[BugFix] Fix stack of tensorclasses (and nontensors)

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 144. Improved: $\large\color{#35bf28}4$. Worsened: $\large\color{#d91a1a}22$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	34.0930μs	17.1897μs	58.1745 KOps/s	60.8753 KOps/s	$\color{#d91a1a}-4.44\%$
test_plain_set_stack_nested	49.8340μs	17.4352μs	57.3552 KOps/s	60.6307 KOps/s	$\textbf{\color{#d91a1a}-5.40\%}$
test_plain_set_nested_inplace	57.3780μs	19.5598μs	51.1253 KOps/s	53.0998 KOps/s	$\color{#d91a1a}-3.72\%$
test_plain_set_stack_nested_inplace	73.4380μs	19.2301μs	52.0018 KOps/s	53.5923 KOps/s	$\color{#d91a1a}-2.97\%$
test_items	36.1380μs	2.7389μs	365.1092 KOps/s	384.6385 KOps/s	$\textbf{\color{#d91a1a}-5.08\%}$
test_items_nested	0.4142ms	0.2633ms	3.7976 KOps/s	3.7425 KOps/s	$\color{#35bf28}+1.47\%$
test_items_nested_locked	1.1477ms	0.2648ms	3.7764 KOps/s	3.7382 KOps/s	$\color{#35bf28}+1.02\%$
test_items_nested_leaf	0.1361ms	76.9078μs	13.0026 KOps/s	12.8973 KOps/s	$\color{#35bf28}+0.82\%$
test_items_stack_nested	0.4188ms	0.2666ms	3.7509 KOps/s	3.7272 KOps/s	$\color{#35bf28}+0.63\%$
test_items_stack_nested_leaf	0.1428ms	77.5607μs	12.8931 KOps/s	13.1804 KOps/s	$\color{#d91a1a}-2.18\%$
test_items_stack_nested_locked	1.1430ms	0.2674ms	3.7401 KOps/s	3.7389 KOps/s	$\color{#35bf28}+0.03\%$
test_keys	22.5420μs	4.0271μs	248.3178 KOps/s	260.7721 KOps/s	$\color{#d91a1a}-4.78\%$
test_keys_nested	0.2122ms	0.1381ms	7.2434 KOps/s	7.1114 KOps/s	$\color{#35bf28}+1.86\%$
test_keys_nested_locked	0.7168ms	0.1432ms	6.9824 KOps/s	6.9589 KOps/s	$\color{#35bf28}+0.34\%$
test_keys_nested_leaf	0.2075ms	0.1162ms	8.6034 KOps/s	8.4797 KOps/s	$\color{#35bf28}+1.46\%$
test_keys_stack_nested	0.2378ms	0.1387ms	7.2121 KOps/s	7.3019 KOps/s	$\color{#d91a1a}-1.23\%$
test_keys_stack_nested_leaf	0.1965ms	0.1169ms	8.5561 KOps/s	8.6310 KOps/s	$\color{#d91a1a}-0.87\%$
test_keys_stack_nested_locked	0.3057ms	0.1447ms	6.9102 KOps/s	7.1197 KOps/s	$\color{#d91a1a}-2.94\%$
test_values	9.3298μs	1.1735μs	852.1274 KOps/s	880.8301 KOps/s	$\color{#d91a1a}-3.26\%$
test_values_nested	0.1048ms	50.3781μs	19.8499 KOps/s	19.4865 KOps/s	$\color{#35bf28}+1.86\%$
test_values_nested_locked	0.1010ms	50.3453μs	19.8628 KOps/s	19.4414 KOps/s	$\color{#35bf28}+2.17\%$
test_values_nested_leaf	85.7710μs	45.9300μs	21.7723 KOps/s	21.5985 KOps/s	$\color{#35bf28}+0.80\%$
test_values_stack_nested	99.8160μs	51.0966μs	19.5708 KOps/s	19.3302 KOps/s	$\color{#35bf28}+1.24\%$
test_values_stack_nested_leaf	87.6140μs	45.6974μs	21.8831 KOps/s	22.1686 KOps/s	$\color{#d91a1a}-1.29\%$
test_values_stack_nested_locked	0.1102ms	50.2708μs	19.8923 KOps/s	19.5574 KOps/s	$\color{#35bf28}+1.71\%$
test_membership	35.9770μs	1.3268μs	753.7140 KOps/s	732.8642 KOps/s	$\color{#35bf28}+2.84\%$
test_membership_nested	40.6160μs	3.4294μs	291.5935 KOps/s	280.7667 KOps/s	$\color{#35bf28}+3.86\%$
test_membership_nested_leaf	39.0840μs	3.4240μs	292.0522 KOps/s	280.2631 KOps/s	$\color{#35bf28}+4.21\%$
test_membership_stacked_nested	38.7630μs	3.4397μs	290.7196 KOps/s	284.0692 KOps/s	$\color{#35bf28}+2.34\%$
test_membership_stacked_nested_leaf	29.1150μs	3.4303μs	291.5191 KOps/s	284.2234 KOps/s	$\color{#35bf28}+2.57\%$
test_membership_nested_last	40.6360μs	4.2312μs	236.3413 KOps/s	232.5825 KOps/s	$\color{#35bf28}+1.62\%$
test_membership_nested_leaf_last	49.7270μs	4.1845μs	238.9746 KOps/s	232.9815 KOps/s	$\color{#35bf28}+2.57\%$
test_membership_stacked_nested_last	24.2150μs	4.2971μs	232.7133 KOps/s	73.8089 KOps/s	$\textbf{\color{#35bf28}+215.29\%}$
test_membership_stacked_nested_leaf_last	41.4670μs	4.2196μs	236.9900 KOps/s	74.1847 KOps/s	$\textbf{\color{#35bf28}+219.46\%}$
test_nested_getleaf	36.7790μs	10.5047μs	95.1956 KOps/s	93.0481 KOps/s	$\color{#35bf28}+2.31\%$
test_nested_get	47.8800μs	10.0411μs	99.5910 KOps/s	98.6265 KOps/s	$\color{#35bf28}+0.98\%$
test_stacked_getleaf	52.7480μs	10.3842μs	96.3004 KOps/s	93.7722 KOps/s	$\color{#35bf28}+2.70\%$
test_stacked_get	45.5850μs	9.9835μs	100.1650 KOps/s	99.9561 KOps/s	$\color{#35bf28}+0.21\%$
test_nested_getitemleaf	66.7780μs	11.0328μs	90.6385 KOps/s	91.5765 KOps/s	$\color{#d91a1a}-1.02\%$
test_nested_getitem	46.8870μs	10.2331μs	97.7225 KOps/s	97.9164 KOps/s	$\color{#d91a1a}-0.20\%$
test_stacked_getitemleaf	45.3250μs	11.2147μs	89.1686 KOps/s	90.4063 KOps/s	$\color{#d91a1a}-1.37\%$
test_stacked_getitem	31.8900μs	10.2192μs	97.8548 KOps/s	98.1783 KOps/s	$\color{#d91a1a}-0.33\%$
test_lock_nested	0.8087ms	0.3447ms	2.9010 KOps/s	2.9173 KOps/s	$\color{#d91a1a}-0.56\%$
test_lock_stack_nested	0.6857ms	0.3137ms	3.1881 KOps/s	3.3438 KOps/s	$\color{#d91a1a}-4.65\%$
test_unlock_nested	0.9498ms	0.3477ms	2.8757 KOps/s	2.8355 KOps/s	$\color{#35bf28}+1.42\%$
test_unlock_stack_nested	0.6346ms	0.3216ms	3.1099 KOps/s	3.2646 KOps/s	$\color{#d91a1a}-4.74\%$
test_flatten_speed	0.5393ms	93.9752μs	10.6411 KOps/s	10.4144 KOps/s	$\color{#35bf28}+2.18\%$
test_unflatten_speed	0.6190ms	0.4038ms	2.4765 KOps/s	2.4080 KOps/s	$\color{#35bf28}+2.84\%$
test_common_ops	4.6699ms	0.7476ms	1.3376 KOps/s	1.4180 KOps/s	$\textbf{\color{#d91a1a}-5.67\%}$
test_creation	51.6870μs	1.9809μs	504.8305 KOps/s	522.7033 KOps/s	$\color{#d91a1a}-3.42\%$
test_creation_empty	46.6170μs	11.0524μs	90.4778 KOps/s	108.0304 KOps/s	$\textbf{\color{#d91a1a}-16.25\%}$
test_creation_nested_1	41.2970μs	13.7409μs	72.7752 KOps/s	82.7492 KOps/s	$\textbf{\color{#d91a1a}-12.05\%}$
test_creation_nested_2	58.4290μs	17.1237μs	58.3984 KOps/s	64.9887 KOps/s	$\textbf{\color{#d91a1a}-10.14\%}$
test_clone	0.1894ms	13.4275μs	74.4743 KOps/s	74.9993 KOps/s	$\color{#d91a1a}-0.70\%$
test_getitem[int]	52.7880μs	11.3909μs	87.7894 KOps/s	87.8218 KOps/s	$\color{#d91a1a}-0.04\%$
test_getitem[slice_int]	72.5650μs	22.8362μs	43.7900 KOps/s	43.6397 KOps/s	$\color{#35bf28}+0.34\%$
test_getitem[range]	86.4310μs	61.8414μs	16.1704 KOps/s	16.6605 KOps/s	$\color{#d91a1a}-2.94\%$
test_getitem[tuple]	64.7820μs	18.7414μs	53.3577 KOps/s	52.8816 KOps/s	$\color{#35bf28}+0.90\%$
test_getitem[list]	0.1778ms	42.7920μs	23.3688 KOps/s	24.2160 KOps/s	$\color{#d91a1a}-3.50\%$
test_setitem_dim[int]	63.5790μs	34.9728μs	28.5936 KOps/s	28.5599 KOps/s	$\color{#35bf28}+0.12\%$
test_setitem_dim[slice_int]	0.1114ms	63.1980μs	15.8233 KOps/s	15.4684 KOps/s	$\color{#35bf28}+2.29\%$
test_setitem_dim[range]	0.2618ms	87.3200μs	11.4521 KOps/s	11.7661 KOps/s	$\color{#d91a1a}-2.67\%$
test_setitem_dim[tuple]	0.1181ms	51.1064μs	19.5670 KOps/s	19.7985 KOps/s	$\color{#d91a1a}-1.17\%$
test_setitem	71.4140μs	20.5245μs	48.7223 KOps/s	52.1022 KOps/s	$\textbf{\color{#d91a1a}-6.49\%}$
test_set	64.4410μs	20.0689μs	49.8283 KOps/s	53.6159 KOps/s	$\textbf{\color{#d91a1a}-7.06\%}$
test_set_shared	4.0178ms	0.1466ms	6.8191 KOps/s	6.9158 KOps/s	$\color{#d91a1a}-1.40\%$
test_update	0.1681ms	23.1562μs	43.1850 KOps/s	50.8227 KOps/s	$\textbf{\color{#d91a1a}-15.03\%}$
test_update_nested	96.6210μs	31.6188μs	31.6267 KOps/s	34.6748 KOps/s	$\textbf{\color{#d91a1a}-8.79\%}$
test_update__nested	76.2330μs	25.0452μs	39.9278 KOps/s	38.5926 KOps/s	$\color{#35bf28}+3.46\%$
test_set_nested	0.1054ms	22.1874μs	45.0707 KOps/s	47.1343 KOps/s	$\color{#d91a1a}-4.38\%$
test_set_nested_new	97.8130μs	26.1974μs	38.1718 KOps/s	38.2946 KOps/s	$\color{#d91a1a}-0.32\%$
test_select	0.1240ms	41.7797μs	23.9351 KOps/s	24.8441 KOps/s	$\color{#d91a1a}-3.66\%$
test_select_nested	0.1121ms	59.8738μs	16.7018 KOps/s	16.8578 KOps/s	$\color{#d91a1a}-0.93\%$
test_exclude_nested	0.2918ms	0.1182ms	8.4605 KOps/s	8.3963 KOps/s	$\color{#35bf28}+0.76\%$
test_empty[True]	0.6454ms	0.4030ms	2.4816 KOps/s	2.5359 KOps/s	$\color{#d91a1a}-2.14\%$
test_empty[False]	8.1472μs	1.1681μs	856.0737 KOps/s	851.4972 KOps/s	$\color{#35bf28}+0.54\%$
test_unbind_speed	0.4437ms	0.2538ms	3.9405 KOps/s	3.8822 KOps/s	$\color{#35bf28}+1.50\%$
test_unbind_speed_stack0	0.4097ms	0.2568ms	3.8940 KOps/s	4.0572 KOps/s	$\color{#d91a1a}-4.02\%$
test_unbind_speed_stack1	0.8171ms	0.6517ms	1.5344 KOps/s	1.4004 KOps/s	$\textbf{\color{#35bf28}+9.57\%}$
test_split	69.6045ms	1.6156ms	618.9544 Ops/s	625.4742 Ops/s	$\color{#d91a1a}-1.04\%$
test_chunk	70.8881ms	1.6148ms	619.2741 Ops/s	619.4332 Ops/s	$\color{#d91a1a}-0.03\%$
test_creation[device0]	0.2052ms	86.5312μs	11.5565 KOps/s	11.7076 KOps/s	$\color{#d91a1a}-1.29\%$
test_creation_from_tensor	3.5792ms	87.8421μs	11.3841 KOps/s	11.3096 KOps/s	$\color{#35bf28}+0.66\%$
test_add_one[memmap_tensor0]	0.1261ms	5.6842μs	175.9262 KOps/s	182.0096 KOps/s	$\color{#d91a1a}-3.34\%$
test_contiguous[memmap_tensor0]	7.5440μs	0.6337μs	1.5779 MOps/s	1.5731 MOps/s	$\color{#35bf28}+0.31\%$
test_stack[memmap_tensor0]	26.5590μs	3.7435μs	267.1298 KOps/s	282.4426 KOps/s	$\textbf{\color{#d91a1a}-5.42\%}$
test_memmaptd_index	0.9995ms	0.2522ms	3.9651 KOps/s	4.0007 KOps/s	$\color{#d91a1a}-0.89\%$
test_memmaptd_index_astensor	0.7350ms	0.3279ms	3.0501 KOps/s	3.0871 KOps/s	$\color{#d91a1a}-1.20\%$
test_memmaptd_index_op	1.0183ms	0.6244ms	1.6014 KOps/s	1.6947 KOps/s	$\textbf{\color{#d91a1a}-5.51\%}$
test_serialize_model	0.1821s	0.1153s	8.6741 Ops/s	8.5203 Ops/s	$\color{#35bf28}+1.81\%$
test_serialize_model_pickle	0.4475s	0.3799s	2.6323 Ops/s	2.4591 Ops/s	$\textbf{\color{#35bf28}+7.05\%}$
test_serialize_weights	0.1759s	0.1122s	8.9154 Ops/s	8.5751 Ops/s	$\color{#35bf28}+3.97\%$
test_serialize_weights_returnearly	0.1977s	0.1352s	7.3990 Ops/s	7.1674 Ops/s	$\color{#35bf28}+3.23\%$
test_serialize_weights_pickle	0.7076s	0.4853s	2.0605 Ops/s	2.4651 Ops/s	$\textbf{\color{#d91a1a}-16.41\%}$
test_serialize_weights_filesystem	94.6158ms	91.8466ms	10.8877 Ops/s	10.7686 Ops/s	$\color{#35bf28}+1.11\%$
test_serialize_model_filesystem	0.1631s	0.1023s	9.7789 Ops/s	9.6710 Ops/s	$\color{#35bf28}+1.12\%$
test_reshape_pytree	53.7000μs	25.3638μs	39.4263 KOps/s	39.0742 KOps/s	$\color{#35bf28}+0.90\%$
test_reshape_td	78.1660μs	33.8176μs	29.5704 KOps/s	28.5995 KOps/s	$\color{#35bf28}+3.39\%$
test_view_pytree	68.6990μs	25.4950μs	39.2234 KOps/s	38.8954 KOps/s	$\color{#35bf28}+0.84\%$
test_view_td	0.1212ms	38.4239μs	26.0255 KOps/s	25.7361 KOps/s	$\color{#35bf28}+1.12\%$
test_unbind_pytree	73.6980μs	29.5471μs	33.8442 KOps/s	33.9126 KOps/s	$\color{#d91a1a}-0.20\%$
test_unbind_td	0.3653ms	37.7611μs	26.4823 KOps/s	26.2891 KOps/s	$\color{#35bf28}+0.73\%$
test_split_pytree	73.0470μs	29.5196μs	33.8758 KOps/s	34.1940 KOps/s	$\color{#d91a1a}-0.93\%$
test_split_td	0.1237ms	40.4752μs	24.7065 KOps/s	24.8254 KOps/s	$\color{#d91a1a}-0.48\%$
test_add_pytree	88.3360μs	35.8756μs	27.8741 KOps/s	28.6214 KOps/s	$\color{#d91a1a}-2.61\%$
test_add_td	0.1196ms	55.8544μs	17.9037 KOps/s	18.4731 KOps/s	$\color{#d91a1a}-3.08\%$
test_distributed	0.2018ms	0.1019ms	9.8172 KOps/s	9.6132 KOps/s	$\color{#35bf28}+2.12\%$
test_tdmodule	46.1970μs	18.4091μs	54.3210 KOps/s	58.7876 KOps/s	$\textbf{\color{#d91a1a}-7.60\%}$
test_tdmodule_dispatch	69.1190μs	35.2257μs	28.3883 KOps/s	29.9371 KOps/s	$\textbf{\color{#d91a1a}-5.17\%}$
test_tdseq	54.8830μs	20.6105μs	48.5191 KOps/s	51.4226 KOps/s	$\textbf{\color{#d91a1a}-5.65\%}$
test_tdseq_dispatch	75.7820μs	40.5059μs	24.6877 KOps/s	26.0618 KOps/s	$\textbf{\color{#d91a1a}-5.27\%}$
test_instantiation_functorch	1.5852ms	1.2897ms	775.3525 Ops/s	753.5812 Ops/s	$\color{#35bf28}+2.89\%$
test_instantiation_td	1.7091ms	1.0221ms	978.4017 Ops/s	971.2304 Ops/s	$\color{#35bf28}+0.74\%$
test_exec_functorch	0.3041ms	0.1617ms	6.1833 KOps/s	6.1664 KOps/s	$\color{#35bf28}+0.27\%$
test_exec_functional_call	0.2813ms	0.1494ms	6.6944 KOps/s	6.6970 KOps/s	$\color{#d91a1a}-0.04\%$
test_exec_td	0.2485ms	0.1452ms	6.8879 KOps/s	6.8474 KOps/s	$\color{#35bf28}+0.59\%$
test_exec_td_decorator	0.9500ms	0.2241ms	4.4626 KOps/s	4.3612 KOps/s	$\color{#35bf28}+2.32\%$
test_vmap_mlp_speed[True-True]	0.7117ms	0.5000ms	2.0000 KOps/s	2.0449 KOps/s	$\color{#d91a1a}-2.19\%$
test_vmap_mlp_speed[True-False]	0.8166ms	0.4973ms	2.0109 KOps/s	2.0845 KOps/s	$\color{#d91a1a}-3.53\%$
test_vmap_mlp_speed[False-True]	0.6065ms	0.4050ms	2.4691 KOps/s	2.5202 KOps/s	$\color{#d91a1a}-2.03\%$
test_vmap_mlp_speed[False-False]	0.8009ms	0.4090ms	2.4448 KOps/s	2.5198 KOps/s	$\color{#d91a1a}-2.97\%$
test_vmap_mlp_speed_decorator[True-True]	1.3417ms	0.5733ms	1.7443 KOps/s	1.7863 KOps/s	$\color{#d91a1a}-2.35\%$
test_vmap_mlp_speed_decorator[True-False]	0.7897ms	0.5682ms	1.7599 KOps/s	1.7904 KOps/s	$\color{#d91a1a}-1.70\%$
test_vmap_mlp_speed_decorator[False-True]	0.7250ms	0.4682ms	2.1356 KOps/s	2.1770 KOps/s	$\color{#d91a1a}-1.90\%$
test_vmap_mlp_speed_decorator[False-False]	0.6578ms	0.4653ms	2.1492 KOps/s	2.1687 KOps/s	$\color{#d91a1a}-0.90\%$
test_to_module_speed[True]	2.3785ms	1.6990ms	588.5954 Ops/s	589.1059 Ops/s	$\color{#d91a1a}-0.09\%$
test_to_module_speed[False]	72.9227ms	1.8010ms	555.2496 Ops/s	550.5737 Ops/s	$\color{#35bf28}+0.85\%$
test_tc_init	64.4610μs	30.1319μs	33.1874 KOps/s	38.1334 KOps/s	$\textbf{\color{#d91a1a}-12.97\%}$
test_tc_init_nested	0.1227ms	61.1356μs	16.3571 KOps/s	18.8585 KOps/s	$\textbf{\color{#d91a1a}-13.26\%}$
test_tc_first_layer_tensor	3.7749μs	0.6812μs	1.4680 MOps/s	1.4143 MOps/s	$\color{#35bf28}+3.80\%$
test_tc_first_layer_nontensor	2.1153μs	0.6657μs	1.5022 MOps/s	1.4439 MOps/s	$\color{#35bf28}+4.04\%$
test_tc_second_layer_tensor	18.7980μs	1.8719μs	534.2093 KOps/s	526.8644 KOps/s	$\color{#35bf28}+1.39\%$
test_tc_second_layer_nontensor	42.8410μs	1.6297μs	613.6222 KOps/s	653.6085 KOps/s	$\textbf{\color{#d91a1a}-6.12\%}$
test_unbind	81.9658ms	7.4390ms	134.4266 Ops/s	138.2737 Ops/s	$\color{#d91a1a}-2.78\%$
test_full_like	15.7704ms	10.6495ms	93.9008 Ops/s	94.6739 Ops/s	$\color{#d91a1a}-0.82\%$
test_zeros_like	12.1753ms	6.1137ms	163.5678 Ops/s	176.0668 Ops/s	$\textbf{\color{#d91a1a}-7.10\%}$
test_ones_like	12.2791ms	6.3496ms	157.4911 Ops/s	162.4875 Ops/s	$\color{#d91a1a}-3.07\%$
test_clone	16.5575ms	8.0128ms	124.7999 Ops/s	128.6842 Ops/s	$\color{#d91a1a}-3.02\%$
test_squeeze	60.7440μs	13.6691μs	73.1580 KOps/s	69.9096 KOps/s	$\color{#35bf28}+4.65\%$
test_unsqueeze	0.1257ms	59.6242μs	16.7717 KOps/s	16.7404 KOps/s	$\color{#35bf28}+0.19\%$
test_split	0.1960ms	0.1130ms	8.8484 KOps/s	8.7849 KOps/s	$\color{#35bf28}+0.72\%$
test_permute	0.2000ms	0.1286ms	7.7780 KOps/s	7.7739 KOps/s	$\color{#35bf28}+0.05\%$
test_stack	27.6823ms	22.6909ms	44.0705 Ops/s	44.9535 Ops/s	$\color{#d91a1a}-1.96\%$
test_cat	28.7136ms	24.3236ms	41.1124 Ops/s	44.9512 Ops/s	$\textbf{\color{#d91a1a}-8.54\%}$

[github-actions]

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

Total Benchmarks: 152. Improved: $\large\color{#35bf28}7$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	24.8710μs	12.5577μs	79.6323 KOps/s	80.7910 KOps/s	$\color{#d91a1a}-1.43\%$
test_plain_set_stack_nested	28.5110μs	12.8887μs	77.5873 KOps/s	78.8146 KOps/s	$\color{#d91a1a}-1.56\%$
test_plain_set_nested_inplace	37.6120μs	14.0120μs	71.3673 KOps/s	72.8356 KOps/s	$\color{#d91a1a}-2.02\%$
test_plain_set_stack_nested_inplace	74.2150μs	14.0182μs	71.3356 KOps/s	72.5156 KOps/s	$\color{#d91a1a}-1.63\%$
test_items	28.7620μs	4.7223μs	211.7611 KOps/s	209.8478 KOps/s	$\color{#35bf28}+0.91\%$
test_items_nested	0.3633ms	0.3414ms	2.9288 KOps/s	2.9541 KOps/s	$\color{#d91a1a}-0.86\%$
test_items_nested_locked	0.3674ms	0.3404ms	2.9373 KOps/s	2.9391 KOps/s	$\color{#d91a1a}-0.06\%$
test_items_nested_leaf	0.1012ms	82.2934μs	12.1516 KOps/s	12.0547 KOps/s	$\color{#35bf28}+0.80\%$
test_items_stack_nested	0.3585ms	0.3371ms	2.9666 KOps/s	2.9086 KOps/s	$\color{#35bf28}+2.00\%$
test_items_stack_nested_leaf	0.1110ms	82.6973μs	12.0923 KOps/s	12.0161 KOps/s	$\color{#35bf28}+0.63\%$
test_items_stack_nested_locked	0.3812ms	0.3410ms	2.9322 KOps/s	2.9262 KOps/s	$\color{#35bf28}+0.21\%$
test_keys	22.8410μs	4.3647μs	229.1095 KOps/s	229.2003 KOps/s	$\color{#d91a1a}-0.04\%$
test_keys_nested	88.8450μs	66.6552μs	15.0026 KOps/s	14.7529 KOps/s	$\color{#35bf28}+1.69\%$
test_keys_nested_locked	2.4762ms	71.4138μs	14.0029 KOps/s	13.7910 KOps/s	$\color{#35bf28}+1.54\%$
test_keys_nested_leaf	80.8250μs	57.1412μs	17.5005 KOps/s	17.1968 KOps/s	$\color{#35bf28}+1.77\%$
test_keys_stack_nested	94.4660μs	65.8606μs	15.1836 KOps/s	14.8218 KOps/s	$\color{#35bf28}+2.44\%$
test_keys_stack_nested_leaf	84.0750μs	57.0160μs	17.5389 KOps/s	17.2275 KOps/s	$\color{#35bf28}+1.81\%$
test_keys_stack_nested_locked	0.1015ms	70.4269μs	14.1991 KOps/s	13.9533 KOps/s	$\color{#35bf28}+1.76\%$
test_values	10.4740μs	1.8258μs	547.7190 KOps/s	537.5097 KOps/s	$\color{#35bf28}+1.90\%$
test_values_nested	58.3540μs	35.2060μs	28.4042 KOps/s	28.5012 KOps/s	$\color{#d91a1a}-0.34\%$
test_values_nested_locked	56.3040μs	36.9057μs	27.0961 KOps/s	26.9379 KOps/s	$\color{#35bf28}+0.59\%$
test_values_nested_leaf	51.3930μs	31.3639μs	31.8838 KOps/s	32.0048 KOps/s	$\color{#d91a1a}-0.38\%$
test_values_stack_nested	63.9240μs	35.9578μs	27.8103 KOps/s	27.7501 KOps/s	$\color{#35bf28}+0.22\%$
test_values_stack_nested_leaf	55.1540μs	31.8362μs	31.4108 KOps/s	31.2306 KOps/s	$\color{#35bf28}+0.58\%$
test_values_stack_nested_locked	62.6640μs	37.4814μs	26.6799 KOps/s	26.4866 KOps/s	$\color{#35bf28}+0.73\%$
test_membership	4.3931μs	0.7263μs	1.3768 MOps/s	1.4216 MOps/s	$\color{#d91a1a}-3.15\%$
test_membership_nested	19.9210μs	2.5892μs	386.2189 KOps/s	383.5603 KOps/s	$\color{#35bf28}+0.69\%$
test_membership_nested_leaf	25.1020μs	2.6154μs	382.3499 KOps/s	380.2530 KOps/s	$\color{#35bf28}+0.55\%$
test_membership_stacked_nested	21.4910μs	2.6163μs	382.2127 KOps/s	386.7757 KOps/s	$\color{#d91a1a}-1.18\%$
test_membership_stacked_nested_leaf	20.5510μs	2.5689μs	389.2777 KOps/s	387.0145 KOps/s	$\color{#35bf28}+0.58\%$
test_membership_nested_last	32.6620μs	3.0998μs	322.6055 KOps/s	319.5239 KOps/s	$\color{#35bf28}+0.96\%$
test_membership_nested_leaf_last	21.6610μs	3.0826μs	324.4057 KOps/s	318.1077 KOps/s	$\color{#35bf28}+1.98\%$
test_membership_stacked_nested_last	40.3120μs	9.8155μs	101.8801 KOps/s	278.4616 KOps/s	$\textbf{\color{#d91a1a}-63.41\%}$
test_membership_stacked_nested_leaf_last	24.3610μs	9.7845μs	102.2021 KOps/s	278.7410 KOps/s	$\textbf{\color{#d91a1a}-63.33\%}$
test_nested_getleaf	34.3320μs	8.4383μs	118.5073 KOps/s	119.4465 KOps/s	$\color{#d91a1a}-0.79\%$
test_nested_get	34.5630μs	7.9280μs	126.1356 KOps/s	127.3868 KOps/s	$\color{#d91a1a}-0.98\%$
test_stacked_getleaf	27.7320μs	8.4314μs	118.6037 KOps/s	118.7666 KOps/s	$\color{#d91a1a}-0.14\%$
test_stacked_get	37.8520μs	7.9316μs	126.0776 KOps/s	126.3014 KOps/s	$\color{#d91a1a}-0.18\%$
test_nested_getitemleaf	32.6520μs	8.5825μs	116.5164 KOps/s	116.7016 KOps/s	$\color{#d91a1a}-0.16\%$
test_nested_getitem	23.8110μs	8.0598μs	124.0720 KOps/s	124.9090 KOps/s	$\color{#d91a1a}-0.67\%$
test_stacked_getitemleaf	35.3820μs	8.6591μs	115.4855 KOps/s	116.0807 KOps/s	$\color{#d91a1a}-0.51\%$
test_stacked_getitem	29.9120μs	8.1707μs	122.3884 KOps/s	124.3248 KOps/s	$\color{#d91a1a}-1.56\%$
test_lock_nested	59.9662ms	0.4000ms	2.4998 KOps/s	2.5272 KOps/s	$\color{#d91a1a}-1.09\%$
test_lock_stack_nested	0.3108ms	0.2896ms	3.4532 KOps/s	3.3663 KOps/s	$\color{#35bf28}+2.58\%$
test_unlock_nested	61.5180ms	0.4036ms	2.4774 KOps/s	2.4761 KOps/s	$\color{#35bf28}+0.05\%$
test_unlock_stack_nested	0.3368ms	0.3003ms	3.3305 KOps/s	3.2672 KOps/s	$\color{#35bf28}+1.94\%$
test_flatten_speed	0.3934ms	0.1014ms	9.8666 KOps/s	9.8981 KOps/s	$\color{#d91a1a}-0.32\%$
test_unflatten_speed	0.3353ms	0.2924ms	3.4201 KOps/s	3.4369 KOps/s	$\color{#d91a1a}-0.49\%$
test_common_ops	1.0374ms	0.5715ms	1.7497 KOps/s	1.7599 KOps/s	$\color{#d91a1a}-0.58\%$
test_creation	37.1420μs	1.6643μs	600.8709 KOps/s	600.5082 KOps/s	$\color{#35bf28}+0.06\%$
test_creation_empty	23.1420μs	8.2462μs	121.2686 KOps/s	124.7682 KOps/s	$\color{#d91a1a}-2.80\%$
test_creation_nested_1	34.3820μs	10.0159μs	99.8414 KOps/s	102.3222 KOps/s	$\color{#d91a1a}-2.42\%$
test_creation_nested_2	44.5030μs	12.2744μs	81.4703 KOps/s	83.2697 KOps/s	$\color{#d91a1a}-2.16\%$
test_clone	0.1059ms	11.6566μs	85.7886 KOps/s	85.7024 KOps/s	$\color{#35bf28}+0.10\%$
test_getitem[int]	26.1110μs	10.7838μs	92.7320 KOps/s	93.0268 KOps/s	$\color{#d91a1a}-0.32\%$
test_getitem[slice_int]	57.6030μs	20.3667μs	49.0997 KOps/s	48.2879 KOps/s	$\color{#35bf28}+1.68\%$
test_getitem[range]	65.2440μs	47.7970μs	20.9218 KOps/s	21.6972 KOps/s	$\color{#d91a1a}-3.57\%$
test_getitem[tuple]	55.7340μs	18.5628μs	53.8711 KOps/s	53.9451 KOps/s	$\color{#d91a1a}-0.14\%$
test_getitem[list]	0.1189ms	34.0958μs	29.3291 KOps/s	29.8544 KOps/s	$\color{#d91a1a}-1.76\%$
test_setitem_dim[int]	50.3440μs	28.0381μs	35.6658 KOps/s	35.9692 KOps/s	$\color{#d91a1a}-0.84\%$
test_setitem_dim[slice_int]	70.5350μs	49.4391μs	20.2269 KOps/s	20.8307 KOps/s	$\color{#d91a1a}-2.90\%$
test_setitem_dim[range]	0.1081ms	66.1750μs	15.1114 KOps/s	15.2565 KOps/s	$\color{#d91a1a}-0.95\%$
test_setitem_dim[tuple]	62.3740μs	41.5762μs	24.0522 KOps/s	23.7802 KOps/s	$\color{#35bf28}+1.14\%$
test_setitem	50.1730μs	16.1784μs	61.8108 KOps/s	63.5600 KOps/s	$\color{#d91a1a}-2.75\%$
test_set	0.1377ms	15.6956μs	63.7123 KOps/s	65.7019 KOps/s	$\color{#d91a1a}-3.03\%$
test_set_shared	1.6249ms	0.1004ms	9.9605 KOps/s	10.0918 KOps/s	$\color{#d91a1a}-1.30\%$
test_update	91.3960μs	18.1164μs	55.1987 KOps/s	58.3043 KOps/s	$\textbf{\color{#d91a1a}-5.33\%}$
test_update_nested	58.0240μs	23.6856μs	42.2198 KOps/s	45.0623 KOps/s	$\textbf{\color{#d91a1a}-6.31\%}$
test_update__nested	69.4150μs	22.4512μs	44.5410 KOps/s	44.8206 KOps/s	$\color{#d91a1a}-0.62\%$
test_set_nested	52.1130μs	16.6743μs	59.9724 KOps/s	61.2423 KOps/s	$\color{#d91a1a}-2.07\%$
test_set_nested_new	60.7340μs	19.3520μs	51.6743 KOps/s	52.5873 KOps/s	$\color{#d91a1a}-1.74\%$
test_select	76.9750μs	32.4296μs	30.8360 KOps/s	30.5816 KOps/s	$\color{#35bf28}+0.83\%$
test_select_nested	0.8763ms	55.8618μs	17.9013 KOps/s	18.4689 KOps/s	$\color{#d91a1a}-3.07\%$
test_exclude_nested	0.1331ms	0.1086ms	9.2046 KOps/s	9.2439 KOps/s	$\color{#d91a1a}-0.43\%$
test_empty[True]	0.3831ms	0.3484ms	2.8699 KOps/s	2.9225 KOps/s	$\color{#d91a1a}-1.80\%$
test_empty[False]	2.3232μs	0.9336μs	1.0712 MOps/s	1.0706 MOps/s	$\color{#35bf28}+0.05\%$
test_to	0.1033ms	77.4261μs	12.9155 KOps/s	13.3318 KOps/s	$\color{#d91a1a}-3.12\%$
test_to_nonblocking	0.2114ms	62.2499μs	16.0643 KOps/s	16.5890 KOps/s	$\color{#d91a1a}-3.16\%$
test_unbind_speed	0.8515ms	0.2562ms	3.9025 KOps/s	3.8484 KOps/s	$\color{#35bf28}+1.41\%$
test_unbind_speed_stack0	0.2956ms	0.2561ms	3.9046 KOps/s	3.8443 KOps/s	$\color{#35bf28}+1.57\%$
test_unbind_speed_stack1	76.6163ms	0.7929ms	1.2613 KOps/s	1.2532 KOps/s	$\color{#35bf28}+0.64\%$
test_split	76.6260ms	1.6779ms	596.0008 Ops/s	595.0581 Ops/s	$\color{#35bf28}+0.16\%$
test_chunk	76.8836ms	1.6705ms	598.6310 Ops/s	599.8837 Ops/s	$\color{#d91a1a}-0.21\%$
test_creation[device0]	0.1129ms	58.4498μs	17.1087 KOps/s	17.1486 KOps/s	$\color{#d91a1a}-0.23\%$
test_creation_from_tensor	0.1621ms	54.2785μs	18.4235 KOps/s	18.5918 KOps/s	$\color{#d91a1a}-0.91\%$
test_add_one[memmap_tensor0]	87.2060μs	6.7916μs	147.2418 KOps/s	149.0618 KOps/s	$\color{#d91a1a}-1.22\%$
test_contiguous[memmap_tensor0]	25.3410μs	0.7085μs	1.4115 MOps/s	1.4504 MOps/s	$\color{#d91a1a}-2.68\%$
test_stack[memmap_tensor0]	33.3920μs	4.7359μs	211.1519 KOps/s	217.9426 KOps/s	$\color{#d91a1a}-3.12\%$
test_memmaptd_index	1.0840ms	0.2852ms	3.5060 KOps/s	3.4759 KOps/s	$\color{#35bf28}+0.87\%$
test_memmaptd_index_astensor	0.7045ms	0.3557ms	2.8115 KOps/s	2.8025 KOps/s	$\color{#35bf28}+0.32\%$
test_memmaptd_index_op	1.0395ms	0.6408ms	1.5605 KOps/s	1.5872 KOps/s	$\color{#d91a1a}-1.68\%$
test_serialize_model	0.1829s	0.1099s	9.0955 Ops/s	9.5211 Ops/s	$\color{#d91a1a}-4.47\%$
test_serialize_model_pickle	1.3704s	1.2387s	0.8073 Ops/s	0.8071 Ops/s	$\color{#35bf28}+0.03\%$
test_serialize_weights	0.1815s	0.1085s	9.2152 Ops/s	8.7908 Ops/s	$\color{#35bf28}+4.83\%$
test_serialize_weights_returnearly	0.2577s	0.1001s	9.9853 Ops/s	12.4686 Ops/s	$\textbf{\color{#d91a1a}-19.92\%}$
test_serialize_weights_pickle	1.3507s	1.2488s	0.8008 Ops/s	0.8009 Ops/s	$\color{#d91a1a}-0.01\%$
test_reshape_pytree	0.1719ms	26.3667μs	37.9266 KOps/s	38.4222 KOps/s	$\color{#d91a1a}-1.29\%$
test_reshape_td	0.1610ms	31.4599μs	31.7865 KOps/s	32.8143 KOps/s	$\color{#d91a1a}-3.13\%$
test_view_pytree	0.1574ms	26.3161μs	37.9996 KOps/s	38.7853 KOps/s	$\color{#d91a1a}-2.03\%$
test_view_td	0.1572ms	36.3987μs	27.4735 KOps/s	27.1546 KOps/s	$\color{#35bf28}+1.17\%$
test_unbind_pytree	58.6840μs	31.4727μs	31.7736 KOps/s	29.8248 KOps/s	$\textbf{\color{#35bf28}+6.53\%}$
test_unbind_td	0.4608ms	39.8834μs	25.0731 KOps/s	25.1870 KOps/s	$\color{#d91a1a}-0.45\%$
test_split_pytree	54.0730μs	33.9993μs	29.4124 KOps/s	27.8065 KOps/s	$\textbf{\color{#35bf28}+5.78\%}$
test_split_td	0.1046ms	39.9286μs	25.0447 KOps/s	25.5118 KOps/s	$\color{#d91a1a}-1.83\%$
test_add_pytree	72.5750μs	37.1987μs	26.8827 KOps/s	25.6463 KOps/s	$\color{#35bf28}+4.82\%$
test_add_td	82.3750μs	50.5184μs	19.7948 KOps/s	20.0095 KOps/s	$\color{#d91a1a}-1.07\%$
test_distributed	0.1830ms	70.5772μs	14.1689 KOps/s	13.8423 KOps/s	$\color{#35bf28}+2.36\%$
test_tdmodule	0.1360ms	14.5357μs	68.7963 KOps/s	66.9373 KOps/s	$\color{#35bf28}+2.78\%$
test_tdmodule_dispatch	43.7620μs	28.6674μs	34.8828 KOps/s	35.2070 KOps/s	$\color{#d91a1a}-0.92\%$
test_tdseq	32.5420μs	16.4918μs	60.6363 KOps/s	60.2860 KOps/s	$\color{#35bf28}+0.58\%$
test_tdseq_dispatch	47.8830μs	31.8433μs	31.4038 KOps/s	31.0279 KOps/s	$\color{#35bf28}+1.21\%$
test_instantiation_functorch	1.6269ms	1.5167ms	659.3109 Ops/s	652.7405 Ops/s	$\color{#35bf28}+1.01\%$
test_instantiation_td	1.8628ms	1.0350ms	966.2251 Ops/s	937.4874 Ops/s	$\color{#35bf28}+3.07\%$
test_exec_functorch	0.1858ms	0.1459ms	6.8525 KOps/s	6.6546 KOps/s	$\color{#35bf28}+2.97\%$
test_exec_functional_call	0.1795ms	0.1310ms	7.6342 KOps/s	7.4389 KOps/s	$\color{#35bf28}+2.63\%$
test_exec_td	0.1647ms	0.1301ms	7.6879 KOps/s	7.1609 KOps/s	$\textbf{\color{#35bf28}+7.36\%}$
test_exec_td_decorator	0.5109ms	0.2008ms	4.9788 KOps/s	4.7954 KOps/s	$\color{#35bf28}+3.82\%$
test_vmap_mlp_speed[True-True]	0.7561ms	0.5658ms	1.7673 KOps/s	1.7208 KOps/s	$\color{#35bf28}+2.70\%$
test_vmap_mlp_speed[True-False]	0.6578ms	0.5624ms	1.7779 KOps/s	1.7527 KOps/s	$\color{#35bf28}+1.44\%$
test_vmap_mlp_speed[False-True]	0.5621ms	0.5035ms	1.9860 KOps/s	1.9552 KOps/s	$\color{#35bf28}+1.57\%$
test_vmap_mlp_speed[False-False]	0.5683ms	0.5127ms	1.9506 KOps/s	1.9567 KOps/s	$\color{#d91a1a}-0.32\%$
test_vmap_mlp_speed_decorator[True-True]	1.1656ms	0.6385ms	1.5662 KOps/s	1.5527 KOps/s	$\color{#35bf28}+0.87\%$
test_vmap_mlp_speed_decorator[True-False]	0.7920ms	0.6364ms	1.5713 KOps/s	1.5686 KOps/s	$\color{#35bf28}+0.18\%$
test_vmap_mlp_speed_decorator[False-True]	0.7044ms	0.5647ms	1.7708 KOps/s	1.5819 KOps/s	$\textbf{\color{#35bf28}+11.94\%}$
test_vmap_mlp_speed_decorator[False-False]	0.7598ms	0.5837ms	1.7131 KOps/s	1.7466 KOps/s	$\color{#d91a1a}-1.92\%$
test_vmap_transformer_speed[True-True]	8.0190ms	7.5788ms	131.9463 Ops/s	136.6080 Ops/s	$\color{#d91a1a}-3.41\%$
test_vmap_transformer_speed[True-False]	8.0025ms	7.5023ms	133.2925 Ops/s	137.0938 Ops/s	$\color{#d91a1a}-2.77\%$
test_vmap_transformer_speed[False-True]	8.2188ms	7.4683ms	133.8988 Ops/s	136.6549 Ops/s	$\color{#d91a1a}-2.02\%$
test_vmap_transformer_speed[False-False]	7.7921ms	7.4334ms	134.5273 Ops/s	138.0213 Ops/s	$\color{#d91a1a}-2.53\%$
test_vmap_transformer_speed_decorator[True-True]	19.0319ms	18.2517ms	54.7894 Ops/s	56.1436 Ops/s	$\color{#d91a1a}-2.41\%$
test_vmap_transformer_speed_decorator[True-False]	18.7769ms	18.2600ms	54.7645 Ops/s	55.0494 Ops/s	$\color{#d91a1a}-0.52\%$
test_vmap_transformer_speed_decorator[False-True]	18.4784ms	18.1192ms	55.1900 Ops/s	56.7702 Ops/s	$\color{#d91a1a}-2.78\%$
test_vmap_transformer_speed_decorator[False-False]	18.8025ms	18.1893ms	54.9774 Ops/s	56.7676 Ops/s	$\color{#d91a1a}-3.15\%$
test_to_module_speed[True]	1.8819ms	1.5726ms	635.8944 Ops/s	650.9032 Ops/s	$\color{#d91a1a}-2.31\%$
test_to_module_speed[False]	1.8102ms	1.5475ms	646.2233 Ops/s	655.8360 Ops/s	$\color{#d91a1a}-1.47\%$
test_tc_init	0.1576ms	24.4753μs	40.8575 KOps/s	41.1552 KOps/s	$\color{#d91a1a}-0.72\%$
test_tc_init_nested	0.1903ms	53.4223μs	18.7188 KOps/s	20.9665 KOps/s	$\textbf{\color{#d91a1a}-10.72\%}$
test_tc_first_layer_tensor	3.4955μs	0.3649μs	2.7402 MOps/s	2.7547 MOps/s	$\color{#d91a1a}-0.52\%$
test_tc_first_layer_nontensor	10.4935μs	0.3992μs	2.5049 MOps/s	2.5375 MOps/s	$\color{#d91a1a}-1.29\%$
test_tc_second_layer_tensor	26.0616μs	0.9839μs	1.0163 MOps/s	931.8189 KOps/s	$\textbf{\color{#35bf28}+9.07\%}$
test_tc_second_layer_nontensor	21.6780μs	0.8385μs	1.1925 MOps/s	1.2187 MOps/s	$\color{#d91a1a}-2.14\%$
test_unbind	0.1061s	6.3835ms	156.6537 Ops/s	126.5784 Ops/s	$\textbf{\color{#35bf28}+23.76\%}$
test_full_like	12.3694ms	11.8126ms	84.6552 Ops/s	75.1922 Ops/s	$\textbf{\color{#35bf28}+12.59\%}$
test_zeros_like	8.6668ms	7.9469ms	125.8351 Ops/s	126.6928 Ops/s	$\color{#d91a1a}-0.68\%$
test_ones_like	8.3081ms	7.8801ms	126.9020 Ops/s	125.3878 Ops/s	$\color{#35bf28}+1.21\%$
test_clone	9.8927ms	9.4707ms	105.5885 Ops/s	104.4127 Ops/s	$\color{#35bf28}+1.13\%$
test_squeeze	55.5530μs	10.8906μs	91.8221 KOps/s	90.3298 KOps/s	$\color{#35bf28}+1.65\%$
test_unsqueeze	95.0160μs	51.0622μs	19.5840 KOps/s	18.8186 KOps/s	$\color{#35bf28}+4.07\%$
test_split	0.1562ms	98.1719μs	10.1862 KOps/s	9.9531 KOps/s	$\color{#35bf28}+2.34\%$
test_permute	0.1421ms	0.1095ms	9.1350 KOps/s	8.7085 KOps/s	$\color{#35bf28}+4.90\%$
test_stack	28.3179ms	27.5490ms	36.2990 Ops/s	36.2740 Ops/s	$\color{#35bf28}+0.07\%$
test_cat	27.6968ms	27.2959ms	36.6356 Ops/s	36.5803 Ops/s	$\color{#35bf28}+0.15\%$