[Refactor] Avoid lambda functions in core functionality

[vmoens]

Stack from ghstack (oldest at bottom):

• -> [Refactor] Avoid lambda functions in core functionality #1136
• [FBCode] Deactivate vmap monkey-patching in FBCode #1135
• [Quality] Avoid torch.distributed imports at root #1134

[github-actions]

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}15$. Worsened: $\large\color{#d91a1a}29$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	0.1615ms	17.9902μs	55.5857 KOps/s	61.3447 KOps/s	$\textbf{\color{#d91a1a}-9.39\%}$
test_plain_set_stack_nested	45.2340μs	18.1520μs	55.0904 KOps/s	58.1023 KOps/s	$\textbf{\color{#d91a1a}-5.18\%}$
test_plain_set_nested_inplace	58.1290μs	19.8286μs	50.4323 KOps/s	53.7221 KOps/s	$\textbf{\color{#d91a1a}-6.12\%}$
test_plain_set_stack_nested_inplace	69.7520μs	19.9511μs	50.1225 KOps/s	54.1458 KOps/s	$\textbf{\color{#d91a1a}-7.43\%}$
test_items	49.3430μs	4.2510μs	235.2371 KOps/s	248.9756 KOps/s	$\textbf{\color{#d91a1a}-5.52\%}$
test_items_nested	0.6184ms	0.3991ms	2.5059 KOps/s	2.5122 KOps/s	$\color{#d91a1a}-0.25\%$
test_items_nested_locked	0.6070ms	0.3993ms	2.5045 KOps/s	2.5204 KOps/s	$\color{#d91a1a}-0.63\%$
test_items_nested_leaf	0.1305ms	71.9897μs	13.8909 KOps/s	14.1778 KOps/s	$\color{#d91a1a}-2.02\%$
test_items_stack_nested	0.7287ms	0.4030ms	2.4817 KOps/s	2.4639 KOps/s	$\color{#35bf28}+0.72\%$
test_items_stack_nested_leaf	0.1264ms	73.5033μs	13.6048 KOps/s	13.7333 KOps/s	$\color{#d91a1a}-0.94\%$
test_items_stack_nested_locked	0.7235ms	0.4017ms	2.4894 KOps/s	2.4863 KOps/s	$\color{#35bf28}+0.13\%$
test_keys	26.6400μs	3.5961μs	278.0771 KOps/s	287.1486 KOps/s	$\color{#d91a1a}-3.16\%$
test_keys_nested	0.2093ms	0.1389ms	7.2002 KOps/s	7.3093 KOps/s	$\color{#d91a1a}-1.49\%$
test_keys_nested_locked	2.1166ms	0.1433ms	6.9782 KOps/s	7.0095 KOps/s	$\color{#d91a1a}-0.45\%$
test_keys_nested_leaf	0.2273ms	0.1165ms	8.5841 KOps/s	8.4635 KOps/s	$\color{#35bf28}+1.42\%$
test_keys_stack_nested	0.2676ms	0.1361ms	7.3485 KOps/s	7.4956 KOps/s	$\color{#d91a1a}-1.96\%$
test_keys_stack_nested_leaf	0.1923ms	0.1140ms	8.7710 KOps/s	8.8372 KOps/s	$\color{#d91a1a}-0.75\%$
test_keys_stack_nested_locked	0.2631ms	0.1412ms	7.0814 KOps/s	7.0898 KOps/s	$\color{#d91a1a}-0.12\%$
test_values	7.3898μs	1.0479μs	954.2625 KOps/s	968.6693 KOps/s	$\color{#d91a1a}-1.49\%$
test_values_nested	0.1247ms	55.3582μs	18.0642 KOps/s	17.6323 KOps/s	$\color{#35bf28}+2.45\%$
test_values_nested_locked	0.1027ms	54.6874μs	18.2857 KOps/s	18.1758 KOps/s	$\color{#35bf28}+0.60\%$
test_values_nested_leaf	0.1551ms	59.5523μs	16.7920 KOps/s	16.8706 KOps/s	$\color{#d91a1a}-0.47\%$
test_values_stack_nested	0.1101ms	56.2297μs	17.7842 KOps/s	17.6856 KOps/s	$\color{#35bf28}+0.56\%$
test_values_stack_nested_leaf	0.1170ms	59.7533μs	16.7355 KOps/s	16.9386 KOps/s	$\color{#d91a1a}-1.20\%$
test_values_stack_nested_locked	0.1026ms	56.4997μs	17.6992 KOps/s	17.8586 KOps/s	$\color{#d91a1a}-0.89\%$
test_membership	13.6860μs	0.9395μs	1.0644 MOps/s	1.3350 MOps/s	$\textbf{\color{#d91a1a}-20.27\%}$
test_membership_nested	34.8160μs	3.0057μs	332.7018 KOps/s	348.8410 KOps/s	$\color{#d91a1a}-4.63\%$
test_membership_nested_leaf	24.8980μs	3.0135μs	331.8444 KOps/s	344.7860 KOps/s	$\color{#d91a1a}-3.75\%$
test_membership_stacked_nested	32.5010μs	2.9788μs	335.7007 KOps/s	349.5491 KOps/s	$\color{#d91a1a}-3.96\%$
test_membership_stacked_nested_leaf	38.9230μs	2.9881μs	334.6563 KOps/s	349.7650 KOps/s	$\color{#d91a1a}-4.32\%$
test_membership_nested_last	31.6790μs	4.3173μs	231.6280 KOps/s	236.3910 KOps/s	$\color{#d91a1a}-2.01\%$
test_membership_nested_leaf_last	21.7710μs	4.3294μs	230.9801 KOps/s	238.5978 KOps/s	$\color{#d91a1a}-3.19\%$
test_membership_stacked_nested_last	28.4330μs	5.4734μs	182.7008 KOps/s	76.5255 KOps/s	$\textbf{\color{#35bf28}+138.75\%}$
test_membership_stacked_nested_leaf_last	34.5650μs	5.4768μs	182.5892 KOps/s	76.6236 KOps/s	$\textbf{\color{#35bf28}+138.29\%}$
test_nested_getleaf	34.9360μs	10.8155μs	92.4598 KOps/s	92.2669 KOps/s	$\color{#35bf28}+0.21\%$
test_nested_get	33.2320μs	10.4255μs	95.9184 KOps/s	98.0258 KOps/s	$\color{#d91a1a}-2.15\%$
test_stacked_getleaf	32.3810μs	10.8961μs	91.7760 KOps/s	93.5192 KOps/s	$\color{#d91a1a}-1.86\%$
test_stacked_get	54.2020μs	10.5518μs	94.7704 KOps/s	97.9777 KOps/s	$\color{#d91a1a}-3.27\%$
test_nested_getitemleaf	42.6890μs	11.1740μs	89.4931 KOps/s	88.0223 KOps/s	$\color{#35bf28}+1.67\%$
test_nested_getitem	45.4550μs	10.6087μs	94.2626 KOps/s	96.3922 KOps/s	$\color{#d91a1a}-2.21\%$
test_stacked_getitemleaf	38.9930μs	11.2071μs	89.2290 KOps/s	89.3793 KOps/s	$\color{#d91a1a}-0.17\%$
test_stacked_getitem	34.5650μs	10.5622μs	94.6772 KOps/s	95.3185 KOps/s	$\color{#d91a1a}-0.67\%$
test_lock_nested	3.1524ms	0.4410ms	2.2677 KOps/s	2.2284 KOps/s	$\color{#35bf28}+1.76\%$
test_lock_stack_nested	0.8299ms	0.4074ms	2.4548 KOps/s	2.4791 KOps/s	$\color{#d91a1a}-0.98\%$
test_unlock_nested	0.7515ms	0.3587ms	2.7875 KOps/s	2.7295 KOps/s	$\color{#35bf28}+2.13\%$
test_unlock_stack_nested	0.4192ms	0.3253ms	3.0742 KOps/s	3.1064 KOps/s	$\color{#d91a1a}-1.04\%$
test_flatten_speed	0.1548ms	93.8856μs	10.6513 KOps/s	10.7787 KOps/s	$\color{#d91a1a}-1.18\%$
test_unflatten_speed	0.5753ms	0.4917ms	2.0339 KOps/s	2.0552 KOps/s	$\color{#d91a1a}-1.04\%$
test_common_ops	4.5534ms	0.7981ms	1.2530 KOps/s	1.3372 KOps/s	$\textbf{\color{#d91a1a}-6.29\%}$
test_creation	24.6770μs	2.0651μs	484.2290 KOps/s	495.1213 KOps/s	$\color{#d91a1a}-2.20\%$
test_creation_empty	33.4120μs	11.6517μs	85.8241 KOps/s	109.2750 KOps/s	$\textbf{\color{#d91a1a}-21.46\%}$
test_creation_nested_1	38.8730μs	14.5196μs	68.8725 KOps/s	82.3761 KOps/s	$\textbf{\color{#d91a1a}-16.39\%}$
test_creation_nested_2	51.7570μs	18.7175μs	53.4259 KOps/s	60.1660 KOps/s	$\textbf{\color{#d91a1a}-11.20\%}$
test_clone	1.4683ms	13.1730μs	75.9128 KOps/s	75.1755 KOps/s	$\color{#35bf28}+0.98\%$
test_getitem[int]	0.9916ms	12.5463μs	79.7046 KOps/s	77.4725 KOps/s	$\color{#35bf28}+2.88\%$
test_getitem[slice_int]	0.1343ms	24.6922μs	40.4987 KOps/s	39.6547 KOps/s	$\color{#35bf28}+2.13\%$
test_getitem[range]	0.1650ms	45.8494μs	21.8105 KOps/s	20.2965 KOps/s	$\textbf{\color{#35bf28}+7.46\%}$
test_getitem[tuple]	0.1529ms	19.8538μs	50.3682 KOps/s	48.5469 KOps/s	$\color{#35bf28}+3.75\%$
test_getitem[list]	0.3645ms	42.1615μs	23.7183 KOps/s	22.4159 KOps/s	$\textbf{\color{#35bf28}+5.81\%}$
test_setitem_dim[int]	72.5160μs	24.8328μs	40.2692 KOps/s	39.8997 KOps/s	$\color{#35bf28}+0.93\%$
test_setitem_dim[slice_int]	0.1031ms	52.4667μs	19.0597 KOps/s	19.2728 KOps/s	$\color{#d91a1a}-1.11\%$
test_setitem_dim[range]	0.1283ms	72.7054μs	13.7541 KOps/s	12.8777 KOps/s	$\textbf{\color{#35bf28}+6.81\%}$
test_setitem_dim[tuple]	76.1640μs	41.0872μs	24.3385 KOps/s	24.8642 KOps/s	$\color{#d91a1a}-2.11\%$
test_setitem	0.1069ms	20.4925μs	48.7982 KOps/s	52.4169 KOps/s	$\textbf{\color{#d91a1a}-6.90\%}$
test_set	0.1079ms	19.8870μs	50.2841 KOps/s	53.2364 KOps/s	$\textbf{\color{#d91a1a}-5.55\%}$
test_set_shared	1.2035ms	0.1669ms	5.9916 KOps/s	5.8985 KOps/s	$\color{#35bf28}+1.58\%$
test_update	0.1682ms	23.0781μs	43.3312 KOps/s	50.2154 KOps/s	$\textbf{\color{#d91a1a}-13.71\%}$
test_update_nested	0.2573ms	32.8467μs	30.4445 KOps/s	32.5279 KOps/s	$\textbf{\color{#d91a1a}-6.40\%}$
test_update__nested	0.3874ms	32.5284μs	30.7423 KOps/s	30.7379 KOps/s	$\color{#35bf28}+0.01\%$
test_set_nested	53.3910μs	21.7331μs	46.0127 KOps/s	48.5527 KOps/s	$\textbf{\color{#d91a1a}-5.23\%}$
test_set_nested_new	0.2058ms	26.4084μs	37.8668 KOps/s	39.5443 KOps/s	$\color{#d91a1a}-4.24\%$
test_select	0.2121ms	42.3272μs	23.6255 KOps/s	23.6541 KOps/s	$\color{#d91a1a}-0.12\%$
test_select_nested	0.1199ms	61.1685μs	16.3483 KOps/s	15.6760 KOps/s	$\color{#35bf28}+4.29\%$
test_exclude_nested	0.1440ms	78.8940μs	12.6752 KOps/s	12.2367 KOps/s	$\color{#35bf28}+3.58\%$
test_empty[True]	0.4926ms	0.3830ms	2.6111 KOps/s	2.5745 KOps/s	$\color{#35bf28}+1.42\%$
test_empty[False]	5.7308μs	1.2144μs	823.4356 KOps/s	852.2666 KOps/s	$\color{#d91a1a}-3.38\%$
test_unbind_speed	0.3604ms	0.2601ms	3.8446 KOps/s	3.7450 KOps/s	$\color{#35bf28}+2.66\%$
test_unbind_speed_stack0	0.4200ms	0.2549ms	3.9233 KOps/s	3.9358 KOps/s	$\color{#d91a1a}-0.32\%$
test_unbind_speed_stack1	0.1275s	0.8774ms	1.1398 KOps/s	1.4554 KOps/s	$\textbf{\color{#d91a1a}-21.69\%}$
test_split	0.1219s	1.7914ms	558.2188 Ops/s	554.5952 Ops/s	$\color{#35bf28}+0.65\%$
test_chunk	0.1106s	1.7653ms	566.4618 Ops/s	552.1505 Ops/s	$\color{#35bf28}+2.59\%$
test_consolidate_njt[False-None]	9.5072ms	8.4379ms	118.5127 Ops/s	121.6192 Ops/s	$\color{#d91a1a}-2.55\%$
test_creation[device0]	0.3286ms	92.1279μs	10.8545 KOps/s	10.9368 KOps/s	$\color{#d91a1a}-0.75\%$
test_creation_from_tensor	3.8954ms	95.8762μs	10.4301 KOps/s	10.4796 KOps/s	$\color{#d91a1a}-0.47\%$
test_add_one[memmap_tensor0]	0.1806ms	5.0158μs	199.3719 KOps/s	206.6765 KOps/s	$\color{#d91a1a}-3.53\%$
test_contiguous[memmap_tensor0]	14.9780μs	0.5214μs	1.9181 MOps/s	1.9956 MOps/s	$\color{#d91a1a}-3.88\%$
test_stack[memmap_tensor0]	33.4430μs	3.4413μs	290.5898 KOps/s	302.9242 KOps/s	$\color{#d91a1a}-4.07\%$
test_memmaptd_index	1.3150ms	0.2358ms	4.2405 KOps/s	4.3079 KOps/s	$\color{#d91a1a}-1.56\%$
test_memmaptd_index_astensor	0.6844ms	0.3105ms	3.2206 KOps/s	3.2477 KOps/s	$\color{#d91a1a}-0.83\%$
test_memmaptd_index_op	1.3537ms	0.5900ms	1.6948 KOps/s	1.8882 KOps/s	$\textbf{\color{#d91a1a}-10.24\%}$
test_serialize_model	0.1345s	0.1239s	8.0714 Ops/s	8.1331 Ops/s	$\color{#d91a1a}-0.76\%$
test_serialize_model_pickle	0.4608s	0.3902s	2.5625 Ops/s	2.3871 Ops/s	$\textbf{\color{#35bf28}+7.35\%}$
test_serialize_weights	0.2394s	0.1398s	7.1556 Ops/s	8.7853 Ops/s	$\textbf{\color{#d91a1a}-18.55\%}$
test_serialize_weights_returnearly	0.1690s	0.1572s	6.3633 Ops/s	6.1674 Ops/s	$\color{#35bf28}+3.18\%$
test_serialize_weights_pickle	0.4504s	0.4084s	2.4485 Ops/s	1.0743 Ops/s	$\textbf{\color{#35bf28}+127.93\%}$
test_serialize_weights_filesystem	0.1551s	0.1431s	6.9878 Ops/s	7.0377 Ops/s	$\color{#d91a1a}-0.71\%$
test_serialize_model_filesystem	0.1687s	0.1584s	6.3142 Ops/s	6.9777 Ops/s	$\textbf{\color{#d91a1a}-9.51\%}$
test_reshape_pytree	67.4270μs	27.5858μs	36.2506 KOps/s	36.9393 KOps/s	$\color{#d91a1a}-1.86\%$
test_reshape_td	70.1220μs	32.6400μs	30.6373 KOps/s	30.4028 KOps/s	$\color{#35bf28}+0.77\%$
test_view_pytree	67.8870μs	27.4010μs	36.4950 KOps/s	36.6768 KOps/s	$\color{#d91a1a}-0.50\%$
test_view_td	81.2430μs	36.9313μs	27.0773 KOps/s	25.0026 KOps/s	$\textbf{\color{#35bf28}+8.30\%}$
test_unbind_pytree	62.7990μs	30.4865μs	32.8014 KOps/s	33.0192 KOps/s	$\color{#d91a1a}-0.66\%$
test_unbind_td	0.3137ms	38.3515μs	26.0746 KOps/s	25.1745 KOps/s	$\color{#35bf28}+3.58\%$
test_split_pytree	74.6900μs	30.1118μs	33.2096 KOps/s	33.8966 KOps/s	$\color{#d91a1a}-2.03\%$
test_split_td	0.4763ms	44.4000μs	22.5225 KOps/s	22.0948 KOps/s	$\color{#35bf28}+1.94\%$
test_add_pytree	74.7800μs	35.5269μs	28.1477 KOps/s	28.0972 KOps/s	$\color{#35bf28}+0.18\%$
test_add_td	0.1897ms	55.3453μs	18.0684 KOps/s	19.1978 KOps/s	$\textbf{\color{#d91a1a}-5.88\%}$
test_compile_add_one_nested[tensordict-compile]	0.1272ms	62.0900μs	16.1056 KOps/s	16.1709 KOps/s	$\color{#d91a1a}-0.40\%$
test_compile_add_one_nested[tensordict-eager]	0.6699ms	0.1585ms	6.3092 KOps/s	6.2536 KOps/s	$\color{#35bf28}+0.89\%$
test_compile_add_one_nested[pytree-compile]	0.1070ms	45.2694μs	22.0900 KOps/s	21.6523 KOps/s	$\color{#35bf28}+2.02\%$
test_compile_add_one_nested[pytree-eager]	0.2410ms	0.1190ms	8.4004 KOps/s	8.2624 KOps/s	$\color{#35bf28}+1.67\%$
test_compile_copy_nested[tensordict-compile]	77.1450μs	25.4092μs	39.3559 KOps/s	39.1099 KOps/s	$\color{#35bf28}+0.63\%$
test_compile_copy_nested[tensordict-eager]	0.1212ms	54.0063μs	18.5164 KOps/s	18.1788 KOps/s	$\color{#35bf28}+1.86\%$
test_compile_copy_nested[pytree-compile]	0.1532ms	78.2143μs	12.7854 KOps/s	12.6584 KOps/s	$\color{#35bf28}+1.00\%$
test_compile_copy_nested[pytree-eager]	0.1235ms	68.0640μs	14.6920 KOps/s	14.5921 KOps/s	$\color{#35bf28}+0.68\%$
test_compile_add_one_flat[tensordict-compile]	0.1969ms	0.1051ms	9.5157 KOps/s	9.5698 KOps/s	$\color{#d91a1a}-0.57\%$
test_compile_add_one_flat[tensordict-eager]	0.3685ms	0.1963ms	5.0932 KOps/s	5.0249 KOps/s	$\color{#35bf28}+1.36\%$
test_compile_add_one_flat[tensorclass-compile]	0.1059ms	44.6105μs	22.4162 KOps/s	22.5772 KOps/s	$\color{#d91a1a}-0.71\%$
test_compile_add_one_flat[tensorclass-eager]	0.4682ms	60.8642μs	16.4300 KOps/s	16.2994 KOps/s	$\color{#35bf28}+0.80\%$
test_compile_add_one_flat[pytree-compile]	0.5923ms	0.1038ms	9.6343 KOps/s	9.6471 KOps/s	$\color{#d91a1a}-0.13\%$
test_compile_add_one_flat[pytree-eager]	0.3407ms	0.2019ms	4.9534 KOps/s	4.8820 KOps/s	$\color{#35bf28}+1.46\%$
test_compile_add_self_flat[tensordict-eager]	0.3812ms	0.2077ms	4.8151 KOps/s	4.7794 KOps/s	$\color{#35bf28}+0.75\%$
test_compile_add_self_flat[tensordict-compile]	0.1825ms	0.1045ms	9.5713 KOps/s	9.4256 KOps/s	$\color{#35bf28}+1.55\%$
test_compile_add_self_flat[tensorclass-eager]	0.2043ms	54.2905μs	18.4194 KOps/s	18.8309 KOps/s	$\color{#d91a1a}-2.19\%$
test_compile_add_self_flat[tensorclass-compile]	0.1651ms	45.2318μs	22.1083 KOps/s	22.2309 KOps/s	$\color{#d91a1a}-0.55\%$
test_compile_add_self_flat[pytree-eager]	1.3838ms	0.1641ms	6.0955 KOps/s	6.2005 KOps/s	$\color{#d91a1a}-1.69\%$
test_compile_add_self_flat[pytree-compile]	0.2238ms	0.1016ms	9.8465 KOps/s	9.5794 KOps/s	$\color{#35bf28}+2.79\%$
test_compile_copy_flat[tensordict-compile]	52.6390μs	20.9783μs	47.6684 KOps/s	48.0640 KOps/s	$\color{#d91a1a}-0.82\%$
test_compile_copy_flat[tensordict-eager]	0.1493ms	58.5696μs	17.0737 KOps/s	16.9930 KOps/s	$\color{#35bf28}+0.48\%$
test_compile_copy_flat[pytree-compile]	0.1337ms	80.7687μs	12.3810 KOps/s	11.2193 KOps/s	$\textbf{\color{#35bf28}+10.35\%}$
test_compile_copy_flat[pytree-eager]	0.1444ms	68.9355μs	14.5063 KOps/s	14.0354 KOps/s	$\color{#35bf28}+3.36\%$
test_compile_assign_and_add[tensordict-compile]	0.2911ms	0.2016ms	4.9608 KOps/s	4.8425 KOps/s	$\color{#35bf28}+2.44\%$
test_compile_assign_and_add[tensordict-eager]	1.3947ms	1.2585ms	794.6230 Ops/s	783.5138 Ops/s	$\color{#35bf28}+1.42\%$
test_compile_assign_and_add[pytree-compile]	0.4206ms	0.1997ms	5.0074 KOps/s	4.9932 KOps/s	$\color{#35bf28}+0.28\%$
test_compile_assign_and_add[pytree-eager]	0.9418ms	0.7764ms	1.2879 KOps/s	1.2253 KOps/s	$\textbf{\color{#35bf28}+5.11\%}$
test_compile_assign_and_add_stack[compile]	0.7897ms	0.4457ms	2.2438 KOps/s	2.2241 KOps/s	$\color{#35bf28}+0.89\%$
test_compile_assign_and_add_stack[eager]	5.4390ms	2.6745ms	373.8990 Ops/s	402.1591 Ops/s	$\textbf{\color{#d91a1a}-7.03\%}$
test_compile_indexing[tensor-tensordict-compile]	83.3970μs	35.0447μs	28.5350 KOps/s	28.7209 KOps/s	$\color{#d91a1a}-0.65\%$
test_compile_indexing[tensor-tensordict-eager]	0.5707ms	31.7362μs	31.5098 KOps/s	29.4039 KOps/s	$\textbf{\color{#35bf28}+7.16\%}$
test_compile_indexing[tensor-tensorclass-compile]	80.9420μs	28.4517μs	35.1473 KOps/s	34.7463 KOps/s	$\color{#35bf28}+1.15\%$
test_compile_indexing[tensor-tensorclass-eager]	76.0730μs	23.3772μs	42.7767 KOps/s	43.0280 KOps/s	$\color{#d91a1a}-0.58\%$
test_compile_indexing[tensor-pytree-compile]	93.9060μs	30.2946μs	33.0092 KOps/s	33.6635 KOps/s	$\color{#d91a1a}-1.94\%$
test_compile_indexing[tensor-pytree-eager]	77.8460μs	23.5725μs	42.4223 KOps/s	41.8630 KOps/s	$\color{#35bf28}+1.34\%$
test_compile_indexing[slice-tensordict-compile]	0.1369ms	50.9059μs	19.6441 KOps/s	19.8743 KOps/s	$\color{#d91a1a}-1.16\%$
test_compile_indexing[slice-tensordict-eager]	0.5582ms	20.6987μs	48.3122 KOps/s	47.8134 KOps/s	$\color{#35bf28}+1.04\%$
test_compile_indexing[slice-tensorclass-compile]	0.1230ms	44.9818μs	22.2312 KOps/s	23.0055 KOps/s	$\color{#d91a1a}-3.37\%$
test_compile_indexing[slice-tensorclass-eager]	54.5520μs	19.0663μs	52.4487 KOps/s	52.8552 KOps/s	$\color{#d91a1a}-0.77\%$
test_compile_indexing[slice-pytree-compile]	95.7700μs	45.3262μs	22.0623 KOps/s	22.4747 KOps/s	$\color{#d91a1a}-1.83\%$
test_compile_indexing[slice-pytree-eager]	53.9810μs	19.2159μs	52.0403 KOps/s	53.0226 KOps/s	$\color{#d91a1a}-1.85\%$
test_compile_indexing[int-tensordict-compile]	0.1039ms	52.2752μs	19.1295 KOps/s	19.0546 KOps/s	$\color{#35bf28}+0.39\%$
test_compile_indexing[int-tensordict-eager]	0.9649ms	20.3661μs	49.1012 KOps/s	48.1254 KOps/s	$\color{#35bf28}+2.03\%$
test_compile_indexing[int-tensorclass-compile]	0.1394ms	45.2277μs	22.1104 KOps/s	22.2350 KOps/s	$\color{#d91a1a}-0.56\%$
test_compile_indexing[int-tensorclass-eager]	53.3200μs	19.2478μs	51.9541 KOps/s	53.4077 KOps/s	$\color{#d91a1a}-2.72\%$
test_compile_indexing[int-pytree-compile]	94.7680μs	45.2624μs	22.0934 KOps/s	22.3433 KOps/s	$\color{#d91a1a}-1.12\%$
test_compile_indexing[int-pytree-eager]	50.1140μs	19.1872μs	52.1182 KOps/s	53.3927 KOps/s	$\color{#d91a1a}-2.39\%$
test_mod_add[eager]	71.2040μs	34.8073μs	28.7296 KOps/s	31.2471 KOps/s	$\textbf{\color{#d91a1a}-8.06\%}$
test_mod_add[compile]	0.1091ms	46.5949μs	21.4616 KOps/s	21.7830 KOps/s	$\color{#d91a1a}-1.48\%$
test_mod_add[compile-overhead]	95.7700μs	46.0432μs	21.7187 KOps/s	20.9033 KOps/s	$\color{#35bf28}+3.90\%$
test_mod_wrap[eager]	0.3719ms	0.2276ms	4.3928 KOps/s	4.4510 KOps/s	$\color{#d91a1a}-1.31\%$
test_mod_wrap[compile]	0.2813ms	0.2042ms	4.8979 KOps/s	4.8694 KOps/s	$\color{#35bf28}+0.59\%$
test_mod_wrap[compile-overhead]	0.3859ms	0.2037ms	4.9085 KOps/s	4.7148 KOps/s	$\color{#35bf28}+4.11\%$
test_mod_wrap_and_backward[eager]	13.6929ms	11.4472ms	87.3579 Ops/s	89.2593 Ops/s	$\color{#d91a1a}-2.13\%$
test_mod_wrap_and_backward[compile]	17.5734ms	12.4571ms	80.2753 Ops/s	92.6016 Ops/s	$\textbf{\color{#d91a1a}-13.31\%}$
test_mod_wrap_and_backward[compile-overhead]	17.8597ms	12.4771ms	80.1467 Ops/s	91.4471 Ops/s	$\textbf{\color{#d91a1a}-12.36\%}$
test_seq_add[eager]	0.2099ms	0.1121ms	8.9194 KOps/s	9.0851 KOps/s	$\color{#d91a1a}-1.82\%$
test_seq_add[compile]	0.1145ms	59.5935μs	16.7803 KOps/s	16.6167 KOps/s	$\color{#35bf28}+0.98\%$
test_seq_add[compile-overhead]	0.1142ms	58.6169μs	17.0599 KOps/s	17.0570 KOps/s	$\color{#35bf28}+0.02\%$
test_seq_wrap[eager]	0.7297ms	0.4480ms	2.2319 KOps/s	2.3069 KOps/s	$\color{#d91a1a}-3.25\%$
test_seq_wrap[compile]	0.3709ms	0.2239ms	4.4669 KOps/s	4.4596 KOps/s	$\color{#35bf28}+0.16\%$
test_seq_wrap[compile-overhead]	0.3270ms	0.2245ms	4.4546 KOps/s	4.4877 KOps/s	$\color{#d91a1a}-0.74\%$
test_func_call_runtime[False-eager]	1.5701ms	0.5637ms	1.7740 KOps/s	1.7960 KOps/s	$\color{#d91a1a}-1.23\%$
test_func_call_runtime[False-compile]	0.8229ms	0.4277ms	2.3381 KOps/s	2.3410 KOps/s	$\color{#d91a1a}-0.12\%$
test_func_call_runtime[False-compile-overhead]	0.5088ms	0.4257ms	2.3489 KOps/s	2.3585 KOps/s	$\color{#d91a1a}-0.41\%$
test_func_call_runtime[True-eager]	1.3007ms	0.7807ms	1.2809 KOps/s	1.3071 KOps/s	$\color{#d91a1a}-2.00\%$
test_func_call_runtime[True-compile]	0.8621ms	0.4707ms	2.1243 KOps/s	2.1873 KOps/s	$\color{#d91a1a}-2.88\%$
test_func_call_runtime[True-compile-overhead]	0.7032ms	0.4725ms	2.1166 KOps/s	2.1753 KOps/s	$\color{#d91a1a}-2.70\%$
test_func_call_cm_runtime[False-eager]	0.6966ms	0.5602ms	1.7851 KOps/s	1.7993 KOps/s	$\color{#d91a1a}-0.79\%$
test_func_call_cm_runtime[False-compile]	0.8046ms	0.4294ms	2.3286 KOps/s	2.3460 KOps/s	$\color{#d91a1a}-0.74\%$
test_func_call_cm_runtime[False-compile-overhead]	0.5984ms	0.4262ms	2.3461 KOps/s	2.3657 KOps/s	$\color{#d91a1a}-0.83\%$
test_func_call_cm_runtime[True-eager]	1.1434ms	0.9038ms	1.1064 KOps/s	1.1068 KOps/s	$\color{#d91a1a}-0.04\%$
test_func_call_cm_runtime[True-compile]	0.6128ms	0.4952ms	2.0195 KOps/s	2.0404 KOps/s	$\color{#d91a1a}-1.02\%$
test_func_call_cm_runtime[True-compile-overhead]	0.7656ms	0.4942ms	2.0235 KOps/s	2.0630 KOps/s	$\color{#d91a1a}-1.91\%$
test_vmap_func_call_cm_runtime[eager]	2.2885ms	1.8639ms	536.5086 Ops/s	528.0269 Ops/s	$\color{#35bf28}+1.61\%$
test_vmap_func_call_cm_runtime[compile]	0.6377ms	0.5148ms	1.9424 KOps/s	1.9150 KOps/s	$\color{#35bf28}+1.43\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.6403ms	0.5203ms	1.9219 KOps/s	1.9272 KOps/s	$\color{#d91a1a}-0.27\%$
test_distributed	0.2310ms	0.1237ms	8.0866 KOps/s	7.8885 KOps/s	$\color{#35bf28}+2.51\%$
test_tdmodule	72.8470μs	27.0126μs	37.0198 KOps/s	40.4922 KOps/s	$\textbf{\color{#d91a1a}-8.58\%}$
test_tdmodule_dispatch	68.6090μs	49.0030μs	20.4069 KOps/s	21.6858 KOps/s	$\textbf{\color{#d91a1a}-5.90\%}$
test_tdseq	42.5700μs	26.4499μs	37.8073 KOps/s	40.4691 KOps/s	$\textbf{\color{#d91a1a}-6.58\%}$
test_tdseq_dispatch	96.3510μs	52.3778μs	19.0921 KOps/s	21.1424 KOps/s	$\textbf{\color{#d91a1a}-9.70\%}$
test_instantiation_functorch	1.7323ms	1.5151ms	660.0115 Ops/s	657.2404 Ops/s	$\color{#35bf28}+0.42\%$
test_exec_functorch	0.3019ms	0.1892ms	5.2842 KOps/s	5.5014 KOps/s	$\color{#d91a1a}-3.95\%$
test_exec_functional_call	0.2509ms	0.1798ms	5.5603 KOps/s	5.7619 KOps/s	$\color{#d91a1a}-3.50\%$
test_exec_td_decorator	0.4511ms	0.2341ms	4.2711 KOps/s	4.3610 KOps/s	$\color{#d91a1a}-2.06\%$
test_vmap_mlp_speed_decorator[True-True]	0.9189ms	0.6433ms	1.5544 KOps/s	1.5395 KOps/s	$\color{#35bf28}+0.97\%$
test_vmap_mlp_speed_decorator[True-False]	0.9694ms	0.6485ms	1.5420 KOps/s	1.5393 KOps/s	$\color{#35bf28}+0.17\%$
test_vmap_mlp_speed_decorator[False-True]	0.7211ms	0.5210ms	1.9195 KOps/s	1.9064 KOps/s	$\color{#35bf28}+0.69\%$
test_vmap_mlp_speed_decorator[False-False]	0.8159ms	0.5194ms	1.9255 KOps/s	1.9047 KOps/s	$\color{#35bf28}+1.09\%$
test_to_module_speed[True]	1.6503ms	1.2871ms	776.9278 Ops/s	777.4735 Ops/s	$\color{#d91a1a}-0.07\%$
test_to_module_speed[False]	1.9294ms	1.2586ms	794.5059 Ops/s	797.4742 Ops/s	$\color{#d91a1a}-0.37\%$
test_tc_init	0.1087ms	45.7202μs	21.8722 KOps/s	22.7642 KOps/s	$\color{#d91a1a}-3.92\%$
test_tc_init_nested	0.1630ms	89.3607μs	11.1906 KOps/s	11.4789 KOps/s	$\color{#d91a1a}-2.51\%$
test_tc_first_layer_tensor	29.1640μs	1.5169μs	659.2588 KOps/s	669.5466 KOps/s	$\color{#d91a1a}-1.54\%$
test_tc_first_layer_nontensor	28.7040μs	4.6778μs	213.7735 KOps/s	207.1166 KOps/s	$\color{#35bf28}+3.21\%$
test_tc_second_layer_tensor	25.7190μs	2.7741μs	360.4785 KOps/s	360.0583 KOps/s	$\color{#35bf28}+0.12\%$
test_tc_second_layer_nontensor	46.4770μs	6.0092μs	166.4127 KOps/s	163.6661 KOps/s	$\color{#35bf28}+1.68\%$
test_unbind	0.2376s	13.5926ms	73.5696 Ops/s	73.6849 Ops/s	$\color{#d91a1a}-0.16\%$
test_full_like	10.1976ms	7.5538ms	132.3841 Ops/s	117.6516 Ops/s	$\textbf{\color{#35bf28}+12.52\%}$
test_zeros_like	3.5778ms	2.9607ms	337.7587 Ops/s	126.0508 Ops/s	$\textbf{\color{#35bf28}+167.95\%}$
test_ones_like	4.1600ms	3.3986ms	294.2387 Ops/s	121.2062 Ops/s	$\textbf{\color{#35bf28}+142.76\%}$
test_clone	5.9663ms	5.1873ms	192.7784 Ops/s	95.4165 Ops/s	$\textbf{\color{#35bf28}+102.04\%}$
test_squeeze	57.4380μs	11.8527μs	84.3688 KOps/s	84.5630 KOps/s	$\color{#d91a1a}-0.23\%$
test_unsqueeze	0.1779ms	86.8755μs	11.5107 KOps/s	11.2340 KOps/s	$\color{#35bf28}+2.46\%$
test_split	0.4912ms	0.1949ms	5.1308 KOps/s	4.9961 KOps/s	$\color{#35bf28}+2.70\%$
test_permute	0.3925ms	0.2034ms	4.9169 KOps/s	4.8618 KOps/s	$\color{#35bf28}+1.13\%$
test_stack	41.1557ms	27.9385ms	35.7928 Ops/s	34.5738 Ops/s	$\color{#35bf28}+3.53\%$
test_cat	36.4113ms	30.8822ms	32.3811 Ops/s	35.3550 Ops/s	$\textbf{\color{#d91a1a}-8.41\%}$

[github-actions]

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}7$. Worsened: $\large\color{#d91a1a}31$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	32.4800μs	11.1919μs	89.3505 KOps/s	101.4115 KOps/s	$\textbf{\color{#d91a1a}-11.89\%}$
test_plain_set_stack_nested	33.6700μs	11.2087μs	89.2167 KOps/s	101.1327 KOps/s	$\textbf{\color{#d91a1a}-11.78\%}$
test_plain_set_nested_inplace	39.9710μs	12.1397μs	82.3747 KOps/s	92.6912 KOps/s	$\textbf{\color{#d91a1a}-11.13\%}$
test_plain_set_stack_nested_inplace	44.0310μs	12.0534μs	82.9641 KOps/s	92.1827 KOps/s	$\textbf{\color{#d91a1a}-10.00\%}$
test_items	28.0510μs	2.8944μs	345.4894 KOps/s	342.8455 KOps/s	$\color{#35bf28}+0.77\%$
test_items_nested	0.4088ms	0.3507ms	2.8511 KOps/s	2.7827 KOps/s	$\color{#35bf28}+2.46\%$
test_items_nested_locked	0.4387ms	0.3560ms	2.8087 KOps/s	2.7661 KOps/s	$\color{#35bf28}+1.54\%$
test_items_nested_leaf	93.5320μs	58.5972μs	17.0657 KOps/s	17.1204 KOps/s	$\color{#d91a1a}-0.32\%$
test_items_stack_nested	0.4133ms	0.3529ms	2.8340 KOps/s	2.7682 KOps/s	$\color{#35bf28}+2.38\%$
test_items_stack_nested_leaf	87.5620μs	57.9753μs	17.2487 KOps/s	16.7700 KOps/s	$\color{#35bf28}+2.85\%$
test_items_stack_nested_locked	0.4159ms	0.3533ms	2.8301 KOps/s	2.7685 KOps/s	$\color{#35bf28}+2.23\%$
test_keys	45.7610μs	3.4571μs	289.2616 KOps/s	288.5006 KOps/s	$\color{#35bf28}+0.26\%$
test_keys_nested	0.1135ms	69.9389μs	14.2982 KOps/s	14.1748 KOps/s	$\color{#35bf28}+0.87\%$
test_keys_nested_locked	0.7422ms	76.0930μs	13.1418 KOps/s	13.0234 KOps/s	$\color{#35bf28}+0.91\%$
test_keys_nested_leaf	2.5046ms	61.9441μs	16.1436 KOps/s	16.1552 KOps/s	$\color{#d91a1a}-0.07\%$
test_keys_stack_nested	0.1123ms	70.3037μs	14.2240 KOps/s	14.0180 KOps/s	$\color{#35bf28}+1.47\%$
test_keys_stack_nested_leaf	89.7920μs	61.4289μs	16.2790 KOps/s	15.9987 KOps/s	$\color{#35bf28}+1.75\%$
test_keys_stack_nested_locked	0.1152ms	76.0065μs	13.1568 KOps/s	13.0844 KOps/s	$\color{#35bf28}+0.55\%$
test_values	7.5052μs	0.8539μs	1.1711 MOps/s	1.1698 MOps/s	$\color{#35bf28}+0.12\%$
test_values_nested	59.8410μs	31.3612μs	31.8865 KOps/s	32.0839 KOps/s	$\color{#d91a1a}-0.62\%$
test_values_nested_locked	68.4910μs	32.8821μs	30.4117 KOps/s	30.6440 KOps/s	$\color{#d91a1a}-0.76\%$
test_values_nested_leaf	58.2410μs	33.6215μs	29.7429 KOps/s	29.8590 KOps/s	$\color{#d91a1a}-0.39\%$
test_values_stack_nested	79.4310μs	31.2571μs	31.9928 KOps/s	31.5424 KOps/s	$\color{#35bf28}+1.43\%$
test_values_stack_nested_leaf	54.5910μs	33.7697μs	29.6124 KOps/s	29.3425 KOps/s	$\color{#35bf28}+0.92\%$
test_values_stack_nested_locked	60.2210μs	33.1101μs	30.2023 KOps/s	30.3297 KOps/s	$\color{#d91a1a}-0.42\%$
test_membership	2.0446μs	0.5075μs	1.9706 MOps/s	1.9600 MOps/s	$\color{#35bf28}+0.54\%$
test_membership_nested	28.4600μs	2.0943μs	477.4792 KOps/s	485.9775 KOps/s	$\color{#d91a1a}-1.75\%$
test_membership_nested_leaf	15.9905μs	2.0447μs	489.0742 KOps/s	490.5246 KOps/s	$\color{#d91a1a}-0.30\%$
test_membership_stacked_nested	39.4300μs	2.1249μs	470.6060 KOps/s	481.2241 KOps/s	$\color{#d91a1a}-2.21\%$
test_membership_stacked_nested_leaf	24.7100μs	2.0867μs	479.2256 KOps/s	475.2505 KOps/s	$\color{#35bf28}+0.84\%$
test_membership_nested_last	37.9400μs	2.9588μs	337.9754 KOps/s	339.4166 KOps/s	$\color{#d91a1a}-0.42\%$
test_membership_nested_leaf_last	39.1010μs	2.9678μs	336.9446 KOps/s	339.9568 KOps/s	$\color{#d91a1a}-0.89\%$
test_membership_stacked_nested_last	29.8710μs	2.9829μs	335.2441 KOps/s	239.0505 KOps/s	$\textbf{\color{#35bf28}+40.24\%}$
test_membership_stacked_nested_leaf_last	39.5810μs	2.9816μs	335.3921 KOps/s	241.7572 KOps/s	$\textbf{\color{#35bf28}+38.73\%}$
test_nested_getleaf	32.8910μs	6.1719μs	162.0248 KOps/s	162.3134 KOps/s	$\color{#d91a1a}-0.18\%$
test_nested_get	28.1410μs	5.8963μs	169.5984 KOps/s	171.4832 KOps/s	$\color{#d91a1a}-1.10\%$
test_stacked_getleaf	41.7510μs	6.1649μs	162.2085 KOps/s	162.4696 KOps/s	$\color{#d91a1a}-0.16\%$
test_stacked_get	32.2710μs	5.8605μs	170.6343 KOps/s	171.5328 KOps/s	$\color{#d91a1a}-0.52\%$
test_nested_getitemleaf	41.1810μs	6.2545μs	159.8852 KOps/s	158.9402 KOps/s	$\color{#35bf28}+0.59\%$
test_nested_getitem	29.2410μs	5.9402μs	168.3443 KOps/s	167.9184 KOps/s	$\color{#35bf28}+0.25\%$
test_stacked_getitemleaf	49.2400μs	6.2235μs	160.6802 KOps/s	160.6210 KOps/s	$\color{#35bf28}+0.04\%$
test_stacked_getitem	28.8210μs	5.9163μs	169.0232 KOps/s	169.4437 KOps/s	$\color{#d91a1a}-0.25\%$
test_lock_nested	2.4324ms	0.3683ms	2.7153 KOps/s	2.6746 KOps/s	$\color{#35bf28}+1.52\%$
test_lock_stack_nested	0.3910ms	0.3398ms	2.9430 KOps/s	3.0044 KOps/s	$\color{#d91a1a}-2.05\%$
test_unlock_nested	0.7470ms	0.3105ms	3.2205 KOps/s	3.2725 KOps/s	$\color{#d91a1a}-1.59\%$
test_unlock_stack_nested	0.3240ms	0.2799ms	3.5729 KOps/s	3.6908 KOps/s	$\color{#d91a1a}-3.19\%$
test_flatten_speed	0.1077ms	74.3108μs	13.4570 KOps/s	13.2514 KOps/s	$\color{#35bf28}+1.55\%$
test_unflatten_speed	0.4586ms	0.3066ms	3.2612 KOps/s	3.2703 KOps/s	$\color{#d91a1a}-0.28\%$
test_common_ops	1.5882ms	0.6222ms	1.6073 KOps/s	1.7542 KOps/s	$\textbf{\color{#d91a1a}-8.37\%}$
test_creation	21.4000μs	1.4775μs	676.8117 KOps/s	679.4620 KOps/s	$\color{#d91a1a}-0.39\%$
test_creation_empty	33.9410μs	8.6541μs	115.5523 KOps/s	167.0895 KOps/s	$\textbf{\color{#d91a1a}-30.84\%}$
test_creation_nested_1	31.0110μs	10.2369μs	97.6854 KOps/s	133.9725 KOps/s	$\textbf{\color{#d91a1a}-27.09\%}$
test_creation_nested_2	1.8261ms	12.7808μs	78.2422 KOps/s	99.2740 KOps/s	$\textbf{\color{#d91a1a}-21.19\%}$
test_clone	40.1810μs	11.0070μs	90.8511 KOps/s	90.2738 KOps/s	$\color{#35bf28}+0.64\%$
test_getitem[int]	1.2114ms	11.0123μs	90.8072 KOps/s	91.4532 KOps/s	$\color{#d91a1a}-0.71\%$
test_getitem[slice_int]	0.1234ms	21.8359μs	45.7960 KOps/s	44.2064 KOps/s	$\color{#35bf28}+3.60\%$
test_getitem[range]	0.1432ms	39.4139μs	25.3718 KOps/s	25.2771 KOps/s	$\color{#35bf28}+0.37\%$
test_getitem[tuple]	0.1209ms	18.9474μs	52.7776 KOps/s	52.7094 KOps/s	$\color{#35bf28}+0.13\%$
test_getitem[list]	0.1347ms	33.9316μs	29.4710 KOps/s	29.1489 KOps/s	$\color{#35bf28}+1.11\%$
test_setitem_dim[int]	38.6600μs	19.8517μs	50.3735 KOps/s	49.6449 KOps/s	$\color{#35bf28}+1.47\%$
test_setitem_dim[slice_int]	65.8210μs	39.2990μs	25.4459 KOps/s	25.2245 KOps/s	$\color{#35bf28}+0.88\%$
test_setitem_dim[range]	93.0020μs	54.7134μs	18.2771 KOps/s	18.0147 KOps/s	$\color{#35bf28}+1.46\%$
test_setitem_dim[tuple]	50.9210μs	33.1265μs	30.1873 KOps/s	29.2624 KOps/s	$\color{#35bf28}+3.16\%$
test_setitem	0.1387ms	15.9766μs	62.5915 KOps/s	67.0149 KOps/s	$\textbf{\color{#d91a1a}-6.60\%}$
test_set	42.6410μs	15.8301μs	63.1708 KOps/s	69.3624 KOps/s	$\textbf{\color{#d91a1a}-8.93\%}$
test_set_shared	1.6034ms	0.1493ms	6.6981 KOps/s	6.7275 KOps/s	$\color{#d91a1a}-0.44\%$
test_update	0.4640ms	18.5402μs	53.9369 KOps/s	63.1234 KOps/s	$\textbf{\color{#d91a1a}-14.55\%}$
test_update_nested	0.1393ms	23.7347μs	42.1325 KOps/s	47.5773 KOps/s	$\textbf{\color{#d91a1a}-11.44\%}$
test_update__nested	0.6559ms	25.0214μs	39.9659 KOps/s	39.4557 KOps/s	$\color{#35bf28}+1.29\%$
test_set_nested	51.5010μs	16.8790μs	59.2451 KOps/s	63.9606 KOps/s	$\textbf{\color{#d91a1a}-7.37\%}$
test_set_nested_new	0.1291ms	18.6466μs	53.6289 KOps/s	55.4787 KOps/s	$\color{#d91a1a}-3.33\%$
test_select	62.3410μs	31.3838μs	31.8636 KOps/s	34.3375 KOps/s	$\textbf{\color{#d91a1a}-7.20\%}$
test_select_nested	84.2120μs	41.3598μs	24.1781 KOps/s	23.9762 KOps/s	$\color{#35bf28}+0.84\%$
test_exclude_nested	0.1199ms	60.9995μs	16.3936 KOps/s	16.2880 KOps/s	$\color{#35bf28}+0.65\%$
test_empty[True]	0.3452ms	0.2762ms	3.6211 KOps/s	3.5773 KOps/s	$\color{#35bf28}+1.23\%$
test_empty[False]	3.8061μs	0.7531μs	1.3279 MOps/s	1.3387 MOps/s	$\color{#d91a1a}-0.81\%$
test_to	91.7920μs	56.7683μs	17.6155 KOps/s	17.6146 KOps/s	$+0.01\%$
test_to_nonblocking	81.4710μs	47.1442μs	21.2115 KOps/s	21.1140 KOps/s	$\color{#35bf28}+0.46\%$
test_unbind_speed	0.2782ms	0.2334ms	4.2848 KOps/s	4.2949 KOps/s	$\color{#d91a1a}-0.23\%$
test_unbind_speed_stack0	0.2908ms	0.2346ms	4.2617 KOps/s	4.2706 KOps/s	$\color{#d91a1a}-0.21\%$
test_unbind_speed_stack1	93.3304ms	0.6570ms	1.5221 KOps/s	1.5571 KOps/s	$\color{#d91a1a}-2.25\%$
test_split	95.6362ms	1.7570ms	569.1661 Ops/s	565.7132 Ops/s	$\color{#35bf28}+0.61\%$
test_chunk	95.9101ms	1.6222ms	616.4479 Ops/s	668.4603 Ops/s	$\textbf{\color{#d91a1a}-7.78\%}$
test_consolidate[False-None]	3.0568ms	2.6422ms	378.4678 Ops/s	339.5625 Ops/s	$\textbf{\color{#35bf28}+11.46\%}$
test_consolidate[default-None]	1.7985ms	1.7101ms	584.7497 Ops/s	586.0678 Ops/s	$\color{#d91a1a}-0.22\%$
test_consolidate[reduce-overhead-None]	1.8410ms	1.7421ms	574.0154 Ops/s	580.8856 Ops/s	$\color{#d91a1a}-1.18\%$
test_consolidate_njt[False-None]	6.7748ms	6.4894ms	154.0986 Ops/s	149.6457 Ops/s	$\color{#35bf28}+2.98\%$
test_to[False-False-None]	1.7850ms	1.7014ms	587.7661 Ops/s	580.2804 Ops/s	$\color{#35bf28}+1.29\%$
test_to[True-False-None]	1.6250ms	1.3561ms	737.4273 Ops/s	742.2304 Ops/s	$\color{#d91a1a}-0.65\%$
test_to[within-False-None]	4.3382ms	4.0288ms	248.2135 Ops/s	243.1745 Ops/s	$\color{#35bf28}+2.07\%$
test_to[True-default-None]	5.5146ms	5.3013ms	188.6321 Ops/s	184.9717 Ops/s	$\color{#35bf28}+1.98\%$
test_to_njt[False-False-None]	7.2395ms	7.0472ms	141.9003 Ops/s	141.5662 Ops/s	$\color{#35bf28}+0.24\%$
test_to_njt[True-False-None]	5.7597ms	5.5869ms	178.9917 Ops/s	179.0926 Ops/s	$\color{#d91a1a}-0.06\%$
test_to_njt[within-False-None]	12.5242ms	12.2574ms	81.5832 Ops/s	80.9669 Ops/s	$\color{#35bf28}+0.76\%$
test_creation[device0]	0.4626ms	81.6333μs	12.2499 KOps/s	12.6531 KOps/s	$\color{#d91a1a}-3.19\%$
test_creation_from_tensor	0.4665ms	83.3042μs	12.0042 KOps/s	12.0505 KOps/s	$\color{#d91a1a}-0.38\%$
test_add_one[memmap_tensor0]	0.3944ms	7.2050μs	138.7917 KOps/s	135.0555 KOps/s	$\color{#35bf28}+2.77\%$
test_contiguous[memmap_tensor0]	1.7530μs	0.4160μs	2.4038 MOps/s	2.3940 MOps/s	$\color{#35bf28}+0.41\%$
test_stack[memmap_tensor0]	23.9100μs	4.6562μs	214.7664 KOps/s	211.7727 KOps/s	$\color{#35bf28}+1.41\%$
test_memmaptd_index	1.5934ms	0.2573ms	3.8861 KOps/s	3.8941 KOps/s	$\color{#d91a1a}-0.21\%$
test_memmaptd_index_astensor	0.5851ms	0.3138ms	3.1864 KOps/s	3.1906 KOps/s	$\color{#d91a1a}-0.13\%$
test_memmaptd_index_op	1.0635ms	0.6170ms	1.6209 KOps/s	1.7266 KOps/s	$\textbf{\color{#d91a1a}-6.12\%}$
test_serialize_model	0.4430s	0.1746s	5.7280 Ops/s	5.4500 Ops/s	$\textbf{\color{#35bf28}+5.10\%}$
test_serialize_model_pickle	1.3511s	1.2146s	0.8233 Ops/s	0.8194 Ops/s	$\color{#35bf28}+0.48\%$
test_serialize_weights	0.1306s	0.1300s	7.6930 Ops/s	7.7425 Ops/s	$\color{#d91a1a}-0.64\%$
test_serialize_weights_returnearly	0.3295s	54.9163ms	18.2095 Ops/s	23.4464 Ops/s	$\textbf{\color{#d91a1a}-22.34\%}$
test_serialize_weights_pickle	1.3777s	1.2174s	0.8214 Ops/s	0.8128 Ops/s	$\color{#35bf28}+1.07\%$
test_reshape_pytree	53.3310μs	22.5913μs	44.2648 KOps/s	44.0284 KOps/s	$\color{#35bf28}+0.54\%$
test_reshape_td	49.8610μs	26.9044μs	37.1686 KOps/s	36.8617 KOps/s	$\color{#35bf28}+0.83\%$
test_view_pytree	48.3600μs	22.4500μs	44.5434 KOps/s	44.7505 KOps/s	$\color{#d91a1a}-0.46\%$
test_view_td	61.2420μs	30.6491μs	32.6274 KOps/s	33.4084 KOps/s	$\color{#d91a1a}-2.34\%$
test_unbind_pytree	57.1010μs	28.3996μs	35.2118 KOps/s	35.3519 KOps/s	$\color{#d91a1a}-0.40\%$
test_unbind_td	0.7627ms	36.3608μs	27.5021 KOps/s	27.5217 KOps/s	$\color{#d91a1a}-0.07\%$
test_split_pytree	64.6020μs	30.6774μs	32.5973 KOps/s	32.7743 KOps/s	$\color{#d91a1a}-0.54\%$
test_split_td	0.9421ms	39.2604μs	25.4710 KOps/s	24.8034 KOps/s	$\color{#35bf28}+2.69\%$
test_add_pytree	76.9310μs	35.5455μs	28.1330 KOps/s	27.6840 KOps/s	$\color{#35bf28}+1.62\%$
test_add_td	86.5020μs	51.2052μs	19.5293 KOps/s	21.7957 KOps/s	$\textbf{\color{#d91a1a}-10.40\%}$
test_compile_add_one_nested[tensordict-compile]	0.1746ms	0.1220ms	8.1993 KOps/s	8.0523 KOps/s	$\color{#35bf28}+1.82\%$
test_compile_add_one_nested[tensordict-eager]	0.2170ms	0.1254ms	7.9764 KOps/s	7.9589 KOps/s	$\color{#35bf28}+0.22\%$
test_compile_add_one_nested[pytree-compile]	0.1385ms	98.4961μs	10.1527 KOps/s	10.0844 KOps/s	$\color{#35bf28}+0.68\%$
test_compile_add_one_nested[pytree-eager]	1.3648ms	0.1530ms	6.5361 KOps/s	6.4905 KOps/s	$\color{#35bf28}+0.70\%$
test_compile_copy_nested[tensordict-compile]	54.7910μs	23.2852μs	42.9457 KOps/s	41.8913 KOps/s	$\color{#35bf28}+2.52\%$
test_compile_copy_nested[tensordict-eager]	55.7910μs	26.6859μs	37.4729 KOps/s	37.3051 KOps/s	$\color{#35bf28}+0.45\%$
test_compile_copy_nested[pytree-compile]	91.6720μs	64.3882μs	15.5308 KOps/s	15.3222 KOps/s	$\color{#35bf28}+1.36\%$
test_compile_copy_nested[pytree-eager]	78.7910μs	49.0694μs	20.3793 KOps/s	20.1000 KOps/s	$\color{#35bf28}+1.39\%$
test_compile_add_one_flat[tensordict-compile]	0.1930ms	0.1455ms	6.8725 KOps/s	6.9083 KOps/s	$\color{#d91a1a}-0.52\%$
test_compile_add_one_flat[tensordict-eager]	0.3245ms	0.2076ms	4.8160 KOps/s	4.8305 KOps/s	$\color{#d91a1a}-0.30\%$
test_compile_add_one_flat[tensorclass-compile]	0.1433ms	0.1003ms	9.9699 KOps/s	10.0885 KOps/s	$\color{#d91a1a}-1.18\%$
test_compile_add_one_flat[tensorclass-eager]	0.1520ms	53.5428μs	18.6766 KOps/s	18.9386 KOps/s	$\color{#d91a1a}-1.38\%$
test_compile_add_one_flat[pytree-compile]	0.1783ms	0.1378ms	7.2544 KOps/s	7.2370 KOps/s	$\color{#35bf28}+0.24\%$
test_compile_add_one_flat[pytree-eager]	0.5388ms	0.4921ms	2.0320 KOps/s	1.9831 KOps/s	$\color{#35bf28}+2.46\%$
test_compile_add_self_flat[tensordict-eager]	0.3574ms	0.2485ms	4.0244 KOps/s	3.9951 KOps/s	$\color{#35bf28}+0.73\%$
test_compile_add_self_flat[tensordict-compile]	0.1994ms	0.1453ms	6.8807 KOps/s	6.8650 KOps/s	$\color{#35bf28}+0.23\%$
test_compile_add_self_flat[tensorclass-eager]	0.1385ms	62.5487μs	15.9875 KOps/s	16.0343 KOps/s	$\color{#d91a1a}-0.29\%$
test_compile_add_self_flat[tensorclass-compile]	0.1382ms	0.1023ms	9.7797 KOps/s	10.0658 KOps/s	$\color{#d91a1a}-2.84\%$
test_compile_add_self_flat[pytree-eager]	0.4514ms	0.4186ms	2.3889 KOps/s	2.3567 KOps/s	$\color{#35bf28}+1.37\%$
test_compile_add_self_flat[pytree-compile]	0.1758ms	0.1394ms	7.1734 KOps/s	7.3081 KOps/s	$\color{#d91a1a}-1.84\%$
test_compile_copy_flat[tensordict-compile]	0.1409ms	22.7038μs	44.0454 KOps/s	55.5162 KOps/s	$\textbf{\color{#d91a1a}-20.66\%}$
test_compile_copy_flat[tensordict-eager]	52.7110μs	26.6321μs	37.5487 KOps/s	37.2860 KOps/s	$\color{#35bf28}+0.70\%$
test_compile_copy_flat[pytree-compile]	99.7520μs	69.7998μs	14.3267 KOps/s	14.1567 KOps/s	$\color{#35bf28}+1.20\%$
test_compile_copy_flat[pytree-eager]	82.0510μs	50.9707μs	19.6191 KOps/s	19.3205 KOps/s	$\color{#35bf28}+1.55\%$
test_compile_assign_and_add[tensordict-compile]	1.6521ms	0.3979ms	2.5132 KOps/s	2.1659 KOps/s	$\textbf{\color{#35bf28}+16.03\%}$
test_compile_assign_and_add[tensordict-eager]	2.8009ms	2.6689ms	374.6921 Ops/s	372.4241 Ops/s	$\color{#35bf28}+0.61\%$
test_compile_assign_and_add[pytree-compile]	1.6356ms	0.4430ms	2.2575 KOps/s	2.2375 KOps/s	$\color{#35bf28}+0.89\%$
test_compile_assign_and_add[pytree-eager]	2.8335ms	2.7540ms	363.1036 Ops/s	362.4002 Ops/s	$\color{#35bf28}+0.19\%$
test_compile_indexing[tensor-tensordict-compile]	0.7330ms	0.1181ms	8.4650 KOps/s	8.7200 KOps/s	$\color{#d91a1a}-2.92\%$
test_compile_indexing[tensor-tensordict-eager]	0.5672ms	79.5074μs	12.5775 KOps/s	12.3489 KOps/s	$\color{#35bf28}+1.85\%$
test_compile_indexing[tensor-tensorclass-compile]	0.6934ms	0.1131ms	8.8393 KOps/s	9.2927 KOps/s	$\color{#d91a1a}-4.88\%$
test_compile_indexing[tensor-tensorclass-eager]	0.1771ms	71.6578μs	13.9552 KOps/s	14.4271 KOps/s	$\color{#d91a1a}-3.27\%$
test_compile_indexing[tensor-pytree-compile]	0.1613ms	0.1140ms	8.7734 KOps/s	9.2635 KOps/s	$\textbf{\color{#d91a1a}-5.29\%}$
test_compile_indexing[tensor-pytree-eager]	0.1188ms	71.9731μs	13.8941 KOps/s	14.4145 KOps/s	$\color{#d91a1a}-3.61\%$
test_compile_indexing[slice-tensordict-compile]	0.1469ms	0.1046ms	9.5566 KOps/s	9.8091 KOps/s	$\color{#d91a1a}-2.57\%$
test_compile_indexing[slice-tensordict-eager]	0.1416ms	17.9097μs	55.8358 KOps/s	53.8267 KOps/s	$\color{#35bf28}+3.73\%$
test_compile_indexing[slice-tensorclass-compile]	0.1456ms	0.1031ms	9.7028 KOps/s	10.2181 KOps/s	$\textbf{\color{#d91a1a}-5.04\%}$
test_compile_indexing[slice-tensorclass-eager]	49.3610μs	16.2526μs	61.5286 KOps/s	60.5636 KOps/s	$\color{#35bf28}+1.59\%$
test_compile_indexing[slice-pytree-compile]	0.1394ms	0.1019ms	9.8111 KOps/s	10.1446 KOps/s	$\color{#d91a1a}-3.29\%$
test_compile_indexing[slice-pytree-eager]	47.8810μs	16.1901μs	61.7661 KOps/s	61.0185 KOps/s	$\color{#35bf28}+1.23\%$
test_compile_indexing[int-tensordict-compile]	0.1495ms	0.1081ms	9.2496 KOps/s	9.7613 KOps/s	$\textbf{\color{#d91a1a}-5.24\%}$
test_compile_indexing[int-tensordict-eager]	0.5780ms	17.5380μs	57.0191 KOps/s	53.7766 KOps/s	$\textbf{\color{#35bf28}+6.03\%}$
test_compile_indexing[int-tensorclass-compile]	0.1479ms	0.1022ms	9.7841 KOps/s	10.1765 KOps/s	$\color{#d91a1a}-3.86\%$
test_compile_indexing[int-tensorclass-eager]	0.1770ms	16.2025μs	61.7187 KOps/s	61.4109 KOps/s	$\color{#35bf28}+0.50\%$
test_compile_indexing[int-pytree-compile]	0.1515ms	0.1031ms	9.6984 KOps/s	10.1599 KOps/s	$\color{#d91a1a}-4.54\%$
test_compile_indexing[int-pytree-eager]	48.2710μs	16.1366μs	61.9710 KOps/s	61.7528 KOps/s	$\color{#35bf28}+0.35\%$
test_mod_add[eager]	85.7020μs	40.9910μs	24.3956 KOps/s	26.7557 KOps/s	$\textbf{\color{#d91a1a}-8.82\%}$
test_mod_add[compile]	0.3570ms	88.5708μs	11.2904 KOps/s	11.9917 KOps/s	$\textbf{\color{#d91a1a}-5.85\%}$
test_mod_add[compile-overhead]	0.3285ms	0.1712ms	5.8407 KOps/s	5.5069 KOps/s	$\textbf{\color{#35bf28}+6.06\%}$
test_mod_wrap[eager]	0.3622ms	0.2569ms	3.8925 KOps/s	3.9010 KOps/s	$\color{#d91a1a}-0.22\%$
test_mod_wrap[compile]	0.3429ms	0.2885ms	3.4662 KOps/s	3.4382 KOps/s	$\color{#35bf28}+0.82\%$
test_mod_wrap[compile-overhead]	7.5938ms	3.8101ms	262.4601 Ops/s	265.5355 Ops/s	$\color{#d91a1a}-1.16\%$
test_mod_wrap_and_backward[eager]	1.5021ms	1.3841ms	722.4996 Ops/s	721.3870 Ops/s	$\color{#35bf28}+0.15\%$
test_mod_wrap_and_backward[compile]	1.3972ms	1.2916ms	774.2326 Ops/s	774.3799 Ops/s	$\color{#d91a1a}-0.02\%$
test_mod_wrap_and_backward[compile-overhead]	1.3668ms	0.9265ms	1.0794 KOps/s	1.0673 KOps/s	$\color{#35bf28}+1.13\%$
test_seq_add[eager]	0.2092ms	0.1149ms	8.7061 KOps/s	8.9247 KOps/s	$\color{#d91a1a}-2.45\%$
test_seq_add[compile]	0.1346ms	89.6175μs	11.1585 KOps/s	11.1499 KOps/s	$\color{#35bf28}+0.08\%$
test_seq_add[compile-overhead]	0.1897ms	0.1313ms	7.6179 KOps/s	7.6245 KOps/s	$\color{#d91a1a}-0.09\%$
test_seq_wrap[eager]	0.4941ms	0.4201ms	2.3801 KOps/s	2.3977 KOps/s	$\color{#d91a1a}-0.73\%$
test_seq_wrap[compile]	0.3778ms	0.3039ms	3.2909 KOps/s	3.2677 KOps/s	$\color{#35bf28}+0.71\%$
test_seq_wrap[compile-overhead]	0.2845ms	0.2257ms	4.4311 KOps/s	4.3793 KOps/s	$\color{#35bf28}+1.18\%$
test_func_call_runtime[False-eager]	0.8266ms	0.7495ms	1.3341 KOps/s	1.3178 KOps/s	$\color{#35bf28}+1.24\%$
test_func_call_runtime[False-compile]	0.8268ms	0.7610ms	1.3141 KOps/s	1.2808 KOps/s	$\color{#35bf28}+2.61\%$
test_func_call_runtime[False-compile-overhead]	0.4389ms	0.3670ms	2.7251 KOps/s	2.7288 KOps/s	$\color{#d91a1a}-0.14\%$
test_func_call_runtime[True-eager]	1.0062ms	0.9140ms	1.0941 KOps/s	1.0846 KOps/s	$\color{#35bf28}+0.88\%$
test_func_call_runtime[True-compile]	0.8627ms	0.7820ms	1.2788 KOps/s	1.2926 KOps/s	$\color{#d91a1a}-1.06\%$
test_func_call_runtime[True-compile-overhead]	0.4577ms	0.3873ms	2.5821 KOps/s	2.5820 KOps/s	$+0.01\%$
test_func_call_cm_runtime[False-eager]	0.8440ms	0.7480ms	1.3370 KOps/s	1.3239 KOps/s	$\color{#35bf28}+0.99\%$
test_func_call_cm_runtime[False-compile]	0.8375ms	0.7633ms	1.3101 KOps/s	1.3185 KOps/s	$\color{#d91a1a}-0.63\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4224ms	0.3692ms	2.7084 KOps/s	2.6959 KOps/s	$\color{#35bf28}+0.46\%$
test_func_call_cm_runtime[True-eager]	1.0996ms	1.0074ms	992.6681 Ops/s	951.7170 Ops/s	$\color{#35bf28}+4.30\%$
test_func_call_cm_runtime[True-compile]	0.8780ms	0.8102ms	1.2343 KOps/s	1.2242 KOps/s	$\color{#35bf28}+0.82\%$
test_func_call_cm_runtime[True-compile-overhead]	0.4749ms	0.4144ms	2.4129 KOps/s	2.4075 KOps/s	$\color{#35bf28}+0.22\%$
test_vmap_func_call_cm_runtime[eager]	2.5493ms	2.0911ms	478.2279 Ops/s	471.9219 Ops/s	$\color{#35bf28}+1.34\%$
test_vmap_func_call_cm_runtime[compile]	0.8885ms	0.8264ms	1.2101 KOps/s	1.2078 KOps/s	$\color{#35bf28}+0.19\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.4917ms	0.4161ms	2.4034 KOps/s	2.3958 KOps/s	$\color{#35bf28}+0.32\%$
test_distributed	6.0066ms	0.2635ms	3.7945 KOps/s	8.4727 KOps/s	$\textbf{\color{#d91a1a}-55.21\%}$
test_tdmodule	51.6910μs	20.0280μs	49.9300 KOps/s	54.5969 KOps/s	$\textbf{\color{#d91a1a}-8.55\%}$
test_tdmodule_dispatch	57.7010μs	35.6524μs	28.0486 KOps/s	31.0324 KOps/s	$\textbf{\color{#d91a1a}-9.62\%}$
test_tdseq	37.9710μs	19.5013μs	51.2786 KOps/s	56.4877 KOps/s	$\textbf{\color{#d91a1a}-9.22\%}$
test_tdseq_dispatch	66.3210μs	37.3427μs	26.7790 KOps/s	29.8487 KOps/s	$\textbf{\color{#d91a1a}-10.28\%}$
test_instantiation_functorch	1.6607ms	1.5563ms	642.5679 Ops/s	639.4148 Ops/s	$\color{#35bf28}+0.49\%$
test_exec_functorch	0.2113ms	0.1477ms	6.7701 KOps/s	6.7623 KOps/s	$\color{#35bf28}+0.11\%$
test_exec_functional_call	0.1976ms	0.1435ms	6.9689 KOps/s	6.9881 KOps/s	$\color{#d91a1a}-0.27\%$
test_exec_td_decorator	0.3718ms	0.1871ms	5.3433 KOps/s	5.2357 KOps/s	$\color{#35bf28}+2.06\%$
test_vmap_mlp_speed_decorator[True-True]	0.7988ms	0.6906ms	1.4481 KOps/s	1.4602 KOps/s	$\color{#d91a1a}-0.83\%$
test_vmap_mlp_speed_decorator[True-False]	0.8402ms	0.6936ms	1.4417 KOps/s	1.4472 KOps/s	$\color{#d91a1a}-0.38\%$
test_vmap_mlp_speed_decorator[False-True]	0.7177ms	0.5983ms	1.6714 KOps/s	1.6625 KOps/s	$\color{#35bf28}+0.54\%$
test_vmap_mlp_speed_decorator[False-False]	0.7429ms	0.6051ms	1.6527 KOps/s	1.6615 KOps/s	$\color{#d91a1a}-0.53\%$
test_vmap_transformer_speed_decorator[True-True]	19.5842ms	19.3695ms	51.6276 Ops/s	51.6527 Ops/s	$\color{#d91a1a}-0.05\%$
test_vmap_transformer_speed_decorator[True-False]	20.0924ms	19.4601ms	51.3871 Ops/s	51.6064 Ops/s	$\color{#d91a1a}-0.43\%$
test_vmap_transformer_speed_decorator[False-True]	20.3249ms	19.4427ms	51.4333 Ops/s	52.0357 Ops/s	$\color{#d91a1a}-1.16\%$
test_vmap_transformer_speed_decorator[False-False]	19.4118ms	19.2816ms	51.8628 Ops/s	51.6279 Ops/s	$\color{#35bf28}+0.46\%$
test_to_module_speed[True]	1.0490ms	0.9273ms	1.0784 KOps/s	1.0629 KOps/s	$\color{#35bf28}+1.46\%$
test_to_module_speed[False]	1.3586ms	0.9239ms	1.0824 KOps/s	1.0875 KOps/s	$\color{#d91a1a}-0.46\%$
test_tc_init	65.6820μs	35.0737μs	28.5114 KOps/s	29.7329 KOps/s	$\color{#d91a1a}-4.11\%$
test_tc_init_nested	0.1026ms	71.7649μs	13.9344 KOps/s	14.4438 KOps/s	$\color{#d91a1a}-3.53\%$
test_tc_first_layer_tensor	5.2159μs	0.7011μs	1.4263 MOps/s	1.4345 MOps/s	$\color{#d91a1a}-0.57\%$
test_tc_first_layer_nontensor	46.8110μs	2.3038μs	434.0655 KOps/s	429.5098 KOps/s	$\color{#35bf28}+1.06\%$
test_tc_second_layer_tensor	8.0278μs	1.4209μs	703.7657 KOps/s	705.8673 KOps/s	$\color{#d91a1a}-0.30\%$
test_tc_second_layer_nontensor	23.8410μs	3.0607μs	326.7203 KOps/s	327.7199 KOps/s	$\color{#d91a1a}-0.31\%$
test_unbind	0.2212s	9.8099ms	101.9379 Ops/s	151.4896 Ops/s	$\textbf{\color{#d91a1a}-32.71\%}$
test_full_like	10.2900ms	9.1583ms	109.1903 Ops/s	104.7619 Ops/s	$\color{#35bf28}+4.23\%$
test_zeros_like	5.3933ms	4.3027ms	232.4098 Ops/s	231.3542 Ops/s	$\color{#35bf28}+0.46\%$
test_ones_like	9.1580ms	7.1113ms	140.6205 Ops/s	240.5168 Ops/s	$\textbf{\color{#d91a1a}-41.53\%}$
test_clone	6.8021ms	6.3590ms	157.2566 Ops/s	157.8830 Ops/s	$\color{#d91a1a}-0.40\%$
test_squeeze	61.2110μs	9.6866μs	103.2359 KOps/s	104.7696 KOps/s	$\color{#d91a1a}-1.46\%$
test_unsqueeze	0.1609ms	72.4710μs	13.7986 KOps/s	13.9495 KOps/s	$\color{#d91a1a}-1.08\%$
test_split	0.3926ms	0.1602ms	6.2406 KOps/s	6.1777 KOps/s	$\color{#35bf28}+1.02\%$
test_permute	0.2391ms	0.1773ms	5.6396 KOps/s	5.6510 KOps/s	$\color{#d91a1a}-0.20\%$
test_stack	50.7203ms	50.3507ms	19.8607 Ops/s	19.7223 Ops/s	$\color{#35bf28}+0.70\%$
test_cat	50.5696ms	50.2366ms	19.9058 Ops/s	19.7980 Ops/s	$\color{#35bf28}+0.54\%$