[BugFix] Fix non-blocking arg in copy_

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 113. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	28.5030μs	16.1078μs	62.0817 KOps/s	64.6332 KOps/s	$\color{#d91a1a}-3.95\%$
test_plain_set_stack_nested	0.2163ms	0.1424ms	7.0240 KOps/s	7.0069 KOps/s	$\color{#35bf28}+0.25\%$
test_plain_set_nested_inplace	53.3490μs	17.9520μs	55.7040 KOps/s	56.3685 KOps/s	$\color{#d91a1a}-1.18\%$
test_plain_set_stack_nested_inplace	0.2435ms	0.1779ms	5.6216 KOps/s	5.7137 KOps/s	$\color{#d91a1a}-1.61\%$
test_items	45.6250μs	2.4784μs	403.4862 KOps/s	371.5470 KOps/s	$\textbf{\color{#35bf28}+8.60\%}$
test_items_nested	0.3386ms	0.2678ms	3.7347 KOps/s	3.7268 KOps/s	$\color{#35bf28}+0.21\%$
test_items_nested_locked	0.3307ms	0.2703ms	3.6992 KOps/s	3.7044 KOps/s	$\color{#d91a1a}-0.14\%$
test_items_nested_leaf	0.7612ms	0.1670ms	5.9890 KOps/s	5.9480 KOps/s	$\color{#35bf28}+0.69\%$
test_items_stack_nested	3.9993ms	1.5175ms	658.9813 Ops/s	685.3528 Ops/s	$\color{#d91a1a}-3.85\%$
test_items_stack_nested_leaf	2.1408ms	1.3730ms	728.3579 Ops/s	754.1273 Ops/s	$\color{#d91a1a}-3.42\%$
test_items_stack_nested_locked	1.9555ms	0.7766ms	1.2876 KOps/s	1.2978 KOps/s	$\color{#d91a1a}-0.78\%$
test_keys	51.3150μs	3.8763μs	257.9754 KOps/s	258.7448 KOps/s	$\color{#d91a1a}-0.30\%$
test_keys_nested	0.5399ms	0.1397ms	7.1602 KOps/s	6.4841 KOps/s	$\textbf{\color{#35bf28}+10.43\%}$
test_keys_nested_locked	0.2706ms	0.1386ms	7.2140 KOps/s	7.0163 KOps/s	$\color{#35bf28}+2.82\%$
test_keys_nested_leaf	0.3921ms	0.1392ms	7.1838 KOps/s	7.1254 KOps/s	$\color{#35bf28}+0.82\%$
test_keys_stack_nested	1.6015ms	1.4108ms	708.8027 Ops/s	710.7868 Ops/s	$\color{#d91a1a}-0.28\%$
test_keys_stack_nested_leaf	2.5342ms	1.4174ms	705.5386 Ops/s	711.5283 Ops/s	$\color{#d91a1a}-0.84\%$
test_keys_stack_nested_locked	0.7899ms	0.6782ms	1.4744 KOps/s	1.4470 KOps/s	$\color{#35bf28}+1.89\%$
test_values	12.6185μs	1.1515μs	868.4328 KOps/s	837.4843 KOps/s	$\color{#35bf28}+3.70\%$
test_values_nested	0.1234ms	48.6959μs	20.5356 KOps/s	20.4750 KOps/s	$\color{#35bf28}+0.30\%$
test_values_nested_locked	0.1202ms	49.6861μs	20.1264 KOps/s	20.7065 KOps/s	$\color{#d91a1a}-2.80\%$
test_values_nested_leaf	81.9330μs	43.8930μs	22.7827 KOps/s	22.9146 KOps/s	$\color{#d91a1a}-0.58\%$
test_values_stack_nested	1.3496ms	1.2151ms	822.9954 Ops/s	837.2354 Ops/s	$\color{#d91a1a}-1.70\%$
test_values_stack_nested_leaf	2.1042ms	1.2120ms	825.0740 Ops/s	844.7286 Ops/s	$\color{#d91a1a}-2.33\%$
test_values_stack_nested_locked	0.8929ms	0.5198ms	1.9240 KOps/s	1.9321 KOps/s	$\color{#d91a1a}-0.42\%$
test_membership	19.2560μs	1.3597μs	735.4564 KOps/s	740.7804 KOps/s	$\color{#d91a1a}-0.72\%$
test_membership_nested	25.2770μs	2.8136μs	355.4226 KOps/s	352.7159 KOps/s	$\color{#35bf28}+0.77\%$
test_membership_nested_leaf	28.8930μs	2.8666μs	348.8483 KOps/s	351.7047 KOps/s	$\color{#d91a1a}-0.81\%$
test_membership_stacked_nested	56.7160μs	11.7955μs	84.7782 KOps/s	85.7627 KOps/s	$\color{#d91a1a}-1.15\%$
test_membership_stacked_nested_leaf	0.1967ms	12.5982μs	79.3761 KOps/s	86.2923 KOps/s	$\textbf{\color{#d91a1a}-8.01\%}$
test_membership_nested_last	32.6710μs	6.0283μs	165.8839 KOps/s	165.3198 KOps/s	$\color{#35bf28}+0.34\%$
test_membership_nested_leaf_last	44.7820μs	6.0133μs	166.2990 KOps/s	172.4669 KOps/s	$\color{#d91a1a}-3.58\%$
test_membership_stacked_nested_last	0.3616ms	0.1678ms	5.9584 KOps/s	6.0669 KOps/s	$\color{#d91a1a}-1.79\%$
test_membership_stacked_nested_leaf_last	79.9090μs	14.0537μs	71.1558 KOps/s	72.9510 KOps/s	$\color{#d91a1a}-2.46\%$
test_nested_getleaf	60.2530μs	10.7118μs	93.3550 KOps/s	94.7822 KOps/s	$\color{#d91a1a}-1.51\%$
test_nested_get	58.8600μs	10.1370μs	98.6482 KOps/s	100.8677 KOps/s	$\color{#d91a1a}-2.20\%$
test_stacked_getleaf	1.0929ms	0.6541ms	1.5288 KOps/s	1.5751 KOps/s	$\color{#d91a1a}-2.94\%$
test_stacked_get	4.8093ms	0.6264ms	1.5963 KOps/s	1.6586 KOps/s	$\color{#d91a1a}-3.76\%$
test_nested_getitemleaf	63.5480μs	10.8960μs	91.7765 KOps/s	95.2524 KOps/s	$\color{#d91a1a}-3.65\%$
test_nested_getitem	57.3270μs	10.2876μs	97.2045 KOps/s	99.4481 KOps/s	$\color{#d91a1a}-2.26\%$
test_stacked_getitemleaf	1.2039ms	0.6611ms	1.5125 KOps/s	1.5736 KOps/s	$\color{#d91a1a}-3.88\%$
test_stacked_getitem	0.9182ms	0.6229ms	1.6053 KOps/s	1.6589 KOps/s	$\color{#d91a1a}-3.23\%$
test_lock_nested	72.6735ms	0.6442ms	1.5523 KOps/s	1.7842 KOps/s	$\textbf{\color{#d91a1a}-13.00\%}$
test_lock_stack_nested	8.9668ms	5.3424ms	187.1809 Ops/s	193.8497 Ops/s	$\color{#d91a1a}-3.44\%$
test_unlock_nested	1.0260ms	0.4451ms	2.2469 KOps/s	2.2335 KOps/s	$\color{#35bf28}+0.60\%$
test_unlock_stack_nested	86.4107ms	7.4292ms	134.6045 Ops/s	129.2356 Ops/s	$\color{#35bf28}+4.15\%$
test_flatten_speed	0.3590ms	0.2672ms	3.7426 KOps/s	3.7685 KOps/s	$\color{#d91a1a}-0.69\%$
test_unflatten_speed	0.5915ms	0.4626ms	2.1616 KOps/s	2.2228 KOps/s	$\color{#d91a1a}-2.75\%$
test_common_ops	3.0959ms	0.6862ms	1.4572 KOps/s	1.4931 KOps/s	$\color{#d91a1a}-2.40\%$
test_creation	47.6990μs	2.5015μs	399.7563 KOps/s	399.6632 KOps/s	$\color{#35bf28}+0.02\%$
test_creation_empty	22.0920μs	8.2318μs	121.4802 KOps/s	123.9570 KOps/s	$\color{#d91a1a}-2.00\%$
test_creation_nested_1	56.4050μs	11.6667μs	85.7142 KOps/s	88.5428 KOps/s	$\color{#d91a1a}-3.19\%$
test_creation_nested_2	46.3570μs	15.2465μs	65.5889 KOps/s	67.1439 KOps/s	$\color{#d91a1a}-2.32\%$
test_clone	0.1421ms	13.5992μs	73.5340 KOps/s	73.5499 KOps/s	$\color{#d91a1a}-0.02\%$
test_getitem[int]	43.9320μs	13.1331μs	76.1438 KOps/s	75.3394 KOps/s	$\color{#35bf28}+1.07\%$
test_getitem[slice_int]	93.1760μs	25.1305μs	39.7922 KOps/s	40.1697 KOps/s	$\color{#d91a1a}-0.94\%$
test_getitem[range]	93.4040μs	45.1757μs	22.1358 KOps/s	22.1209 KOps/s	$\color{#35bf28}+0.07\%$
test_getitem[tuple]	77.6420μs	20.3202μs	49.2122 KOps/s	48.8001 KOps/s	$\color{#35bf28}+0.84\%$
test_getitem[list]	83.9060μs	40.5275μs	24.6746 KOps/s	24.5196 KOps/s	$\color{#35bf28}+0.63\%$
test_setitem_dim[int]	84.1370μs	27.3383μs	36.5787 KOps/s	35.5063 KOps/s	$\color{#35bf28}+3.02\%$
test_setitem_dim[slice_int]	88.6560μs	50.9024μs	19.6455 KOps/s	19.2063 KOps/s	$\color{#35bf28}+2.29\%$
test_setitem_dim[range]	0.1481ms	72.0636μs	13.8766 KOps/s	13.9180 KOps/s	$\color{#d91a1a}-0.30\%$
test_setitem_dim[tuple]	75.1700μs	40.0877μs	24.9453 KOps/s	23.6639 KOps/s	$\textbf{\color{#35bf28}+5.42\%}$
test_setitem	0.1954ms	18.5877μs	53.7991 KOps/s	54.9012 KOps/s	$\color{#d91a1a}-2.01\%$
test_set	0.1999ms	17.7755μs	56.2573 KOps/s	56.6286 KOps/s	$\color{#d91a1a}-0.66\%$
test_set_shared	2.1245ms	0.1423ms	7.0275 KOps/s	6.9475 KOps/s	$\color{#35bf28}+1.15\%$
test_update	0.1727ms	19.3236μs	51.7501 KOps/s	53.8176 KOps/s	$\color{#d91a1a}-3.84\%$
test_update_nested	0.1612ms	26.9197μs	37.1475 KOps/s	38.3735 KOps/s	$\color{#d91a1a}-3.19\%$
test_set_nested	0.1481ms	19.5129μs	51.2480 KOps/s	51.7214 KOps/s	$\color{#d91a1a}-0.92\%$
test_set_nested_new	0.1640ms	25.5944μs	39.0710 KOps/s	41.3357 KOps/s	$\textbf{\color{#d91a1a}-5.48\%}$
test_select	1.0166ms	53.6850μs	18.6272 KOps/s	20.4372 KOps/s	$\textbf{\color{#d91a1a}-8.86\%}$
test_unbind_speed	0.8637ms	0.3761ms	2.6585 KOps/s	2.7138 KOps/s	$\color{#d91a1a}-2.04\%$
test_unbind_speed_stack0	73.2662ms	5.1454ms	194.3469 Ops/s	208.0051 Ops/s	$\textbf{\color{#d91a1a}-6.57\%}$
test_unbind_speed_stack1	3.0181μs	0.6867μs	1.4563 MOps/s	1.5835 MOps/s	$\textbf{\color{#d91a1a}-8.03\%}$
test_split	58.8216ms	1.7738ms	563.7708 Ops/s	555.7244 Ops/s	$\color{#35bf28}+1.45\%$
test_chunk	1.8019ms	1.6513ms	605.5954 Ops/s	605.0634 Ops/s	$\color{#35bf28}+0.09\%$
test_creation[device0]	60.9090ms	0.3402ms	2.9395 KOps/s	3.4080 KOps/s	$\textbf{\color{#d91a1a}-13.75\%}$
test_creation_from_tensor	0.4243ms	0.3235ms	3.0908 KOps/s	3.0236 KOps/s	$\color{#35bf28}+2.22\%$
test_add_one[memmap_tensor0]	0.4096ms	25.7550μs	38.8274 KOps/s	39.2666 KOps/s	$\color{#d91a1a}-1.12\%$
test_contiguous[memmap_tensor0]	40.3760μs	5.8147μs	171.9780 KOps/s	173.1877 KOps/s	$\color{#d91a1a}-0.70\%$
test_stack[memmap_tensor0]	93.2740μs	19.1256μs	52.2861 KOps/s	53.2546 KOps/s	$\color{#d91a1a}-1.82\%$
test_memmaptd_index	0.3355ms	0.2047ms	4.8847 KOps/s	4.9357 KOps/s	$\color{#d91a1a}-1.03\%$
test_memmaptd_index_astensor	0.4503ms	0.2641ms	3.7864 KOps/s	3.8063 KOps/s	$\color{#d91a1a}-0.52\%$
test_memmaptd_index_op	1.6529ms	0.5218ms	1.9166 KOps/s	2.0283 KOps/s	$\textbf{\color{#d91a1a}-5.51\%}$
test_reshape_pytree	94.2560μs	23.5367μs	42.4868 KOps/s	43.7955 KOps/s	$\color{#d91a1a}-2.99\%$
test_reshape_td	70.7520μs	32.5638μs	30.7089 KOps/s	31.2885 KOps/s	$\color{#d91a1a}-1.85\%$
test_view_pytree	77.7360μs	23.2349μs	43.0387 KOps/s	43.3007 KOps/s	$\color{#d91a1a}-0.60\%$
test_view_td	26.6200μs	4.9676μs	201.3035 KOps/s	202.0544 KOps/s	$\color{#d91a1a}-0.37\%$
test_unbind_pytree	76.7130μs	26.5358μs	37.6850 KOps/s	37.8642 KOps/s	$\color{#d91a1a}-0.47\%$
test_unbind_td	0.1266ms	59.7480μs	16.7370 KOps/s	16.9144 KOps/s	$\color{#d91a1a}-1.05\%$
test_split_pytree	93.5270μs	26.3044μs	38.0165 KOps/s	37.7114 KOps/s	$\color{#35bf28}+0.81\%$
test_split_td	0.1141ms	46.6042μs	21.4573 KOps/s	21.8685 KOps/s	$\color{#d91a1a}-1.88\%$
test_add_pytree	89.3860μs	31.8475μs	31.3997 KOps/s	31.5296 KOps/s	$\color{#d91a1a}-0.41\%$
test_add_td	0.1112ms	45.4573μs	21.9987 KOps/s	22.5008 KOps/s	$\color{#d91a1a}-2.23\%$
test_distributed	26.5500μs	5.9820μs	167.1692 KOps/s	165.1314 KOps/s	$\color{#35bf28}+1.23\%$
test_tdmodule	1.5496ms	22.6542μs	44.1420 KOps/s	45.8679 KOps/s	$\color{#d91a1a}-3.76\%$
test_tdmodule_dispatch	0.2245ms	39.2703μs	25.4645 KOps/s	26.7646 KOps/s	$\color{#d91a1a}-4.86\%$
test_tdseq	0.1214ms	24.3680μs	41.0374 KOps/s	42.2046 KOps/s	$\color{#d91a1a}-2.77\%$
test_tdseq_dispatch	0.4982ms	43.6218μs	22.9243 KOps/s	23.5773 KOps/s	$\color{#d91a1a}-2.77\%$
test_instantiation_functorch	2.8794ms	1.3096ms	763.6179 Ops/s	770.2210 Ops/s	$\color{#d91a1a}-0.86\%$
test_instantiation_td	1.8817ms	1.0479ms	954.3015 Ops/s	980.1585 Ops/s	$\color{#d91a1a}-2.64\%$
test_exec_functorch	0.2620ms	0.1619ms	6.1760 KOps/s	6.3238 KOps/s	$\color{#d91a1a}-2.34\%$
test_exec_functional_call	0.2395ms	0.1505ms	6.6451 KOps/s	6.8597 KOps/s	$\color{#d91a1a}-3.13\%$
test_exec_td	0.2317ms	0.1437ms	6.9607 KOps/s	6.9951 KOps/s	$\color{#d91a1a}-0.49\%$
test_exec_td_decorator	0.8031ms	0.1776ms	5.6297 KOps/s	5.7024 KOps/s	$\color{#d91a1a}-1.27\%$
test_vmap_mlp_speed[True-True]	1.2382ms	0.8796ms	1.1369 KOps/s	1.1154 KOps/s	$\color{#35bf28}+1.93\%$
test_vmap_mlp_speed[True-False]	0.5834ms	0.4610ms	2.1692 KOps/s	2.1103 KOps/s	$\color{#35bf28}+2.79\%$
test_vmap_mlp_speed[False-True]	1.1067ms	0.7614ms	1.3133 KOps/s	1.2703 KOps/s	$\color{#35bf28}+3.38\%$
test_vmap_mlp_speed[False-False]	0.6503ms	0.3812ms	2.6236 KOps/s	2.5658 KOps/s	$\color{#35bf28}+2.25\%$
test_vmap_mlp_speed_decorator[True-True]	2.6656ms	1.7569ms	569.1762 Ops/s	547.7805 Ops/s	$\color{#35bf28}+3.91\%$
test_vmap_mlp_speed_decorator[True-False]	81.8769ms	0.5618ms	1.7800 KOps/s	1.9125 KOps/s	$\textbf{\color{#d91a1a}-6.93\%}$
test_vmap_mlp_speed_decorator[False-True]	1.9657ms	1.4673ms	681.5343 Ops/s	665.6422 Ops/s	$\color{#35bf28}+2.39\%$
test_vmap_mlp_speed_decorator[False-False]	1.0893ms	0.3964ms	2.5229 KOps/s	2.4793 KOps/s	$\color{#35bf28}+1.76\%$

[github-actions]

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

Total Benchmarks: 127. Improved: $\large\color{#35bf28}2$. Worsened: $\large\color{#d91a1a}19$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	25.4800μs	12.8306μs	77.9388 KOps/s	78.7731 KOps/s	$\color{#d91a1a}-1.06\%$
test_plain_set_stack_nested	0.1473ms	0.1169ms	8.5522 KOps/s	8.3297 KOps/s	$\color{#35bf28}+2.67\%$
test_plain_set_nested_inplace	29.9100μs	14.1570μs	70.6362 KOps/s	71.0977 KOps/s	$\color{#d91a1a}-0.65\%$
test_plain_set_stack_nested_inplace	0.1826ms	0.1462ms	6.8407 KOps/s	6.9111 KOps/s	$\color{#d91a1a}-1.02\%$
test_items	26.0300μs	4.6688μs	214.1884 KOps/s	210.3381 KOps/s	$\color{#35bf28}+1.83\%$
test_items_nested	0.3924ms	0.3372ms	2.9658 KOps/s	2.9588 KOps/s	$\color{#35bf28}+0.24\%$
test_items_nested_locked	0.3916ms	0.3386ms	2.9532 KOps/s	2.9321 KOps/s	$\color{#35bf28}+0.72\%$
test_items_nested_leaf	0.2450ms	0.1976ms	5.0603 KOps/s	5.0429 KOps/s	$\color{#35bf28}+0.35\%$
test_items_stack_nested	1.6304ms	1.5286ms	654.1915 Ops/s	662.5899 Ops/s	$\color{#d91a1a}-1.27\%$
test_items_stack_nested_leaf	1.4501ms	1.3459ms	742.9795 Ops/s	746.5671 Ops/s	$\color{#d91a1a}-0.48\%$
test_items_stack_nested_locked	2.1607ms	0.8510ms	1.1751 KOps/s	1.1864 KOps/s	$\color{#d91a1a}-0.95\%$
test_keys	18.8210μs	4.6037μs	217.2172 KOps/s	219.0210 KOps/s	$\color{#d91a1a}-0.82\%$
test_keys_nested	0.4830ms	90.6809μs	11.0277 KOps/s	11.1203 KOps/s	$\color{#d91a1a}-0.83\%$
test_keys_nested_locked	0.1179ms	90.1904μs	11.0877 KOps/s	11.1463 KOps/s	$\color{#d91a1a}-0.53\%$
test_keys_nested_leaf	43.9641ms	87.0321μs	11.4900 KOps/s	12.2189 KOps/s	$\textbf{\color{#d91a1a}-5.96\%}$
test_keys_stack_nested	1.4368ms	1.3319ms	750.8090 Ops/s	773.6256 Ops/s	$\color{#d91a1a}-2.95\%$
test_keys_stack_nested_leaf	1.4217ms	1.3195ms	757.8659 Ops/s	773.3090 Ops/s	$\color{#d91a1a}-2.00\%$
test_keys_stack_nested_locked	0.7080ms	0.6549ms	1.5270 KOps/s	1.5700 KOps/s	$\color{#d91a1a}-2.74\%$
test_values	6.7300μs	1.8866μs	530.0664 KOps/s	522.8253 KOps/s	$\color{#35bf28}+1.38\%$
test_values_nested	57.5610μs	42.7080μs	23.4148 KOps/s	22.7092 KOps/s	$\color{#35bf28}+3.11\%$
test_values_nested_locked	62.9810μs	44.9519μs	22.2460 KOps/s	21.3124 KOps/s	$\color{#35bf28}+4.38\%$
test_values_nested_leaf	59.2610μs	37.2939μs	26.8140 KOps/s	26.1867 KOps/s	$\color{#35bf28}+2.40\%$
test_values_stack_nested	1.2655ms	1.1646ms	858.6580 Ops/s	868.9868 Ops/s	$\color{#d91a1a}-1.19\%$
test_values_stack_nested_leaf	1.2753ms	1.1602ms	861.9155 Ops/s	883.3477 Ops/s	$\color{#d91a1a}-2.43\%$
test_values_stack_nested_locked	0.5926ms	0.5302ms	1.8862 KOps/s	1.9564 KOps/s	$\color{#d91a1a}-3.59\%$
test_membership	3.6500μs	0.9391μs	1.0648 MOps/s	1.0464 MOps/s	$\color{#35bf28}+1.76\%$
test_membership_nested	23.7600μs	2.1583μs	463.3240 KOps/s	459.1089 KOps/s	$\color{#35bf28}+0.92\%$
test_membership_nested_leaf	10.1305μs	2.0983μs	476.5833 KOps/s	476.9854 KOps/s	$\color{#d91a1a}-0.08\%$
test_membership_stacked_nested	30.2810μs	11.0465μs	90.5264 KOps/s	90.1905 KOps/s	$\color{#35bf28}+0.37\%$
test_membership_stacked_nested_leaf	35.0110μs	10.9795μs	91.0792 KOps/s	90.2692 KOps/s	$\color{#35bf28}+0.90\%$
test_membership_nested_last	18.0710μs	4.5537μs	219.6037 KOps/s	220.8910 KOps/s	$\color{#d91a1a}-0.58\%$
test_membership_nested_leaf_last	19.8310μs	4.5839μs	218.1530 KOps/s	220.6416 KOps/s	$\color{#d91a1a}-1.13\%$
test_membership_stacked_nested_last	0.1740ms	0.1345ms	7.4353 KOps/s	7.4437 KOps/s	$\color{#d91a1a}-0.11\%$
test_membership_stacked_nested_leaf_last	31.4300μs	13.0207μs	76.8006 KOps/s	77.4676 KOps/s	$\color{#d91a1a}-0.86\%$
test_nested_getleaf	23.0800μs	8.3920μs	119.1612 KOps/s	118.8625 KOps/s	$\color{#35bf28}+0.25\%$
test_nested_get	26.6000μs	7.9119μs	126.3926 KOps/s	126.3992 KOps/s	$-0.01\%$
test_stacked_getleaf	0.6486ms	0.5814ms	1.7201 KOps/s	1.7253 KOps/s	$\color{#d91a1a}-0.30\%$
test_stacked_get	0.5900ms	0.5252ms	1.9042 KOps/s	1.8527 KOps/s	$\color{#35bf28}+2.78\%$
test_nested_getitemleaf	22.6110μs	8.4488μs	118.3594 KOps/s	118.4758 KOps/s	$\color{#d91a1a}-0.10\%$
test_nested_getitem	21.9600μs	7.9492μs	125.7989 KOps/s	125.0643 KOps/s	$\color{#35bf28}+0.59\%$
test_stacked_getitemleaf	0.6404ms	0.5705ms	1.7527 KOps/s	1.7404 KOps/s	$\color{#35bf28}+0.71\%$
test_stacked_getitem	0.6076ms	0.5447ms	1.8360 KOps/s	1.8499 KOps/s	$\color{#d91a1a}-0.75\%$
test_lock_nested	3.2293ms	0.5651ms	1.7695 KOps/s	1.8107 KOps/s	$\color{#d91a1a}-2.27\%$
test_lock_stack_nested	81.9023ms	7.4007ms	135.1219 Ops/s	137.4924 Ops/s	$\color{#d91a1a}-1.72\%$
test_unlock_nested	2.4230ms	0.4434ms	2.2551 KOps/s	2.3240 KOps/s	$\color{#d91a1a}-2.97\%$
test_unlock_stack_nested	67.8373ms	6.4354ms	155.3915 Ops/s	162.6617 Ops/s	$\color{#d91a1a}-4.47\%$
test_flatten_speed	0.2382ms	0.1874ms	5.3359 KOps/s	5.3636 KOps/s	$\color{#d91a1a}-0.52\%$
test_unflatten_speed	0.4188ms	0.3643ms	2.7452 KOps/s	2.7787 KOps/s	$\color{#d91a1a}-1.20\%$
test_common_ops	1.1720ms	0.6355ms	1.5736 KOps/s	1.6173 KOps/s	$\color{#d91a1a}-2.70\%$
test_creation	32.3800μs	2.1362μs	468.1209 KOps/s	474.7009 KOps/s	$\color{#d91a1a}-1.39\%$
test_creation_empty	20.4710μs	7.1181μs	140.4860 KOps/s	140.1415 KOps/s	$\color{#35bf28}+0.25\%$
test_creation_nested_1	23.9300μs	9.5247μs	104.9900 KOps/s	105.4605 KOps/s	$\color{#d91a1a}-0.45\%$
test_creation_nested_2	37.4600μs	12.0783μs	82.7930 KOps/s	82.8462 KOps/s	$\color{#d91a1a}-0.06\%$
test_clone	92.7020μs	15.0847μs	66.2921 KOps/s	68.2404 KOps/s	$\color{#d91a1a}-2.85\%$
test_getitem[int]	27.1000μs	12.6511μs	79.0446 KOps/s	79.5639 KOps/s	$\color{#d91a1a}-0.65\%$
test_getitem[slice_int]	50.2410μs	25.0973μs	39.8450 KOps/s	42.2764 KOps/s	$\textbf{\color{#d91a1a}-5.75\%}$
test_getitem[range]	67.7610μs	43.5909μs	22.9406 KOps/s	24.2779 KOps/s	$\textbf{\color{#d91a1a}-5.51\%}$
test_getitem[tuple]	40.2210μs	20.9360μs	47.7646 KOps/s	48.5056 KOps/s	$\color{#d91a1a}-1.53\%$
test_getitem[list]	0.3130ms	39.7386μs	25.1644 KOps/s	26.1616 KOps/s	$\color{#d91a1a}-3.81\%$
test_setitem_dim[int]	46.2910μs	27.6330μs	36.1886 KOps/s	37.7237 KOps/s	$\color{#d91a1a}-4.07\%$
test_setitem_dim[slice_int]	68.0010μs	49.1357μs	20.3518 KOps/s	21.4540 KOps/s	$\textbf{\color{#d91a1a}-5.14\%}$
test_setitem_dim[range]	90.6610μs	66.9909μs	14.9274 KOps/s	15.7620 KOps/s	$\textbf{\color{#d91a1a}-5.29\%}$
test_setitem_dim[tuple]	59.4910μs	42.3692μs	23.6020 KOps/s	25.0521 KOps/s	$\textbf{\color{#d91a1a}-5.79\%}$
test_setitem	0.1078ms	19.8063μs	50.4891 KOps/s	54.1196 KOps/s	$\textbf{\color{#d91a1a}-6.71\%}$
test_set	85.6410μs	18.6904μs	53.5034 KOps/s	54.2346 KOps/s	$\color{#d91a1a}-1.35\%$
test_set_shared	2.4812ms	0.1103ms	9.0673 KOps/s	8.4759 KOps/s	$\textbf{\color{#35bf28}+6.98\%}$
test_update	95.6710μs	20.4499μs	48.9001 KOps/s	50.9149 KOps/s	$\color{#d91a1a}-3.96\%$
test_update_nested	92.8220μs	26.6439μs	37.5320 KOps/s	37.3758 KOps/s	$\color{#35bf28}+0.42\%$
test_set_nested	93.0110μs	20.4245μs	48.9607 KOps/s	50.3404 KOps/s	$\color{#d91a1a}-2.74\%$
test_set_nested_new	0.1268ms	24.7211μs	40.4512 KOps/s	41.8311 KOps/s	$\color{#d91a1a}-3.30\%$
test_select	0.1129ms	50.0465μs	19.9814 KOps/s	21.5182 KOps/s	$\textbf{\color{#d91a1a}-7.14\%}$
test_to	78.5910μs	56.4286μs	17.7215 KOps/s	18.6708 KOps/s	$\textbf{\color{#d91a1a}-5.08\%}$
test_to_nonblocking	67.4210μs	37.6170μs	26.5838 KOps/s	27.2182 KOps/s	$\color{#d91a1a}-2.33\%$
test_unbind_speed	0.4487ms	0.3689ms	2.7108 KOps/s	2.7742 KOps/s	$\color{#d91a1a}-2.29\%$
test_unbind_speed_stack0	63.5311ms	4.5284ms	220.8280 Ops/s	250.7490 Ops/s	$\textbf{\color{#d91a1a}-11.93\%}$
test_unbind_speed_stack1	1.5300μs	0.5235μs	1.9103 MOps/s	1.8866 MOps/s	$\color{#35bf28}+1.26\%$
test_split	54.2051ms	1.9305ms	517.9913 Ops/s	564.1756 Ops/s	$\textbf{\color{#d91a1a}-8.19\%}$
test_chunk	1.9101ms	1.8194ms	549.6223 Ops/s	568.7057 Ops/s	$\color{#d91a1a}-3.36\%$
test_creation[device0]	0.5733ms	0.3108ms	3.2173 KOps/s	3.2507 KOps/s	$\color{#d91a1a}-1.03\%$
test_creation[device1]	0.7028ms	0.3145ms	3.1801 KOps/s	3.2109 KOps/s	$\color{#d91a1a}-0.96\%$
test_creation_from_tensor	0.5650ms	0.3389ms	2.9510 KOps/s	2.7460 KOps/s	$\textbf{\color{#35bf28}+7.47\%}$
test_add_one[memmap_tensor0]	0.2746ms	26.6706μs	37.4945 KOps/s	39.5285 KOps/s	$\textbf{\color{#d91a1a}-5.15\%}$
test_add_one[memmap_tensor1]	0.2137ms	77.6819μs	12.8730 KOps/s	13.2468 KOps/s	$\color{#d91a1a}-2.82\%$
test_contiguous[memmap_tensor0]	31.3800μs	6.4431μs	155.2052 KOps/s	164.9268 KOps/s	$\textbf{\color{#d91a1a}-5.89\%}$
test_contiguous[memmap_tensor1]	52.2500μs	22.8859μs	43.6950 KOps/s	44.3196 KOps/s	$\color{#d91a1a}-1.41\%$
test_stack[memmap_tensor0]	51.3200μs	21.1798μs	47.2148 KOps/s	50.1568 KOps/s	$\textbf{\color{#d91a1a}-5.87\%}$
test_stack[memmap_tensor1]	0.1654ms	77.6374μs	12.8804 KOps/s	13.2112 KOps/s	$\color{#d91a1a}-2.50\%$
test_memmaptd_index	0.3174ms	0.2568ms	3.8943 KOps/s	4.1426 KOps/s	$\textbf{\color{#d91a1a}-5.99\%}$
test_memmaptd_index_astensor	0.3743ms	0.3125ms	3.1996 KOps/s	3.3556 KOps/s	$\color{#d91a1a}-4.65\%$
test_memmaptd_index_op	0.6961ms	0.6166ms	1.6217 KOps/s	1.7177 KOps/s	$\textbf{\color{#d91a1a}-5.59\%}$
test_reshape_pytree	39.7310μs	21.5853μs	46.3278 KOps/s	47.3457 KOps/s	$\color{#d91a1a}-2.15\%$
test_reshape_td	52.6010μs	31.4683μs	31.7780 KOps/s	33.2620 KOps/s	$\color{#d91a1a}-4.46\%$
test_view_pytree	41.8110μs	21.3205μs	46.9033 KOps/s	48.1585 KOps/s	$\color{#d91a1a}-2.61\%$
test_view_td	18.3610μs	4.1067μs	243.5050 KOps/s	248.5765 KOps/s	$\color{#d91a1a}-2.04\%$
test_unbind_pytree	51.5910μs	26.1320μs	38.2673 KOps/s	38.4220 KOps/s	$\color{#d91a1a}-0.40\%$
test_unbind_td	86.3320μs	58.4678μs	17.1034 KOps/s	17.6095 KOps/s	$\color{#d91a1a}-2.87\%$
test_split_pytree	45.6210μs	24.9699μs	40.0483 KOps/s	40.4766 KOps/s	$\color{#d91a1a}-1.06\%$
test_split_td	64.8100μs	46.7983μs	21.3683 KOps/s	22.9378 KOps/s	$\textbf{\color{#d91a1a}-6.84\%}$
test_add_pytree	56.9110μs	34.4658μs	29.0143 KOps/s	30.5062 KOps/s	$\color{#d91a1a}-4.89\%$
test_add_td	70.2410μs	48.0806μs	20.7984 KOps/s	21.4485 KOps/s	$\color{#d91a1a}-3.03\%$
test_distributed	18.6510μs	5.4414μs	183.7779 KOps/s	175.8735 KOps/s	$\color{#35bf28}+4.49\%$
test_tdmodule	31.9200μs	16.8009μs	59.5206 KOps/s	59.1348 KOps/s	$\color{#35bf28}+0.65\%$
test_tdmodule_dispatch	0.1960ms	33.4342μs	29.9095 KOps/s	29.7212 KOps/s	$\color{#35bf28}+0.63\%$
test_tdseq	35.9800μs	20.0260μs	49.9350 KOps/s	49.7033 KOps/s	$\color{#35bf28}+0.47\%$
test_tdseq_dispatch	54.6610μs	36.1507μs	27.6620 KOps/s	27.4540 KOps/s	$\color{#35bf28}+0.76\%$
test_instantiation_functorch	1.8656ms	1.7116ms	584.2470 Ops/s	584.8492 Ops/s	$\color{#d91a1a}-0.10\%$
test_instantiation_td	65.3680ms	1.2755ms	784.0038 Ops/s	846.8996 Ops/s	$\textbf{\color{#d91a1a}-7.43\%}$
test_exec_functorch	0.2052ms	0.1651ms	6.0554 KOps/s	6.1230 KOps/s	$\color{#d91a1a}-1.10\%$
test_exec_functional_call	0.2239ms	0.1666ms	6.0036 KOps/s	6.1941 KOps/s	$\color{#d91a1a}-3.08\%$
test_exec_td	0.1938ms	0.1570ms	6.3695 KOps/s	6.5658 KOps/s	$\color{#d91a1a}-2.99\%$
test_exec_td_decorator	0.9152ms	0.1944ms	5.1447 KOps/s	5.2518 KOps/s	$\color{#d91a1a}-2.04\%$
test_vmap_mlp_speed[True-True]	1.1878ms	1.0985ms	910.3429 Ops/s	928.5978 Ops/s	$\color{#d91a1a}-1.97\%$
test_vmap_mlp_speed[True-False]	0.6973ms	0.6279ms	1.5925 KOps/s	1.6243 KOps/s	$\color{#d91a1a}-1.95\%$
test_vmap_mlp_speed[False-True]	1.0866ms	1.0041ms	995.8938 Ops/s	1.0212 KOps/s	$\color{#d91a1a}-2.48\%$
test_vmap_mlp_speed[False-False]	0.6166ms	0.5550ms	1.8020 KOps/s	1.8456 KOps/s	$\color{#d91a1a}-2.36\%$
test_vmap_mlp_speed_decorator[True-True]	2.5924ms	2.0822ms	480.2676 Ops/s	487.9255 Ops/s	$\color{#d91a1a}-1.57\%$
test_vmap_mlp_speed_decorator[True-False]	1.0798ms	0.6734ms	1.4849 KOps/s	1.5212 KOps/s	$\color{#d91a1a}-2.39\%$
test_vmap_mlp_speed_decorator[False-True]	2.2495ms	1.8131ms	551.5445 Ops/s	563.4929 Ops/s	$\color{#d91a1a}-2.12\%$
test_vmap_mlp_speed_decorator[False-False]	1.0021ms	0.5707ms	1.7521 KOps/s	1.7901 KOps/s	$\color{#d91a1a}-2.12\%$
test_vmap_transformer_speed[True-True]	13.1151ms	12.9622ms	77.1476 Ops/s	78.9779 Ops/s	$\color{#d91a1a}-2.32\%$
test_vmap_transformer_speed[True-False]	8.7184ms	8.4870ms	117.8268 Ops/s	120.9117 Ops/s	$\color{#d91a1a}-2.55\%$
test_vmap_transformer_speed[False-True]	13.9215ms	12.9353ms	77.3081 Ops/s	80.0397 Ops/s	$\color{#d91a1a}-3.41\%$
test_vmap_transformer_speed[False-False]	8.7248ms	8.4044ms	118.9851 Ops/s	122.0678 Ops/s	$\color{#d91a1a}-2.53\%$
test_vmap_transformer_speed_decorator[True-True]	67.2791ms	66.2806ms	15.0874 Ops/s	15.3713 Ops/s	$\color{#d91a1a}-1.85\%$
test_vmap_transformer_speed_decorator[True-False]	97.8803ms	22.2199ms	45.0046 Ops/s	49.8353 Ops/s	$\textbf{\color{#d91a1a}-9.69\%}$
test_vmap_transformer_speed_decorator[False-True]	61.7245ms	60.4289ms	16.5484 Ops/s	16.9925 Ops/s	$\color{#d91a1a}-2.61\%$
test_vmap_transformer_speed_decorator[False-False]	22.3982ms	20.2392ms	49.4090 Ops/s	50.7167 Ops/s	$\color{#d91a1a}-2.58\%$