28}+1.00\%$
test_func_call_cm_runtime[True-eager]	1.1839ms	0.8897ms	1.1239 KOps/s	1.0600 KOps/s	$\textbf{\color{#35bf28}+6.03\%}$
test_func_call_cm_runtime[True-compile]	1.6323ms	0.7976ms	1.2538 KOps/s	1.2170 KOps/s	$\color{#35bf28}+3.02\%$
test_func_call_cm_runtime[True-compile-overhead]	0.9996ms	0.7928ms	1.2614 KOps/s	1.2006 KOps/s	$\textbf{\color{#35bf28}+5.06\%}$
test_vmap_func_call_cm_runtime[eager]	2.5539ms	1.9059ms	524.6803 Ops/s	517.6729 Ops/s	$\color{#35bf28}+1.35\%$
test_vmap_func_call_cm_runtime[compile]	0.7975ms	0.5361ms	1.8655 KOps/s	1.8333 KOps/s	$\color{#35bf28}+1.75\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.7105ms	0.5316ms	1.8810 KOps/s	1.8476 KOps/s	$\color{#35bf28}+1.81\%$
test_distributed	0.2674ms	0.1251ms	7.9911 KOps/s	7.9289 KOps/s	$\color{#35bf28}+0.78\%$
test_tdmodule	55.1230μs	28.5838μs	34.9848 KOps/s	34.4668 KOps/s	$\color{#35bf28}+1.50\%$
test_tdmodule_dispatch	72.3750μs	51.3517μs	19.4736 KOps/s	19.0105 KOps/s	$\color{#35bf28}+2.44\%$
test_tdseq	51.6460μs	29.3995μs	34.0142 KOps/s	32.2695 KOps/s	$\textbf{\color{#35bf28}+5.41\%}$
test_tdseq_dispatch	91.3100μs	55.8901μs	17.8922 KOps/s	17.8342 KOps/s	$\color{#35bf28}+0.33\%$
test_instantiation_functorch	1.8548ms	1.5401ms	649.3048 Ops/s	635.9829 Ops/s	$\color{#35bf28}+2.09\%$
test_exec_functorch	0.4111ms	0.1779ms	5.6199 KOps/s	5.3596 KOps/s	$\color{#35bf28}+4.86\%$
test_exec_functional_call	0.2678ms	0.1686ms	5.9308 KOps/s	5.5756 KOps/s	$\textbf{\color{#35bf28}+6.37\%}$
test_exec_td_decorator	0.5210ms	0.2305ms	4.3387 KOps/s	4.1192 KOps/s	$\textbf{\color{#35bf28}+5.33\%}$
test_vmap_mlp_speed_decorator[True-True]	1.2217ms	0.6752ms	1.4810 KOps/s	1.4997 KOps/s	$\color{#d91a1a}-1.25\%$
test_vmap_mlp_speed_decorator[True-False]	0.8892ms	0.6552ms	1.5263 KOps/s	1.4487 KOps/s	$\textbf{\color{#35bf28}+5.36\%}$
test_vmap_mlp_speed_decorator[False-True]	0.8607ms	0.5290ms	1.8902 KOps/s	1.8649 KOps/s	$\color{#35bf28}+1.36\%$
test_vmap_mlp_speed_decorator[False-False]	0.7211ms	0.5291ms	1.8899 KOps/s	1.8687 KOps/s	$\color{#35bf28}+1.14\%$
test_to_module_speed[True]	2.1223ms	1.3287ms	752.6056 Ops/s	746.2825 Ops/s	$\color{#35bf28}+0.85\%$
test_to_module_speed[False]	1.8075ms	1.2988ms	769.9648 Ops/s	768.8240 Ops/s	$\color{#35bf28}+0.15\%$
test_tc_init	92.2920μs	46.4107μs	21.5467 KOps/s	21.1815 KOps/s	$\color{#35bf28}+1.72\%$
test_tc_init_nested	0.1566ms	90.1032μs	11.0984 KOps/s	10.6133 KOps/s	$\color{#35bf28}+4.57\%$
test_tc_first_layer_tensor	41.2170μs	1.5184μs	658.6024 KOps/s	640.5723 KOps/s	$\color{#35bf28}+2.81\%$
test_tc_first_layer_nontensor	20.7490μs	4.7094μs	212.3393 KOps/s	203.7800 KOps/s	$\color{#35bf28}+4.20\%$
test_tc_second_layer_tensor	20.1280μs	2.8332μs	352.9601 KOps/s	348.4751 KOps/s	$\color{#35bf28}+1.29\%$
test_tc_second_layer_nontensor	48.4270μs	5.9732μs	167.4147 KOps/s	164.4088 KOps/s	$\color{#35bf28}+1.83\%$
test_unbind	0.2526s	14.0519ms	71.1646 Ops/s	66.5919 Ops/s	$\textbf{\color{#35bf28}+6.87\%}$
test_full_like	9.6803ms	8.1258ms	123.0646 Ops/s	113.6074 Ops/s	$\textbf{\color{#35bf28}+8.32\%}$
test_zeros_like	5.2544ms	3.2426ms	308.3975 Ops/s	294.1530 Ops/s	$\color{#35bf28}+4.84\%$
test_ones_like	4.2547ms	3.5762ms	279.6296 Ops/s	274.3985 Ops/s	$\color{#35bf28}+1.91\%$
test_clone	7.6227ms	6.0229ms	166.0322 Ops/s	158.8713 Ops/s	$\color{#35bf28}+4.51\%$
test_squeeze	63.6480μs	12.9216μs	77.3900 KOps/s	80.8970 KOps/s	$\color{#d91a1a}-4.34\%$
test_unsqueeze	0.2866ms	94.9194μs	10.5352 KOps/s	10.5847 KOps/s	$\color{#d91a1a}-0.47\%$
test_split	0.3351ms	0.2002ms	4.9949 KOps/s	5.1515 KOps/s	$\color{#d91a1a}-3.04\%$
test_permute	0.3393ms	0.2044ms	4.8921 KOps/s	4.9755 KOps/s	$\color{#d91a1a}-1.68\%$
test_stack	34.1060ms	28.3357ms	35.2911 Ops/s	35.5628 Ops/s	$\color{#d91a1a}-0.76\%$
test_cat	32.4771ms	27.7521ms	36.0333 Ops/s	35.8983 Ops/s	$\color{#35bf28}+0.38\%$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}43$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	36.2310μs	11.4406μs	87.4077 KOps/s	81.5809 KOps/s	$\textbf{\color{#35bf28}+7.14\%}$
test_plain_set_stack_nested	34.8210μs	11.4903μs	87.0296 KOps/s	80.8901 KOps/s	$\textbf{\color{#35bf28}+7.59\%}$
test_plain_set_nested_inplace	0.1142ms	12.5417μs	79.7337 KOps/s	75.5789 KOps/s	$\textbf{\color{#35bf28}+5.50\%}$
test_plain_set_stack_nested_inplace	0.2054ms	12.4023μs	80.6299 KOps/s	75.2230 KOps/s	$\textbf{\color{#35bf28}+7.19\%}$
test_items	36.9100μs	2.8660μs	348.9241 KOps/s	347.7772 KOps/s	$\color{#35bf28}+0.33\%$
test_items_nested	0.4339ms	0.3605ms	2.7740 KOps/s	2.7515 KOps/s	$\color{#35bf28}+0.82\%$
test_items_nested_locked	0.4505ms	0.3620ms	2.7626 KOps/s	2.7621 KOps/s	$\color{#35bf28}+0.02\%$
test_items_nested_leaf	0.1173ms	60.5751μs	16.5084 KOps/s	16.5507 KOps/s	$\color{#d91a1a}-0.26\%$
test_items_stack_nested	0.4403ms	0.3638ms	2.7491 KOps/s	2.7627 KOps/s	$\color{#d91a1a}-0.49\%$
test_items_stack_nested_leaf	92.2420μs	61.0378μs	16.3833 KOps/s	16.5533 KOps/s	$\color{#d91a1a}-1.03\%$
test_items_stack_nested_locked	0.4335ms	0.3647ms	2.7422 KOps/s	2.7444 KOps/s	$\color{#d91a1a}-0.08\%$
test_keys	26.0400μs	3.4114μs	293.1373 KOps/s	289.8681 KOps/s	$\color{#35bf28}+1.13\%$
test_keys_nested	0.1336ms	87.2895μs	11.4561 KOps/s	11.4104 KOps/s	$\color{#35bf28}+0.40\%$
test_keys_nested_locked	0.7868ms	93.1768μs	10.7323 KOps/s	10.7182 KOps/s	$\color{#35bf28}+0.13\%$
test_keys_nested_leaf	0.1079ms	78.9390μs	12.6680 KOps/s	12.6779 KOps/s	$\color{#d91a1a}-0.08\%$
test_keys_stack_nested	0.1410ms	87.2305μs	11.4639 KOps/s	11.4604 KOps/s	$\color{#35bf28}+0.03\%$
test_keys_stack_nested_leaf	0.1155ms	78.8853μs	12.6766 KOps/s	12.7364 KOps/s	$\color{#d91a1a}-0.47\%$
test_keys_stack_nested_locked	0.2647ms	93.2072μs	10.7288 KOps/s	10.6713 KOps/s	$\color{#35bf28}+0.54\%$
test_values	29.1605μs	0.8490μs	1.1778 MOps/s	1.1717 MOps/s	$\color{#35bf28}+0.52\%$
test_values_nested	0.1033ms	37.1464μs	26.9205 KOps/s	26.9649 KOps/s	$\color{#d91a1a}-0.16\%$
test_values_nested_locked	68.3410μs	38.7113μs	25.8322 KOps/s	25.7750 KOps/s	$\color{#35bf28}+0.22\%$
test_values_nested_leaf	0.2285ms	42.0965μs	23.7550 KOps/s	23.7014 KOps/s	$\color{#35bf28}+0.23\%$
test_values_stack_nested	76.4320μs	36.9091μs	27.0936 KOps/s	26.9024 KOps/s	$\color{#35bf28}+0.71\%$
test_values_stack_nested_leaf	91.9610μs	42.2471μs	23.6702 KOps/s	23.6941 KOps/s	$\color{#d91a1a}-0.10\%$
test_values_stack_nested_locked	0.1867ms	38.7134μs	25.8309 KOps/s	25.7226 KOps/s	$\color{#35bf28}+0.42\%$
test_membership	2.1240μs	0.4994μs	2.0025 MOps/s	1.9905 MOps/s	$\color{#35bf28}+0.61\%$
test_membership_nested	16.7905μs	2.0053μs	498.6846 KOps/s	491.7575 KOps/s	$\color{#35bf28}+1.41\%$
test_membership_nested_leaf	14.3805μs	2.0103μs	497.4304 KOps/s	485.2954 KOps/s	$\color{#35bf28}+2.50\%$
test_membership_stacked_nested	26.0810μs	2.0486μs	488.1354 KOps/s	471.0617 KOps/s	$\color{#35bf28}+3.62\%$
test_membership_stacked_nested_leaf	31.9500μs	2.0752μs	481.8813 KOps/s	481.4770 KOps/s	$\color{#35bf28}+0.08\%$
test_membership_nested_last	35.6410μs	3.0291μs	330.1341 KOps/s	329.2344 KOps/s	$\color{#35bf28}+0.27\%$
test_membership_nested_leaf_last	31.3210μs	3.0137μs	331.8159 KOps/s	326.0945 KOps/s	$\color{#35bf28}+1.75\%$
test_membership_stacked_nested_last	66.3620μs	3.0303μs	329.9988 KOps/s	329.6665 KOps/s	$\color{#35bf28}+0.10\%$
test_membership_stacked_nested_leaf_last	25.2700μs	3.0006μs	333.2702 KOps/s	329.5924 KOps/s	$\color{#35bf28}+1.12\%$
test_nested_getleaf	42.3010μs	6.2154μs	160.8908 KOps/s	160.5505 KOps/s	$\color{#35bf28}+0.21\%$
test_nested_get	0.1164ms	5.9626μs	167.7132 KOps/s	168.2630 KOps/s	$\color{#d91a1a}-0.33\%$
test_stacked_getleaf	31.9510μs	6.1610μs	162.3106 KOps/s	161.5803 KOps/s	$\color{#35bf28}+0.45\%$
test_stacked_get	36.0410μs	5.8336μs	171.4208 KOps/s	173.7489 KOps/s	$\color{#d91a1a}-1.34\%$
test_nested_getitemleaf	0.1255ms	6.4735μs	154.4766 KOps/s	155.9692 KOps/s	$\color{#d91a1a}-0.96\%$
test_nested_getitem	35.9210μs	6.1001μs	163.9313 KOps/s	164.5481 KOps/s	$\color{#d91a1a}-0.37\%$
test_stacked_getitemleaf	33.4200μs	6.3868μs	156.5719 KOps/s	156.6567 KOps/s	$\color{#d91a1a}-0.05\%$
test_stacked_getitem	39.9700μs	5.9833μs	167.1307 KOps/s	167.7430 KOps/s	$\color{#d91a1a}-0.37\%$
test_lock_nested	0.4747ms	0.3308ms	3.0229 KOps/s	2.9183 KOps/s	$\color{#35bf28}+3.59\%$
test_lock_stack_nested	0.3941ms	0.3366ms	2.9706 KOps/s	2.8648 KOps/s	$\color{#35bf28}+3.69\%$
test_unlock_nested	0.3573ms	0.2767ms	3.6140 KOps/s	3.5022 KOps/s	$\color{#35bf28}+3.19\%$
test_unlock_stack_nested	0.4217ms	0.2777ms	3.6013 KOps/s	3.4836 KOps/s	$\color{#35bf28}+3.38\%$
test_flatten_speed	0.1062ms	77.4138μs	12.9176 KOps/s	12.9673 KOps/s	$\color{#d91a1a}-0.38\%$
test_unflatten_speed	0.3678ms	0.3191ms	3.1341 KOps/s	3.1163 KOps/s	$\color{#35bf28}+0.57\%$
test_common_ops	0.7724ms	0.5824ms	1.7169 KOps/s	1.6307 KOps/s	$\textbf{\color{#35bf28}+5.29\%}$
test_creation	0.1266ms	1.7263μs	579.2671 KOps/s	577.6470 KOps/s	$\color{#35bf28}+0.28\%$
test_creation_empty	27.9500μs	6.4062μs	156.0980 KOps/s	125.1888 KOps/s	$\textbf{\color{#35bf28}+24.69\%}$
test_creation_nested_1	62.9810μs	8.0094μs	124.8540 KOps/s	103.6756 KOps/s	$\textbf{\color{#35bf28}+20.43\%}$
test_creation_nested_2	77.9320μs	10.7271μs	93.2215 KOps/s	81.2825 KOps/s	$\textbf{\color{#35bf28}+14.69\%}$
test_clone	0.1939ms	10.3964μs	96.1873 KOps/s	91.5009 KOps/s	$\textbf{\color{#35bf28}+5.12\%}$
test_getitem[int]	1.5392ms	10.4054μs	96.1039 KOps/s	91.8392 KOps/s	$\color{#35bf28}+4.64\%$
test_getitem[slice_int]	0.1085ms	20.3750μs	49.0796 KOps/s	46.2434 KOps/s	$\textbf{\color{#35bf28}+6.13\%}$
test_getitem[range]	0.1735ms	37.5607μs	26.6236 KOps/s	25.8219 KOps/s	$\color{#35bf28}+3.10\%$
test_getitem[tuple]	0.1559ms	17.6096μs	56.7873 KOps/s	54.3665 KOps/s	$\color{#35bf28}+4.45\%$
test_getitem[list]	0.1907ms	32.6837μs	30.5962 KOps/s	29.8704 KOps/s	$\color{#35bf28}+2.43\%$
test_setitem_dim[int]	39.9500μs	18.6644μs	53.5780 KOps/s	50.9895 KOps/s	$\textbf{\color{#35bf28}+5.08\%}$
test_setitem_dim[slice_int]	60.6110μs	37.3433μs	26.7785 KOps/s	25.8724 KOps/s	$\color{#35bf28}+3.50\%$
test_setitem_dim[range]	89.1220μs	52.6939μs	18.9775 KOps/s	18.7532 KOps/s	$\color{#35bf28}+1.20\%$
test_setitem_dim[tuple]	71.9420μs	31.4483μs	31.7982 KOps/s	30.9763 KOps/s	$\color{#35bf28}+2.65\%$
test_setitem	71.2310μs	14.0465μs	71.1920 KOps/s	65.5619 KOps/s	$\textbf{\color{#35bf28}+8.59\%}$
test_set	71.9720μs	13.3586μs	74.8582 KOps/s	68.0937 KOps/s	$\textbf{\color{#35bf28}+9.93\%}$
test_set_shared	0.5102ms	0.1570ms	6.3700 KOps/s	6.3121 KOps/s	$\color{#35bf28}+0.92\%$
test_update	0.2414ms	16.7603μs	59.6649 KOps/s	52.1121 KOps/s	$\textbf{\color{#35bf28}+14.49\%}$
test_update_nested	0.1231ms	25.5204μs	39.1844 KOps/s	35.7283 KOps/s	$\textbf{\color{#35bf28}+9.67\%}$
test_update__nested	0.6402ms	25.1350μs	39.7851 KOps/s	40.3965 KOps/s	$\color{#d91a1a}-1.51\%$
test_set_nested	0.1261ms	14.6855μs	68.0944 KOps/s	62.3071 KOps/s	$\textbf{\color{#35bf28}+9.29\%}$
test_set_nested_new	73.6920μs	16.9853μs	58.8745 KOps/s	54.5333 KOps/s	$\textbf{\color{#35bf28}+7.96\%}$
test_select	0.2039ms	27.4517μs	36.4276 KOps/s	33.4798 KOps/s	$\textbf{\color{#35bf28}+8.80\%}$
test_select_nested	0.2386ms	43.3372μs	23.0748 KOps/s	23.0424 KOps/s	$\color{#35bf28}+0.14\%$
test_exclude_nested	0.2587ms	63.0478μs	15.8610 KOps/s	15.8224 KOps/s	$\color{#35bf28}+0.24\%$
test_empty[True]	0.3352ms	0.2932ms	3.4108 KOps/s	3.3717 KOps/s	$\color{#35bf28}+1.16\%$
test_empty[False]	8.9502μs	0.8170μs	1.2240 MOps/s	1.2080 MOps/s	$\color{#35bf28}+1.33\%$
test_to	91.2220μs	56.9881μs	17.5475 KOps/s	17.5806 KOps/s	$\color{#d91a1a}-0.19\%$
test_to_nonblocking	0.1898ms	46.9671μs	21.2915 KOps/s	21.4436 KOps/s	$\color{#d91a1a}-0.71\%$
test_unbind_speed	0.3784ms	0.2384ms	4.1942 KOps/s	4.1107 KOps/s	$\color{#35bf28}+2.03\%$
test_unbind_speed_stack0	0.2792ms	0.2319ms	4.3124 KOps/s	4.0833 KOps/s	$\textbf{\color{#35bf28}+5.61\%}$
test_unbind_speed_stack1	0.1070s	0.7545ms	1.3253 KOps/s	1.3199 KOps/s	$\color{#35bf28}+0.41\%$
test_split	0.1107s	1.6020ms	624.2306 Ops/s	611.0602 Ops/s	$\color{#35bf28}+2.16\%$
test_chunk	0.1169s	1.6036ms	623.6107 Ops/s	610.8381 Ops/s	$\color{#35bf28}+2.09\%$
test_consolidate[False-None]	0.1134s	3.0418ms	328.7571 Ops/s	365.0420 Ops/s	$\textbf{\color{#d91a1a}-9.94\%}$
test_consolidate[default-None]	1.8684ms	1.7219ms	580.7535 Ops/s	570.5995 Ops/s	$\color{#35bf28}+1.78\%$
test_consolidate[reduce-overhead-None]	2.8340ms	1.7500ms	571.4328 Ops/s	562.7783 Ops/s	$\color{#35bf28}+1.54\%$
test_consolidate_njt[False-None]	6.8068ms	6.4009ms	156.2279 Ops/s	109.5951 Ops/s	$\textbf{\color{#35bf28}+42.55\%}$
test_to[False-False-None]	1.8865ms	1.7030ms	587.2136 Ops/s	578.0506 Ops/s	$\color{#35bf28}+1.59\%$
test_to[True-False-None]	1.6015ms	1.3164ms	759.6647 Ops/s	739.2369 Ops/s	$\color{#35bf28}+2.76\%$
test_to[within-False-None]	4.2656ms	4.1141ms	243.0689 Ops/s	237.4226 Ops/s	$\color{#35bf28}+2.38\%$
test_to[True-default-None]	5.3621ms	5.0972ms	196.1866 Ops/s	193.7092 Ops/s	$\color{#35bf28}+1.28\%$
test_to_njt[False-False-None]	7.1235ms	6.9165ms	144.5819 Ops/s	142.8386 Ops/s	$\color{#35bf28}+1.22\%$
test_to_njt[True-False-None]	5.7122ms	5.4549ms	183.3228 Ops/s	180.9926 Ops/s	$\color{#35bf28}+1.29\%$
test_to_njt[within-False-None]	12.4901ms	11.9364ms	83.7771 Ops/s	82.4518 Ops/s	$\color{#35bf28}+1.61\%$
test_creation[device0]	0.4556ms	80.1877μs	12.4707 KOps/s	12.4291 KOps/s	$\color{#35bf28}+0.34\%$
test_creation_from_tensor	0.4992ms	85.7858μs	11.6569 KOps/s	11.8301 KOps/s	$\color{#d91a1a}-1.46\%$
test_add_one[memmap_tensor0]	0.4474ms	6.6643μs	150.0535 KOps/s	142.4109 KOps/s	$\textbf{\color{#35bf28}+5.37\%}$
test_contiguous[memmap_tensor0]	2.4610μs	0.4442μs	2.2511 MOps/s	2.3342 MOps/s	$\color{#d91a1a}-3.56\%$
test_stack[memmap_tensor0]	0.1516ms	4.3729μs	228.6821 KOps/s	214.1648 KOps/s	$\textbf{\color{#35bf28}+6.78\%}$
test_memmaptd_index	1.5841ms	0.2364ms	4.2308 KOps/s	4.0145 KOps/s	$\textbf{\color{#35bf28}+5.39\%}$
test_memmaptd_index_astensor	0.4612ms	0.2981ms	3.3548 KOps/s	3.2172 KOps/s	$\color{#35bf28}+4.28\%$
test_memmaptd_index_op	0.6842ms	0.5366ms	1.8635 KOps/s	1.7124 KOps/s	$\textbf{\color{#35bf28}+8.83\%}$
test_serialize_model	0.1344s	0.1330s	7.5196 Ops/s	7.5375 Ops/s	$\color{#d91a1a}-0.24\%$
test_serialize_model_pickle	1.3498s	1.2165s	0.8221 Ops/s	0.8400 Ops/s	$\color{#d91a1a}-2.14\%$
test_serialize_weights	0.1326s	0.1316s	7.5981 Ops/s	7.5379 Ops/s	$\color{#35bf28}+0.80\%$
test_serialize_weights_returnearly	0.3452s	55.1876ms	18.1200 Ops/s	13.8965 Ops/s	$\textbf{\color{#35bf28}+30.39\%}$
test_serialize_weights_pickle	1.3739s	1.2184s	0.8208 Ops/s	0.8223 Ops/s	$\color{#d91a1a}-0.18\%$
test_reshape_pytree	0.1022ms	22.6110μs	44.2263 KOps/s	43.4829 KOps/s	$\color{#35bf28}+1.71\%$
test_reshape_td	0.1138ms	26.3021μs	38.0197 KOps/s	37.5655 KOps/s	$\color{#35bf28}+1.21\%$
test_view_pytree	0.1176ms	22.1067μs	45.2351 KOps/s	44.8090 KOps/s	$\color{#35bf28}+0.95\%$
test_view_td	84.1920μs	31.4744μs	31.7719 KOps/s	32.5001 KOps/s	$\color{#d91a1a}-2.24\%$
test_unbind_pytree	0.1677ms	27.6734μs	36.1358 KOps/s	34.7086 KOps/s	$\color{#35bf28}+4.11\%$
test_unbind_td	0.1830s	49.3244μs	20.2739 KOps/s	26.5537 KOps/s	$\textbf{\color{#d91a1a}-23.65\%}$
test_split_pytree	0.1227ms	29.5328μs	33.8607 KOps/s	33.2205 KOps/s	$\color{#35bf28}+1.93\%$
test_split_td	0.1691ms	37.4952μs	26.6701 KOps/s	25.1986 KOps/s	$\textbf{\color{#35bf28}+5.84\%}$
test_add_pytree	0.1463ms	34.7028μs	28.8161 KOps/s	28.0096 KOps/s	$\color{#35bf28}+2.88\%$
test_add_td	0.1887ms	44.2048μs	22.6220 KOps/s	20.3591 KOps/s	$\textbf{\color{#35bf28}+11.11\%}$
test_compile_add_one_nested[tensordict-compile]	0.2971ms	0.1193ms	8.3806 KOps/s	7.7390 KOps/s	$\textbf{\color{#35bf28}+8.29\%}$
test_compile_add_one_nested[tensordict-eager]	0.3184ms	0.1314ms	7.6078 KOps/s	7.5332 KOps/s	$\color{#35bf28}+0.99\%$
test_compile_add_one_nested[pytree-compile]	0.2869ms	96.4798μs	10.3649 KOps/s	10.2908 KOps/s	$\color{#35bf28}+0.72\%$
test_compile_add_one_nested[pytree-eager]	1.0965ms	0.1479ms	6.7627 KOps/s	6.5653 KOps/s	$\color{#35bf28}+3.01\%$
test_compile_copy_nested[tensordict-compile]	0.1591ms	23.5990μs	42.3748 KOps/s	39.7015 KOps/s	$\textbf{\color{#35bf28}+6.73\%}$
test_compile_copy_nested[tensordict-eager]	0.2135ms	29.2823μs	34.1503 KOps/s	33.8458 KOps/s	$\color{#35bf28}+0.90\%$
test_compile_copy_nested[pytree-compile]	0.2541ms	63.2925μs	15.7997 KOps/s	15.1468 KOps/s	$\color{#35bf28}+4.31\%$
test_compile_copy_nested[pytree-eager]	91.6310μs	50.4169μs	19.8346 KOps/s	19.7016 KOps/s	$\color{#35bf28}+0.68\%$
test_compile_add_one_flat[tensordict-compile]	0.2902ms	0.1416ms	7.0624 KOps/s	7.0869 KOps/s	$\color{#d91a1a}-0.35\%$
test_compile_add_one_flat[tensordict-eager]	0.3741ms	0.2170ms	4.6089 KOps/s	4.6173 KOps/s	$\color{#d91a1a}-0.18\%$
test_compile_add_one_flat[tensorclass-compile]	0.2523ms	97.7013μs	10.2353 KOps/s	10.2404 KOps/s	$\color{#d91a1a}-0.05\%$
test_compile_add_one_flat[tensorclass-eager]	0.2161ms	55.3723μs	18.0596 KOps/s	17.8864 KOps/s	$\color{#35bf28}+0.97\%$
test_compile_add_one_flat[pytree-compile]	0.2797ms	0.1358ms	7.3626 KOps/s	7.3878 KOps/s	$\color{#d91a1a}-0.34\%$
test_compile_add_one_flat[pytree-eager]	0.6518ms	0.4737ms	2.1110 KOps/s	2.0570 KOps/s	$\color{#35bf28}+2.63\%$
test_compile_add_self_flat[tensordict-eager]	0.4060ms	0.2613ms	3.8270 KOps/s	3.8424 KOps/s	$\color{#d91a1a}-0.40\%$
test_compile_add_self_flat[tensordict-compile]	0.2882ms	0.1431ms	6.9882 KOps/s	7.0422 KOps/s	$\color{#d91a1a}-0.77\%$
test_compile_add_self_flat[tensorclass-eager]	0.2145ms	67.7597μs	14.7580 KOps/s	14.6023 KOps/s	$\color{#35bf28}+1.07\%$
test_compile_add_self_flat[tensorclass-compile]	0.2474ms	98.8313μs	10.1183 KOps/s	10.1166 KOps/s	$\color{#35bf28}+0.02\%$
test_compile_add_self_flat[pytree-eager]	0.5688ms	0.4023ms	2.4855 KOps/s	2.4736 KOps/s	$\color{#35bf28}+0.48\%$
test_compile_add_self_flat[pytree-compile]	0.2791ms	0.1356ms	7.3731 KOps/s	7.4351 KOps/s	$\color{#d91a1a}-0.83\%$
test_compile_copy_flat[tensordict-compile]	0.1564ms	18.3789μs	54.4102 KOps/s	55.2159 KOps/s	$\color{#d91a1a}-1.46\%$
test_compile_copy_flat[tensordict-eager]	0.1333ms	31.2873μs	31.9618 KOps/s	32.0326 KOps/s	$\color{#d91a1a}-0.22\%$
test_compile_copy_flat[pytree-compile]	0.2105ms	69.6066μs	14.3665 KOps/s	14.4083 KOps/s	$\color{#d91a1a}-0.29\%$
test_compile_copy_flat[pytree-eager]	0.2193ms	52.3956μs	19.0856 KOps/s	19.2167 KOps/s	$\color{#d91a1a}-0.68\%$
test_compile_assign_and_add[tensordict-compile]	1.6689ms	0.4510ms	2.2173 KOps/s	2.1469 KOps/s	$\color{#35bf28}+3.28\%$
test_compile_assign_and_add[tensordict-eager]	2.9773ms	2.6024ms	384.2574 Ops/s	375.7479 Ops/s	$\color{#35bf28}+2.26\%$
test_compile_assign_and_add[pytree-compile]	1.6066ms	0.4344ms	2.3020 KOps/s	2.1513 KOps/s	$\textbf{\color{#35bf28}+7.00\%}$
test_compile_assign_and_add[pytree-eager]	2.8019ms	2.5695ms	389.1845 Ops/s	376.1965 Ops/s	$\color{#35bf28}+3.45\%$
test_compile_indexing[tensor-tensordict-compile]	0.6989ms	0.1156ms	8.6528 KOps/s	8.5993 KOps/s	$\color{#35bf28}+0.62\%$
test_compile_indexing[tensor-tensordict-eager]	0.5836ms	78.9920μs	12.6595 KOps/s	12.2800 KOps/s	$\color{#35bf28}+3.09\%$
test_compile_indexing[tensor-tensorclass-compile]	0.4404ms	0.1082ms	9.2432 KOps/s	9.3474 KOps/s	$\color{#d91a1a}-1.11\%$
test_compile_indexing[tensor-tensorclass-eager]	0.2834ms	67.8405μs	14.7405 KOps/s	13.8884 KOps/s	$\textbf{\color{#35bf28}+6.13\%}$
test_compile_indexing[tensor-pytree-compile]	0.2766ms	0.1088ms	9.1879 KOps/s	8.8016 KOps/s	$\color{#35bf28}+4.39\%$
test_compile_indexing[tensor-pytree-eager]	0.2500ms	68.6665μs	14.5632 KOps/s	13.9613 KOps/s	$\color{#35bf28}+4.31\%$
test_compile_indexing[slice-tensordict-compile]	0.2516ms	0.1004ms	9.9641 KOps/s	9.7330 KOps/s	$\color{#35bf28}+2.37\%$
test_compile_indexing[slice-tensordict-eager]	0.1627ms	16.7924μs	59.5509 KOps/s	56.3356 KOps/s	$\textbf{\color{#35bf28}+5.71\%}$
test_compile_indexing[slice-tensorclass-compile]	0.2425ms	95.4046μs	10.4817 KOps/s	10.1415 KOps/s	$\color{#35bf28}+3.35\%$
test_compile_indexing[slice-tensorclass-eager]	0.1454ms	15.5368μs	64.3632 KOps/s	61.1226 KOps/s	$\textbf{\color{#35bf28}+5.30\%}$
test_compile_indexing[slice-pytree-compile]	0.2469ms	96.2756μs	10.3869 KOps/s	10.1040 KOps/s	$\color{#35bf28}+2.80\%$
test_compile_indexing[slice-pytree-eager]	0.1982ms	15.5527μs	64.2976 KOps/s	61.5900 KOps/s	$\color{#35bf28}+4.40\%$
test_compile_indexing[int-tensordict-compile]	0.2690ms	0.1038ms	9.6377 KOps/s	9.7135 KOps/s	$\color{#d91a1a}-0.78\%$
test_compile_indexing[int-tensordict-eager]	0.7036ms	16.8507μs	59.3446 KOps/s	56.8098 KOps/s	$\color{#35bf28}+4.46\%$
test_compile_indexing[int-tensorclass-compile]	0.2486ms	98.3763μs	10.1650 KOps/s	10.2787 KOps/s	$\color{#d91a1a}-1.11\%$
test_compile_indexing[int-tensorclass-eager]	0.1495ms	15.5141μs	64.4574 KOps/s	62.3353 KOps/s	$\color{#35bf28}+3.40\%$
test_compile_indexing[int-pytree-compile]	0.2869ms	97.7696μs	10.2281 KOps/s	10.2777 KOps/s	$\color{#d91a1a}-0.48\%$
test_compile_indexing[int-pytree-eager]	0.1422ms	15.9988μs	62.5047 KOps/s	62.4621 KOps/s	$\color{#35bf28}+0.07\%$
test_mod_add[eager]	0.2246ms	37.2329μs	26.8580 KOps/s	25.4531 KOps/s	$\textbf{\color{#35bf28}+5.52\%}$
test_mod_add[compile]	0.3412ms	80.9524μs	12.3529 KOps/s	12.3318 KOps/s	$\color{#35bf28}+0.17\%$
test_mod_add[compile-overhead]	0.3619ms	0.1830ms	5.4632 KOps/s	5.2541 KOps/s	$\color{#35bf28}+3.98\%$
test_mod_wrap[eager]	0.4244ms	0.2529ms	3.9543 KOps/s	3.7882 KOps/s	$\color{#35bf28}+4.38\%$
test_mod_wrap[compile]	0.4591ms	0.2843ms	3.5179 KOps/s	3.4565 KOps/s	$\color{#35bf28}+1.78\%$
test_mod_wrap[compile-overhead]	7.6453ms	3.8057ms	262.7642 Ops/s	262.1880 Ops/s	$\color{#35bf28}+0.22\%$
test_mod_wrap_and_backward[eager]	1.6279ms	1.3916ms	718.6190 Ops/s	677.7352 Ops/s	$\textbf{\color{#35bf28}+6.03\%}$
test_mod_wrap_and_backward[compile]	2.0797ms	1.3769ms	726.2538 Ops/s	713.0560 Ops/s	$\color{#35bf28}+1.85\%$
test_mod_wrap_and_backward[compile-overhead]	1.6051ms	1.0667ms	937.5009 Ops/s	836.3832 Ops/s	$\textbf{\color{#35bf28}+12.09\%}$
test_seq_add[eager]	0.2672ms	0.1130ms	8.8489 KOps/s	8.4933 KOps/s	$\color{#35bf28}+4.19\%$
test_seq_add[compile]	0.2474ms	89.9250μs	11.1204 KOps/s	11.1823 KOps/s	$\color{#d91a1a}-0.55\%$
test_seq_add[compile-overhead]	0.3169ms	0.1292ms	7.7410 KOps/s	7.5706 KOps/s	$\color{#35bf28}+2.25\%$
test_seq_wrap[eager]	1.8089ms	0.4269ms	2.3422 KOps/s	2.2579 KOps/s	$\color{#35bf28}+3.73\%$
test_seq_wrap[compile]	0.4838ms	0.3120ms	3.2048 KOps/s	3.2427 KOps/s	$\color{#d91a1a}-1.17\%$
test_seq_wrap[compile-overhead]	0.3648ms	0.2280ms	4.3859 KOps/s	4.3154 KOps/s	$\color{#35bf28}+1.63\%$
test_func_call_runtime[False-eager]	0.9704ms	0.7839ms	1.2756 KOps/s	1.2604 KOps/s	$\color{#35bf28}+1.21\%$
test_func_call_runtime[False-compile]	1.2072ms	0.7488ms	1.3355 KOps/s	1.2827 KOps/s	$\color{#35bf28}+4.12\%$
test_func_call_runtime[False-compile-overhead]	0.5336ms	0.3632ms	2.7531 KOps/s	2.7003 KOps/s	$\color{#35bf28}+1.96\%$
test_func_call_runtime[True-eager]	1.0857ms	0.9150ms	1.0929 KOps/s	1.0885 KOps/s	$\color{#35bf28}+0.41\%$
test_func_call_runtime[True-compile]	0.9269ms	0.7745ms	1.2912 KOps/s	1.2875 KOps/s	$\color{#35bf28}+0.28\%$
test_func_call_runtime[True-compile-overhead]	0.5196ms	0.3881ms	2.5770 KOps/s	2.5628 KOps/s	$\color{#35bf28}+0.55\%$
test_func_call_cm_runtime[False-eager]	1.0107ms	0.8003ms	1.2496 KOps/s	1.3227 KOps/s	$\textbf{\color{#d91a1a}-5.52\%}$
test_func_call_cm_runtime[False-compile]	0.9501ms	0.7533ms	1.3275 KOps/s	1.3156 KOps/s	$\color{#35bf28}+0.90\%$
test_func_call_cm_runtime[False-compile-overhead]	0.5677ms	0.3663ms	2.7302 KOps/s	2.6835 KOps/s	$\color{#35bf28}+1.74\%$
test_func_call_cm_runtime[True-eager]	1.1953ms	1.0209ms	979.5592 Ops/s	961.4674 Ops/s	$\color{#35bf28}+1.88\%$
test_func_call_cm_runtime[True-compile]	1.2524ms	1.0357ms	965.5459 Ops/s	977.6814 Ops/s	$\color{#d91a1a}-1.24\%$
test_func_call_cm_runtime[True-compile-overhead]	1.2114ms	1.0288ms	971.9859 Ops/s	958.1894 Ops/s	$\color{#35bf28}+1.44\%$
test_vmap_func_call_cm_runtime[eager]	2.5069ms	2.1049ms	475.0757 Ops/s	470.5979 Ops/s	$\color{#35bf28}+0.95\%$
test_vmap_func_call_cm_runtime[compile]	0.9697ms	0.8113ms	1.2326 KOps/s	1.2083 KOps/s	$\color{#35bf28}+2.01\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.5809ms	0.4222ms	2.3683 KOps/s	2.3553 KOps/s	$\color{#35bf28}+0.55\%$
test_distributed	2.5170ms	0.1824ms	5.4825 KOps/s	8.4820 KOps/s	$\textbf{\color{#d91a1a}-35.36\%}$
test_tdmodule	0.1697ms	20.1735μs	49.5700 KOps/s	47.1064 KOps/s	$\textbf{\color{#35bf28}+5.23\%}$
test_tdmodule_dispatch	74.1310μs	32.9283μs	30.3690 KOps/s	28.1470 KOps/s	$\textbf{\color{#35bf28}+7.89\%}$
test_tdseq	42.1910μs	19.2230μs	52.0209 KOps/s	46.9865 KOps/s	$\textbf{\color{#35bf28}+10.71\%}$
test_tdseq_dispatch	68.9210μs	35.2773μs	28.3468 KOps/s	25.7104 KOps/s	$\textbf{\color{#35bf28}+10.25\%}$
test_instantiation_functorch	1.7045ms	1.5396ms	649.5159 Ops/s	643.1221 Ops/s	$\color{#35bf28}+0.99\%$
test_exec_functorch	0.3021ms	0.1440ms	6.9430 KOps/s	6.8332 KOps/s	$\color{#35bf28}+1.61\%$
test_exec_functional_call	0.2438ms	0.1376ms	7.2699 KOps/s	7.1574 KOps/s	$\color{#35bf28}+1.57\%$
test_exec_td_decorator	0.3752ms	0.1867ms	5.3576 KOps/s	5.2678 KOps/s	$\color{#35bf28}+1.70\%$
test_vmap_mlp_speed_decorator[True-True]	0.8779ms	0.6854ms	1.4590 KOps/s	1.4505 KOps/s	$\color{#35bf28}+0.59\%$
test_vmap_mlp_speed_decorator[True-False]	0.8852ms	0.6859ms	1.4579 KOps/s	1.4487 KOps/s	$\color{#35bf28}+0.64\%$
test_vmap_mlp_speed_decorator[False-True]	0.7573ms	0.6002ms	1.6660 KOps/s	1.6685 KOps/s	$\color{#d91a1a}-0.15\%$
test_vmap_mlp_speed_decorator[False-False]	0.7807ms	0.6002ms	1.6662 KOps/s	1.6696 KOps/s	$\color{#d91a1a}-0.20\%$
test_vmap_transformer_speed_decorator[True-True]	20.1787ms	19.3692ms	51.6284 Ops/s	51.5075 Ops/s	$\color{#35bf28}+0.23\%$
test_vmap_transformer_speed_decorator[True-False]	19.6449ms	19.3316ms	51.7287 Ops/s	51.6116 Ops/s	$\color{#35bf28}+0.23\%$
test_vmap_transformer_speed_decorator[False-True]	19.5940ms	19.2216ms	52.0248 Ops/s	51.9914 Ops/s	$\color{#35bf28}+0.06\%$
test_vmap_transformer_speed_decorator[False-False]	19.4219ms	19.2002ms	52.0827 Ops/s	52.0644 Ops/s	$\color{#35bf28}+0.04\%$
test_to_module_speed[True]	1.5253ms	0.9608ms	1.0408 KOps/s	1.0470 KOps/s	$\color{#d91a1a}-0.59\%$
test_to_module_speed[False]	1.0022ms	0.9357ms	1.0687 KOps/s	1.0663 KOps/s	$\color{#35bf28}+0.22\%$
test_tc_init	54.6210μs	33.1583μs	30.1584 KOps/s	27.1418 KOps/s	$\textbf{\color{#35bf28}+11.11\%}$
test_tc_init_nested	0.1585ms	68.2771μs	14.6462 KOps/s	13.8952 KOps/s	$\textbf{\color{#35bf28}+5.40\%}$
test_tc_first_layer_tensor	21.6200μs	0.8080μs	1.2376 MOps/s	1.2461 MOps/s	$\color{#d91a1a}-0.68\%$
test_tc_first_layer_nontensor	21.8310μs	2.2219μs	450.0637 KOps/s	451.0852 KOps/s	$\color{#d91a1a}-0.23\%$
test_tc_second_layer_tensor	22.8810μs	1.5274μs	654.6923 KOps/s	704.2706 KOps/s	$\textbf{\color{#d91a1a}-7.04\%}$
test_tc_second_layer_nontensor	27.6610μs	2.9679μs	336.9350 KOps/s	338.3516 KOps/s	$\color{#d91a1a}-0.42\%$
test_unbind	7.3247ms	7.0033ms	142.7905 Ops/s	143.6961 Ops/s	$\color{#d91a1a}-0.63\%$
test_full_like	14.4592ms	11.1026ms	90.0686 Ops/s	88.9879 Ops/s	$\color{#35bf28}+1.21\%$
test_zeros_like	6.5990ms	4.6984ms	212.8383 Ops/s	110.5146 Ops/s	$\textbf{\color{#35bf28}+92.59\%}$
test_ones_like	5.7099ms	4.6866ms	213.3730 Ops/s	208.4638 Ops/s	$\color{#35bf28}+2.35\%$
test_clone	8.9898ms	7.6825ms	130.1666 Ops/s	128.5378 Ops/s	$\color{#35bf28}+1.27\%$
test_squeeze	0.1193ms	9.5409μs	104.8114 KOps/s	100.6283 KOps/s	$\color{#35bf28}+4.16\%$
test_unsqueeze	0.1661ms	71.6593μs	13.9549 KOps/s	13.7146 KOps/s	$\color{#35bf28}+1.75\%$
test_split	0.2491s	0.2364ms	4.2305 KOps/s	6.1933 KOps/s	$\textbf{\color{#d91a1a}-31.69\%}$
test_permute	0.3655ms	0.1789ms	5.5894 KOps/s	5.4790 KOps/s	$\color{#35bf28}+2.01\%$
test_stack	55.0638ms	53.6348ms	18.6446 Ops/s	18.8363 Ops/s	$\color{#d91a1a}-1.02\%$
test_cat	54.6280ms	53.6243ms	18.6483 Ops/s	18.8704 Ops/s	$\color{#d91a1a}-1.18\%$