[CI] Add regular benchmarks to CI in PRs without upload

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 105. Improved: $\large\color{#35bf28}6$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	31.0880μs	14.9259μs	66.9975 KOps/s	66.3825 KOps/s	$\color{#35bf28}+0.93\%$
test_plain_set_stack_nested	0.1939ms	0.1374ms	7.2768 KOps/s	7.1652 KOps/s	$\color{#35bf28}+1.56\%$
test_plain_set_nested_inplace	39.2130μs	17.8066μs	56.1591 KOps/s	55.4817 KOps/s	$\color{#35bf28}+1.22\%$
test_plain_set_stack_nested_inplace	0.3419ms	0.1689ms	5.9203 KOps/s	5.9196 KOps/s	$\color{#35bf28}+0.01\%$
test_items	35.1350μs	2.6451μs	378.0619 KOps/s	367.3160 KOps/s	$\color{#35bf28}+2.93\%$
test_items_nested	0.5546ms	0.2665ms	3.7526 KOps/s	3.7572 KOps/s	$\color{#d91a1a}-0.12\%$
test_items_nested_locked	0.9516ms	0.2690ms	3.7181 KOps/s	3.7237 KOps/s	$\color{#d91a1a}-0.15\%$
test_items_nested_leaf	0.2207ms	0.1643ms	6.0864 KOps/s	6.0760 KOps/s	$\color{#35bf28}+0.17\%$
test_items_stack_nested	1.5745ms	1.3683ms	730.8287 Ops/s	729.4420 Ops/s	$\color{#35bf28}+0.19\%$
test_items_stack_nested_leaf	1.4323ms	1.2401ms	806.4057 Ops/s	801.7863 Ops/s	$\color{#35bf28}+0.58\%$
test_items_stack_nested_locked	1.9552ms	0.7364ms	1.3580 KOps/s	1.3544 KOps/s	$\color{#35bf28}+0.26\%$
test_keys	17.3830μs	4.2777μs	233.7731 KOps/s	230.4820 KOps/s	$\color{#35bf28}+1.43\%$
test_keys_nested	0.5191ms	0.1361ms	7.3463 KOps/s	6.6999 KOps/s	$\textbf{\color{#35bf28}+9.65\%}$
test_keys_nested_locked	0.2015ms	0.1367ms	7.3134 KOps/s	7.2166 KOps/s	$\color{#35bf28}+1.34\%$
test_keys_nested_leaf	0.2340ms	0.1342ms	7.4532 KOps/s	7.3084 KOps/s	$\color{#35bf28}+1.98\%$
test_keys_stack_nested	2.1173ms	1.2710ms	786.7659 Ops/s	777.4680 Ops/s	$\color{#35bf28}+1.20\%$
test_keys_stack_nested_leaf	1.8747ms	1.2617ms	792.5612 Ops/s	778.5878 Ops/s	$\color{#35bf28}+1.79\%$
test_keys_stack_nested_locked	1.0474ms	0.6087ms	1.6430 KOps/s	1.5930 KOps/s	$\color{#35bf28}+3.14\%$
test_values	22.3156μs	1.1402μs	877.0152 KOps/s	883.4583 KOps/s	$\color{#d91a1a}-0.73\%$
test_values_nested	80.0990μs	48.0012μs	20.8328 KOps/s	20.7153 KOps/s	$\color{#35bf28}+0.57\%$
test_values_nested_locked	94.9680μs	48.4587μs	20.6361 KOps/s	20.5181 KOps/s	$\color{#35bf28}+0.58\%$
test_values_nested_leaf	79.8780μs	43.2977μs	23.0959 KOps/s	23.1685 KOps/s	$\color{#d91a1a}-0.31\%$
test_values_stack_nested	1.7247ms	1.0970ms	911.5651 Ops/s	900.5881 Ops/s	$\color{#35bf28}+1.22\%$
test_values_stack_nested_leaf	1.8531ms	1.0878ms	919.3000 Ops/s	911.8909 Ops/s	$\color{#35bf28}+0.81\%$
test_values_stack_nested_locked	0.9627ms	0.4800ms	2.0835 KOps/s	2.0482 KOps/s	$\color{#35bf28}+1.72\%$
test_membership	12.3930μs	1.3518μs	739.7641 KOps/s	738.7440 KOps/s	$\color{#35bf28}+0.14\%$
test_membership_nested	16.1500μs	2.8639μs	349.1787 KOps/s	350.0720 KOps/s	$\color{#d91a1a}-0.26\%$
test_membership_nested_leaf	25.3970μs	2.9125μs	343.3484 KOps/s	340.4383 KOps/s	$\color{#35bf28}+0.85\%$
test_membership_stacked_nested	41.2770μs	11.3938μs	87.7668 KOps/s	85.1004 KOps/s	$\color{#35bf28}+3.13\%$
test_membership_stacked_nested_leaf	0.1994ms	11.5035μs	86.9301 KOps/s	87.2288 KOps/s	$\color{#d91a1a}-0.34\%$
test_membership_nested_last	25.8080μs	6.0609μs	164.9932 KOps/s	170.4341 KOps/s	$\color{#d91a1a}-3.19\%$
test_membership_nested_leaf_last	28.1020μs	5.9544μs	167.9424 KOps/s	170.1718 KOps/s	$\color{#d91a1a}-1.31\%$
test_membership_stacked_nested_last	0.3302ms	0.1782ms	5.6129 KOps/s	5.6023 KOps/s	$\color{#35bf28}+0.19\%$
test_membership_stacked_nested_leaf_last	47.5080μs	13.3953μs	74.6530 KOps/s	73.8102 KOps/s	$\color{#35bf28}+1.14\%$
test_nested_getleaf	60.4430μs	12.2686μs	81.5092 KOps/s	82.0379 KOps/s	$\color{#d91a1a}-0.64\%$
test_nested_get	44.8730μs	11.5705μs	86.4266 KOps/s	86.2096 KOps/s	$\color{#35bf28}+0.25\%$
test_stacked_getleaf	3.8734ms	0.5707ms	1.7523 KOps/s	1.7271 KOps/s	$\color{#35bf28}+1.46\%$
test_stacked_get	0.6833ms	0.5433ms	1.8405 KOps/s	1.8155 KOps/s	$\color{#35bf28}+1.37\%$
test_nested_getitemleaf	51.2450μs	12.2140μs	81.8732 KOps/s	82.5655 KOps/s	$\color{#d91a1a}-0.84\%$
test_nested_getitem	33.2220μs	11.6065μs	86.1590 KOps/s	87.1597 KOps/s	$\color{#d91a1a}-1.15\%$
test_stacked_getitemleaf	0.6701ms	0.5706ms	1.7524 KOps/s	1.7191 KOps/s	$\color{#35bf28}+1.94\%$
test_stacked_getitem	0.9479ms	0.5477ms	1.8257 KOps/s	1.8250 KOps/s	$\color{#35bf28}+0.04\%$
test_lock_nested	55.7303ms	0.9406ms	1.0632 KOps/s	1.1361 KOps/s	$\textbf{\color{#d91a1a}-6.42\%}$
test_lock_stack_nested	80.4594ms	13.1474ms	76.0607 Ops/s	73.4599 Ops/s	$\color{#35bf28}+3.54\%$
test_unlock_nested	54.7156ms	0.9421ms	1.0615 KOps/s	1.0625 KOps/s	$\color{#d91a1a}-0.10\%$
test_unlock_stack_nested	76.3571ms	13.5021ms	74.0623 Ops/s	71.7490 Ops/s	$\color{#35bf28}+3.22\%$
test_flatten_speed	0.7786ms	0.6625ms	1.5094 KOps/s	1.5030 KOps/s	$\color{#35bf28}+0.43\%$
test_unflatten_speed	1.3489ms	1.1555ms	865.4416 Ops/s	868.9491 Ops/s	$\color{#d91a1a}-0.40\%$
test_common_ops	4.9994ms	0.6192ms	1.6150 KOps/s	1.5830 KOps/s	$\color{#35bf28}+2.02\%$
test_creation	23.8740μs	2.2099μs	452.5180 KOps/s	456.3596 KOps/s	$\color{#d91a1a}-0.84\%$
test_creation_empty	26.5890μs	7.2580μs	137.7798 KOps/s	138.8925 KOps/s	$\color{#d91a1a}-0.80\%$
test_creation_nested_1	60.9130μs	11.0190μs	90.7521 KOps/s	90.8386 KOps/s	$\color{#d91a1a}-0.10\%$
test_creation_nested_2	33.3620μs	13.5855μs	73.6080 KOps/s	73.9091 KOps/s	$\color{#d91a1a}-0.41\%$
test_clone	79.1270μs	10.6074μs	94.2737 KOps/s	93.7472 KOps/s	$\color{#35bf28}+0.56\%$
test_getitem[int]	35.2160μs	12.7884μs	78.1956 KOps/s	77.8155 KOps/s	$\color{#35bf28}+0.49\%$
test_getitem[slice_int]	80.9910μs	28.5481μs	35.0286 KOps/s	33.6920 KOps/s	$\color{#35bf28}+3.97\%$
test_getitem[range]	0.1047ms	53.2838μs	18.7674 KOps/s	17.8482 KOps/s	$\textbf{\color{#35bf28}+5.15\%}$
test_getitem[tuple]	53.6100μs	23.1877μs	43.1264 KOps/s	43.5283 KOps/s	$\color{#d91a1a}-0.92\%$
test_getitem[list]	0.3184ms	48.0795μs	20.7989 KOps/s	20.2059 KOps/s	$\color{#35bf28}+2.93\%$
test_setitem_dim[int]	47.2480μs	25.1127μs	39.8205 KOps/s	38.3905 KOps/s	$\color{#35bf28}+3.73\%$
test_setitem_dim[slice_int]	76.2210μs	47.7813μs	20.9287 KOps/s	20.2173 KOps/s	$\color{#35bf28}+3.52\%$
test_setitem_dim[range]	0.1056ms	68.0154μs	14.7025 KOps/s	14.1067 KOps/s	$\color{#35bf28}+4.22\%$
test_setitem_dim[tuple]	69.4990μs	37.3771μs	26.7544 KOps/s	26.2132 KOps/s	$\color{#35bf28}+2.06\%$
test_setitem	1.0520ms	15.0694μs	66.3596 KOps/s	69.7409 KOps/s	$\color{#d91a1a}-4.85\%$
test_set	86.4000μs	14.4315μs	69.2926 KOps/s	73.0360 KOps/s	$\textbf{\color{#d91a1a}-5.13\%}$
test_set_shared	5.0656ms	0.1544ms	6.4779 KOps/s	5.9741 KOps/s	$\textbf{\color{#35bf28}+8.43\%}$
test_update	0.1399ms	18.6104μs	53.7333 KOps/s	52.5453 KOps/s	$\color{#35bf28}+2.26\%$
test_update_nested	0.1647ms	27.0236μs	37.0047 KOps/s	36.8483 KOps/s	$\color{#35bf28}+0.42\%$
test_set_nested	0.1077ms	16.0434μs	62.3311 KOps/s	64.2154 KOps/s	$\color{#d91a1a}-2.93\%$
test_set_nested_new	0.1420ms	21.9203μs	45.6198 KOps/s	45.8390 KOps/s	$\color{#d91a1a}-0.48\%$
test_select	0.1280ms	45.1620μs	22.1425 KOps/s	21.8442 KOps/s	$\color{#35bf28}+1.37\%$
test_unbind_speed	0.5273ms	0.2816ms	3.5514 KOps/s	3.4926 KOps/s	$\color{#35bf28}+1.68\%$
test_unbind_speed_stack0	62.4943ms	4.5175ms	221.3619 Ops/s	223.7759 Ops/s	$\color{#d91a1a}-1.08\%$
test_unbind_speed_stack1	2.2932μs	0.5962μs	1.6774 MOps/s	1.6776 MOps/s	$\color{#d91a1a}-0.01\%$
test_creation[device0]	3.5079ms	0.2943ms	3.3979 KOps/s	3.3036 KOps/s	$\color{#35bf28}+2.85\%$
test_creation_from_tensor	0.8475ms	0.3222ms	3.1033 KOps/s	2.7223 KOps/s	$\textbf{\color{#35bf28}+14.00\%}$
test_add_one[memmap_tensor0]	0.3962ms	24.6955μs	40.4933 KOps/s	39.3871 KOps/s	$\color{#35bf28}+2.81\%$
test_contiguous[memmap_tensor0]	28.8340μs	5.7668μs	173.4072 KOps/s	176.4231 KOps/s	$\color{#d91a1a}-1.71\%$
test_stack[memmap_tensor0]	55.9240μs	18.9889μs	52.6624 KOps/s	52.1609 KOps/s	$\color{#35bf28}+0.96\%$
test_memmaptd_index	0.4851ms	0.1800ms	5.5564 KOps/s	5.6051 KOps/s	$\color{#d91a1a}-0.87\%$
test_memmaptd_index_astensor	0.3330ms	0.2391ms	4.1819 KOps/s	4.1600 KOps/s	$\color{#35bf28}+0.53\%$
test_memmaptd_index_op	0.8003ms	0.4774ms	2.0945 KOps/s	2.1931 KOps/s	$\color{#d91a1a}-4.50\%$
test_reshape_pytree	79.6090μs	23.1028μs	43.2847 KOps/s	43.4108 KOps/s	$\color{#d91a1a}-0.29\%$
test_reshape_td	59.2000μs	20.7973μs	48.0831 KOps/s	48.6535 KOps/s	$\color{#d91a1a}-1.17\%$
test_view_pytree	54.9220μs	22.9543μs	43.5648 KOps/s	43.8214 KOps/s	$\color{#d91a1a}-0.59\%$
test_view_td	22.8830μs	4.3089μs	232.0794 KOps/s	216.7219 KOps/s	$\textbf{\color{#35bf28}+7.09\%}$
test_unbind_pytree	69.6400μs	26.6041μs	37.5882 KOps/s	37.7564 KOps/s	$\color{#d91a1a}-0.45\%$
test_unbind_td	87.6630μs	39.2382μs	25.4854 KOps/s	25.3050 KOps/s	$\color{#35bf28}+0.71\%$
test_split_pytree	66.6140μs	26.2201μs	38.1387 KOps/s	38.2370 KOps/s	$\color{#d91a1a}-0.26\%$
test_split_td	0.1428ms	73.0961μs	13.6806 KOps/s	13.4566 KOps/s	$\color{#35bf28}+1.66\%$
test_add_pytree	80.7100μs	31.7164μs	31.5295 KOps/s	31.6321 KOps/s	$\color{#d91a1a}-0.32\%$
test_add_td	99.4650μs	41.3300μs	24.1955 KOps/s	24.1757 KOps/s	$\color{#35bf28}+0.08\%$
test_distributed	21.9200μs	5.9508μs	168.0443 KOps/s	166.9208 KOps/s	$\color{#35bf28}+0.67\%$
test_tdmodule	0.1628ms	20.8839μs	47.8837 KOps/s	48.5833 KOps/s	$\color{#d91a1a}-1.44\%$
test_tdmodule_dispatch	0.1813ms	36.9549μs	27.0600 KOps/s	26.6713 KOps/s	$\color{#35bf28}+1.46\%$
test_tdseq	0.1113ms	23.0279μs	43.4256 KOps/s	40.9307 KOps/s	$\textbf{\color{#35bf28}+6.10\%}$
test_tdseq_dispatch	0.6305ms	40.5512μs	24.6602 KOps/s	23.6944 KOps/s	$\color{#35bf28}+4.08\%$
test_instantiation_functorch	1.5420ms	1.2864ms	777.3700 Ops/s	768.6810 Ops/s	$\color{#35bf28}+1.13\%$
test_instantiation_td	67.4629ms	1.1228ms	890.6354 Ops/s	959.9089 Ops/s	$\textbf{\color{#d91a1a}-7.22\%}$
test_exec_functorch	0.3334ms	0.1481ms	6.7505 KOps/s	6.7293 KOps/s	$\color{#35bf28}+0.31\%$
test_exec_td	0.2190ms	0.1433ms	6.9762 KOps/s	7.0883 KOps/s	$\color{#d91a1a}-1.58\%$
test_vmap_mlp_speed[True-True]	1.2204ms	0.8464ms	1.1815 KOps/s	1.1799 KOps/s	$\color{#35bf28}+0.13\%$
test_vmap_mlp_speed[True-False]	0.7270ms	0.4611ms	2.1690 KOps/s	2.1645 KOps/s	$\color{#35bf28}+0.21\%$
test_vmap_mlp_speed[False-True]	1.1242ms	0.7423ms	1.3472 KOps/s	1.3309 KOps/s	$\color{#35bf28}+1.22\%$
test_vmap_mlp_speed[False-False]	0.6245ms	0.3822ms	2.6162 KOps/s	2.6293 KOps/s	$\color{#d91a1a}-0.50\%$

[github-actions]

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

Total Benchmarks: 115. Improved: $\large\color{#35bf28}11$. Worsened: $\large\color{#d91a1a}1$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	65.3910μs	12.2956μs	81.3296 KOps/s	81.0736 KOps/s	$\color{#35bf28}+0.32\%$
test_plain_set_stack_nested	0.1376ms	0.1161ms	8.6119 KOps/s	8.5890 KOps/s	$\color{#35bf28}+0.27\%$
test_plain_set_nested_inplace	27.8000μs	14.6831μs	68.1056 KOps/s	68.0125 KOps/s	$\color{#35bf28}+0.14\%$
test_plain_set_stack_nested_inplace	0.1699ms	0.1415ms	7.0651 KOps/s	7.0869 KOps/s	$\color{#d91a1a}-0.31\%$
test_items	28.2610μs	4.7885μs	208.8335 KOps/s	211.0785 KOps/s	$\color{#d91a1a}-1.06\%$
test_items_nested	0.3735ms	0.3399ms	2.9423 KOps/s	2.9616 KOps/s	$\color{#d91a1a}-0.65\%$
test_items_nested_locked	0.3589ms	0.3379ms	2.9596 KOps/s	2.9621 KOps/s	$\color{#d91a1a}-0.08\%$
test_items_nested_leaf	0.2194ms	0.1993ms	5.0171 KOps/s	5.0480 KOps/s	$\color{#d91a1a}-0.61\%$
test_items_stack_nested	1.4684ms	1.4122ms	708.1243 Ops/s	700.1690 Ops/s	$\color{#35bf28}+1.14\%$
test_items_stack_nested_leaf	1.3102ms	1.2366ms	808.6906 Ops/s	792.9701 Ops/s	$\color{#35bf28}+1.98\%$
test_items_stack_nested_locked	0.8333ms	0.7992ms	1.2512 KOps/s	1.2402 KOps/s	$\color{#35bf28}+0.89\%$
test_keys	24.9200μs	4.5677μs	218.9306 KOps/s	217.0303 KOps/s	$\color{#35bf28}+0.88\%$
test_keys_nested	0.4946ms	90.9191μs	10.9988 KOps/s	10.4951 KOps/s	$\color{#35bf28}+4.80\%$
test_keys_nested_locked	0.1151ms	90.2505μs	11.0803 KOps/s	11.0369 KOps/s	$\color{#35bf28}+0.39\%$
test_keys_nested_leaf	0.1679ms	82.8525μs	12.0696 KOps/s	12.1883 KOps/s	$\color{#d91a1a}-0.97\%$
test_keys_stack_nested	1.2992ms	1.2258ms	815.8077 Ops/s	814.5359 Ops/s	$\color{#35bf28}+0.16\%$
test_keys_stack_nested_leaf	1.3688ms	1.2322ms	811.5307 Ops/s	817.8607 Ops/s	$\color{#d91a1a}-0.77\%$
test_keys_stack_nested_locked	0.6437ms	0.5915ms	1.6907 KOps/s	1.7126 KOps/s	$\color{#d91a1a}-1.28\%$
test_values	9.7000μs	1.8977μs	526.9544 KOps/s	527.3737 KOps/s	$\color{#d91a1a}-0.08\%$
test_values_nested	65.7810μs	43.4507μs	23.0146 KOps/s	23.0490 KOps/s	$\color{#d91a1a}-0.15\%$
test_values_nested_locked	65.9310μs	43.5115μs	22.9824 KOps/s	22.8805 KOps/s	$\color{#35bf28}+0.45\%$
test_values_nested_leaf	55.3210μs	38.2988μs	26.1105 KOps/s	26.3704 KOps/s	$\color{#d91a1a}-0.99\%$
test_values_stack_nested	1.1617ms	1.0953ms	913.0307 Ops/s	924.6192 Ops/s	$\color{#d91a1a}-1.25\%$
test_values_stack_nested_leaf	1.1629ms	1.0738ms	931.2849 Ops/s	933.0879 Ops/s	$\color{#d91a1a}-0.19\%$
test_values_stack_nested_locked	0.5872ms	0.4823ms	2.0736 KOps/s	2.0650 KOps/s	$\color{#35bf28}+0.41\%$
test_membership	4.9333μs	0.9213μs	1.0854 MOps/s	1.0738 MOps/s	$\color{#35bf28}+1.08\%$
test_membership_nested	18.0310μs	2.2335μs	447.7348 KOps/s	456.3075 KOps/s	$\color{#d91a1a}-1.88\%$
test_membership_nested_leaf	29.2610μs	2.2091μs	452.6636 KOps/s	453.5883 KOps/s	$\color{#d91a1a}-0.20\%$
test_membership_stacked_nested	61.8210μs	10.9596μs	91.2442 KOps/s	92.7748 KOps/s	$\color{#d91a1a}-1.65\%$
test_membership_stacked_nested_leaf	42.6910μs	10.8349μs	92.2946 KOps/s	92.8859 KOps/s	$\color{#d91a1a}-0.64\%$
test_membership_nested_last	19.3910μs	4.6023μs	217.2818 KOps/s	218.6473 KOps/s	$\color{#d91a1a}-0.62\%$
test_membership_nested_leaf_last	21.0910μs	4.6036μs	217.2192 KOps/s	217.6629 KOps/s	$\color{#d91a1a}-0.20\%$
test_membership_stacked_nested_last	0.1795ms	0.1440ms	6.9466 KOps/s	6.9587 KOps/s	$\color{#d91a1a}-0.17\%$
test_membership_stacked_nested_leaf_last	39.2110μs	12.5893μs	79.4326 KOps/s	79.7379 KOps/s	$\color{#d91a1a}-0.38\%$
test_nested_getleaf	38.6310μs	9.3750μs	106.6670 KOps/s	107.0910 KOps/s	$\color{#d91a1a}-0.40\%$
test_nested_get	41.6710μs	8.8516μs	112.9734 KOps/s	112.9773 KOps/s	$-0.00\%$
test_stacked_getleaf	0.5659ms	0.5260ms	1.9012 KOps/s	1.9216 KOps/s	$\color{#d91a1a}-1.07\%$
test_stacked_get	0.5378ms	0.4952ms	2.0193 KOps/s	2.0665 KOps/s	$\color{#d91a1a}-2.28\%$
test_nested_getitemleaf	22.6300μs	9.4015μs	106.3666 KOps/s	106.4980 KOps/s	$\color{#d91a1a}-0.12\%$
test_nested_getitem	32.0510μs	8.8648μs	112.8054 KOps/s	112.4017 KOps/s	$\color{#35bf28}+0.36\%$
test_stacked_getitemleaf	0.5544ms	0.5151ms	1.9412 KOps/s	1.8974 KOps/s	$\color{#35bf28}+2.31\%$
test_stacked_getitem	0.5272ms	0.4958ms	2.0171 KOps/s	2.0201 KOps/s	$\color{#d91a1a}-0.15\%$
test_lock_nested	46.6560ms	0.9357ms	1.0688 KOps/s	1.1201 KOps/s	$\color{#d91a1a}-4.59\%$
test_lock_stack_nested	57.0932ms	12.0273ms	83.1440 Ops/s	81.3153 Ops/s	$\color{#35bf28}+2.25\%$
test_unlock_nested	45.2928ms	0.9613ms	1.0402 KOps/s	1.0239 KOps/s	$\color{#35bf28}+1.59\%$
test_unlock_stack_nested	57.2930ms	12.8563ms	77.7829 Ops/s	76.1280 Ops/s	$\color{#35bf28}+2.17\%$
test_flatten_speed	0.6070ms	0.5536ms	1.8063 KOps/s	1.8202 KOps/s	$\color{#d91a1a}-0.76\%$
test_unflatten_speed	1.0222ms	0.9977ms	1.0023 KOps/s	1.0055 KOps/s	$\color{#d91a1a}-0.32\%$
test_common_ops	0.6466ms	0.5600ms	1.7858 KOps/s	1.7222 KOps/s	$\color{#35bf28}+3.69\%$
test_creation	24.1500μs	1.8089μs	552.8155 KOps/s	572.1075 KOps/s	$\color{#d91a1a}-3.37\%$
test_creation_empty	22.0700μs	5.9289μs	168.6667 KOps/s	168.6617 KOps/s	$+0.00\%$
test_creation_nested_1	27.1020μs	8.8680μs	112.7653 KOps/s	111.8013 KOps/s	$\color{#35bf28}+0.86\%$
test_creation_nested_2	68.4700μs	10.9132μs	91.6321 KOps/s	92.3921 KOps/s	$\color{#d91a1a}-0.82\%$
test_clone	50.4100μs	11.7188μs	85.3330 KOps/s	85.0797 KOps/s	$\color{#35bf28}+0.30\%$
test_getitem[int]	26.6910μs	12.2679μs	81.5137 KOps/s	77.1713 KOps/s	$\textbf{\color{#35bf28}+5.63\%}$
test_getitem[slice_int]	54.3810μs	28.0748μs	35.6191 KOps/s	33.0011 KOps/s	$\textbf{\color{#35bf28}+7.93\%}$
test_getitem[range]	75.4710μs	48.3130μs	20.6984 KOps/s	20.4823 KOps/s	$\color{#35bf28}+1.05\%$
test_getitem[tuple]	42.2500μs	23.9588μs	41.7383 KOps/s	39.8513 KOps/s	$\color{#35bf28}+4.73\%$
test_getitem[list]	0.1778ms	45.4290μs	22.0124 KOps/s	22.2337 KOps/s	$\color{#d91a1a}-1.00\%$
test_setitem_dim[int]	42.3500μs	25.6597μs	38.9715 KOps/s	37.1339 KOps/s	$\color{#35bf28}+4.95\%$
test_setitem_dim[slice_int]	64.2010μs	44.6639μs	22.3894 KOps/s	21.3017 KOps/s	$\textbf{\color{#35bf28}+5.11\%}$
test_setitem_dim[range]	87.2910μs	62.1334μs	16.0944 KOps/s	15.8757 KOps/s	$\color{#35bf28}+1.38\%$
test_setitem_dim[tuple]	57.9410μs	38.9489μs	25.6747 KOps/s	24.5227 KOps/s	$\color{#35bf28}+4.70\%$
test_setitem	60.2110μs	14.8633μs	67.2798 KOps/s	64.8663 KOps/s	$\color{#35bf28}+3.72\%$
test_set	67.5910μs	14.3718μs	69.5808 KOps/s	67.7465 KOps/s	$\color{#35bf28}+2.71\%$
test_set_shared	0.1909ms	0.1120ms	8.9252 KOps/s	8.6845 KOps/s	$\color{#35bf28}+2.77\%$
test_update	84.2910μs	17.7554μs	56.3210 KOps/s	54.9274 KOps/s	$\color{#35bf28}+2.54\%$
test_update_nested	0.1501ms	24.6553μs	40.5593 KOps/s	39.2830 KOps/s	$\color{#35bf28}+3.25\%$
test_set_nested	62.6410μs	15.6680μs	63.8245 KOps/s	62.4115 KOps/s	$\color{#35bf28}+2.26\%$
test_set_nested_new	66.5410μs	20.8510μs	47.9594 KOps/s	46.8204 KOps/s	$\color{#35bf28}+2.43\%$
test_select	88.8910μs	43.0613μs	23.2227 KOps/s	22.8147 KOps/s	$\color{#35bf28}+1.79\%$
test_to	72.6110μs	52.7094μs	18.9720 KOps/s	18.5170 KOps/s	$\color{#35bf28}+2.46\%$
test_to_nonblocking	60.2910μs	34.4522μs	29.0257 KOps/s	27.2637 KOps/s	$\textbf{\color{#35bf28}+6.46\%}$
test_unbind_speed	0.3885ms	0.2825ms	3.5401 KOps/s	3.4687 KOps/s	$\color{#35bf28}+2.06\%$
test_unbind_speed_stack0	51.4765ms	3.7183ms	268.9392 Ops/s	249.0503 Ops/s	$\textbf{\color{#35bf28}+7.99\%}$
test_unbind_speed_stack1	1.9041μs	0.4921μs	2.0323 MOps/s	2.0138 MOps/s	$\color{#35bf28}+0.92\%$
test_creation[device0]	0.7415ms	0.3087ms	3.2399 KOps/s	3.2100 KOps/s	$\color{#35bf28}+0.93\%$
test_creation[device1]	0.6830ms	0.3119ms	3.2058 KOps/s	3.1313 KOps/s	$\color{#35bf28}+2.38\%$
test_creation_from_tensor	0.6832ms	0.3381ms	2.9578 KOps/s	2.8705 KOps/s	$\color{#35bf28}+3.04\%$
test_add_one[memmap_tensor0]	54.2317ms	32.0830μs	31.1692 KOps/s	38.0639 KOps/s	$\textbf{\color{#d91a1a}-18.11\%}$
test_add_one[memmap_tensor1]	0.1906ms	75.1431μs	13.3079 KOps/s	13.3301 KOps/s	$\color{#d91a1a}-0.17\%$
test_contiguous[memmap_tensor0]	27.0810μs	5.8308μs	171.5016 KOps/s	162.2747 KOps/s	$\textbf{\color{#35bf28}+5.69\%}$
test_contiguous[memmap_tensor1]	0.2248ms	22.2438μs	44.9563 KOps/s	43.9505 KOps/s	$\color{#35bf28}+2.29\%$
test_stack[memmap_tensor0]	45.2410μs	19.5860μs	51.0568 KOps/s	47.3788 KOps/s	$\textbf{\color{#35bf28}+7.76\%}$
test_stack[memmap_tensor1]	0.1588ms	74.3386μs	13.4520 KOps/s	13.1863 KOps/s	$\color{#35bf28}+2.01\%$
test_memmaptd_index	0.2489ms	0.2168ms	4.6118 KOps/s	4.2930 KOps/s	$\textbf{\color{#35bf28}+7.43\%}$
test_memmaptd_index_astensor	0.3410ms	0.2763ms	3.6189 KOps/s	3.5038 KOps/s	$\color{#35bf28}+3.29\%$
test_memmaptd_index_op	0.5834ms	0.5246ms	1.9063 KOps/s	1.7921 KOps/s	$\textbf{\color{#35bf28}+6.37\%}$
test_reshape_pytree	50.1910μs	21.2161μs	47.1341 KOps/s	46.8572 KOps/s	$\color{#35bf28}+0.59\%$
test_reshape_td	39.7300μs	21.3154μs	46.9145 KOps/s	45.8380 KOps/s	$\color{#35bf28}+2.35\%$
test_view_pytree	54.1910μs	20.9896μs	47.6427 KOps/s	46.9401 KOps/s	$\color{#35bf28}+1.50\%$
test_view_td	19.0020μs	3.3768μs	296.1397 KOps/s	300.1787 KOps/s	$\color{#d91a1a}-1.35\%$
test_unbind_pytree	50.1610μs	26.1431μs	38.2510 KOps/s	36.9766 KOps/s	$\color{#35bf28}+3.45\%$
test_unbind_td	62.1600μs	40.4411μs	24.7273 KOps/s	23.5124 KOps/s	$\textbf{\color{#35bf28}+5.17\%}$
test_split_pytree	47.0310μs	23.8776μs	41.8803 KOps/s	40.4728 KOps/s	$\color{#35bf28}+3.48\%$
test_split_td	0.1401ms	72.0755μs	13.8743 KOps/s	13.4419 KOps/s	$\color{#35bf28}+3.22\%$
test_add_pytree	60.1100μs	32.9007μs	30.3945 KOps/s	29.5501 KOps/s	$\color{#35bf28}+2.86\%$
test_add_td	68.1310μs	43.4180μs	23.0319 KOps/s	21.7735 KOps/s	$\textbf{\color{#35bf28}+5.78\%}$
test_distributed	21.4200μs	5.5713μs	179.4907 KOps/s	178.4085 KOps/s	$\color{#35bf28}+0.61\%$
test_tdmodule	39.9900μs	17.1303μs	58.3762 KOps/s	59.8777 KOps/s	$\color{#d91a1a}-2.51\%$
test_tdmodule_dispatch	0.2231ms	31.8906μs	31.3572 KOps/s	32.0671 KOps/s	$\color{#d91a1a}-2.21\%$
test_tdseq	39.0100μs	19.6405μs	50.9153 KOps/s	49.8640 KOps/s	$\color{#35bf28}+2.11\%$
test_tdseq_dispatch	50.3500μs	34.4426μs	29.0338 KOps/s	28.7503 KOps/s	$\color{#35bf28}+0.99\%$
test_instantiation_functorch	1.7501ms	1.6738ms	597.4489 Ops/s	582.9304 Ops/s	$\color{#35bf28}+2.49\%$
test_instantiation_td	1.7298ms	1.2056ms	829.4932 Ops/s	819.8146 Ops/s	$\color{#35bf28}+1.18\%$
test_exec_functorch	0.2204ms	0.1582ms	6.3193 KOps/s	6.1579 KOps/s	$\color{#35bf28}+2.62\%$
test_exec_td	0.1876ms	0.1489ms	6.7148 KOps/s	6.4647 KOps/s	$\color{#35bf28}+3.87\%$
test_vmap_mlp_speed[True-True]	1.1489ms	1.0607ms	942.7349 Ops/s	942.4423 Ops/s	$\color{#35bf28}+0.03\%$
test_vmap_mlp_speed[True-False]	0.6715ms	0.6232ms	1.6046 KOps/s	1.5932 KOps/s	$\color{#35bf28}+0.72\%$
test_vmap_mlp_speed[False-True]	1.0760ms	1.0100ms	990.0884 Ops/s	1.0235 KOps/s	$\color{#d91a1a}-3.27\%$
test_vmap_mlp_speed[False-False]	0.6463ms	0.5824ms	1.7170 KOps/s	1.7761 KOps/s	$\color{#d91a1a}-3.33\%$
test_vmap_transformer_speed[True-True]	13.1967ms	12.6463ms	79.0747 Ops/s	79.1753 Ops/s	$\color{#d91a1a}-0.13\%$
test_vmap_transformer_speed[True-False]	8.5091ms	8.3919ms	119.1619 Ops/s	118.1824 Ops/s	$\color{#35bf28}+0.83\%$
test_vmap_transformer_speed[False-True]	13.6355ms	12.5679ms	79.5681 Ops/s	79.6068 Ops/s	$\color{#d91a1a}-0.05\%$
test_vmap_transformer_speed[False-False]	8.4797ms	8.3251ms	120.1191 Ops/s	119.3198 Ops/s	$\color{#35bf28}+0.67\%$