[Performance] Faster to_module

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 113. Improved: $\large\color{#35bf28}5$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	37.1490μs	16.0992μs	62.1148 KOps/s	62.1769 KOps/s	$\color{#d91a1a}-0.10\%$
test_plain_set_stack_nested	0.2536ms	0.1454ms	6.8769 KOps/s	6.8277 KOps/s	$\color{#35bf28}+0.72\%$
test_plain_set_nested_inplace	46.0060μs	19.3833μs	51.5909 KOps/s	52.1739 KOps/s	$\color{#d91a1a}-1.12\%$
test_plain_set_stack_nested_inplace	0.3055ms	0.1771ms	5.6462 KOps/s	5.6618 KOps/s	$\color{#d91a1a}-0.28\%$
test_items	0.1294ms	2.6046μs	383.9299 KOps/s	355.0682 KOps/s	$\textbf{\color{#35bf28}+8.13\%}$
test_items_nested	0.4759ms	0.2706ms	3.6955 KOps/s	3.7514 KOps/s	$\color{#d91a1a}-1.49\%$
test_items_nested_locked	0.9910ms	0.2705ms	3.6963 KOps/s	3.7441 KOps/s	$\color{#d91a1a}-1.28\%$
test_items_nested_leaf	0.5848ms	0.1650ms	6.0608 KOps/s	6.0306 KOps/s	$\color{#35bf28}+0.50\%$
test_items_stack_nested	1.6879ms	1.4844ms	673.6512 Ops/s	675.2712 Ops/s	$\color{#d91a1a}-0.24\%$
test_items_stack_nested_leaf	2.0860ms	1.3681ms	730.9665 Ops/s	739.1634 Ops/s	$\color{#d91a1a}-1.11\%$
test_items_stack_nested_locked	0.8691ms	0.7655ms	1.3064 KOps/s	1.2949 KOps/s	$\color{#35bf28}+0.89\%$
test_keys	0.1263ms	3.8974μs	256.5800 KOps/s	261.0417 KOps/s	$\color{#d91a1a}-1.71\%$
test_keys_nested	1.4512ms	0.1427ms	7.0060 KOps/s	6.6669 KOps/s	$\textbf{\color{#35bf28}+5.09\%}$
test_keys_nested_locked	0.1944ms	0.1418ms	7.0499 KOps/s	7.0865 KOps/s	$\color{#d91a1a}-0.52\%$
test_keys_nested_leaf	0.3243ms	0.1425ms	7.0152 KOps/s	7.0783 KOps/s	$\color{#d91a1a}-0.89\%$
test_keys_stack_nested	2.1390ms	1.4132ms	707.5926 Ops/s	704.4243 Ops/s	$\color{#35bf28}+0.45\%$
test_keys_stack_nested_leaf	2.1344ms	1.4081ms	710.1575 Ops/s	704.5780 Ops/s	$\color{#35bf28}+0.79\%$
test_keys_stack_nested_locked	1.1629ms	0.6725ms	1.4871 KOps/s	1.4407 KOps/s	$\color{#35bf28}+3.22\%$
test_values	8.2378μs	1.1873μs	842.2167 KOps/s	856.3997 KOps/s	$\color{#d91a1a}-1.66\%$
test_values_nested	85.7500μs	49.4506μs	20.2222 KOps/s	20.3051 KOps/s	$\color{#d91a1a}-0.41\%$
test_values_nested_locked	98.3640μs	49.5034μs	20.2006 KOps/s	20.1147 KOps/s	$\color{#35bf28}+0.43\%$
test_values_nested_leaf	55.7240μs	43.9320μs	22.7625 KOps/s	22.5214 KOps/s	$\color{#35bf28}+1.07\%$
test_values_stack_nested	1.3934ms	1.1883ms	841.5384 Ops/s	831.9000 Ops/s	$\color{#35bf28}+1.16\%$
test_values_stack_nested_leaf	1.2703ms	1.1853ms	843.6415 Ops/s	836.3661 Ops/s	$\color{#35bf28}+0.87\%$
test_values_stack_nested_locked	0.8939ms	0.5101ms	1.9605 KOps/s	1.9189 KOps/s	$\color{#35bf28}+2.17\%$
test_membership	16.0700μs	1.3606μs	734.9906 KOps/s	739.8790 KOps/s	$\color{#d91a1a}-0.66\%$
test_membership_nested	36.8490μs	2.7888μs	358.5803 KOps/s	345.7939 KOps/s	$\color{#35bf28}+3.70\%$
test_membership_nested_leaf	21.7200μs	2.8290μs	353.4816 KOps/s	344.4963 KOps/s	$\color{#35bf28}+2.61\%$
test_membership_stacked_nested	45.5450μs	11.7055μs	85.4299 KOps/s	84.3855 KOps/s	$\color{#35bf28}+1.24\%$
test_membership_stacked_nested_leaf	40.7360μs	11.5619μs	86.4907 KOps/s	83.6561 KOps/s	$\color{#35bf28}+3.39\%$
test_membership_nested_last	28.0020μs	5.8693μs	170.3768 KOps/s	162.8009 KOps/s	$\color{#35bf28}+4.65\%$
test_membership_nested_leaf_last	39.9240μs	5.9031μs	169.4018 KOps/s	167.2527 KOps/s	$\color{#35bf28}+1.28\%$
test_membership_stacked_nested_last	0.3300ms	0.1691ms	5.9145 KOps/s	5.8964 KOps/s	$\color{#35bf28}+0.31\%$
test_membership_stacked_nested_leaf_last	32.7510μs	13.5994μs	73.5329 KOps/s	73.7285 KOps/s	$\color{#d91a1a}-0.27\%$
test_nested_getleaf	46.5970μs	10.7366μs	93.1396 KOps/s	95.1910 KOps/s	$\color{#d91a1a}-2.15\%$
test_nested_get	36.1080μs	10.2612μs	97.4547 KOps/s	99.3129 KOps/s	$\color{#d91a1a}-1.87\%$
test_stacked_getleaf	0.8595ms	0.6464ms	1.5471 KOps/s	1.5420 KOps/s	$\color{#35bf28}+0.33\%$
test_stacked_get	1.3914ms	0.6133ms	1.6306 KOps/s	1.6055 KOps/s	$\color{#35bf28}+1.56\%$
test_nested_getitemleaf	49.9930μs	10.7118μs	93.3549 KOps/s	92.7389 KOps/s	$\color{#35bf28}+0.66\%$
test_nested_getitem	39.4340μs	10.1618μs	98.4080 KOps/s	99.0053 KOps/s	$\color{#d91a1a}-0.60\%$
test_stacked_getitemleaf	1.0988ms	0.6451ms	1.5502 KOps/s	1.5464 KOps/s	$\color{#35bf28}+0.25\%$
test_stacked_getitem	1.1529ms	0.6268ms	1.5953 KOps/s	1.6313 KOps/s	$\color{#d91a1a}-2.21\%$
test_lock_nested	55.0275ms	0.5424ms	1.8438 KOps/s	2.0256 KOps/s	$\textbf{\color{#d91a1a}-8.97\%}$
test_lock_stack_nested	74.1596ms	8.2480ms	121.2418 Ops/s	124.8375 Ops/s	$\color{#d91a1a}-2.88\%$
test_unlock_nested	60.7838ms	0.5023ms	1.9909 KOps/s	1.9536 KOps/s	$\color{#35bf28}+1.91\%$
test_unlock_stack_nested	68.5761ms	8.0016ms	124.9752 Ops/s	206.1984 Ops/s	$\textbf{\color{#d91a1a}-39.39\%}$
test_flatten_speed	1.1797ms	0.2788ms	3.5870 KOps/s	3.6930 KOps/s	$\color{#d91a1a}-2.87\%$
test_unflatten_speed	0.5351ms	0.4677ms	2.1383 KOps/s	2.1598 KOps/s	$\color{#d91a1a}-1.00\%$
test_common_ops	4.1997ms	0.6804ms	1.4698 KOps/s	1.4932 KOps/s	$\color{#d91a1a}-1.57\%$
test_creation	25.7980μs	2.4049μs	415.8128 KOps/s	418.3835 KOps/s	$\color{#d91a1a}-0.61\%$
test_creation_empty	39.6340μs	7.9539μs	125.7243 KOps/s	122.5708 KOps/s	$\color{#35bf28}+2.57\%$
test_creation_nested_1	40.5860μs	11.3128μs	88.3954 KOps/s	85.2253 KOps/s	$\color{#35bf28}+3.72\%$
test_creation_nested_2	38.5520μs	14.6970μs	68.0412 KOps/s	66.2535 KOps/s	$\color{#35bf28}+2.70\%$
test_clone	85.1090μs	13.2138μs	75.6784 KOps/s	74.8756 KOps/s	$\color{#35bf28}+1.07\%$
test_getitem[int]	44.7530μs	12.9914μs	76.9741 KOps/s	75.2508 KOps/s	$\color{#35bf28}+2.29\%$
test_getitem[slice_int]	72.7760μs	25.0768μs	39.8776 KOps/s	39.5558 KOps/s	$\color{#35bf28}+0.81\%$
test_getitem[range]	84.3670μs	45.5076μs	21.9744 KOps/s	21.6114 KOps/s	$\color{#35bf28}+1.68\%$
test_getitem[tuple]	66.7840μs	20.4001μs	49.0194 KOps/s	48.4561 KOps/s	$\color{#35bf28}+1.16\%$
test_getitem[list]	0.2674ms	40.3544μs	24.7804 KOps/s	24.2328 KOps/s	$\color{#35bf28}+2.26\%$
test_setitem_dim[int]	0.1004ms	28.2860μs	35.3532 KOps/s	36.3653 KOps/s	$\color{#d91a1a}-2.78\%$
test_setitem_dim[slice_int]	85.9900μs	52.4884μs	19.0518 KOps/s	18.9072 KOps/s	$\color{#35bf28}+0.77\%$
test_setitem_dim[range]	0.1118ms	72.4376μs	13.8050 KOps/s	13.6967 KOps/s	$\color{#35bf28}+0.79\%$
test_setitem_dim[tuple]	87.0130μs	41.1120μs	24.3238 KOps/s	24.6220 KOps/s	$\color{#d91a1a}-1.21\%$
test_setitem	0.1266ms	18.2367μs	54.8345 KOps/s	53.8737 KOps/s	$\color{#35bf28}+1.78\%$
test_set	0.1272ms	17.4067μs	57.4490 KOps/s	56.1146 KOps/s	$\color{#35bf28}+2.38\%$
test_set_shared	1.9672ms	0.1401ms	7.1383 KOps/s	7.1165 KOps/s	$\color{#35bf28}+0.31\%$
test_update	0.1106ms	19.1860μs	52.1215 KOps/s	53.0755 KOps/s	$\color{#d91a1a}-1.80\%$
test_update_nested	0.1493ms	26.5327μs	37.6893 KOps/s	38.1510 KOps/s	$\color{#d91a1a}-1.21\%$
test_set_nested	0.1175ms	19.9209μs	50.1985 KOps/s	50.7384 KOps/s	$\color{#d91a1a}-1.06\%$
test_set_nested_new	0.1160ms	24.7793μs	40.3562 KOps/s	38.8773 KOps/s	$\color{#35bf28}+3.80\%$
test_select	0.1217ms	50.3912μs	19.8448 KOps/s	19.9157 KOps/s	$\color{#d91a1a}-0.36\%$
test_unbind_speed	0.4404ms	0.3745ms	2.6703 KOps/s	2.6889 KOps/s	$\color{#d91a1a}-0.69\%$
test_unbind_speed_stack0	65.5388ms	5.2956ms	188.8346 Ops/s	248.8094 Ops/s	$\textbf{\color{#d91a1a}-24.10\%}$
test_unbind_speed_stack1	2.6093μs	0.6335μs	1.5787 MOps/s	1.5718 MOps/s	$\color{#35bf28}+0.44\%$
test_split	55.3698ms	1.7556ms	569.6016 Ops/s	557.7401 Ops/s	$\color{#35bf28}+2.13\%$
test_chunk	58.6198ms	1.7392ms	574.9751 Ops/s	567.6994 Ops/s	$\color{#35bf28}+1.28\%$
test_creation[device0]	5.2488ms	0.2950ms	3.3901 KOps/s	3.2776 KOps/s	$\color{#35bf28}+3.43\%$
test_creation_from_tensor	59.5799ms	0.3580ms	2.7933 KOps/s	2.9859 KOps/s	$\textbf{\color{#d91a1a}-6.45\%}$
test_add_one[memmap_tensor0]	70.6520μs	25.7879μs	38.7779 KOps/s	40.0790 KOps/s	$\color{#d91a1a}-3.25\%$
test_contiguous[memmap_tensor0]	29.4350μs	6.0130μs	166.3074 KOps/s	171.7384 KOps/s	$\color{#d91a1a}-3.16\%$
test_stack[memmap_tensor0]	96.9910μs	19.6944μs	50.7759 KOps/s	51.3259 KOps/s	$\color{#d91a1a}-1.07\%$
test_memmaptd_index	0.4862ms	0.4016ms	2.4899 KOps/s	2.4456 KOps/s	$\color{#35bf28}+1.81\%$
test_memmaptd_index_astensor	0.9022ms	0.4683ms	2.1352 KOps/s	2.0830 KOps/s	$\color{#35bf28}+2.51\%$
test_memmaptd_index_op	0.8051ms	0.7051ms	1.4183 KOps/s	1.3855 KOps/s	$\color{#35bf28}+2.36\%$
test_reshape_pytree	0.3323ms	23.2215μs	43.0635 KOps/s	41.6877 KOps/s	$\color{#35bf28}+3.30\%$
test_reshape_td	89.5580μs	31.6180μs	31.6276 KOps/s	30.5861 KOps/s	$\color{#35bf28}+3.41\%$
test_view_pytree	75.1900μs	23.4766μs	42.5956 KOps/s	42.6087 KOps/s	$\color{#d91a1a}-0.03\%$
test_view_td	23.1530μs	4.8547μs	205.9853 KOps/s	203.5797 KOps/s	$\color{#35bf28}+1.18\%$
test_unbind_pytree	86.3010μs	26.3338μs	37.9740 KOps/s	37.5214 KOps/s	$\color{#35bf28}+1.21\%$
test_unbind_td	0.1154ms	59.7871μs	16.7260 KOps/s	16.6501 KOps/s	$\color{#35bf28}+0.46\%$
test_split_pytree	89.1680μs	26.2076μs	38.1568 KOps/s	37.5763 KOps/s	$\color{#35bf28}+1.54\%$
test_split_td	0.1298ms	46.9680μs	21.2911 KOps/s	20.9089 KOps/s	$\color{#35bf28}+1.83\%$
test_add_pytree	70.2610μs	32.3736μs	30.8894 KOps/s	30.8967 KOps/s	$\color{#d91a1a}-0.02\%$
test_add_td	0.1073ms	45.0460μs	22.1995 KOps/s	21.9269 KOps/s	$\color{#35bf28}+1.24\%$
test_distributed	24.8660μs	6.0096μs	166.4017 KOps/s	166.5763 KOps/s	$\color{#d91a1a}-0.10\%$
test_tdmodule	0.1021ms	20.9949μs	47.6305 KOps/s	46.4625 KOps/s	$\color{#35bf28}+2.51\%$
test_tdmodule_dispatch	0.1678ms	38.4929μs	25.9788 KOps/s	25.5022 KOps/s	$\color{#35bf28}+1.87\%$
test_tdseq	0.3638ms	24.4907μs	40.8318 KOps/s	40.6807 KOps/s	$\color{#35bf28}+0.37\%$
test_tdseq_dispatch	0.4113ms	42.3081μs	23.6362 KOps/s	23.4523 KOps/s	$\color{#35bf28}+0.78\%$
test_instantiation_functorch	1.9890ms	1.3153ms	760.3111 Ops/s	766.2344 Ops/s	$\color{#d91a1a}-0.77\%$
test_instantiation_td	1.5170ms	1.0264ms	974.2583 Ops/s	977.4129 Ops/s	$\color{#d91a1a}-0.32\%$
test_exec_functorch	0.2263ms	0.1617ms	6.1849 KOps/s	6.2688 KOps/s	$\color{#d91a1a}-1.34\%$
test_exec_functional_call	0.3898ms	0.1465ms	6.8240 KOps/s	6.6695 KOps/s	$\color{#35bf28}+2.32\%$
test_exec_td	0.2165ms	0.1423ms	7.0269 KOps/s	6.8472 KOps/s	$\color{#35bf28}+2.62\%$
test_exec_td_decorator	1.0105ms	0.1807ms	5.5343 KOps/s	3.6724 KOps/s	$\textbf{\color{#35bf28}+50.70\%}$
test_vmap_mlp_speed[True-True]	1.0075ms	0.8958ms	1.1164 KOps/s	1.0970 KOps/s	$\color{#35bf28}+1.77\%$
test_vmap_mlp_speed[True-False]	0.7111ms	0.4673ms	2.1398 KOps/s	2.0827 KOps/s	$\color{#35bf28}+2.74\%$
test_vmap_mlp_speed[False-True]	1.1664ms	0.7819ms	1.2790 KOps/s	1.2631 KOps/s	$\color{#35bf28}+1.26\%$
test_vmap_mlp_speed[False-False]	0.5048ms	0.3861ms	2.5898 KOps/s	2.5397 KOps/s	$\color{#35bf28}+1.97\%$
test_vmap_mlp_speed_decorator[True-True]	2.7442ms	1.7742ms	563.6298 Ops/s	623.8952 Ops/s	$\textbf{\color{#d91a1a}-9.66\%}$
test_vmap_mlp_speed_decorator[True-False]	0.9940ms	0.5179ms	1.9310 KOps/s	1.7831 KOps/s	$\textbf{\color{#35bf28}+8.29\%}$
test_vmap_mlp_speed_decorator[False-True]	2.3741ms	1.4872ms	672.3859 Ops/s	728.0136 Ops/s	$\textbf{\color{#d91a1a}-7.64\%}$
test_vmap_mlp_speed_decorator[False-False]	1.2460ms	0.4025ms	2.4844 KOps/s	2.2905 KOps/s	$\textbf{\color{#35bf28}+8.47\%}$

[github-actions]

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

Total Benchmarks: 127. Improved: $\large\color{#35bf28}9$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	0.4211ms	12.6294μs	79.1805 KOps/s	78.9239 KOps/s	$\color{#35bf28}+0.33\%$
test_plain_set_stack_nested	0.1431ms	0.1154ms	8.6671 KOps/s	8.3673 KOps/s	$\color{#35bf28}+3.58\%$
test_plain_set_nested_inplace	39.8720μs	14.8730μs	67.2359 KOps/s	66.2317 KOps/s	$\color{#35bf28}+1.52\%$
test_plain_set_stack_nested_inplace	0.1716ms	0.1394ms	7.1752 KOps/s	7.1217 KOps/s	$\color{#35bf28}+0.75\%$
test_items	24.0710μs	4.9031μs	203.9512 KOps/s	207.8566 KOps/s	$\color{#d91a1a}-1.88\%$
test_items_nested	0.4046ms	0.3358ms	2.9784 KOps/s	2.9564 KOps/s	$\color{#35bf28}+0.74\%$
test_items_nested_locked	0.3949ms	0.3365ms	2.9718 KOps/s	2.9811 KOps/s	$\color{#d91a1a}-0.31\%$
test_items_nested_leaf	0.2241ms	0.1981ms	5.0482 KOps/s	5.0160 KOps/s	$\color{#35bf28}+0.64\%$
test_items_stack_nested	1.5875ms	1.4776ms	676.7658 Ops/s	678.4091 Ops/s	$\color{#d91a1a}-0.24\%$
test_items_stack_nested_leaf	1.3704ms	1.3053ms	766.0841 Ops/s	764.0761 Ops/s	$\color{#35bf28}+0.26\%$
test_items_stack_nested_locked	1.7633ms	0.7967ms	1.2552 KOps/s	1.2552 KOps/s	$+0.00\%$
test_keys	24.3810μs	4.5738μs	218.6377 KOps/s	218.6668 KOps/s	$\color{#d91a1a}-0.01\%$
test_keys_nested	0.4960ms	90.3431μs	11.0689 KOps/s	11.1941 KOps/s	$\color{#d91a1a}-1.12\%$
test_keys_nested_locked	0.1210ms	89.6516μs	11.1543 KOps/s	11.2335 KOps/s	$\color{#d91a1a}-0.71\%$
test_keys_nested_leaf	42.0050ms	86.9698μs	11.4982 KOps/s	12.3349 KOps/s	$\textbf{\color{#d91a1a}-6.78\%}$
test_keys_stack_nested	1.3674ms	1.2767ms	783.2743 Ops/s	772.7949 Ops/s	$\color{#35bf28}+1.36\%$
test_keys_stack_nested_leaf	1.3863ms	1.2673ms	789.0860 Ops/s	776.1860 Ops/s	$\color{#35bf28}+1.66\%$
test_keys_stack_nested_locked	0.6909ms	0.5958ms	1.6783 KOps/s	1.6771 KOps/s	$\color{#35bf28}+0.07\%$
test_values	8.2603μs	1.8848μs	530.5684 KOps/s	533.7036 KOps/s	$\color{#d91a1a}-0.59\%$
test_values_nested	74.6130μs	42.8407μs	23.3423 KOps/s	23.2731 KOps/s	$\color{#35bf28}+0.30\%$
test_values_nested_locked	65.3330μs	43.0486μs	23.2296 KOps/s	22.9672 KOps/s	$\color{#35bf28}+1.14\%$
test_values_nested_leaf	64.8340μs	37.1143μs	26.9438 KOps/s	26.5796 KOps/s	$\color{#35bf28}+1.37\%$
test_values_stack_nested	1.1897ms	1.1283ms	886.3239 Ops/s	893.0326 Ops/s	$\color{#d91a1a}-0.75\%$
test_values_stack_nested_leaf	1.1748ms	1.1087ms	901.9867 Ops/s	899.7830 Ops/s	$\color{#35bf28}+0.24\%$
test_values_stack_nested_locked	0.5304ms	0.4728ms	2.1151 KOps/s	2.0980 KOps/s	$\color{#35bf28}+0.81\%$
test_membership	4.5818μs	0.9278μs	1.0778 MOps/s	1.0693 MOps/s	$\color{#35bf28}+0.80\%$
test_membership_nested	28.3510μs	2.1844μs	457.7935 KOps/s	468.9322 KOps/s	$\color{#d91a1a}-2.38\%$
test_membership_nested_leaf	16.0055μs	2.1360μs	468.1577 KOps/s	475.1231 KOps/s	$\color{#d91a1a}-1.47\%$
test_membership_stacked_nested	44.0520μs	10.7129μs	93.3450 KOps/s	92.6988 KOps/s	$\color{#35bf28}+0.70\%$
test_membership_stacked_nested_leaf	35.3520μs	10.7207μs	93.2775 KOps/s	91.1184 KOps/s	$\color{#35bf28}+2.37\%$
test_membership_nested_last	21.5510μs	4.5702μs	218.8085 KOps/s	217.3792 KOps/s	$\color{#35bf28}+0.66\%$
test_membership_nested_leaf_last	33.2210μs	4.5652μs	219.0503 KOps/s	218.4525 KOps/s	$\color{#35bf28}+0.27\%$
test_membership_stacked_nested_last	0.1649ms	0.1330ms	7.5187 KOps/s	7.4985 KOps/s	$\color{#35bf28}+0.27\%$
test_membership_stacked_nested_leaf_last	32.1320μs	12.5882μs	79.4396 KOps/s	79.1724 KOps/s	$\color{#35bf28}+0.34\%$
test_nested_getleaf	29.7310μs	8.3609μs	119.6048 KOps/s	118.9282 KOps/s	$\color{#35bf28}+0.57\%$
test_nested_get	29.3810μs	7.8730μs	127.0170 KOps/s	125.7927 KOps/s	$\color{#35bf28}+0.97\%$
test_stacked_getleaf	0.6145ms	0.5606ms	1.7839 KOps/s	1.7410 KOps/s	$\color{#35bf28}+2.46\%$
test_stacked_get	0.5766ms	0.5282ms	1.8932 KOps/s	1.8597 KOps/s	$\color{#35bf28}+1.80\%$
test_nested_getitemleaf	31.4010μs	8.3752μs	119.3996 KOps/s	118.1746 KOps/s	$\color{#35bf28}+1.04\%$
test_nested_getitem	28.8910μs	7.9380μs	125.9770 KOps/s	124.9850 KOps/s	$\color{#35bf28}+0.79\%$
test_stacked_getitemleaf	0.6342ms	0.5613ms	1.7814 KOps/s	1.7608 KOps/s	$\color{#35bf28}+1.17\%$
test_stacked_getitem	0.6048ms	0.5378ms	1.8596 KOps/s	1.8769 KOps/s	$\color{#d91a1a}-0.92\%$
test_lock_nested	4.3950ms	0.4539ms	2.2033 KOps/s	2.1870 KOps/s	$\color{#35bf28}+0.75\%$
test_lock_stack_nested	67.9166ms	6.5143ms	153.5091 Ops/s	151.5574 Ops/s	$\color{#35bf28}+1.29\%$
test_unlock_nested	1.2988ms	0.4327ms	2.3108 KOps/s	2.0322 KOps/s	$\textbf{\color{#35bf28}+13.71\%}$
test_unlock_stack_nested	63.8541ms	7.2507ms	137.9185 Ops/s	138.2704 Ops/s	$\color{#d91a1a}-0.25\%$
test_flatten_speed	0.5201ms	0.1869ms	5.3505 KOps/s	5.3941 KOps/s	$\color{#d91a1a}-0.81\%$
test_unflatten_speed	0.4305ms	0.3620ms	2.7625 KOps/s	2.7980 KOps/s	$\color{#d91a1a}-1.27\%$
test_common_ops	1.0558ms	0.5823ms	1.7174 KOps/s	1.6958 KOps/s	$\color{#35bf28}+1.27\%$
test_creation	13.5710μs	1.9300μs	518.1304 KOps/s	520.0878 KOps/s	$\color{#d91a1a}-0.38\%$
test_creation_empty	24.9510μs	6.5387μs	152.9363 KOps/s	141.9366 KOps/s	$\textbf{\color{#35bf28}+7.75\%}$
test_creation_nested_1	41.6520μs	8.9675μs	111.5143 KOps/s	106.3376 KOps/s	$\color{#35bf28}+4.87\%$
test_creation_nested_2	30.2810μs	11.6067μs	86.1575 KOps/s	83.5301 KOps/s	$\color{#35bf28}+3.15\%$
test_clone	0.1066ms	13.7770μs	72.5850 KOps/s	72.5156 KOps/s	$\color{#35bf28}+0.10\%$
test_getitem[int]	39.7020μs	11.8738μs	84.2192 KOps/s	83.8293 KOps/s	$\color{#35bf28}+0.47\%$
test_getitem[slice_int]	48.3020μs	22.5313μs	44.3828 KOps/s	43.1771 KOps/s	$\color{#35bf28}+2.79\%$
test_getitem[range]	61.6730μs	38.7413μs	25.8123 KOps/s	25.1509 KOps/s	$\color{#35bf28}+2.63\%$
test_getitem[tuple]	49.5520μs	19.3865μs	51.5824 KOps/s	50.3319 KOps/s	$\color{#35bf28}+2.48\%$
test_getitem[list]	0.3019ms	35.5470μs	28.1317 KOps/s	27.2563 KOps/s	$\color{#35bf28}+3.21\%$
test_setitem_dim[int]	40.8520μs	24.0906μs	41.5099 KOps/s	38.5385 KOps/s	$\textbf{\color{#35bf28}+7.71\%}$
test_setitem_dim[slice_int]	61.1930μs	43.5627μs	22.9554 KOps/s	21.8642 KOps/s	$\color{#35bf28}+4.99\%$
test_setitem_dim[range]	83.4740μs	61.2008μs	16.3397 KOps/s	15.8878 KOps/s	$\color{#35bf28}+2.84\%$
test_setitem_dim[tuple]	78.6440μs	37.5969μs	26.5980 KOps/s	25.8887 KOps/s	$\color{#35bf28}+2.74\%$
test_setitem	0.1126ms	17.5392μs	57.0153 KOps/s	57.2480 KOps/s	$\color{#d91a1a}-0.41\%$
test_set	0.1082ms	16.8393μs	59.3850 KOps/s	58.2965 KOps/s	$\color{#35bf28}+1.87\%$
test_set_shared	2.6463ms	98.9800μs	10.1030 KOps/s	9.3730 KOps/s	$\textbf{\color{#35bf28}+7.79\%}$
test_update	0.1069ms	18.0709μs	55.3375 KOps/s	54.4232 KOps/s	$\color{#35bf28}+1.68\%$
test_update_nested	0.1285ms	24.5734μs	40.6944 KOps/s	40.5572 KOps/s	$\color{#35bf28}+0.34\%$
test_set_nested	0.1069ms	18.2419μs	54.8187 KOps/s	55.2669 KOps/s	$\color{#d91a1a}-0.81\%$
test_set_nested_new	0.1208ms	22.5770μs	44.2930 KOps/s	43.8337 KOps/s	$\color{#35bf28}+1.05\%$
test_select	0.1467ms	46.2471μs	21.6230 KOps/s	21.9435 KOps/s	$\color{#d91a1a}-1.46\%$
test_to	73.6140μs	51.1312μs	19.5575 KOps/s	19.7928 KOps/s	$\color{#d91a1a}-1.19\%$
test_to_nonblocking	62.2230μs	33.2236μs	30.0990 KOps/s	29.6131 KOps/s	$\color{#35bf28}+1.64\%$
test_unbind_speed	0.3799ms	0.3452ms	2.8967 KOps/s	2.8854 KOps/s	$\color{#35bf28}+0.39\%$
test_unbind_speed_stack0	60.0775ms	5.0693ms	197.2671 Ops/s	195.3944 Ops/s	$\color{#35bf28}+0.96\%$
test_unbind_speed_stack1	1.9831μs	0.5290μs	1.8902 MOps/s	1.9091 MOps/s	$\color{#d91a1a}-0.99\%$
test_split	53.0894ms	1.7574ms	569.0289 Ops/s	562.7664 Ops/s	$\color{#35bf28}+1.11\%$
test_chunk	53.0076ms	1.7579ms	568.8754 Ops/s	567.4860 Ops/s	$\color{#35bf28}+0.24\%$
test_creation[device0]	0.4213ms	0.3093ms	3.2334 KOps/s	3.2287 KOps/s	$\color{#35bf28}+0.15\%$
test_creation[device1]	54.9972ms	0.3358ms	2.9781 KOps/s	3.1891 KOps/s	$\textbf{\color{#d91a1a}-6.62\%}$
test_creation_from_tensor	0.5787ms	0.3376ms	2.9620 KOps/s	2.6957 KOps/s	$\textbf{\color{#35bf28}+9.88\%}$
test_add_one[memmap_tensor0]	70.2840μs	22.6726μs	44.1062 KOps/s	42.6968 KOps/s	$\color{#35bf28}+3.30\%$
test_add_one[memmap_tensor1]	0.2095ms	71.9854μs	13.8917 KOps/s	13.9939 KOps/s	$\color{#d91a1a}-0.73\%$
test_contiguous[memmap_tensor0]	29.9920μs	5.7976μs	172.4843 KOps/s	174.7782 KOps/s	$\color{#d91a1a}-1.31\%$
test_contiguous[memmap_tensor1]	53.0330μs	21.0752μs	47.4491 KOps/s	47.8573 KOps/s	$\color{#d91a1a}-0.85\%$
test_stack[memmap_tensor0]	49.0720μs	18.9636μs	52.7326 KOps/s	51.9975 KOps/s	$\color{#35bf28}+1.41\%$
test_stack[memmap_tensor1]	0.1528ms	72.1606μs	13.8580 KOps/s	13.4228 KOps/s	$\color{#35bf28}+3.24\%$
test_memmaptd_index	0.4609ms	0.4199ms	2.3812 KOps/s	2.3747 KOps/s	$\color{#35bf28}+0.28\%$
test_memmaptd_index_astensor	0.5294ms	0.4776ms	2.0939 KOps/s	2.0862 KOps/s	$\color{#35bf28}+0.37\%$
test_memmaptd_index_op	0.7716ms	0.7150ms	1.3987 KOps/s	1.3514 KOps/s	$\color{#35bf28}+3.50\%$
test_reshape_pytree	42.7710μs	20.6918μs	48.3282 KOps/s	47.9222 KOps/s	$\color{#35bf28}+0.85\%$
test_reshape_td	48.2920μs	29.8524μs	33.4982 KOps/s	33.5291 KOps/s	$\color{#d91a1a}-0.09\%$
test_view_pytree	35.4120μs	20.4906μs	48.8028 KOps/s	48.3753 KOps/s	$\color{#35bf28}+0.88\%$
test_view_td	23.4510μs	4.0882μs	244.6036 KOps/s	245.3667 KOps/s	$\color{#d91a1a}-0.31\%$
test_unbind_pytree	49.5920μs	25.4534μs	39.2875 KOps/s	39.3311 KOps/s	$\color{#d91a1a}-0.11\%$
test_unbind_td	77.6140μs	54.9088μs	18.2120 KOps/s	17.8613 KOps/s	$\color{#35bf28}+1.96\%$
test_split_pytree	0.8458ms	24.1525μs	41.4035 KOps/s	41.6226 KOps/s	$\color{#d91a1a}-0.53\%$
test_split_td	73.0030μs	42.3103μs	23.6349 KOps/s	22.4112 KOps/s	$\textbf{\color{#35bf28}+5.46\%}$
test_add_pytree	47.7130μs	30.4811μs	32.8073 KOps/s	33.1077 KOps/s	$\color{#d91a1a}-0.91\%$
test_add_td	66.9230μs	40.8044μs	24.5071 KOps/s	23.9581 KOps/s	$\color{#35bf28}+2.29\%$
test_distributed	17.6010μs	5.5205μs	181.1427 KOps/s	175.9385 KOps/s	$\color{#35bf28}+2.96\%$
test_tdmodule	35.4810μs	16.4018μs	60.9690 KOps/s	59.7600 KOps/s	$\color{#35bf28}+2.02\%$
test_tdmodule_dispatch	0.2673ms	32.1188μs	31.1344 KOps/s	30.5154 KOps/s	$\color{#35bf28}+2.03\%$
test_tdseq	34.6420μs	19.4664μs	51.3705 KOps/s	49.8794 KOps/s	$\color{#35bf28}+2.99\%$
test_tdseq_dispatch	0.1510ms	34.8325μs	28.7088 KOps/s	26.9404 KOps/s	$\textbf{\color{#35bf28}+6.56\%}$
test_instantiation_functorch	1.7643ms	1.6793ms	595.5019 Ops/s	593.8954 Ops/s	$\color{#35bf28}+0.27\%$
test_instantiation_td	1.9085ms	1.1762ms	850.2305 Ops/s	852.1358 Ops/s	$\color{#d91a1a}-0.22\%$
test_exec_functorch	0.2046ms	0.1543ms	6.4801 KOps/s	6.4676 KOps/s	$\color{#35bf28}+0.19\%$
test_exec_functional_call	0.2163ms	0.1533ms	6.5229 KOps/s	6.5892 KOps/s	$\color{#d91a1a}-1.01\%$
test_exec_td	0.1734ms	0.1420ms	7.0409 KOps/s	6.9983 KOps/s	$\color{#35bf28}+0.61\%$
test_exec_td_decorator	63.9216ms	0.2010ms	4.9750 KOps/s	4.6120 KOps/s	$\textbf{\color{#35bf28}+7.87\%}$
test_vmap_mlp_speed[True-True]	1.5470ms	1.0549ms	947.9602 Ops/s	945.3579 Ops/s	$\color{#35bf28}+0.28\%$
test_vmap_mlp_speed[True-False]	0.6434ms	0.5903ms	1.6941 KOps/s	1.6718 KOps/s	$\color{#35bf28}+1.34\%$
test_vmap_mlp_speed[False-True]	1.0100ms	0.9586ms	1.0432 KOps/s	1.0312 KOps/s	$\color{#35bf28}+1.16\%$
test_vmap_mlp_speed[False-False]	0.5813ms	0.5237ms	1.9095 KOps/s	1.8943 KOps/s	$\color{#35bf28}+0.80\%$
test_vmap_mlp_speed_decorator[True-True]	2.7425ms	2.0231ms	494.2838 Ops/s	566.1121 Ops/s	$\textbf{\color{#d91a1a}-12.69\%}$
test_vmap_mlp_speed_decorator[True-False]	1.1712ms	0.6410ms	1.5600 KOps/s	1.4916 KOps/s	$\color{#35bf28}+4.59\%$
test_vmap_mlp_speed_decorator[False-True]	2.2573ms	1.7400ms	574.7166 Ops/s	630.2028 Ops/s	$\textbf{\color{#d91a1a}-8.80\%}$
test_vmap_mlp_speed_decorator[False-False]	1.0054ms	0.5454ms	1.8335 KOps/s	1.7749 KOps/s	$\color{#35bf28}+3.30\%$
test_vmap_transformer_speed[True-True]	12.3646ms	12.2601ms	81.5656 Ops/s	81.3220 Ops/s	$\color{#35bf28}+0.30\%$
test_vmap_transformer_speed[True-False]	8.0023ms	7.9440ms	125.8818 Ops/s	125.1025 Ops/s	$\color{#35bf28}+0.62\%$
test_vmap_transformer_speed[False-True]	12.2011ms	12.1082ms	82.5887 Ops/s	81.2234 Ops/s	$\color{#35bf28}+1.68\%$
test_vmap_transformer_speed[False-False]	7.9540ms	7.8556ms	127.2983 Ops/s	126.3453 Ops/s	$\color{#35bf28}+0.75\%$
test_vmap_transformer_speed_decorator[True-True]	64.2383ms	63.2098ms	15.8203 Ops/s	23.7193 Ops/s	$\textbf{\color{#d91a1a}-33.30\%}$
test_vmap_transformer_speed_decorator[True-False]	20.9064ms	19.2437ms	51.9650 Ops/s	47.1718 Ops/s	$\textbf{\color{#35bf28}+10.16\%}$
test_vmap_transformer_speed_decorator[False-True]	58.8411ms	57.6712ms	17.3397 Ops/s	23.9580 Ops/s	$\textbf{\color{#d91a1a}-27.62\%}$
test_vmap_transformer_speed_decorator[False-False]	99.0540ms	20.4384ms	48.9275 Ops/s	48.1389 Ops/s	$\color{#35bf28}+1.64\%$