[BugFix] Fix buffer index with FCD

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 126. Improved: $\large\color{#35bf28}32$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	38.5820μs	16.9390μs	59.0355 KOps/s	56.7014 KOps/s	$\color{#35bf28}+4.12\%$
test_plain_set_stack_nested	62.0160μs	16.8238μs	59.4398 KOps/s	55.7812 KOps/s	$\textbf{\color{#35bf28}+6.56\%}$
test_plain_set_nested_inplace	53.4090μs	19.2936μs	51.8306 KOps/s	48.7430 KOps/s	$\textbf{\color{#35bf28}+6.33\%}$
test_plain_set_stack_nested_inplace	45.8860μs	19.1518μs	52.2144 KOps/s	49.1715 KOps/s	$\textbf{\color{#35bf28}+6.19\%}$
test_items	43.7610μs	2.3919μs	418.0775 KOps/s	408.6106 KOps/s	$\color{#35bf28}+2.32\%$
test_items_nested	0.8285ms	0.2653ms	3.7694 KOps/s	3.6932 KOps/s	$\color{#35bf28}+2.06\%$
test_items_nested_locked	0.3440ms	0.2681ms	3.7296 KOps/s	3.6849 KOps/s	$\color{#35bf28}+1.21\%$
test_items_nested_leaf	0.4873ms	0.1674ms	5.9727 KOps/s	5.9085 KOps/s	$\color{#35bf28}+1.09\%$
test_items_stack_nested	3.7413ms	0.2690ms	3.7174 KOps/s	3.6359 KOps/s	$\color{#35bf28}+2.24\%$
test_items_stack_nested_leaf	0.3218ms	0.1660ms	6.0240 KOps/s	5.9232 KOps/s	$\color{#35bf28}+1.70\%$
test_items_stack_nested_locked	0.3188ms	0.2676ms	3.7364 KOps/s	3.5969 KOps/s	$\color{#35bf28}+3.88\%$
test_keys	41.3770μs	3.9522μs	253.0236 KOps/s	258.7463 KOps/s	$\color{#d91a1a}-2.21\%$
test_keys_nested	2.1211ms	0.1493ms	6.6973 KOps/s	6.3285 KOps/s	$\textbf{\color{#35bf28}+5.83\%}$
test_keys_nested_locked	0.2863ms	0.1550ms	6.4511 KOps/s	6.1961 KOps/s	$\color{#35bf28}+4.12\%$
test_keys_nested_leaf	38.4394ms	0.1358ms	7.3659 KOps/s	7.4292 KOps/s	$\color{#d91a1a}-0.85\%$
test_keys_stack_nested	0.2493ms	0.1502ms	6.6590 KOps/s	6.2858 KOps/s	$\textbf{\color{#35bf28}+5.94\%}$
test_keys_stack_nested_leaf	0.2410ms	0.1306ms	7.6595 KOps/s	7.3240 KOps/s	$\color{#35bf28}+4.58\%$
test_keys_stack_nested_locked	0.2734ms	0.1551ms	6.4490 KOps/s	6.0887 KOps/s	$\textbf{\color{#35bf28}+5.92\%}$
test_values	10.6100μs	1.1724μs	852.9867 KOps/s	861.0411 KOps/s	$\color{#d91a1a}-0.94\%$
test_values_nested	0.1002ms	52.1801μs	19.1644 KOps/s	19.0574 KOps/s	$\color{#35bf28}+0.56\%$
test_values_nested_locked	0.1014ms	52.6940μs	18.9775 KOps/s	19.3843 KOps/s	$\color{#d91a1a}-2.10\%$
test_values_nested_leaf	89.9970μs	46.5908μs	21.4635 KOps/s	21.0204 KOps/s	$\color{#35bf28}+2.11\%$
test_values_stack_nested	96.8810μs	52.3898μs	19.0877 KOps/s	18.7187 KOps/s	$\color{#35bf28}+1.97\%$
test_values_stack_nested_leaf	89.9280μs	46.3479μs	21.5760 KOps/s	21.2044 KOps/s	$\color{#35bf28}+1.75\%$
test_values_stack_nested_locked	0.1008ms	53.0596μs	18.8467 KOps/s	19.1789 KOps/s	$\color{#d91a1a}-1.73\%$
test_membership	22.8430μs	1.3387μs	747.0207 KOps/s	729.5480 KOps/s	$\color{#35bf28}+2.40\%$
test_membership_nested	40.0840μs	3.4413μs	290.5859 KOps/s	291.7394 KOps/s	$\color{#d91a1a}-0.40\%$
test_membership_nested_leaf	25.1570μs	3.4304μs	291.5084 KOps/s	285.5407 KOps/s	$\color{#35bf28}+2.09\%$
test_membership_stacked_nested	38.7720μs	3.4105μs	293.2152 KOps/s	289.2432 KOps/s	$\color{#35bf28}+1.37\%$
test_membership_stacked_nested_leaf	23.1830μs	3.4710μs	288.0976 KOps/s	273.1714 KOps/s	$\textbf{\color{#35bf28}+5.46\%}$
test_membership_nested_last	51.2150μs	6.6205μs	151.0449 KOps/s	150.3525 KOps/s	$\color{#35bf28}+0.46\%$
test_membership_nested_leaf_last	32.2600μs	6.6339μs	150.7416 KOps/s	150.5895 KOps/s	$\color{#35bf28}+0.10\%$
test_membership_stacked_nested_last	43.7120μs	6.5524μs	152.6152 KOps/s	140.2519 KOps/s	$\textbf{\color{#35bf28}+8.82\%}$
test_membership_stacked_nested_leaf_last	25.9490μs	6.5855μs	151.8491 KOps/s	138.9692 KOps/s	$\textbf{\color{#35bf28}+9.27\%}$
test_nested_getleaf	51.9370μs	10.3857μs	96.2859 KOps/s	86.4352 KOps/s	$\textbf{\color{#35bf28}+11.40\%}$
test_nested_get	49.1210μs	9.8393μs	101.6328 KOps/s	91.9636 KOps/s	$\textbf{\color{#35bf28}+10.51\%}$
test_stacked_getleaf	36.6980μs	10.3005μs	97.0831 KOps/s	87.8506 KOps/s	$\textbf{\color{#35bf28}+10.51\%}$
test_stacked_get	54.9330μs	9.8505μs	101.5173 KOps/s	92.9152 KOps/s	$\textbf{\color{#35bf28}+9.26\%}$
test_nested_getitemleaf	57.4270μs	11.9793μs	83.4771 KOps/s	76.6646 KOps/s	$\textbf{\color{#35bf28}+8.89\%}$
test_nested_getitem	31.8400μs	11.3594μs	88.0324 KOps/s	79.5887 KOps/s	$\textbf{\color{#35bf28}+10.61\%}$
test_stacked_getitemleaf	56.9160μs	11.8376μs	84.4767 KOps/s	77.6431 KOps/s	$\textbf{\color{#35bf28}+8.80\%}$
test_stacked_getitem	48.6110μs	11.4198μs	87.5676 KOps/s	81.5645 KOps/s	$\textbf{\color{#35bf28}+7.36\%}$
test_lock_nested	0.7174ms	0.3323ms	3.0093 KOps/s	2.9207 KOps/s	$\color{#35bf28}+3.03\%$
test_lock_stack_nested	0.4460ms	0.2973ms	3.3633 KOps/s	3.2817 KOps/s	$\color{#35bf28}+2.49\%$
test_unlock_nested	93.7485ms	0.4301ms	2.3251 KOps/s	2.3435 KOps/s	$\color{#d91a1a}-0.78\%$
test_unlock_stack_nested	0.4710ms	0.3065ms	3.2625 KOps/s	3.2001 KOps/s	$\color{#35bf28}+1.95\%$
test_flatten_speed	0.6861ms	0.3648ms	2.7411 KOps/s	2.6766 KOps/s	$\color{#35bf28}+2.41\%$
test_unflatten_speed	1.2365ms	0.4494ms	2.2253 KOps/s	2.1345 KOps/s	$\color{#35bf28}+4.26\%$
test_common_ops	4.8766ms	0.6862ms	1.4572 KOps/s	1.3842 KOps/s	$\textbf{\color{#35bf28}+5.28\%}$
test_creation	19.1160μs	1.8305μs	546.2850 KOps/s	541.8700 KOps/s	$\color{#35bf28}+0.81\%$
test_creation_empty	47.7390μs	9.9182μs	100.8249 KOps/s	93.8052 KOps/s	$\textbf{\color{#35bf28}+7.48\%}$
test_creation_nested_1	57.1160μs	12.5586μs	79.6268 KOps/s	74.1373 KOps/s	$\textbf{\color{#35bf28}+7.40\%}$
test_creation_nested_2	36.7690μs	15.6117μs	64.0545 KOps/s	59.5939 KOps/s	$\textbf{\color{#35bf28}+7.49\%}$
test_clone	56.9160μs	13.3155μs	75.1005 KOps/s	72.3593 KOps/s	$\color{#35bf28}+3.79\%$
test_getitem[int]	30.6270μs	11.1799μs	89.4460 KOps/s	89.1572 KOps/s	$\color{#35bf28}+0.32\%$
test_getitem[slice_int]	83.0460μs	22.6603μs	44.1301 KOps/s	44.0286 KOps/s	$\color{#35bf28}+0.23\%$
test_getitem[range]	0.1419ms	41.2908μs	24.2185 KOps/s	23.3773 KOps/s	$\color{#35bf28}+3.60\%$
test_getitem[tuple]	0.1213ms	18.2875μs	54.6821 KOps/s	54.1100 KOps/s	$\color{#35bf28}+1.06\%$
test_getitem[list]	0.1034ms	36.2460μs	27.5893 KOps/s	26.3893 KOps/s	$\color{#35bf28}+4.55\%$
test_setitem_dim[int]	75.3910μs	29.0719μs	34.3975 KOps/s	29.5527 KOps/s	$\textbf{\color{#35bf28}+16.39\%}$
test_setitem_dim[slice_int]	88.9560μs	54.5614μs	18.3280 KOps/s	17.0162 KOps/s	$\textbf{\color{#35bf28}+7.71\%}$
test_setitem_dim[range]	0.1289ms	74.5283μs	13.4177 KOps/s	12.8426 KOps/s	$\color{#35bf28}+4.48\%$
test_setitem_dim[tuple]	83.9270μs	44.4402μs	22.5021 KOps/s	21.0493 KOps/s	$\textbf{\color{#35bf28}+6.90\%}$
test_setitem	0.1120ms	19.6384μs	50.9206 KOps/s	49.2293 KOps/s	$\color{#35bf28}+3.44\%$
test_set	77.9860μs	18.9222μs	52.8480 KOps/s	50.3788 KOps/s	$\color{#35bf28}+4.90\%$
test_set_shared	1.9048ms	0.1416ms	7.0604 KOps/s	7.0690 KOps/s	$\color{#d91a1a}-0.12\%$
test_update	0.1288ms	21.5576μs	46.3874 KOps/s	42.8087 KOps/s	$\textbf{\color{#35bf28}+8.36\%}$
test_update_nested	99.3150μs	28.7489μs	34.7840 KOps/s	32.5313 KOps/s	$\textbf{\color{#35bf28}+6.92\%}$
test_set_nested	0.1251ms	20.5945μs	48.5566 KOps/s	45.8319 KOps/s	$\textbf{\color{#35bf28}+5.95\%}$
test_set_nested_new	81.6230μs	24.4984μs	40.8190 KOps/s	38.1270 KOps/s	$\textbf{\color{#35bf28}+7.06\%}$
test_select	0.1106ms	37.4101μs	26.7307 KOps/s	25.0654 KOps/s	$\textbf{\color{#35bf28}+6.64\%}$
test_select_nested	0.1094ms	57.8043μs	17.2998 KOps/s	16.9614 KOps/s	$\color{#35bf28}+2.00\%$
test_exclude_nested	0.2490ms	0.1181ms	8.4662 KOps/s	8.3922 KOps/s	$\color{#35bf28}+0.88\%$
test_empty[True]	0.5789ms	0.4114ms	2.4306 KOps/s	2.4376 KOps/s	$\color{#d91a1a}-0.29\%$
test_empty[False]	8.8926μs	1.0355μs	965.6818 KOps/s	935.1989 KOps/s	$\color{#35bf28}+3.26\%$
test_unbind_speed	0.4402ms	0.2399ms	4.1679 KOps/s	3.8727 KOps/s	$\textbf{\color{#35bf28}+7.62\%}$
test_unbind_speed_stack0	0.4538ms	0.2398ms	4.1700 KOps/s	4.0854 KOps/s	$\color{#35bf28}+2.07\%$
test_unbind_speed_stack1	1.1910ms	0.5919ms	1.6895 KOps/s	1.4626 KOps/s	$\textbf{\color{#35bf28}+15.51\%}$
test_split	0.1320s	1.6652ms	600.5431 Ops/s	605.9591 Ops/s	$\color{#d91a1a}-0.89\%$
test_chunk	2.2364ms	1.4723ms	679.1877 Ops/s	678.3138 Ops/s	$\color{#35bf28}+0.13\%$
test_creation[device0]	0.1741ms	0.1040ms	9.6181 KOps/s	9.4911 KOps/s	$\color{#35bf28}+1.34\%$
test_creation_from_tensor	4.2664ms	84.0610μs	11.8961 KOps/s	11.9581 KOps/s	$\color{#d91a1a}-0.52\%$
test_add_one[memmap_tensor0]	0.1100ms	5.6615μs	176.6326 KOps/s	186.3369 KOps/s	$\textbf{\color{#d91a1a}-5.21\%}$
test_contiguous[memmap_tensor0]	20.2180μs	0.6326μs	1.5809 MOps/s	1.5460 MOps/s	$\color{#35bf28}+2.25\%$
test_stack[memmap_tensor0]	33.5130μs	3.7718μs	265.1289 KOps/s	278.4280 KOps/s	$\color{#d91a1a}-4.78\%$
test_memmaptd_index	1.1098ms	0.2491ms	4.0144 KOps/s	4.1878 KOps/s	$\color{#d91a1a}-4.14\%$
test_memmaptd_index_astensor	0.5276ms	0.3058ms	3.2703 KOps/s	3.3193 KOps/s	$\color{#d91a1a}-1.48\%$
test_memmaptd_index_op	1.1092ms	0.5990ms	1.6694 KOps/s	1.6662 KOps/s	$\color{#35bf28}+0.19\%$
test_serialize_model	0.2183s	0.1143s	8.7464 Ops/s	8.4547 Ops/s	$\color{#35bf28}+3.45\%$
test_serialize_model_pickle	0.4475s	0.3734s	2.6780 Ops/s	2.6112 Ops/s	$\color{#35bf28}+2.56\%$
test_serialize_weights	0.1076s	97.9361ms	10.2107 Ops/s	9.9464 Ops/s	$\color{#35bf28}+2.66\%$
test_serialize_weights_returnearly	0.2339s	0.1360s	7.3506 Ops/s	8.0434 Ops/s	$\textbf{\color{#d91a1a}-8.61\%}$
test_serialize_weights_pickle	1.0414s	0.6068s	1.6480 Ops/s	2.3852 Ops/s	$\textbf{\color{#d91a1a}-30.91\%}$
test_serialize_weights_filesystem	96.8268ms	92.1685ms	10.8497 Ops/s	9.4387 Ops/s	$\textbf{\color{#35bf28}+14.95\%}$
test_serialize_model_filesystem	97.8732ms	92.0863ms	10.8594 Ops/s	10.6407 Ops/s	$\color{#35bf28}+2.06\%$
test_reshape_pytree	48.2600μs	21.0175μs	47.5794 KOps/s	47.1792 KOps/s	$\color{#35bf28}+0.85\%$
test_reshape_td	79.4480μs	30.9916μs	32.2668 KOps/s	31.8004 KOps/s	$\color{#35bf28}+1.47\%$
test_view_pytree	60.9940μs	21.0176μs	47.5792 KOps/s	47.9969 KOps/s	$\color{#d91a1a}-0.87\%$
test_view_td	0.1289s	60.0912μs	16.6414 KOps/s	16.2458 KOps/s	$\color{#35bf28}+2.43\%$
test_unbind_pytree	52.2780μs	24.3807μs	41.0161 KOps/s	40.6037 KOps/s	$\color{#35bf28}+1.02\%$
test_unbind_td	0.1235ms	36.0927μs	27.7064 KOps/s	27.0882 KOps/s	$\color{#35bf28}+2.28\%$
test_split_pytree	57.5070μs	24.0896μs	41.5117 KOps/s	41.4507 KOps/s	$\color{#35bf28}+0.15\%$
test_split_td	0.1213ms	40.0858μs	24.9465 KOps/s	24.8726 KOps/s	$\color{#35bf28}+0.30\%$
test_add_pytree	73.0360μs	30.3409μs	32.9588 KOps/s	33.0410 KOps/s	$\color{#d91a1a}-0.25\%$
test_add_td	0.1112ms	51.7533μs	19.3224 KOps/s	18.4594 KOps/s	$\color{#35bf28}+4.68\%$
test_distributed	0.2011ms	0.1017ms	9.8287 KOps/s	9.7776 KOps/s	$\color{#35bf28}+0.52\%$
test_tdmodule	0.1741ms	22.4550μs	44.5336 KOps/s	43.4778 KOps/s	$\color{#35bf28}+2.43\%$
test_tdmodule_dispatch	0.1830ms	44.0319μs	22.7108 KOps/s	22.7511 KOps/s	$\color{#d91a1a}-0.18\%$
test_tdseq	0.3868ms	27.4864μs	36.3816 KOps/s	38.2560 KOps/s	$\color{#d91a1a}-4.90\%$
test_tdseq_dispatch	0.1360ms	46.4145μs	21.5450 KOps/s	20.5767 KOps/s	$\color{#35bf28}+4.71\%$
test_instantiation_functorch	2.1921ms	1.2990ms	769.8069 Ops/s	764.1743 Ops/s	$\color{#35bf28}+0.74\%$
test_instantiation_td	1.4659ms	0.9933ms	1.0067 KOps/s	1.0016 KOps/s	$\color{#35bf28}+0.51\%$
test_exec_functorch	0.2938ms	0.1617ms	6.1849 KOps/s	6.2573 KOps/s	$\color{#d91a1a}-1.16\%$
test_exec_functional_call	0.3050ms	0.1511ms	6.6161 KOps/s	6.6287 KOps/s	$\color{#d91a1a}-0.19\%$
test_exec_td	0.2631ms	0.1492ms	6.7044 KOps/s	6.8271 KOps/s	$\color{#d91a1a}-1.80\%$
test_exec_td_decorator	0.7006ms	0.1970ms	5.0765 KOps/s	5.0923 KOps/s	$\color{#d91a1a}-0.31\%$
test_vmap_mlp_speed[True-True]	0.6893ms	0.4763ms	2.0995 KOps/s	2.0870 KOps/s	$\color{#35bf28}+0.60\%$
test_vmap_mlp_speed[True-False]	0.6399ms	0.4740ms	2.1097 KOps/s	2.1049 KOps/s	$\color{#35bf28}+0.23\%$
test_vmap_mlp_speed[False-True]	0.6626ms	0.3888ms	2.5717 KOps/s	2.5713 KOps/s	$\color{#35bf28}+0.01\%$
test_vmap_mlp_speed[False-False]	0.7228ms	0.3898ms	2.5654 KOps/s	2.5670 KOps/s	$\color{#d91a1a}-0.06\%$
test_vmap_mlp_speed_decorator[True-True]	1.1342ms	0.5243ms	1.9074 KOps/s	1.8935 KOps/s	$\color{#35bf28}+0.73\%$
test_vmap_mlp_speed_decorator[True-False]	0.9175ms	0.5257ms	1.9024 KOps/s	1.8969 KOps/s	$\color{#35bf28}+0.29\%$
test_vmap_mlp_speed_decorator[False-True]	0.6705ms	0.4040ms	2.4754 KOps/s	2.4904 KOps/s	$\color{#d91a1a}-0.60\%$
test_vmap_mlp_speed_decorator[False-False]	0.7039ms	0.4034ms	2.4791 KOps/s	2.4879 KOps/s	$\color{#d91a1a}-0.36\%$
test_to_module_speed[True]	2.1880ms	1.3790ms	725.1665 Ops/s	726.2517 Ops/s	$\color{#d91a1a}-0.15\%$
test_to_module_speed[False]	2.1109ms	1.3402ms	746.1451 Ops/s	738.0619 Ops/s	$\color{#35bf28}+1.10\%$

[github-actions]

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

Total Benchmarks: 134. Improved: $\large\color{#35bf28}5$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	0.8770ms	13.4224μs	74.5021 KOps/s	78.1930 KOps/s	$\color{#d91a1a}-4.72\%$
test_plain_set_stack_nested	36.6510μs	13.4359μs	74.4274 KOps/s	77.7855 KOps/s	$\color{#d91a1a}-4.32\%$
test_plain_set_nested_inplace	44.2000μs	14.8122μs	67.5121 KOps/s	70.5694 KOps/s	$\color{#d91a1a}-4.33\%$
test_plain_set_stack_nested_inplace	32.2410μs	14.7580μs	67.7599 KOps/s	70.2817 KOps/s	$\color{#d91a1a}-3.59\%$
test_items	29.3700μs	4.7502μs	210.5197 KOps/s	211.5474 KOps/s	$\color{#d91a1a}-0.49\%$
test_items_nested	0.4245ms	0.3460ms	2.8903 KOps/s	2.9379 KOps/s	$\color{#d91a1a}-1.62\%$
test_items_nested_locked	0.4261ms	0.3496ms	2.8608 KOps/s	2.9258 KOps/s	$\color{#d91a1a}-2.22\%$
test_items_nested_leaf	0.2578ms	0.2070ms	4.8315 KOps/s	4.9824 KOps/s	$\color{#d91a1a}-3.03\%$
test_items_stack_nested	0.5875ms	0.3488ms	2.8669 KOps/s	2.9524 KOps/s	$\color{#d91a1a}-2.90\%$
test_items_stack_nested_leaf	0.2573ms	0.2036ms	4.9115 KOps/s	4.9572 KOps/s	$\color{#d91a1a}-0.92\%$
test_items_stack_nested_locked	0.4380ms	0.3500ms	2.8572 KOps/s	2.9161 KOps/s	$\color{#d91a1a}-2.02\%$
test_keys	19.4600μs	4.6871μs	213.3517 KOps/s	219.2522 KOps/s	$\color{#d91a1a}-2.69\%$
test_keys_nested	48.7730ms	0.1046ms	9.5633 KOps/s	10.5742 KOps/s	$\textbf{\color{#d91a1a}-9.56\%}$
test_keys_nested_locked	0.1526ms	99.5582μs	10.0444 KOps/s	10.2353 KOps/s	$\color{#d91a1a}-1.87\%$
test_keys_nested_leaf	0.1178ms	78.5439μs	12.7317 KOps/s	12.7836 KOps/s	$\color{#d91a1a}-0.41\%$
test_keys_stack_nested	0.2889ms	94.8714μs	10.5406 KOps/s	10.6930 KOps/s	$\color{#d91a1a}-1.42\%$
test_keys_stack_nested_leaf	0.1135ms	78.1040μs	12.8034 KOps/s	12.8228 KOps/s	$\color{#d91a1a}-0.15\%$
test_keys_stack_nested_locked	0.1371ms	0.1002ms	9.9765 KOps/s	10.0744 KOps/s	$\color{#d91a1a}-0.97\%$
test_values	9.8570μs	1.8935μs	528.1194 KOps/s	530.2980 KOps/s	$\color{#d91a1a}-0.41\%$
test_values_nested	73.7310μs	46.0462μs	21.7173 KOps/s	22.1717 KOps/s	$\color{#d91a1a}-2.05\%$
test_values_nested_locked	79.0420μs	48.1759μs	20.7572 KOps/s	21.0618 KOps/s	$\color{#d91a1a}-1.45\%$
test_values_nested_leaf	65.8100μs	40.2523μs	24.8433 KOps/s	25.2473 KOps/s	$\color{#d91a1a}-1.60\%$
test_values_stack_nested	0.1075ms	46.0517μs	21.7147 KOps/s	21.9916 KOps/s	$\color{#d91a1a}-1.26\%$
test_values_stack_nested_leaf	72.4020μs	40.1778μs	24.8893 KOps/s	25.2043 KOps/s	$\color{#d91a1a}-1.25\%$
test_values_stack_nested_locked	82.7810μs	48.3635μs	20.6768 KOps/s	21.0372 KOps/s	$\color{#d91a1a}-1.71\%$
test_membership	59.3188μs	0.9673μs	1.0339 MOps/s	1.0360 MOps/s	$\color{#d91a1a}-0.21\%$
test_membership_nested	16.8610μs	2.8865μs	346.4385 KOps/s	351.2538 KOps/s	$\color{#d91a1a}-1.37\%$
test_membership_nested_leaf	35.6700μs	2.8954μs	345.3720 KOps/s	349.7677 KOps/s	$\color{#d91a1a}-1.26\%$
test_membership_stacked_nested	25.4800μs	2.9400μs	340.1369 KOps/s	347.5046 KOps/s	$\color{#d91a1a}-2.12\%$
test_membership_stacked_nested_leaf	27.5410μs	2.8977μs	345.1043 KOps/s	344.5890 KOps/s	$\color{#35bf28}+0.15\%$
test_membership_nested_last	39.9110μs	5.2493μs	190.5003 KOps/s	191.8349 KOps/s	$\color{#d91a1a}-0.70\%$
test_membership_nested_leaf_last	34.3300μs	5.3640μs	186.4279 KOps/s	190.9364 KOps/s	$\color{#d91a1a}-2.36\%$
test_membership_stacked_nested_last	25.9400μs	5.3283μs	187.6777 KOps/s	191.0843 KOps/s	$\color{#d91a1a}-1.78\%$
test_membership_stacked_nested_leaf_last	20.6710μs	5.2841μs	189.2454 KOps/s	190.3242 KOps/s	$\color{#d91a1a}-0.57\%$
test_nested_getleaf	42.0210μs	8.5826μs	116.5142 KOps/s	119.5986 KOps/s	$\color{#d91a1a}-2.58\%$
test_nested_get	41.7810μs	8.0253μs	124.6063 KOps/s	126.7116 KOps/s	$\color{#d91a1a}-1.66\%$
test_stacked_getleaf	0.2426ms	8.4692μs	118.0751 KOps/s	119.5230 KOps/s	$\color{#d91a1a}-1.21\%$
test_stacked_get	36.3010μs	8.0178μs	124.7231 KOps/s	126.0802 KOps/s	$\color{#d91a1a}-1.08\%$
test_nested_getitemleaf	27.3710μs	9.9211μs	100.7953 KOps/s	102.4575 KOps/s	$\color{#d91a1a}-1.62\%$
test_nested_getitem	37.5910μs	9.4828μs	105.4541 KOps/s	107.7622 KOps/s	$\color{#d91a1a}-2.14\%$
test_stacked_getitemleaf	41.6300μs	9.9340μs	100.6641 KOps/s	102.1984 KOps/s	$\color{#d91a1a}-1.50\%$
test_stacked_getitem	24.0200μs	9.4562μs	105.7506 KOps/s	107.5171 KOps/s	$\color{#d91a1a}-1.64\%$
test_lock_nested	2.2207ms	0.3546ms	2.8198 KOps/s	2.8109 KOps/s	$\color{#35bf28}+0.32\%$
test_lock_stack_nested	0.3962ms	0.3101ms	3.2253 KOps/s	3.2639 KOps/s	$\color{#d91a1a}-1.18\%$
test_unlock_nested	0.7835ms	0.3530ms	2.8325 KOps/s	2.8749 KOps/s	$\color{#d91a1a}-1.47\%$
test_unlock_stack_nested	0.4052ms	0.3204ms	3.1208 KOps/s	3.1662 KOps/s	$\color{#d91a1a}-1.44\%$
test_flatten_speed	0.5072ms	0.2643ms	3.7833 KOps/s	3.9226 KOps/s	$\color{#d91a1a}-3.55\%$
test_unflatten_speed	0.4355ms	0.3640ms	2.7471 KOps/s	2.8317 KOps/s	$\color{#d91a1a}-2.99\%$
test_common_ops	1.0337ms	0.5804ms	1.7230 KOps/s	1.7989 KOps/s	$\color{#d91a1a}-4.22\%$
test_creation	16.8300μs	1.5704μs	636.7906 KOps/s	656.3078 KOps/s	$\color{#d91a1a}-2.97\%$
test_creation_empty	25.4000μs	7.3656μs	135.7659 KOps/s	154.4985 KOps/s	$\textbf{\color{#d91a1a}-12.12\%}$
test_creation_nested_1	41.2710μs	9.1935μs	108.7728 KOps/s	120.8075 KOps/s	$\textbf{\color{#d91a1a}-9.96\%}$
test_creation_nested_2	37.2110μs	11.7078μs	85.4129 KOps/s	93.5162 KOps/s	$\textbf{\color{#d91a1a}-8.67\%}$
test_clone	63.0200μs	13.3769μs	74.7558 KOps/s	74.8502 KOps/s	$\color{#d91a1a}-0.13\%$
test_getitem[int]	26.4700μs	10.9667μs	91.1848 KOps/s	93.5720 KOps/s	$\color{#d91a1a}-2.55\%$
test_getitem[slice_int]	52.1420μs	21.2035μs	47.1619 KOps/s	47.9507 KOps/s	$\color{#d91a1a}-1.64\%$
test_getitem[range]	69.4310μs	50.8170μs	19.6785 KOps/s	19.4656 KOps/s	$\color{#35bf28}+1.09\%$
test_getitem[tuple]	42.6700μs	19.0513μs	52.4898 KOps/s	53.5732 KOps/s	$\color{#d91a1a}-2.02\%$
test_getitem[list]	0.3418ms	37.6328μs	26.5726 KOps/s	27.5434 KOps/s	$\color{#d91a1a}-3.52\%$
test_setitem_dim[int]	44.5410μs	24.6166μs	40.6230 KOps/s	40.6435 KOps/s	$\color{#d91a1a}-0.05\%$
test_setitem_dim[slice_int]	64.8900μs	45.6861μs	21.8885 KOps/s	22.3169 KOps/s	$\color{#d91a1a}-1.92\%$
test_setitem_dim[range]	98.8010μs	66.2030μs	15.1051 KOps/s	15.6350 KOps/s	$\color{#d91a1a}-3.39\%$
test_setitem_dim[tuple]	66.8500μs	39.4714μs	25.3348 KOps/s	25.7817 KOps/s	$\color{#d91a1a}-1.73\%$
test_setitem	54.2620μs	17.6453μs	56.6724 KOps/s	57.3688 KOps/s	$\color{#d91a1a}-1.21\%$
test_set	52.7920μs	17.2991μs	57.8065 KOps/s	59.5022 KOps/s	$\color{#d91a1a}-2.85\%$
test_set_shared	0.1418s	0.1330ms	7.5193 KOps/s	9.8297 KOps/s	$\textbf{\color{#d91a1a}-23.50\%}$
test_update	72.2010μs	19.0033μs	52.6224 KOps/s	55.3112 KOps/s	$\color{#d91a1a}-4.86\%$
test_update_nested	86.4310μs	26.0348μs	38.4101 KOps/s	40.8205 KOps/s	$\textbf{\color{#d91a1a}-5.90\%}$
test_set_nested	65.6320μs	18.5147μs	54.0113 KOps/s	55.4836 KOps/s	$\color{#d91a1a}-2.65\%$
test_set_nested_new	65.9720μs	21.3285μs	46.8857 KOps/s	46.3385 KOps/s	$\color{#35bf28}+1.18\%$
test_select	87.1420μs	34.1070μs	29.3195 KOps/s	29.2893 KOps/s	$\color{#35bf28}+0.10\%$
test_select_nested	89.3410μs	53.9127μs	18.5485 KOps/s	19.0946 KOps/s	$\color{#d91a1a}-2.86\%$
test_exclude_nested	0.3653ms	0.1163ms	8.5977 KOps/s	8.8456 KOps/s	$\color{#d91a1a}-2.80\%$
test_empty[True]	1.1409ms	0.3948ms	2.5332 KOps/s	2.5812 KOps/s	$\color{#d91a1a}-1.86\%$
test_empty[False]	3.4461μs	0.8991μs	1.1122 MOps/s	1.1641 MOps/s	$\color{#d91a1a}-4.46\%$
test_to	94.7010μs	59.6330μs	16.7692 KOps/s	18.1472 KOps/s	$\textbf{\color{#d91a1a}-7.59\%}$
test_to_nonblocking	70.7310μs	33.4956μs	29.8546 KOps/s	29.4713 KOps/s	$\color{#35bf28}+1.30\%$
test_unbind_speed	0.2990ms	0.2610ms	3.8319 KOps/s	3.7837 KOps/s	$\color{#35bf28}+1.27\%$
test_unbind_speed_stack0	0.3232ms	0.2626ms	3.8084 KOps/s	3.8031 KOps/s	$\color{#35bf28}+0.14\%$
test_unbind_speed_stack1	0.1471s	0.7834ms	1.2765 KOps/s	1.2996 KOps/s	$\color{#d91a1a}-1.78\%$
test_split	1.6395ms	1.5480ms	646.0063 Ops/s	643.0103 Ops/s	$\color{#35bf28}+0.47\%$
test_chunk	1.6199ms	1.5451ms	647.2237 Ops/s	645.2759 Ops/s	$\color{#35bf28}+0.30\%$
test_creation[device0]	0.1732ms	73.5901μs	13.5888 KOps/s	13.7923 KOps/s	$\color{#d91a1a}-1.48\%$
test_creation_from_tensor	0.1385ms	55.3728μs	18.0594 KOps/s	18.7800 KOps/s	$\color{#d91a1a}-3.84\%$
test_add_one[memmap_tensor0]	87.5320μs	6.3674μs	157.0497 KOps/s	149.5407 KOps/s	$\textbf{\color{#35bf28}+5.02\%}$
test_contiguous[memmap_tensor0]	17.6000μs	0.6588μs	1.5179 MOps/s	1.5489 MOps/s	$\color{#d91a1a}-2.00\%$
test_stack[memmap_tensor0]	27.8700μs	4.2640μs	234.5232 KOps/s	222.6067 KOps/s	$\textbf{\color{#35bf28}+5.35\%}$
test_memmaptd_index	1.2060ms	0.2525ms	3.9602 KOps/s	3.8146 KOps/s	$\color{#35bf28}+3.82\%$
test_memmaptd_index_astensor	0.6599ms	0.3101ms	3.2246 KOps/s	3.1118 KOps/s	$\color{#35bf28}+3.62\%$
test_memmaptd_index_op	0.9349ms	0.5750ms	1.7391 KOps/s	1.7139 KOps/s	$\color{#35bf28}+1.47\%$
test_serialize_model	0.2565s	0.1108s	9.0293 Ops/s	8.9457 Ops/s	$\color{#35bf28}+0.93\%$
test_serialize_model_pickle	1.3478s	1.2363s	0.8089 Ops/s	0.7166 Ops/s	$\textbf{\color{#35bf28}+12.88\%}$
test_serialize_weights	93.1770ms	88.3897ms	11.3135 Ops/s	10.2786 Ops/s	$\textbf{\color{#35bf28}+10.07\%}$
test_serialize_weights_returnearly	64.8046ms	56.3630ms	17.7421 Ops/s	11.3863 Ops/s	$\textbf{\color{#35bf28}+55.82\%}$
test_serialize_weights_pickle	1.3476s	1.2420s	0.8052 Ops/s	0.8009 Ops/s	$\color{#35bf28}+0.54\%$
test_reshape_pytree	0.2344ms	25.3594μs	39.4331 KOps/s	39.7301 KOps/s	$\color{#d91a1a}-0.75\%$
test_reshape_td	0.1512ms	30.6945μs	32.5791 KOps/s	32.4981 KOps/s	$\color{#35bf28}+0.25\%$
test_view_pytree	55.2610μs	24.3517μs	41.0648 KOps/s	40.3263 KOps/s	$\color{#35bf28}+1.83\%$
test_view_td	0.1456s	58.3734μs	17.1311 KOps/s	21.2131 KOps/s	$\textbf{\color{#d91a1a}-19.24\%}$
test_unbind_pytree	55.4600μs	29.2872μs	34.1446 KOps/s	33.1121 KOps/s	$\color{#35bf28}+3.12\%$
test_unbind_td	0.2280ms	40.1115μs	24.9305 KOps/s	24.7606 KOps/s	$\color{#35bf28}+0.69\%$
test_split_pytree	0.1819ms	29.1398μs	34.3173 KOps/s	34.2562 KOps/s	$\color{#35bf28}+0.18\%$
test_split_td	0.5871ms	39.5546μs	25.2815 KOps/s	24.9823 KOps/s	$\color{#35bf28}+1.20\%$
test_add_pytree	63.8500μs	34.6596μs	28.8521 KOps/s	28.0072 KOps/s	$\color{#35bf28}+3.02\%$
test_add_td	0.2589ms	46.3307μs	21.5839 KOps/s	20.6237 KOps/s	$\color{#35bf28}+4.66\%$
test_distributed	0.3328ms	70.3456μs	14.2155 KOps/s	13.9167 KOps/s	$\color{#35bf28}+2.15\%$
test_tdmodule	66.1610μs	17.3442μs	57.6563 KOps/s	58.9162 KOps/s	$\color{#d91a1a}-2.14\%$
test_tdmodule_dispatch	0.1347ms	34.8268μs	28.7136 KOps/s	29.5435 KOps/s	$\color{#d91a1a}-2.81\%$
test_tdseq	43.3400μs	20.0142μs	49.9645 KOps/s	50.0438 KOps/s	$\color{#d91a1a}-0.16\%$
test_tdseq_dispatch	53.9710μs	37.8781μs	26.4005 KOps/s	27.4272 KOps/s	$\color{#d91a1a}-3.74\%$
test_instantiation_functorch	1.7911ms	1.6834ms	594.0313 Ops/s	593.5196 Ops/s	$\color{#35bf28}+0.09\%$
test_instantiation_td	0.1778s	1.3617ms	734.3893 Ops/s	867.8236 Ops/s	$\textbf{\color{#d91a1a}-15.38\%}$
test_exec_functorch	0.2141ms	0.1575ms	6.3481 KOps/s	6.4875 KOps/s	$\color{#d91a1a}-2.15\%$
test_exec_functional_call	0.2417ms	0.1500ms	6.6674 KOps/s	6.6105 KOps/s	$\color{#35bf28}+0.86\%$
test_exec_td	0.2162ms	0.1392ms	7.1861 KOps/s	7.0086 KOps/s	$\color{#35bf28}+2.53\%$
test_exec_td_decorator	0.5496ms	0.1868ms	5.3536 KOps/s	5.3374 KOps/s	$\color{#35bf28}+0.30\%$
test_vmap_mlp_speed[True-True]	0.6986ms	0.5773ms	1.7323 KOps/s	1.7342 KOps/s	$\color{#d91a1a}-0.11\%$
test_vmap_mlp_speed[True-False]	0.6279ms	0.5756ms	1.7374 KOps/s	1.7382 KOps/s	$\color{#d91a1a}-0.05\%$
test_vmap_mlp_speed[False-True]	0.5602ms	0.5083ms	1.9672 KOps/s	1.9652 KOps/s	$\color{#35bf28}+0.10\%$
test_vmap_mlp_speed[False-False]	0.6544ms	0.5097ms	1.9620 KOps/s	1.8991 KOps/s	$\color{#35bf28}+3.31\%$
test_vmap_mlp_speed_decorator[True-True]	1.0513ms	0.6251ms	1.5999 KOps/s	1.6243 KOps/s	$\color{#d91a1a}-1.50\%$
test_vmap_mlp_speed_decorator[True-False]	0.7004ms	0.6183ms	1.6173 KOps/s	1.6275 KOps/s	$\color{#d91a1a}-0.63\%$
test_vmap_mlp_speed_decorator[False-True]	0.7338ms	0.5276ms	1.8955 KOps/s	1.9157 KOps/s	$\color{#d91a1a}-1.06\%$
test_vmap_mlp_speed_decorator[False-False]	0.6276ms	0.5271ms	1.8971 KOps/s	1.9128 KOps/s	$\color{#d91a1a}-0.82\%$
test_vmap_transformer_speed[True-True]	7.9409ms	7.7729ms	128.6525 Ops/s	130.6912 Ops/s	$\color{#d91a1a}-1.56\%$
test_vmap_transformer_speed[True-False]	8.4306ms	7.9668ms	125.5213 Ops/s	130.5878 Ops/s	$\color{#d91a1a}-3.88\%$
test_vmap_transformer_speed[False-True]	8.4264ms	8.0150ms	124.7658 Ops/s	131.3270 Ops/s	$\color{#d91a1a}-5.00\%$
test_vmap_transformer_speed[False-False]	8.1859ms	7.8844ms	126.8326 Ops/s	130.5240 Ops/s	$\color{#d91a1a}-2.83\%$
test_vmap_transformer_speed_decorator[True-True]	19.0948ms	18.8140ms	53.1520 Ops/s	54.5245 Ops/s	$\color{#d91a1a}-2.52\%$
test_vmap_transformer_speed_decorator[True-False]	19.8402ms	18.9269ms	52.8349 Ops/s	54.5497 Ops/s	$\color{#d91a1a}-3.14\%$
test_vmap_transformer_speed_decorator[False-True]	19.6077ms	18.6084ms	53.7391 Ops/s	54.5879 Ops/s	$\color{#d91a1a}-1.55\%$
test_vmap_transformer_speed_decorator[False-False]	19.2250ms	18.4340ms	54.2476 Ops/s	55.4758 Ops/s	$\color{#d91a1a}-2.21\%$
test_to_module_speed[True]	1.4972ms	1.2637ms	791.2965 Ops/s	799.5254 Ops/s	$\color{#d91a1a}-1.03\%$
test_to_module_speed[False]	1.5222ms	1.2366ms	808.6751 Ops/s	819.7241 Ops/s	$\color{#d91a1a}-1.35\%$