[BE] tensorclass method registration check

[vmoens]

Stack from ghstack (oldest at bottom):

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

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}16$. Worsened: $\large\color{#d91a1a}8$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	72.8070μs	20.6935μs	48.3244 KOps/s	48.7615 KOps/s	$\color{#d91a1a}-0.90\%$
test_plain_set_stack_nested	49.3520μs	20.7352μs	48.2271 KOps/s	47.8774 KOps/s	$\color{#35bf28}+0.73\%$
test_plain_set_nested_inplace	53.6700μs	22.5084μs	44.4278 KOps/s	44.4559 KOps/s	$\color{#d91a1a}-0.06\%$
test_plain_set_stack_nested_inplace	68.1050μs	22.6917μs	44.0690 KOps/s	44.0396 KOps/s	$\color{#35bf28}+0.07\%$
test_items	21.0900μs	4.1740μs	239.5801 KOps/s	241.2721 KOps/s	$\color{#d91a1a}-0.70\%$
test_items_nested	0.5350ms	0.3915ms	2.5540 KOps/s	2.5084 KOps/s	$\color{#35bf28}+1.82\%$
test_items_nested_locked	0.6913ms	0.3944ms	2.5358 KOps/s	2.4977 KOps/s	$\color{#35bf28}+1.53\%$
test_items_nested_leaf	0.1486ms	78.0417μs	12.8137 KOps/s	12.8486 KOps/s	$\color{#d91a1a}-0.27\%$
test_items_stack_nested	0.7461ms	0.3929ms	2.5449 KOps/s	2.4908 KOps/s	$\color{#35bf28}+2.17\%$
test_items_stack_nested_leaf	0.1403ms	77.4047μs	12.9191 KOps/s	12.3950 KOps/s	$\color{#35bf28}+4.23\%$
test_items_stack_nested_locked	0.5807ms	0.3934ms	2.5416 KOps/s	2.5055 KOps/s	$\color{#35bf28}+1.44\%$
test_keys	23.1830μs	3.4832μs	287.0899 KOps/s	285.1479 KOps/s	$\color{#35bf28}+0.68\%$
test_keys_nested	0.2662ms	0.1596ms	6.2673 KOps/s	6.1289 KOps/s	$\color{#35bf28}+2.26\%$
test_keys_nested_locked	0.7469ms	0.1660ms	6.0231 KOps/s	5.8071 KOps/s	$\color{#35bf28}+3.72\%$
test_keys_nested_leaf	0.2323ms	0.1387ms	7.2103 KOps/s	7.0419 KOps/s	$\color{#35bf28}+2.39\%$
test_keys_stack_nested	0.2864ms	0.1603ms	6.2365 KOps/s	6.2298 KOps/s	$\color{#35bf28}+0.11\%$
test_keys_stack_nested_leaf	0.2260ms	0.1388ms	7.2054 KOps/s	7.3238 KOps/s	$\color{#d91a1a}-1.62\%$
test_keys_stack_nested_locked	0.3125ms	0.1670ms	5.9869 KOps/s	6.0397 KOps/s	$\color{#d91a1a}-0.87\%$
test_values	5.7410μs	1.0388μs	962.6054 KOps/s	961.2771 KOps/s	$\color{#35bf28}+0.14\%$
test_values_nested	0.1045ms	59.8105μs	16.7195 KOps/s	16.2511 KOps/s	$\color{#35bf28}+2.88\%$
test_values_nested_locked	0.1163ms	59.7280μs	16.7426 KOps/s	16.1724 KOps/s	$\color{#35bf28}+3.53\%$
test_values_nested_leaf	0.1247ms	69.3279μs	14.4242 KOps/s	13.0304 KOps/s	$\textbf{\color{#35bf28}+10.70\%}$
test_values_stack_nested	0.2095ms	60.2467μs	16.5984 KOps/s	15.8825 KOps/s	$\color{#35bf28}+4.51\%$
test_values_stack_nested_leaf	0.2310ms	70.8115μs	14.1220 KOps/s	14.1959 KOps/s	$\color{#d91a1a}-0.52\%$
test_values_stack_nested_locked	0.1453ms	60.4620μs	16.5393 KOps/s	15.6771 KOps/s	$\textbf{\color{#35bf28}+5.50\%}$
test_membership	5.9883μs	0.7014μs	1.4258 MOps/s	1.3989 MOps/s	$\color{#35bf28}+1.93\%$
test_membership_nested	18.5240μs	2.8764μs	347.6609 KOps/s	345.3337 KOps/s	$\color{#35bf28}+0.67\%$
test_membership_nested_leaf	56.2950μs	2.9436μs	339.7225 KOps/s	341.2766 KOps/s	$\color{#d91a1a}-0.46\%$
test_membership_stacked_nested	18.0530μs	2.9063μs	344.0793 KOps/s	344.6208 KOps/s	$\color{#d91a1a}-0.16\%$
test_membership_stacked_nested_leaf	22.4920μs	2.9213μs	342.3170 KOps/s	342.5003 KOps/s	$\color{#d91a1a}-0.05\%$
test_membership_nested_last	32.2400μs	4.2933μs	232.9219 KOps/s	228.7635 KOps/s	$\color{#35bf28}+1.82\%$
test_membership_nested_leaf_last	45.9750μs	4.3227μs	231.3395 KOps/s	227.4124 KOps/s	$\color{#35bf28}+1.73\%$
test_membership_stacked_nested_last	29.4550μs	4.3917μs	227.7019 KOps/s	74.6628 KOps/s	$\textbf{\color{#35bf28}+204.97\%}$
test_membership_stacked_nested_leaf_last	43.1000μs	4.3148μs	231.7595 KOps/s	75.1376 KOps/s	$\textbf{\color{#35bf28}+208.45\%}$
test_nested_getleaf	51.9470μs	10.4622μs	95.5822 KOps/s	93.7165 KOps/s	$\color{#35bf28}+1.99\%$
test_nested_get	42.8400μs	9.8233μs	101.7993 KOps/s	99.5929 KOps/s	$\color{#35bf28}+2.22\%$
test_stacked_getleaf	55.8240μs	10.3952μs	96.1985 KOps/s	89.2033 KOps/s	$\textbf{\color{#35bf28}+7.84\%}$
test_stacked_get	50.1930μs	9.8678μs	101.3395 KOps/s	99.3530 KOps/s	$\color{#35bf28}+2.00\%$
test_nested_getitemleaf	35.4570μs	10.7835μs	92.7345 KOps/s	90.2101 KOps/s	$\color{#35bf28}+2.80\%$
test_nested_getitem	46.6970μs	10.1186μs	98.8278 KOps/s	96.0723 KOps/s	$\color{#35bf28}+2.87\%$
test_stacked_getitemleaf	48.0700μs	10.8285μs	92.3492 KOps/s	90.6339 KOps/s	$\color{#35bf28}+1.89\%$
test_stacked_getitem	32.4610μs	10.0523μs	99.4800 KOps/s	98.1641 KOps/s	$\color{#35bf28}+1.34\%$
test_lock_nested	6.9413ms	0.4529ms	2.2081 KOps/s	1.8389 KOps/s	$\textbf{\color{#35bf28}+20.08\%}$
test_lock_stack_nested	0.7661ms	0.4226ms	2.3664 KOps/s	2.4528 KOps/s	$\color{#d91a1a}-3.52\%$
test_unlock_nested	0.7317ms	0.3645ms	2.7438 KOps/s	2.7197 KOps/s	$\color{#35bf28}+0.89\%$
test_unlock_stack_nested	0.5485ms	0.3439ms	2.9080 KOps/s	3.0192 KOps/s	$\color{#d91a1a}-3.68\%$
test_flatten_speed	0.1986ms	0.1009ms	9.9132 KOps/s	9.9567 KOps/s	$\color{#d91a1a}-0.44\%$
test_unflatten_speed	0.6713ms	0.5191ms	1.9266 KOps/s	1.9623 KOps/s	$\color{#d91a1a}-1.82\%$
test_common_ops	4.7545ms	0.7801ms	1.2818 KOps/s	1.2594 KOps/s	$\color{#35bf28}+1.78\%$
test_creation	27.5510μs	2.5011μs	399.8305 KOps/s	408.4852 KOps/s	$\color{#d91a1a}-2.12\%$
test_creation_empty	56.6840μs	12.2271μs	81.7857 KOps/s	81.1567 KOps/s	$\color{#35bf28}+0.77\%$
test_creation_nested_1	1.3248ms	15.0030μs	66.6535 KOps/s	66.5134 KOps/s	$\color{#35bf28}+0.21\%$
test_creation_nested_2	85.2190μs	19.7243μs	50.6988 KOps/s	51.4892 KOps/s	$\color{#d91a1a}-1.54\%$
test_clone	0.1896ms	13.2421μs	75.5169 KOps/s	72.8839 KOps/s	$\color{#35bf28}+3.61\%$
test_getitem[int]	0.9348ms	12.6741μs	78.9009 KOps/s	77.8809 KOps/s	$\color{#35bf28}+1.31\%$
test_getitem[slice_int]	0.1433ms	25.0482μs	39.9230 KOps/s	40.1229 KOps/s	$\color{#d91a1a}-0.50\%$
test_getitem[range]	0.1868ms	47.7068μs	20.9614 KOps/s	21.2789 KOps/s	$\color{#d91a1a}-1.49\%$
test_getitem[tuple]	0.1326ms	20.1266μs	49.6855 KOps/s	48.7375 KOps/s	$\color{#35bf28}+1.94\%$
test_getitem[list]	0.1753ms	42.6978μs	23.4204 KOps/s	23.1384 KOps/s	$\color{#35bf28}+1.22\%$
test_setitem_dim[int]	50.4740μs	24.1545μs	41.4002 KOps/s	40.8734 KOps/s	$\color{#35bf28}+1.29\%$
test_setitem_dim[slice_int]	70.2010μs	50.2609μs	19.8962 KOps/s	19.3553 KOps/s	$\color{#35bf28}+2.79\%$
test_setitem_dim[range]	0.1065ms	71.9606μs	13.8965 KOps/s	14.0476 KOps/s	$\color{#d91a1a}-1.08\%$
test_setitem_dim[tuple]	65.4930μs	39.2888μs	25.4526 KOps/s	24.4123 KOps/s	$\color{#35bf28}+4.26\%$
test_setitem	0.1029ms	20.3555μs	49.1267 KOps/s	48.6694 KOps/s	$\color{#35bf28}+0.94\%$
test_set	99.8660μs	19.8979μs	50.2565 KOps/s	49.2755 KOps/s	$\color{#35bf28}+1.99\%$
test_set_shared	1.0938ms	0.1632ms	6.1261 KOps/s	5.9739 KOps/s	$\color{#35bf28}+2.55\%$
test_update	0.3343ms	22.8716μs	43.7224 KOps/s	42.1219 KOps/s	$\color{#35bf28}+3.80\%$
test_update_nested	0.2198ms	32.9791μs	30.3222 KOps/s	29.4497 KOps/s	$\color{#35bf28}+2.96\%$
test_update__nested	0.8285ms	33.6083μs	29.7546 KOps/s	29.6478 KOps/s	$\color{#35bf28}+0.36\%$
test_set_nested	0.1313ms	21.9447μs	45.5691 KOps/s	44.6531 KOps/s	$\color{#35bf28}+2.05\%$
test_set_nested_new	0.1821ms	26.4759μs	37.7702 KOps/s	37.6111 KOps/s	$\color{#35bf28}+0.42\%$
test_select	0.1429ms	43.0020μs	23.2547 KOps/s	22.6028 KOps/s	$\color{#35bf28}+2.88\%$
test_select_nested	0.1247ms	63.8067μs	15.6723 KOps/s	15.7350 KOps/s	$\color{#d91a1a}-0.40\%$
test_exclude_nested	0.1526ms	83.0853μs	12.0358 KOps/s	12.2395 KOps/s	$\color{#d91a1a}-1.66\%$
test_empty[True]	0.7626ms	0.4064ms	2.4604 KOps/s	2.4431 KOps/s	$\color{#35bf28}+0.71\%$
test_empty[False]	10.9155μs	1.3661μs	732.0268 KOps/s	712.2683 KOps/s	$\color{#35bf28}+2.77\%$
test_unbind_speed	0.3115ms	0.2651ms	3.7724 KOps/s	3.8077 KOps/s	$\color{#d91a1a}-0.93\%$
test_unbind_speed_stack0	0.6432ms	0.2639ms	3.7889 KOps/s	3.9232 KOps/s	$\color{#d91a1a}-3.42\%$
test_unbind_speed_stack1	0.1066s	0.8055ms	1.2414 KOps/s	1.4391 KOps/s	$\textbf{\color{#d91a1a}-13.73\%}$
test_split	95.6954ms	1.7427ms	573.8202 Ops/s	574.7687 Ops/s	$\color{#d91a1a}-0.17\%$
test_chunk	0.1044s	1.7656ms	566.3756 Ops/s	571.4576 Ops/s	$\color{#d91a1a}-0.89\%$
test_consolidate_njt[False-None]	8.3333ms	7.9126ms	126.3804 Ops/s	123.2800 Ops/s	$\color{#35bf28}+2.51\%$
test_creation[device0]	0.1751ms	89.3319μs	11.1942 KOps/s	11.1094 KOps/s	$\color{#35bf28}+0.76\%$
test_creation_from_tensor	4.4608ms	93.3299μs	10.7147 KOps/s	10.8504 KOps/s	$\color{#d91a1a}-1.25\%$
test_add_one[memmap_tensor0]	0.2561ms	4.8818μs	204.8445 KOps/s	213.7791 KOps/s	$\color{#d91a1a}-4.18\%$
test_contiguous[memmap_tensor0]	17.2030μs	0.5023μs	1.9909 MOps/s	1.9342 MOps/s	$\color{#35bf28}+2.93\%$
test_stack[memmap_tensor0]	55.5240μs	3.4214μs	292.2776 KOps/s	290.6560 KOps/s	$\color{#35bf28}+0.56\%$
test_memmaptd_index	0.9973ms	0.2313ms	4.3233 KOps/s	4.2196 KOps/s	$\color{#35bf28}+2.46\%$
test_memmaptd_index_astensor	0.7229ms	0.3193ms	3.1314 KOps/s	3.1075 KOps/s	$\color{#35bf28}+0.77\%$
test_memmaptd_index_op	0.9807ms	0.5826ms	1.7163 KOps/s	1.6894 KOps/s	$\color{#35bf28}+1.59\%$
test_serialize_model	0.1229s	0.1145s	8.7342 Ops/s	8.6081 Ops/s	$\color{#35bf28}+1.46\%$
test_serialize_model_pickle	0.4451s	0.3874s	2.5812 Ops/s	2.5482 Ops/s	$\color{#35bf28}+1.29\%$
test_serialize_weights	0.2150s	0.1294s	7.7276 Ops/s	8.6965 Ops/s	$\textbf{\color{#d91a1a}-11.14\%}$
test_serialize_weights_returnearly	0.1913s	0.1550s	6.4514 Ops/s	6.5772 Ops/s	$\color{#d91a1a}-1.91\%$
test_serialize_weights_pickle	0.5127s	0.4458s	2.2431 Ops/s	1.0572 Ops/s	$\textbf{\color{#35bf28}+112.18\%}$
test_serialize_weights_filesystem	0.1464s	0.1413s	7.0758 Ops/s	7.1796 Ops/s	$\color{#d91a1a}-1.44\%$
test_serialize_model_filesystem	0.2563s	0.1615s	6.1914 Ops/s	6.3804 Ops/s	$\color{#d91a1a}-2.96\%$
test_reshape_pytree	82.3320μs	25.9369μs	38.5551 KOps/s	37.9145 KOps/s	$\color{#35bf28}+1.69\%$
test_reshape_td	76.9730μs	33.0919μs	30.2188 KOps/s	30.7369 KOps/s	$\color{#d91a1a}-1.69\%$
test_view_pytree	88.4440μs	26.1089μs	38.3011 KOps/s	38.1349 KOps/s	$\color{#35bf28}+0.44\%$
test_view_td	0.1113ms	37.6032μs	26.5935 KOps/s	26.0723 KOps/s	$\color{#35bf28}+2.00\%$
test_unbind_pytree	64.1590μs	28.7999μs	34.7223 KOps/s	34.1278 KOps/s	$\color{#35bf28}+1.74\%$
test_unbind_td	0.3304ms	39.1822μs	25.5218 KOps/s	25.6361 KOps/s	$\color{#d91a1a}-0.45\%$
test_split_pytree	68.8880μs	28.5472μs	35.0297 KOps/s	34.5108 KOps/s	$\color{#35bf28}+1.50\%$
test_split_td	0.4802ms	44.7146μs	22.3641 KOps/s	22.5970 KOps/s	$\color{#d91a1a}-1.03\%$
test_add_pytree	96.1390μs	35.2706μs	28.3522 KOps/s	28.9247 KOps/s	$\color{#d91a1a}-1.98\%$
test_add_td	0.1264ms	55.8510μs	17.9048 KOps/s	18.1223 KOps/s	$\color{#d91a1a}-1.20\%$
test_compile_add_one_nested[tensordict-compile]	0.1144ms	61.6238μs	16.2275 KOps/s	15.8932 KOps/s	$\color{#35bf28}+2.10\%$
test_compile_add_one_nested[tensordict-eager]	0.5026ms	0.1745ms	5.7310 KOps/s	5.7383 KOps/s	$\color{#d91a1a}-0.13\%$
test_compile_add_one_nested[pytree-compile]	0.1100ms	44.8545μs	22.2943 KOps/s	22.0495 KOps/s	$\color{#35bf28}+1.11\%$
test_compile_add_one_nested[pytree-eager]	0.2205ms	0.1165ms	8.5829 KOps/s	8.5959 KOps/s	$\color{#d91a1a}-0.15\%$
test_compile_copy_nested[tensordict-compile]	70.5420μs	25.0769μs	39.8773 KOps/s	38.1070 KOps/s	$\color{#35bf28}+4.65\%$
test_compile_copy_nested[tensordict-eager]	0.1236ms	58.2545μs	17.1661 KOps/s	17.0514 KOps/s	$\color{#35bf28}+0.67\%$
test_compile_copy_nested[pytree-compile]	0.1469ms	76.7805μs	13.0241 KOps/s	12.8222 KOps/s	$\color{#35bf28}+1.58\%$
test_compile_copy_nested[pytree-eager]	0.1238ms	66.4993μs	15.0378 KOps/s	14.9950 KOps/s	$\color{#35bf28}+0.29\%$
test_compile_add_one_flat[tensordict-compile]	0.2468ms	0.1058ms	9.4491 KOps/s	9.5190 KOps/s	$\color{#d91a1a}-0.73\%$
test_compile_add_one_flat[tensordict-eager]	0.3774ms	0.2132ms	4.6893 KOps/s	4.6993 KOps/s	$\color{#d91a1a}-0.21\%$
test_compile_add_one_flat[tensorclass-compile]	0.1543ms	45.2673μs	22.0910 KOps/s	22.7816 KOps/s	$\color{#d91a1a}-3.03\%$
test_compile_add_one_flat[tensorclass-eager]	0.5108ms	66.2824μs	15.0870 KOps/s	15.2306 KOps/s	$\color{#d91a1a}-0.94\%$
test_compile_add_one_flat[pytree-compile]	0.2233ms	0.1033ms	9.6832 KOps/s	9.7527 KOps/s	$\color{#d91a1a}-0.71\%$
test_compile_add_one_flat[pytree-eager]	0.3399ms	0.2011ms	4.9731 KOps/s	5.0475 KOps/s	$\color{#d91a1a}-1.47\%$
test_compile_add_self_flat[tensordict-eager]	0.5097ms	0.2327ms	4.2976 KOps/s	4.3190 KOps/s	$\color{#d91a1a}-0.49\%$
test_compile_add_self_flat[tensordict-compile]	0.2102ms	0.1078ms	9.2791 KOps/s	9.5520 KOps/s	$\color{#d91a1a}-2.86\%$
test_compile_add_self_flat[tensorclass-eager]	0.2465ms	62.5246μs	15.9937 KOps/s	15.7434 KOps/s	$\color{#35bf28}+1.59\%$
test_compile_add_self_flat[tensorclass-compile]	0.2099ms	46.7066μs	21.4102 KOps/s	22.1575 KOps/s	$\color{#d91a1a}-3.37\%$
test_compile_add_self_flat[pytree-eager]	1.5116ms	0.1571ms	6.3664 KOps/s	6.4653 KOps/s	$\color{#d91a1a}-1.53\%$
test_compile_add_self_flat[pytree-compile]	0.2416ms	0.1023ms	9.7745 KOps/s	9.7607 KOps/s	$\color{#35bf28}+0.14\%$
test_compile_copy_flat[tensordict-compile]	83.3640μs	20.7205μs	48.2615 KOps/s	45.3586 KOps/s	$\textbf{\color{#35bf28}+6.40\%}$
test_compile_copy_flat[tensordict-eager]	0.1106ms	66.7660μs	14.9777 KOps/s	14.7870 KOps/s	$\color{#35bf28}+1.29\%$
test_compile_copy_flat[pytree-compile]	0.1556ms	78.3469μs	12.7637 KOps/s	12.9995 KOps/s	$\color{#d91a1a}-1.81\%$
test_compile_copy_flat[pytree-eager]	0.1247ms	66.3296μs	15.0762 KOps/s	15.0020 KOps/s	$\color{#35bf28}+0.49\%$
test_compile_assign_and_add[tensordict-compile]	0.3513ms	0.2038ms	4.9070 KOps/s	5.0002 KOps/s	$\color{#d91a1a}-1.86\%$
test_compile_assign_and_add[tensordict-eager]	1.4950ms	1.3026ms	767.7052 Ops/s	774.2749 Ops/s	$\color{#d91a1a}-0.85\%$
test_compile_assign_and_add[pytree-compile]	0.3026ms	0.2010ms	4.9761 KOps/s	4.9627 KOps/s	$\color{#35bf28}+0.27\%$
test_compile_assign_and_add[pytree-eager]	1.2939ms	0.7651ms	1.3071 KOps/s	1.3139 KOps/s	$\color{#d91a1a}-0.52\%$
test_compile_assign_and_add_stack[compile]	0.5653ms	0.4546ms	2.1998 KOps/s	2.2195 KOps/s	$\color{#d91a1a}-0.89\%$
test_compile_assign_and_add_stack[eager]	4.2864ms	2.6505ms	377.2939 Ops/s	370.6825 Ops/s	$\color{#35bf28}+1.78\%$
test_compile_indexing[tensor-tensordict-compile]	0.1354ms	34.9416μs	28.6192 KOps/s	28.5266 KOps/s	$\color{#35bf28}+0.32\%$
test_compile_indexing[tensor-tensordict-eager]	0.5187ms	32.5290μs	30.7418 KOps/s	31.4318 KOps/s	$\color{#d91a1a}-2.20\%$
test_compile_indexing[tensor-tensorclass-compile]	0.1011ms	28.8249μs	34.6922 KOps/s	35.3447 KOps/s	$\color{#d91a1a}-1.85\%$
test_compile_indexing[tensor-tensorclass-eager]	73.2960μs	23.6253μs	42.3275 KOps/s	45.5115 KOps/s	$\textbf{\color{#d91a1a}-7.00\%}$
test_compile_indexing[tensor-pytree-compile]	98.8350μs	30.3368μs	32.9633 KOps/s	34.2335 KOps/s	$\color{#d91a1a}-3.71\%$
test_compile_indexing[tensor-pytree-eager]	93.2940μs	23.3429μs	42.8395 KOps/s	45.0875 KOps/s	$\color{#d91a1a}-4.99\%$
test_compile_indexing[slice-tensordict-compile]	0.1104ms	52.3719μs	19.0942 KOps/s	19.7279 KOps/s	$\color{#d91a1a}-3.21\%$
test_compile_indexing[slice-tensordict-eager]	0.2253s	26.8468μs	37.2484 KOps/s	48.6644 KOps/s	$\textbf{\color{#d91a1a}-23.46\%}$
test_compile_indexing[slice-tensorclass-compile]	0.1092ms	44.8968μs	22.2733 KOps/s	23.6048 KOps/s	$\textbf{\color{#d91a1a}-5.64\%}$
test_compile_indexing[slice-tensorclass-eager]	79.8790μs	18.1904μs	54.9741 KOps/s	54.0405 KOps/s	$\color{#35bf28}+1.73\%$
test_compile_indexing[slice-pytree-compile]	98.6140μs	45.3065μs	22.0719 KOps/s	22.8659 KOps/s	$\color{#d91a1a}-3.47\%$
test_compile_indexing[slice-pytree-eager]	50.7350μs	18.3022μs	54.6383 KOps/s	54.5337 KOps/s	$\color{#35bf28}+0.19\%$
test_compile_indexing[int-tensordict-compile]	0.1416ms	52.6367μs	18.9982 KOps/s	19.4444 KOps/s	$\color{#d91a1a}-2.30\%$
test_compile_indexing[int-tensordict-eager]	1.0088ms	19.5411μs	51.1742 KOps/s	49.2851 KOps/s	$\color{#35bf28}+3.83\%$
test_compile_indexing[int-tensorclass-compile]	0.1104ms	45.4339μs	22.0100 KOps/s	22.8290 KOps/s	$\color{#d91a1a}-3.59\%$
test_compile_indexing[int-tensorclass-eager]	92.9950μs	18.2049μs	54.9302 KOps/s	54.7499 KOps/s	$\color{#35bf28}+0.33\%$
test_compile_indexing[int-pytree-compile]	98.9140μs	45.5159μs	21.9703 KOps/s	22.8842 KOps/s	$\color{#d91a1a}-3.99\%$
test_compile_indexing[int-pytree-eager]	77.2240μs	18.2325μs	54.8472 KOps/s	54.9159 KOps/s	$\color{#d91a1a}-0.12\%$
test_mod_add[eager]	82.9250μs	33.8703μs	29.5244 KOps/s	28.2363 KOps/s	$\color{#35bf28}+4.56\%$
test_mod_add[compile]	0.1127ms	47.2832μs	21.1492 KOps/s	21.0773 KOps/s	$\color{#35bf28}+0.34\%$
test_mod_add[compile-overhead]	0.1101ms	46.5834μs	21.4669 KOps/s	21.1805 KOps/s	$\color{#35bf28}+1.35\%$
test_mod_wrap[eager]	0.3806ms	0.2206ms	4.5340 KOps/s	4.4446 KOps/s	$\color{#35bf28}+2.01\%$
test_mod_wrap[compile]	0.3772ms	0.2042ms	4.8972 KOps/s	4.8578 KOps/s	$\color{#35bf28}+0.81\%$
test_mod_wrap[compile-overhead]	0.3138ms	0.2003ms	4.9936 KOps/s	4.8956 KOps/s	$\color{#35bf28}+2.00\%$
test_mod_wrap_and_backward[eager]	15.8141ms	12.0859ms	82.7410 Ops/s	76.0383 Ops/s	$\textbf{\color{#35bf28}+8.81\%}$
test_mod_wrap_and_backward[compile]	19.0075ms	14.2760ms	70.0478 Ops/s	76.3733 Ops/s	$\textbf{\color{#d91a1a}-8.28\%}$
test_mod_wrap_and_backward[compile-overhead]	20.1232ms	14.0829ms	71.0079 Ops/s	79.1028 Ops/s	$\textbf{\color{#d91a1a}-10.23\%}$
test_seq_add[eager]	0.2057ms	0.1098ms	9.1076 KOps/s	8.4578 KOps/s	$\textbf{\color{#35bf28}+7.68\%}$
test_seq_add[compile]	0.1664ms	61.2645μs	16.3227 KOps/s	15.9999 KOps/s	$\color{#35bf28}+2.02\%$
test_seq_add[compile-overhead]	0.1261ms	60.8943μs	16.4219 KOps/s	16.8348 KOps/s	$\color{#d91a1a}-2.45\%$
test_seq_wrap[eager]	0.6184ms	0.4276ms	2.3385 KOps/s	2.2266 KOps/s	$\textbf{\color{#35bf28}+5.03\%}$
test_seq_wrap[compile]	0.4338ms	0.2249ms	4.4470 KOps/s	4.4209 KOps/s	$\color{#35bf28}+0.59\%$
test_seq_wrap[compile-overhead]	0.4434ms	0.2227ms	4.4900 KOps/s	4.4082 KOps/s	$\color{#35bf28}+1.86\%$
test_func_call_runtime[False-eager]	0.9482ms	0.5251ms	1.9044 KOps/s	1.8153 KOps/s	$\color{#35bf28}+4.91\%$
test_func_call_runtime[False-compile]	0.5912ms	0.4219ms	2.3705 KOps/s	2.3921 KOps/s	$\color{#d91a1a}-0.91\%$
test_func_call_runtime[False-compile-overhead]	0.5791ms	0.4224ms	2.3676 KOps/s	2.3865 KOps/s	$\color{#d91a1a}-0.79\%$
test_func_call_runtime[True-eager]	1.4825ms	0.7442ms	1.3437 KOps/s	1.3017 KOps/s	$\color{#35bf28}+3.23\%$
test_func_call_runtime[True-compile]	0.6195ms	0.4620ms	2.1647 KOps/s	2.1780 KOps/s	$\color{#d91a1a}-0.61\%$
test_func_call_runtime[True-compile-overhead]	0.7441ms	0.4641ms	2.1549 KOps/s	2.1747 KOps/s	$\color{#d91a1a}-0.91\%$
test_func_call_cm_runtime[False-eager]	1.1180ms	0.5254ms	1.9034 KOps/s	1.8237 KOps/s	$\color{#35bf28}+4.37\%$
test_func_call_cm_runtime[False-compile]	0.5934ms	0.4232ms	2.3630 KOps/s	2.3734 KOps/s	$\color{#d91a1a}-0.44\%$
test_func_call_cm_runtime[False-compile-overhead]	0.7863ms	0.4221ms	2.3689 KOps/s	2.3736 KOps/s	$\color{#d91a1a}-0.20\%$
test_func_call_cm_runtime[True-eager]	1.2083ms	0.8855ms	1.1293 KOps/s	1.0930 KOps/s	$\color{#35bf28}+3.33\%$
test_func_call_cm_runtime[True-compile]	0.7814ms	0.4866ms	2.0552 KOps/s	2.0597 KOps/s	$\color{#d91a1a}-0.22\%$
test_func_call_cm_runtime[True-compile-overhead]	0.5715ms	0.4844ms	2.0644 KOps/s	2.0776 KOps/s	$\color{#d91a1a}-0.64\%$
test_vmap_func_call_cm_runtime[eager]	2.5472ms	1.8546ms	539.2028 Ops/s	528.0935 Ops/s	$\color{#35bf28}+2.10\%$
test_vmap_func_call_cm_runtime[compile]	1.0252ms	0.5068ms	1.9732 KOps/s	1.9308 KOps/s	$\color{#35bf28}+2.20\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.8353ms	0.5060ms	1.9764 KOps/s	1.9210 KOps/s	$\color{#35bf28}+2.88\%$
test_distributed	0.2527ms	0.1248ms	8.0113 KOps/s	7.7968 KOps/s	$\color{#35bf28}+2.75\%$
test_tdmodule	84.8780μs	26.0086μs	38.4488 KOps/s	37.7190 KOps/s	$\color{#35bf28}+1.93\%$
test_tdmodule_dispatch	67.3050μs	47.5045μs	21.0506 KOps/s	20.2502 KOps/s	$\color{#35bf28}+3.95\%$
test_tdseq	51.3450μs	28.8926μs	34.6110 KOps/s	33.7601 KOps/s	$\color{#35bf28}+2.52\%$
test_tdseq_dispatch	0.1067ms	55.7215μs	17.9464 KOps/s	18.0771 KOps/s	$\color{#d91a1a}-0.72\%$
test_instantiation_functorch	1.7538ms	1.5107ms	661.9592 Ops/s	663.3117 Ops/s	$\color{#d91a1a}-0.20\%$
test_exec_functorch	0.3156ms	0.1789ms	5.5903 KOps/s	5.6075 KOps/s	$\color{#d91a1a}-0.31\%$
test_exec_functional_call	0.2764ms	0.1696ms	5.8960 KOps/s	5.6643 KOps/s	$\color{#35bf28}+4.09\%$
test_exec_td_decorator	0.4593ms	0.2303ms	4.3426 KOps/s	4.2917 KOps/s	$\color{#35bf28}+1.19\%$
test_vmap_mlp_speed_decorator[True-True]	0.9125ms	0.6483ms	1.5425 KOps/s	1.5036 KOps/s	$\color{#35bf28}+2.59\%$
test_vmap_mlp_speed_decorator[True-False]	0.9970ms	0.6511ms	1.5358 KOps/s	1.5392 KOps/s	$\color{#d91a1a}-0.22\%$
test_vmap_mlp_speed_decorator[False-True]	0.9013ms	0.5234ms	1.9107 KOps/s	1.8914 KOps/s	$\color{#35bf28}+1.02\%$
test_vmap_mlp_speed_decorator[False-False]	0.7130ms	0.5181ms	1.9302 KOps/s	1.9043 KOps/s	$\color{#35bf28}+1.36\%$
test_to_module_speed[True]	1.4353ms	1.3476ms	742.0738 Ops/s	741.1508 Ops/s	$\color{#35bf28}+0.12\%$
test_to_module_speed[False]	1.4485ms	1.3202ms	757.4786 Ops/s	761.9892 Ops/s	$\color{#d91a1a}-0.59\%$
test_tc_init	87.0730μs	46.9506μs	21.2990 KOps/s	20.9042 KOps/s	$\color{#35bf28}+1.89\%$
test_tc_init_nested	0.1660ms	93.6580μs	10.6771 KOps/s	10.6656 KOps/s	$\color{#35bf28}+0.11\%$
test_tc_first_layer_tensor	21.2190μs	1.5411μs	648.8765 KOps/s	618.0984 KOps/s	$\color{#35bf28}+4.98\%$
test_tc_first_layer_nontensor	40.9360μs	4.7452μs	210.7372 KOps/s	211.0905 KOps/s	$\color{#d91a1a}-0.17\%$
test_tc_second_layer_tensor	22.5420μs	2.8364μs	352.5557 KOps/s	326.6966 KOps/s	$\textbf{\color{#35bf28}+7.92\%}$
test_tc_second_layer_nontensor	49.0020μs	6.0594μs	165.0335 KOps/s	160.1962 KOps/s	$\color{#35bf28}+3.02\%$
test_unbind	0.2259s	15.3801ms	65.0190 Ops/s	77.4587 Ops/s	$\textbf{\color{#d91a1a}-16.06\%}$
test_full_like	9.1285ms	7.3176ms	136.6575 Ops/s	78.2297 Ops/s	$\textbf{\color{#35bf28}+74.69\%}$
test_zeros_like	3.6504ms	2.8366ms	352.5354 Ops/s	135.8892 Ops/s	$\textbf{\color{#35bf28}+159.43\%}$
test_ones_like	3.9914ms	3.3897ms	295.0140 Ops/s	125.1957 Ops/s	$\textbf{\color{#35bf28}+135.64\%}$
test_clone	5.9382ms	5.3240ms	187.8273 Ops/s	95.4286 Ops/s	$\textbf{\color{#35bf28}+96.82\%}$
test_squeeze	60.2930μs	11.8352μs	84.4940 KOps/s	82.8821 KOps/s	$\color{#35bf28}+1.94\%$
test_unsqueeze	0.1483ms	90.5516μs	11.0434 KOps/s	11.4169 KOps/s	$\color{#d91a1a}-3.27\%$
test_split	0.4797ms	0.1910ms	5.2366 KOps/s	5.1704 KOps/s	$\color{#35bf28}+1.28\%$
test_permute	0.2868ms	0.1957ms	5.1111 KOps/s	4.9885 KOps/s	$\color{#35bf28}+2.46\%$
test_stack	31.7992ms	25.5552ms	39.1309 Ops/s	37.3607 Ops/s	$\color{#35bf28}+4.74\%$
test_cat	32.4882ms	25.6764ms	38.9462 Ops/s	37.6666 Ops/s	$\color{#35bf28}+3.40\%$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}54$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	38.1020μs	11.2582μs	88.8240 KOps/s	77.2915 KOps/s	$\textbf{\color{#35bf28}+14.92\%}$
test_plain_set_stack_nested	45.2920μs	11.3696μs	87.9537 KOps/s	76.5281 KOps/s	$\textbf{\color{#35bf28}+14.93\%}$
test_plain_set_nested_inplace	38.8210μs	12.4365μs	80.4083 KOps/s	71.1978 KOps/s	$\textbf{\color{#35bf28}+12.94\%}$
test_plain_set_stack_nested_inplace	47.7920μs	12.3681μs	80.8530 KOps/s	71.1443 KOps/s	$\textbf{\color{#35bf28}+13.65\%}$
test_items	41.4220μs	2.9037μs	344.3860 KOps/s	340.6185 KOps/s	$\color{#35bf28}+1.11\%$
test_items_nested	0.4080ms	0.3649ms	2.7408 KOps/s	2.7799 KOps/s	$\color{#d91a1a}-1.41\%$
test_items_nested_locked	0.4447ms	0.3649ms	2.7406 KOps/s	2.7554 KOps/s	$\color{#d91a1a}-0.54\%$
test_items_nested_leaf	86.9220μs	58.2760μs	17.1597 KOps/s	17.0954 KOps/s	$\color{#35bf28}+0.38\%$
test_items_stack_nested	0.4100ms	0.3634ms	2.7522 KOps/s	2.7421 KOps/s	$\color{#35bf28}+0.37\%$
test_items_stack_nested_leaf	95.8240μs	61.3595μs	16.2974 KOps/s	16.6788 KOps/s	$\color{#d91a1a}-2.29\%$
test_items_stack_nested_locked	0.4158ms	0.3678ms	2.7188 KOps/s	2.7231 KOps/s	$\color{#d91a1a}-0.16\%$
test_keys	27.0620μs	3.4838μs	287.0393 KOps/s	287.2589 KOps/s	$\color{#d91a1a}-0.08\%$
test_keys_nested	0.1193ms	82.0266μs	12.1912 KOps/s	12.4320 KOps/s	$\color{#d91a1a}-1.94\%$
test_keys_nested_locked	0.4891ms	87.7235μs	11.3994 KOps/s	11.4261 KOps/s	$\color{#d91a1a}-0.23\%$
test_keys_nested_leaf	0.1078ms	72.9958μs	13.6994 KOps/s	13.9644 KOps/s	$\color{#d91a1a}-1.90\%$
test_keys_stack_nested	0.1224ms	83.6243μs	11.9582 KOps/s	12.2403 KOps/s	$\color{#d91a1a}-2.30\%$
test_keys_stack_nested_leaf	0.1128ms	75.3265μs	13.2755 KOps/s	13.7611 KOps/s	$\color{#d91a1a}-3.53\%$
test_keys_stack_nested_locked	0.1226ms	89.5935μs	11.1615 KOps/s	11.3946 KOps/s	$\color{#d91a1a}-2.05\%$
test_values	7.3087μs	0.8458μs	1.1823 MOps/s	1.1711 MOps/s	$\color{#35bf28}+0.95\%$
test_values_nested	76.3530μs	35.0487μs	28.5317 KOps/s	29.0421 KOps/s	$\color{#d91a1a}-1.76\%$
test_values_nested_locked	65.0330μs	36.7354μs	27.2217 KOps/s	27.5199 KOps/s	$\color{#d91a1a}-1.08\%$
test_values_nested_leaf	67.2330μs	39.7201μs	25.1762 KOps/s	25.4610 KOps/s	$\color{#d91a1a}-1.12\%$
test_values_stack_nested	91.4040μs	35.2841μs	28.3414 KOps/s	28.6281 KOps/s	$\color{#d91a1a}-1.00\%$
test_values_stack_nested_leaf	70.4530μs	40.2704μs	24.8322 KOps/s	25.4807 KOps/s	$\color{#d91a1a}-2.55\%$
test_values_stack_nested_locked	79.7540μs	37.4889μs	26.6745 KOps/s	27.2783 KOps/s	$\color{#d91a1a}-2.21\%$
test_membership	2.0831μs	0.5135μs	1.9474 MOps/s	1.9664 MOps/s	$\color{#d91a1a}-0.97\%$
test_membership_nested	16.6260μs	2.0179μs	495.5575 KOps/s	476.7464 KOps/s	$\color{#35bf28}+3.95\%$
test_membership_nested_leaf	14.8410μs	2.0327μs	491.9456 KOps/s	496.7248 KOps/s	$\color{#d91a1a}-0.96\%$
test_membership_stacked_nested	43.4420μs	1.9898μs	502.5728 KOps/s	474.0548 KOps/s	$\textbf{\color{#35bf28}+6.02\%}$
test_membership_stacked_nested_leaf	23.7210μs	2.0793μs	480.9337 KOps/s	472.9376 KOps/s	$\color{#35bf28}+1.69\%$
test_membership_nested_last	25.6410μs	3.0995μs	322.6279 KOps/s	320.0863 KOps/s	$\color{#35bf28}+0.79\%$
test_membership_nested_leaf_last	33.7110μs	3.1305μs	319.4425 KOps/s	316.8745 KOps/s	$\color{#35bf28}+0.81\%$
test_membership_stacked_nested_last	32.0810μs	3.8603μs	259.0471 KOps/s	122.2627 KOps/s	$\textbf{\color{#35bf28}+111.88\%}$
test_membership_stacked_nested_leaf_last	47.9920μs	3.8516μs	259.6354 KOps/s	121.3591 KOps/s	$\textbf{\color{#35bf28}+113.94\%}$
test_nested_getleaf	42.5110μs	6.1655μs	162.1934 KOps/s	160.9658 KOps/s	$\color{#35bf28}+0.76\%$
test_nested_get	35.8110μs	5.8846μs	169.9352 KOps/s	169.0797 KOps/s	$\color{#35bf28}+0.51\%$
test_stacked_getleaf	42.7620μs	6.1736μs	161.9805 KOps/s	163.0061 KOps/s	$\color{#d91a1a}-0.63\%$
test_stacked_get	39.9120μs	5.9229μs	168.8367 KOps/s	171.5056 KOps/s	$\color{#d91a1a}-1.56\%$
test_nested_getitemleaf	49.3320μs	6.3434μs	157.6453 KOps/s	159.2399 KOps/s	$\color{#d91a1a}-1.00\%$
test_nested_getitem	34.3010μs	5.9131μs	169.1155 KOps/s	166.2209 KOps/s	$\color{#35bf28}+1.74\%$
test_stacked_getitemleaf	59.1230μs	6.2529μs	159.9257 KOps/s	159.9304 KOps/s	$-0.00\%$
test_stacked_getitem	28.8310μs	5.9312μs	168.6004 KOps/s	168.4859 KOps/s	$\color{#35bf28}+0.07\%$
test_lock_nested	9.7685ms	0.3881ms	2.5764 KOps/s	2.5800 KOps/s	$\color{#d91a1a}-0.14\%$
test_lock_stack_nested	0.4147ms	0.3519ms	2.8416 KOps/s	2.8715 KOps/s	$\color{#d91a1a}-1.04\%$
test_unlock_nested	0.6863ms	0.3182ms	3.1424 KOps/s	3.1216 KOps/s	$\color{#35bf28}+0.67\%$
test_unlock_stack_nested	0.3371ms	0.2900ms	3.4485 KOps/s	3.5451 KOps/s	$\color{#d91a1a}-2.72\%$
test_flatten_speed	0.1066ms	75.6316μs	13.2220 KOps/s	13.4010 KOps/s	$\color{#d91a1a}-1.34\%$
test_unflatten_speed	0.3784ms	0.3258ms	3.0695 KOps/s	3.1011 KOps/s	$\color{#d91a1a}-1.02\%$
test_common_ops	1.7090ms	0.5793ms	1.7263 KOps/s	1.5412 KOps/s	$\textbf{\color{#35bf28}+12.01\%}$
test_creation	0.1801ms	1.7511μs	571.0738 KOps/s	571.5085 KOps/s	$\color{#d91a1a}-0.08\%$
test_creation_empty	45.4620μs	6.5059μs	153.7070 KOps/s	103.8838 KOps/s	$\textbf{\color{#35bf28}+47.96\%}$
test_creation_nested_1	32.4520μs	8.1605μs	122.5413 KOps/s	86.1975 KOps/s	$\textbf{\color{#35bf28}+42.16\%}$
test_creation_nested_2	38.3820μs	11.0241μs	90.7106 KOps/s	70.7440 KOps/s	$\textbf{\color{#35bf28}+28.22\%}$
test_clone	0.1311ms	10.7394μs	93.1147 KOps/s	86.5771 KOps/s	$\textbf{\color{#35bf28}+7.55\%}$
test_getitem[int]	1.8679ms	10.8640μs	92.0475 KOps/s	88.9082 KOps/s	$\color{#35bf28}+3.53\%$
test_getitem[slice_int]	0.1178ms	21.5758μs	46.3481 KOps/s	44.6517 KOps/s	$\color{#35bf28}+3.80\%$
test_getitem[range]	0.1562ms	37.7011μs	26.5244 KOps/s	24.9559 KOps/s	$\textbf{\color{#35bf28}+6.29\%}$
test_getitem[tuple]	0.1098ms	18.6569μs	53.5994 KOps/s	51.5211 KOps/s	$\color{#35bf28}+4.03\%$
test_getitem[list]	0.3426ms	33.4017μs	29.9386 KOps/s	28.1492 KOps/s	$\textbf{\color{#35bf28}+6.36\%}$
test_setitem_dim[int]	28.1510μs	19.2456μs	51.9599 KOps/s	48.6110 KOps/s	$\textbf{\color{#35bf28}+6.89\%}$
test_setitem_dim[slice_int]	61.0930μs	39.4619μs	25.3409 KOps/s	24.9831 KOps/s	$\color{#35bf28}+1.43\%$
test_setitem_dim[range]	90.4240μs	53.4824μs	18.6977 KOps/s	18.2326 KOps/s	$\color{#35bf28}+2.55\%$
test_setitem_dim[tuple]	57.6820μs	32.4317μs	30.8340 KOps/s	29.4576 KOps/s	$\color{#35bf28}+4.67\%$
test_setitem	0.1271ms	14.4000μs	69.4442 KOps/s	58.8925 KOps/s	$\textbf{\color{#35bf28}+17.92\%}$
test_set	0.1260ms	13.6880μs	73.0566 KOps/s	60.5929 KOps/s	$\textbf{\color{#35bf28}+20.57\%}$
test_set_shared	1.6033ms	0.1535ms	6.5143 KOps/s	6.4779 KOps/s	$\color{#35bf28}+0.56\%$
test_update	0.3555ms	15.6148μs	64.0416 KOps/s	49.3024 KOps/s	$\textbf{\color{#35bf28}+29.90\%}$
test_update_nested	0.1351ms	21.4708μs	46.5748 KOps/s	37.6933 KOps/s	$\textbf{\color{#35bf28}+23.56\%}$
test_update__nested	0.5353ms	25.6583μs	38.9737 KOps/s	37.1422 KOps/s	$\color{#35bf28}+4.93\%$
test_set_nested	0.1247ms	15.2729μs	65.4754 KOps/s	55.8351 KOps/s	$\textbf{\color{#35bf28}+17.27\%}$
test_set_nested_new	46.1820μs	17.8060μs	56.1610 KOps/s	49.1181 KOps/s	$\textbf{\color{#35bf28}+14.34\%}$
test_select	0.2133ms	29.2358μs	34.2047 KOps/s	30.6679 KOps/s	$\textbf{\color{#35bf28}+11.53\%}$
test_select_nested	90.6540μs	43.8343μs	22.8132 KOps/s	22.6790 KOps/s	$\color{#35bf28}+0.59\%$
test_exclude_nested	0.1012ms	63.2318μs	15.8148 KOps/s	15.4711 KOps/s	$\color{#35bf28}+2.22\%$
test_empty[True]	0.3505ms	0.2898ms	3.4502 KOps/s	3.4556 KOps/s	$\color{#d91a1a}-0.16\%$
test_empty[False]	4.1962μs	0.8238μs	1.2138 MOps/s	1.2045 MOps/s	$\color{#35bf28}+0.78\%$
test_to	91.0740μs	58.3797μs	17.1292 KOps/s	17.5168 KOps/s	$\color{#d91a1a}-2.21\%$
test_to_nonblocking	92.1740μs	49.2579μs	20.3013 KOps/s	20.1554 KOps/s	$\color{#35bf28}+0.72\%$
test_unbind_speed	0.3192ms	0.2374ms	4.2121 KOps/s	4.0507 KOps/s	$\color{#35bf28}+3.99\%$
test_unbind_speed_stack0	0.3034ms	0.2420ms	4.1319 KOps/s	4.1742 KOps/s	$\color{#d91a1a}-1.01\%$
test_unbind_speed_stack1	99.5198ms	0.6789ms	1.4729 KOps/s	1.4885 KOps/s	$\color{#d91a1a}-1.05\%$
test_split	99.8070ms	1.6122ms	620.2701 Ops/s	608.3658 Ops/s	$\color{#35bf28}+1.96\%$
test_chunk	99.2944ms	1.6017ms	624.3290 Ops/s	605.1266 Ops/s	$\color{#35bf28}+3.17\%$
test_consolidate[False-None]	0.1019s	2.9629ms	337.5100 Ops/s	327.9929 Ops/s	$\color{#35bf28}+2.90\%$
test_consolidate[default-None]	1.8082ms	1.7141ms	583.4024 Ops/s	577.8927 Ops/s	$\color{#35bf28}+0.95\%$
test_consolidate[reduce-overhead-None]	1.8416ms	1.7418ms	574.1036 Ops/s	564.0802 Ops/s	$\color{#35bf28}+1.78\%$
test_consolidate_njt[False-None]	7.1476ms	6.6397ms	150.6100 Ops/s	149.9489 Ops/s	$\color{#35bf28}+0.44\%$
test_to[False-False-None]	1.8142ms	1.7304ms	577.8948 Ops/s	571.1502 Ops/s	$\color{#35bf28}+1.18\%$
test_to[True-False-None]	1.5544ms	1.3370ms	747.9495 Ops/s	712.0715 Ops/s	$\textbf{\color{#35bf28}+5.04\%}$
test_to[within-False-None]	4.4525ms	4.2142ms	237.2904 Ops/s	231.2857 Ops/s	$\color{#35bf28}+2.60\%$
test_to[True-default-None]	5.6381ms	5.4039ms	185.0530 Ops/s	176.1433 Ops/s	$\textbf{\color{#35bf28}+5.06\%}$
test_to_njt[False-False-None]	7.4062ms	7.0863ms	141.1165 Ops/s	142.5172 Ops/s	$\color{#d91a1a}-0.98\%$
test_to_njt[True-False-None]	5.8898ms	5.5993ms	178.5931 Ops/s	177.9186 Ops/s	$\color{#35bf28}+0.38\%$
test_to_njt[within-False-None]	12.9104ms	12.4376ms	80.4014 Ops/s	79.9785 Ops/s	$\color{#35bf28}+0.53\%$
test_creation[device0]	0.4675ms	84.3485μs	11.8556 KOps/s	11.9653 KOps/s	$\color{#d91a1a}-0.92\%$
test_creation_from_tensor	0.5321ms	87.1563μs	11.4736 KOps/s	11.7892 KOps/s	$\color{#d91a1a}-2.68\%$
test_add_one[memmap_tensor0]	0.4091ms	7.0480μs	141.8852 KOps/s	139.1575 KOps/s	$\color{#35bf28}+1.96\%$
test_contiguous[memmap_tensor0]	4.3942μs	0.4243μs	2.3568 MOps/s	2.3895 MOps/s	$\color{#d91a1a}-1.37\%$
test_stack[memmap_tensor0]	31.5610μs	4.2989μs	232.6203 KOps/s	210.8312 KOps/s	$\textbf{\color{#35bf28}+10.33\%}$
test_memmaptd_index	1.7883ms	0.2577ms	3.8808 KOps/s	3.7921 KOps/s	$\color{#35bf28}+2.34\%$
test_memmaptd_index_astensor	0.9985ms	0.3227ms	3.0985 KOps/s	3.0484 KOps/s	$\color{#35bf28}+1.64\%$
test_memmaptd_index_op	0.9957ms	0.5686ms	1.7587 KOps/s	1.5601 KOps/s	$\textbf{\color{#35bf28}+12.73\%}$
test_serialize_model	0.1329s	0.1312s	7.6204 Ops/s	7.6375 Ops/s	$\color{#d91a1a}-0.22\%$
test_serialize_model_pickle	1.3501s	1.2179s	0.8211 Ops/s	0.8235 Ops/s	$\color{#d91a1a}-0.29\%$
test_serialize_weights	0.1315s	0.1302s	7.6792 Ops/s	7.6156 Ops/s	$\color{#35bf28}+0.84\%$
test_serialize_weights_returnearly	0.5674s	74.9885ms	13.3354 Ops/s	13.2423 Ops/s	$\color{#35bf28}+0.70\%$
test_serialize_weights_pickle	1.3664s	1.2207s	0.8192 Ops/s	0.8403 Ops/s	$\color{#d91a1a}-2.51\%$
test_reshape_pytree	52.3920μs	22.7362μs	43.9828 KOps/s	42.9516 KOps/s	$\color{#35bf28}+2.40\%$
test_reshape_td	52.9520μs	27.1070μs	36.8908 KOps/s	34.5698 KOps/s	$\textbf{\color{#35bf28}+6.71\%}$
test_view_pytree	50.3330μs	22.6094μs	44.2294 KOps/s	43.2897 KOps/s	$\color{#35bf28}+2.17\%$
test_view_td	62.2530μs	29.9895μs	33.3450 KOps/s	30.2552 KOps/s	$\textbf{\color{#35bf28}+10.21\%}$
test_unbind_pytree	52.8630μs	28.5755μs	34.9950 KOps/s	33.8834 KOps/s	$\color{#35bf28}+3.28\%$
test_unbind_td	0.8360ms	36.9542μs	27.0605 KOps/s	26.3636 KOps/s	$\color{#35bf28}+2.64\%$
test_split_pytree	54.2720μs	30.2325μs	33.0770 KOps/s	31.6557 KOps/s	$\color{#35bf28}+4.49\%$
test_split_td	0.9297ms	39.0822μs	25.5871 KOps/s	24.2168 KOps/s	$\textbf{\color{#35bf28}+5.66\%}$
test_add_pytree	65.0830μs	35.5501μs	28.1293 KOps/s	27.0244 KOps/s	$\color{#35bf28}+4.09\%$
test_add_td	79.2840μs	45.0042μs	22.2202 KOps/s	17.9017 KOps/s	$\textbf{\color{#35bf28}+24.12\%}$
test_compile_add_one_nested[tensordict-compile]	0.2290ms	0.1211ms	8.2558 KOps/s	7.8446 KOps/s	$\textbf{\color{#35bf28}+5.24\%}$
test_compile_add_one_nested[tensordict-eager]	0.2290ms	0.1324ms	7.5550 KOps/s	7.3577 KOps/s	$\color{#35bf28}+2.68\%$
test_compile_add_one_nested[pytree-compile]	0.1918ms	96.2738μs	10.3870 KOps/s	10.0748 KOps/s	$\color{#35bf28}+3.10\%$
test_compile_add_one_nested[pytree-eager]	1.3784ms	0.1518ms	6.5864 KOps/s	6.4580 KOps/s	$\color{#35bf28}+1.99\%$
test_compile_copy_nested[tensordict-compile]	55.1920μs	23.0640μs	43.3576 KOps/s	36.9254 KOps/s	$\textbf{\color{#35bf28}+17.42\%}$
test_compile_copy_nested[tensordict-eager]	59.9720μs	30.6383μs	32.6389 KOps/s	33.2084 KOps/s	$\color{#d91a1a}-1.71\%$
test_compile_copy_nested[pytree-compile]	0.3547ms	68.7362μs	14.5484 KOps/s	14.6180 KOps/s	$\color{#d91a1a}-0.48\%$
test_compile_copy_nested[pytree-eager]	87.1230μs	51.0022μs	19.6070 KOps/s	19.3982 KOps/s	$\color{#35bf28}+1.08\%$
test_compile_add_one_flat[tensordict-compile]	0.1815ms	0.1433ms	6.9778 KOps/s	6.9659 KOps/s	$\color{#35bf28}+0.17\%$
test_compile_add_one_flat[tensordict-eager]	0.3105ms	0.2162ms	4.6257 KOps/s	4.6020 KOps/s	$\color{#35bf28}+0.52\%$
test_compile_add_one_flat[tensorclass-compile]	0.1607ms	99.5871μs	10.0415 KOps/s	9.9642 KOps/s	$\color{#35bf28}+0.78\%$
test_compile_add_one_flat[tensorclass-eager]	0.1133ms	56.0668μs	17.8359 KOps/s	17.8654 KOps/s	$\color{#d91a1a}-0.17\%$
test_compile_add_one_flat[pytree-compile]	0.1864ms	0.1374ms	7.2788 KOps/s	7.3169 KOps/s	$\color{#d91a1a}-0.52\%$
test_compile_add_one_flat[pytree-eager]	0.5490ms	0.4785ms	2.0899 KOps/s	2.0138 KOps/s	$\color{#35bf28}+3.78\%$
test_compile_add_self_flat[tensordict-eager]	0.3644ms	0.2602ms	3.8426 KOps/s	3.8451 KOps/s	$\color{#d91a1a}-0.06\%$
test_compile_add_self_flat[tensordict-compile]	0.2085ms	0.1439ms	6.9501 KOps/s	6.9673 KOps/s	$\color{#d91a1a}-0.25\%$
test_compile_add_self_flat[tensorclass-eager]	0.1523ms	66.6339μs	15.0074 KOps/s	14.3707 KOps/s	$\color{#35bf28}+4.43\%$
test_compile_add_self_flat[tensorclass-compile]	0.1415ms	0.1004ms	9.9605 KOps/s	9.7414 KOps/s	$\color{#35bf28}+2.25\%$
test_compile_add_self_flat[pytree-eager]	0.4431ms	0.4054ms	2.4668 KOps/s	2.4323 KOps/s	$\color{#35bf28}+1.42\%$
test_compile_add_self_flat[pytree-compile]	0.1749ms	0.1358ms	7.3621 KOps/s	7.3355 KOps/s	$\color{#35bf28}+0.36\%$
test_compile_copy_flat[tensordict-compile]	87.6840μs	19.5922μs	51.0407 KOps/s	54.3140 KOps/s	$\textbf{\color{#d91a1a}-6.03\%}$
test_compile_copy_flat[tensordict-eager]	61.6520μs	32.1646μs	31.0901 KOps/s	31.5785 KOps/s	$\color{#d91a1a}-1.55\%$
test_compile_copy_flat[pytree-compile]	0.1101ms	72.8528μs	13.7263 KOps/s	13.7637 KOps/s	$\color{#d91a1a}-0.27\%$
test_compile_copy_flat[pytree-eager]	81.6140μs	51.3533μs	19.4729 KOps/s	19.3102 KOps/s	$\color{#35bf28}+0.84\%$
test_compile_assign_and_add[tensordict-compile]	1.6423ms	0.3940ms	2.5381 KOps/s	2.1680 KOps/s	$\textbf{\color{#35bf28}+17.07\%}$
test_compile_assign_and_add[tensordict-eager]	3.0406ms	2.6298ms	380.2602 Ops/s	368.7238 Ops/s	$\color{#35bf28}+3.13\%$
test_compile_assign_and_add[pytree-compile]	1.5838ms	0.4294ms	2.3289 KOps/s	2.1573 KOps/s	$\textbf{\color{#35bf28}+7.95\%}$
test_compile_assign_and_add[pytree-eager]	3.1160ms	2.6349ms	379.5195 Ops/s	356.9188 Ops/s	$\textbf{\color{#35bf28}+6.33\%}$
test_compile_indexing[tensor-tensordict-compile]	0.5727ms	0.1214ms	8.2384 KOps/s	8.1118 KOps/s	$\color{#35bf28}+1.56\%$
test_compile_indexing[tensor-tensordict-eager]	0.5645ms	84.7789μs	11.7954 KOps/s	12.0506 KOps/s	$\color{#d91a1a}-2.12\%$
test_compile_indexing[tensor-tensorclass-compile]	0.5521ms	0.1097ms	9.1126 KOps/s	9.0105 KOps/s	$\color{#35bf28}+1.13\%$
test_compile_indexing[tensor-tensorclass-eager]	0.4967ms	69.3604μs	14.4175 KOps/s	14.2411 KOps/s	$\color{#35bf28}+1.24\%$
test_compile_indexing[tensor-pytree-compile]	0.5647ms	0.1107ms	9.0328 KOps/s	9.1933 KOps/s	$\color{#d91a1a}-1.75\%$
test_compile_indexing[tensor-pytree-eager]	0.4947ms	72.9965μs	13.6993 KOps/s	14.1958 KOps/s	$\color{#d91a1a}-3.50\%$
test_compile_indexing[slice-tensordict-compile]	0.1636ms	0.1013ms	9.8690 KOps/s	9.6874 KOps/s	$\color{#35bf28}+1.87\%$
test_compile_indexing[slice-tensordict-eager]	0.1368ms	17.2718μs	57.8980 KOps/s	54.7170 KOps/s	$\textbf{\color{#35bf28}+5.81\%}$
test_compile_indexing[slice-tensorclass-compile]	0.1476ms	96.8481μs	10.3254 KOps/s	10.0633 KOps/s	$\color{#35bf28}+2.61\%$
test_compile_indexing[slice-tensorclass-eager]	58.4730μs	16.0844μs	62.1722 KOps/s	58.2578 KOps/s	$\textbf{\color{#35bf28}+6.72\%}$
test_compile_indexing[slice-pytree-compile]	0.1448ms	98.2963μs	10.1733 KOps/s	10.0256 KOps/s	$\color{#35bf28}+1.47\%$
test_compile_indexing[slice-pytree-eager]	49.7420μs	15.9831μs	62.5659 KOps/s	57.9752 KOps/s	$\textbf{\color{#35bf28}+7.92\%}$
test_compile_indexing[int-tensordict-compile]	0.1586ms	0.1068ms	9.3675 KOps/s	9.6044 KOps/s	$\color{#d91a1a}-2.47\%$
test_compile_indexing[int-tensordict-eager]	0.5889ms	17.2831μs	57.8598 KOps/s	53.9815 KOps/s	$\textbf{\color{#35bf28}+7.18\%}$
test_compile_indexing[int-tensorclass-compile]	0.1494ms	0.1029ms	9.7168 KOps/s	10.0206 KOps/s	$\color{#d91a1a}-3.03\%$
test_compile_indexing[int-tensorclass-eager]	51.0920μs	16.0779μs	62.1973 KOps/s	59.2916 KOps/s	$\color{#35bf28}+4.90\%$
test_compile_indexing[int-pytree-compile]	0.2487ms	0.1021ms	9.7968 KOps/s	9.9932 KOps/s	$\color{#d91a1a}-1.97\%$
test_compile_indexing[int-pytree-eager]	42.8820μs	15.9256μs	62.7920 KOps/s	58.4976 KOps/s	$\textbf{\color{#35bf28}+7.34\%}$
test_mod_add[eager]	81.7340μs	37.5014μs	26.6657 KOps/s	24.4950 KOps/s	$\textbf{\color{#35bf28}+8.86\%}$
test_mod_add[compile]	0.1288ms	80.4474μs	12.4305 KOps/s	11.8674 KOps/s	$\color{#35bf28}+4.74\%$
test_mod_add[compile-overhead]	0.3243ms	0.1669ms	5.9928 KOps/s	5.6370 KOps/s	$\textbf{\color{#35bf28}+6.31\%}$
test_mod_wrap[eager]	0.3383ms	0.2493ms	4.0106 KOps/s	3.8340 KOps/s	$\color{#35bf28}+4.61\%$
test_mod_wrap[compile]	0.3409ms	0.2972ms	3.3648 KOps/s	3.4070 KOps/s	$\color{#d91a1a}-1.24\%$
test_mod_wrap[compile-overhead]	7.1328ms	3.7449ms	267.0315 Ops/s	274.0481 Ops/s	$\color{#d91a1a}-2.56\%$
test_mod_wrap_and_backward[eager]	1.8708ms	1.4062ms	711.1466 Ops/s	669.0854 Ops/s	$\textbf{\color{#35bf28}+6.29\%}$
test_mod_wrap_and_backward[compile]	1.4576ms	1.2826ms	779.6906 Ops/s	706.1271 Ops/s	$\textbf{\color{#35bf28}+10.42\%}$
test_mod_wrap_and_backward[compile-overhead]	1.4064ms	0.9350ms	1.0695 KOps/s	948.7592 Ops/s	$\textbf{\color{#35bf28}+12.73\%}$
test_seq_add[eager]	0.1732ms	0.1126ms	8.8798 KOps/s	8.1954 KOps/s	$\textbf{\color{#35bf28}+8.35\%}$
test_seq_add[compile]	0.2363ms	88.4220μs	11.3094 KOps/s	11.0513 KOps/s	$\color{#35bf28}+2.34\%$
test_seq_add[compile-overhead]	0.1839ms	0.1297ms	7.7130 KOps/s	7.6053 KOps/s	$\color{#35bf28}+1.42\%$
test_seq_wrap[eager]	0.8673ms	0.4101ms	2.4382 KOps/s	2.2730 KOps/s	$\textbf{\color{#35bf28}+7.27\%}$
test_seq_wrap[compile]	0.7777ms	0.3033ms	3.2969 KOps/s	3.2099 KOps/s	$\color{#35bf28}+2.71\%$
test_seq_wrap[compile-overhead]	0.2788ms	0.2261ms	4.4225 KOps/s	4.3446 KOps/s	$\color{#35bf28}+1.79\%$
test_func_call_runtime[False-eager]	0.8478ms	0.7509ms	1.3317 KOps/s	1.3023 KOps/s	$\color{#35bf28}+2.26\%$
test_func_call_runtime[False-compile]	0.8606ms	0.7580ms	1.3193 KOps/s	1.2970 KOps/s	$\color{#35bf28}+1.72\%$
test_func_call_runtime[False-compile-overhead]	0.4174ms	0.3680ms	2.7174 KOps/s	2.6864 KOps/s	$\color{#35bf28}+1.16\%$
test_func_call_runtime[True-eager]	1.1808ms	0.9327ms	1.0721 KOps/s	1.0657 KOps/s	$\color{#35bf28}+0.60\%$
test_func_call_runtime[True-compile]	0.9510ms	0.7746ms	1.2911 KOps/s	1.2667 KOps/s	$\color{#35bf28}+1.92\%$
test_func_call_runtime[True-compile-overhead]	0.4771ms	0.3895ms	2.5676 KOps/s	2.5556 KOps/s	$\color{#35bf28}+0.47\%$
test_func_call_cm_runtime[False-eager]	0.7990ms	0.7458ms	1.3408 KOps/s	1.3084 KOps/s	$\color{#35bf28}+2.48\%$
test_func_call_cm_runtime[False-compile]	0.8055ms	0.7582ms	1.3189 KOps/s	1.2825 KOps/s	$\color{#35bf28}+2.84\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4331ms	0.3711ms	2.6944 KOps/s	2.6696 KOps/s	$\color{#35bf28}+0.93\%$
test_func_call_cm_runtime[True-eager]	1.1031ms	1.0162ms	984.0180 Ops/s	957.0297 Ops/s	$\color{#35bf28}+2.82\%$
test_func_call_cm_runtime[True-compile]	0.9284ms	0.8055ms	1.2415 KOps/s	1.2146 KOps/s	$\color{#35bf28}+2.22\%$
test_func_call_cm_runtime[True-compile-overhead]	0.4735ms	0.4135ms	2.4186 KOps/s	2.3786 KOps/s	$\color{#35bf28}+1.69\%$
test_vmap_func_call_cm_runtime[eager]	2.5689ms	2.1138ms	473.0860 Ops/s	468.4667 Ops/s	$\color{#35bf28}+0.99\%$
test_vmap_func_call_cm_runtime[compile]	0.9535ms	0.8164ms	1.2249 KOps/s	1.1845 KOps/s	$\color{#35bf28}+3.41\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.4627ms	0.4169ms	2.3984 KOps/s	2.3620 KOps/s	$\color{#35bf28}+1.54\%$
test_distributed	7.1552ms	0.1928ms	5.1868 KOps/s	8.4945 KOps/s	$\textbf{\color{#d91a1a}-38.94\%}$
test_tdmodule	0.3650ms	18.7033μs	53.4664 KOps/s	48.2663 KOps/s	$\textbf{\color{#35bf28}+10.77\%}$
test_tdmodule_dispatch	0.4896ms	32.5007μs	30.7685 KOps/s	27.0603 KOps/s	$\textbf{\color{#35bf28}+13.70\%}$
test_tdseq	46.5720μs	19.3682μs	51.6309 KOps/s	44.0396 KOps/s	$\textbf{\color{#35bf28}+17.24\%}$
test_tdseq_dispatch	58.1130μs	36.0398μs	27.7471 KOps/s	24.2207 KOps/s	$\textbf{\color{#35bf28}+14.56\%}$
test_instantiation_functorch	1.6552ms	1.5849ms	630.9526 Ops/s	614.3234 Ops/s	$\color{#35bf28}+2.71\%$
test_exec_functorch	0.2009ms	0.1458ms	6.8566 KOps/s	6.5447 KOps/s	$\color{#35bf28}+4.77\%$
test_exec_functional_call	0.1915ms	0.1411ms	7.0871 KOps/s	6.8486 KOps/s	$\color{#35bf28}+3.48\%$
test_exec_td_decorator	0.3781ms	0.1889ms	5.2950 KOps/s	5.1614 KOps/s	$\color{#35bf28}+2.59\%$
test_vmap_mlp_speed_decorator[True-True]	0.7892ms	0.6836ms	1.4629 KOps/s	1.4303 KOps/s	$\color{#35bf28}+2.28\%$
test_vmap_mlp_speed_decorator[True-False]	0.8523ms	0.6854ms	1.4590 KOps/s	1.4247 KOps/s	$\color{#35bf28}+2.41\%$
test_vmap_mlp_speed_decorator[False-True]	0.7224ms	0.6014ms	1.6629 KOps/s	1.6475 KOps/s	$\color{#35bf28}+0.93\%$
test_vmap_mlp_speed_decorator[False-False]	0.7124ms	0.6020ms	1.6612 KOps/s	1.6443 KOps/s	$\color{#35bf28}+1.02\%$
test_vmap_transformer_speed_decorator[True-True]	19.4964ms	19.4015ms	51.5425 Ops/s	50.6930 Ops/s	$\color{#35bf28}+1.68\%$
test_vmap_transformer_speed_decorator[True-False]	20.1036ms	19.4064ms	51.5293 Ops/s	50.4135 Ops/s	$\color{#35bf28}+2.21\%$
test_vmap_transformer_speed_decorator[False-True]	19.4221ms	19.3053ms	51.7993 Ops/s	50.4134 Ops/s	$\color{#35bf28}+2.75\%$
test_vmap_transformer_speed_decorator[False-False]	19.4115ms	19.2655ms	51.9062 Ops/s	50.7499 Ops/s	$\color{#35bf28}+2.28\%$
test_to_module_speed[True]	1.2018ms	0.9782ms	1.0223 KOps/s	1.0245 KOps/s	$\color{#d91a1a}-0.21\%$
test_to_module_speed[False]	1.0358ms	0.9541ms	1.0481 KOps/s	1.0499 KOps/s	$\color{#d91a1a}-0.17\%$
test_tc_init	63.4630μs	34.9861μs	28.5828 KOps/s	26.3527 KOps/s	$\textbf{\color{#35bf28}+8.46\%}$
test_tc_init_nested	0.2118ms	70.4217μs	14.2002 KOps/s	12.9803 KOps/s	$\textbf{\color{#35bf28}+9.40\%}$
test_tc_first_layer_tensor	4.9530μs	0.7215μs	1.3860 MOps/s	1.4019 MOps/s	$\color{#d91a1a}-1.13\%$
test_tc_first_layer_nontensor	19.2310μs	2.3481μs	425.8788 KOps/s	439.2956 KOps/s	$\color{#d91a1a}-3.05\%$
test_tc_second_layer_tensor	8.8537μs	1.4833μs	674.1651 KOps/s	687.7579 KOps/s	$\color{#d91a1a}-1.98\%$
test_tc_second_layer_nontensor	29.7310μs	3.0762μs	325.0771 KOps/s	332.2115 KOps/s	$\color{#d91a1a}-2.15\%$
test_unbind	0.2294s	11.9449ms	83.7179 Ops/s	142.8468 Ops/s	$\textbf{\color{#d91a1a}-41.39\%}$
test_full_like	11.0340ms	9.9200ms	100.8061 Ops/s	100.1437 Ops/s	$\color{#35bf28}+0.66\%$
test_zeros_like	5.4012ms	4.4601ms	224.2117 Ops/s	113.6765 Ops/s	$\textbf{\color{#35bf28}+97.24\%}$
test_ones_like	5.5097ms	4.5041ms	222.0218 Ops/s	221.6241 Ops/s	$\color{#35bf28}+0.18\%$
test_clone	7.8184ms	7.0365ms	142.1155 Ops/s	142.9772 Ops/s	$\color{#d91a1a}-0.60\%$
test_squeeze	61.0330μs	9.7999μs	102.0422 KOps/s	102.5669 KOps/s	$\color{#d91a1a}-0.51\%$
test_unsqueeze	0.1349ms	73.5996μs	13.5870 KOps/s	13.0323 KOps/s	$\color{#35bf28}+4.26\%$
test_split	0.3870ms	0.1666ms	6.0020 KOps/s	5.7212 KOps/s	$\color{#35bf28}+4.91\%$
test_permute	0.2262ms	0.1818ms	5.5016 KOps/s	5.2596 KOps/s	$\color{#35bf28}+4.60\%$
test_stack	53.8209ms	52.2802ms	19.1277 Ops/s	19.2267 Ops/s	$\color{#d91a1a}-0.51\%$
test_cat	52.7530ms	52.0632ms	19.2074 Ops/s	19.3262 Ops/s	$\color{#d91a1a}-0.61\%$