[BugFix] Fix error for incongruent devices in load_state_dict

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 109. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	45.0020μs	23.0495μs	43.3848 KOps/s	44.1458 KOps/s	$\color{#d91a1a}-1.72\%$
test_plain_set_stack_nested	0.2586ms	0.2157ms	4.6370 KOps/s	4.7528 KOps/s	$\color{#d91a1a}-2.44\%$
test_plain_set_nested_inplace	0.1544ms	26.9052μs	37.1675 KOps/s	37.6965 KOps/s	$\color{#d91a1a}-1.40\%$
test_plain_set_stack_nested_inplace	0.2908ms	0.2523ms	3.9643 KOps/s	3.9860 KOps/s	$\color{#d91a1a}-0.54\%$
test_items	0.1660ms	4.1970μs	238.2638 KOps/s	238.0113 KOps/s	$\color{#35bf28}+0.11\%$
test_items_nested	2.8173ms	0.4183ms	2.3905 KOps/s	2.4149 KOps/s	$\color{#d91a1a}-1.01\%$
test_items_nested_locked	0.4650ms	0.4152ms	2.4083 KOps/s	2.4071 KOps/s	$\color{#35bf28}+0.05\%$
test_items_nested_leaf	0.3446ms	0.2525ms	3.9597 KOps/s	3.9605 KOps/s	$\color{#d91a1a}-0.02\%$
test_items_stack_nested	2.3943ms	2.3029ms	434.2405 Ops/s	429.4598 Ops/s	$\color{#35bf28}+1.11\%$
test_items_stack_nested_leaf	2.1759ms	2.1013ms	475.9000 Ops/s	471.2449 Ops/s	$\color{#35bf28}+0.99\%$
test_items_stack_nested_locked	1.4312ms	1.1249ms	888.9525 Ops/s	874.8152 Ops/s	$\color{#35bf28}+1.62\%$
test_keys	0.2180ms	6.0780μs	164.5279 KOps/s	163.6806 KOps/s	$\color{#35bf28}+0.52\%$
test_keys_nested	2.0612ms	0.2147ms	4.6584 KOps/s	4.6612 KOps/s	$\color{#d91a1a}-0.06\%$
test_keys_nested_locked	0.2679ms	0.2111ms	4.7361 KOps/s	4.6820 KOps/s	$\color{#35bf28}+1.15\%$
test_keys_nested_leaf	0.8426ms	0.2049ms	4.8802 KOps/s	4.5021 KOps/s	$\textbf{\color{#35bf28}+8.40\%}$
test_keys_stack_nested	2.2307ms	2.1140ms	473.0405 Ops/s	465.3794 Ops/s	$\color{#35bf28}+1.65\%$
test_keys_stack_nested_leaf	2.2060ms	2.1138ms	473.0777 Ops/s	465.3413 Ops/s	$\color{#35bf28}+1.66\%$
test_keys_stack_nested_locked	1.0115ms	0.9297ms	1.0757 KOps/s	1.0394 KOps/s	$\color{#35bf28}+3.49\%$
test_values	62.2030μs	1.8926μs	528.3758 KOps/s	509.5081 KOps/s	$\color{#35bf28}+3.70\%$
test_values_nested	0.1487ms	72.8776μs	13.7216 KOps/s	13.5503 KOps/s	$\color{#35bf28}+1.26\%$
test_values_nested_locked	0.1061ms	73.1970μs	13.6618 KOps/s	13.4973 KOps/s	$\color{#35bf28}+1.22\%$
test_values_nested_leaf	0.3323ms	65.7071μs	15.2191 KOps/s	15.1201 KOps/s	$\color{#35bf28}+0.65\%$
test_values_stack_nested	1.9184ms	1.8475ms	541.2696 Ops/s	531.8885 Ops/s	$\color{#35bf28}+1.76\%$
test_values_stack_nested_leaf	1.9084ms	1.8343ms	545.1580 Ops/s	536.7215 Ops/s	$\color{#35bf28}+1.57\%$
test_values_stack_nested_locked	0.8182ms	0.7408ms	1.3499 KOps/s	1.3254 KOps/s	$\color{#35bf28}+1.85\%$
test_membership	30.0020μs	2.1622μs	462.5012 KOps/s	461.7507 KOps/s	$\color{#35bf28}+0.16\%$
test_membership_nested	52.6030μs	4.0861μs	244.7336 KOps/s	239.8698 KOps/s	$\color{#35bf28}+2.03\%$
test_membership_nested_leaf	35.8020μs	4.0964μs	244.1192 KOps/s	238.0152 KOps/s	$\color{#35bf28}+2.56\%$
test_membership_stacked_nested	50.3030μs	16.9858μs	58.8728 KOps/s	58.8421 KOps/s	$\color{#35bf28}+0.05\%$
test_membership_stacked_nested_leaf	47.3030μs	16.9547μs	58.9807 KOps/s	58.9254 KOps/s	$\color{#35bf28}+0.09\%$
test_membership_nested_last	39.0020μs	8.7773μs	113.9302 KOps/s	114.5600 KOps/s	$\color{#d91a1a}-0.55\%$
test_membership_nested_leaf_last	31.3010μs	8.6827μs	115.1720 KOps/s	115.0287 KOps/s	$\color{#35bf28}+0.12\%$
test_membership_stacked_nested_last	0.2988ms	0.2602ms	3.8427 KOps/s	3.7799 KOps/s	$\color{#35bf28}+1.66\%$
test_membership_stacked_nested_leaf_last	50.5020μs	19.8654μs	50.3387 KOps/s	50.3448 KOps/s	$\color{#d91a1a}-0.01\%$
test_nested_getleaf	85.4050μs	17.8406μs	56.0520 KOps/s	55.2435 KOps/s	$\color{#35bf28}+1.46\%$
test_nested_get	46.8030μs	16.9117μs	59.1307 KOps/s	57.7132 KOps/s	$\color{#35bf28}+2.46\%$
test_stacked_getleaf	1.1671ms	1.0179ms	982.4039 Ops/s	973.1798 Ops/s	$\color{#35bf28}+0.95\%$
test_stacked_get	1.0481ms	0.9745ms	1.0262 KOps/s	1.0131 KOps/s	$\color{#35bf28}+1.29\%$
test_nested_getitemleaf	47.4030μs	17.9197μs	55.8044 KOps/s	54.7831 KOps/s	$\color{#35bf28}+1.86\%$
test_nested_getitem	45.7030μs	16.9894μs	58.8602 KOps/s	58.0504 KOps/s	$\color{#35bf28}+1.40\%$
test_stacked_getitemleaf	1.1625ms	1.0172ms	983.0774 Ops/s	976.3913 Ops/s	$\color{#35bf28}+0.68\%$
test_stacked_getitem	1.0615ms	0.9748ms	1.0259 KOps/s	1.0252 KOps/s	$\color{#35bf28}+0.06\%$
test_lock_nested	80.0257ms	1.7488ms	571.8313 Ops/s	599.0030 Ops/s	$\color{#d91a1a}-4.54\%$
test_lock_stack_nested	0.1057s	23.2786ms	42.9579 Ops/s	46.4561 Ops/s	$\textbf{\color{#d91a1a}-7.53\%}$
test_unlock_nested	2.1150ms	1.6829ms	594.1997 Ops/s	565.2347 Ops/s	$\textbf{\color{#35bf28}+5.12\%}$
test_unlock_stack_nested	0.1039s	22.0838ms	45.2820 Ops/s	45.3297 Ops/s	$\color{#d91a1a}-0.11\%$
test_flatten_speed	1.2555ms	1.1696ms	854.9869 Ops/s	858.8428 Ops/s	$\color{#d91a1a}-0.45\%$
test_unflatten_speed	3.0445ms	2.1088ms	474.2030 Ops/s	476.2028 Ops/s	$\color{#d91a1a}-0.42\%$
test_common_ops	4.4640ms	1.2692ms	787.8883 Ops/s	787.3901 Ops/s	$\color{#35bf28}+0.06\%$
test_creation	1.0508ms	7.4399μs	134.4111 KOps/s	137.1781 KOps/s	$\color{#d91a1a}-2.02\%$
test_creation_empty	59.4040μs	15.8529μs	63.0800 KOps/s	63.7438 KOps/s	$\color{#d91a1a}-1.04\%$
test_creation_nested_1	64.9030μs	28.7479μs	34.7851 KOps/s	35.6660 KOps/s	$\color{#d91a1a}-2.47\%$
test_creation_nested_2	61.0030μs	31.1796μs	32.0723 KOps/s	32.4375 KOps/s	$\color{#d91a1a}-1.13\%$
test_clone	0.1930ms	27.9994μs	35.7150 KOps/s	34.7910 KOps/s	$\color{#35bf28}+2.66\%$
test_getitem[int]	55.0030μs	31.4482μs	31.7983 KOps/s	31.1185 KOps/s	$\color{#35bf28}+2.18\%$
test_getitem[slice_int]	0.1298ms	62.6476μs	15.9623 KOps/s	16.0851 KOps/s	$\color{#d91a1a}-0.76\%$
test_getitem[range]	0.1321ms	94.6155μs	10.5691 KOps/s	10.6270 KOps/s	$\color{#d91a1a}-0.54\%$
test_getitem[tuple]	0.1003ms	52.0700μs	19.2049 KOps/s	19.4854 KOps/s	$\color{#d91a1a}-1.44\%$
test_getitem[list]	0.3940ms	89.2232μs	11.2079 KOps/s	11.1947 KOps/s	$\color{#35bf28}+0.12\%$
test_setitem_dim[int]	81.3040μs	37.7497μs	26.4903 KOps/s	26.2864 KOps/s	$\color{#35bf28}+0.78\%$
test_setitem_dim[slice_int]	0.1089ms	66.9583μs	14.9347 KOps/s	14.6403 KOps/s	$\color{#35bf28}+2.01\%$
test_setitem_dim[range]	0.1204ms	90.8993μs	11.0012 KOps/s	10.8070 KOps/s	$\color{#35bf28}+1.80\%$
test_setitem_dim[tuple]	88.5040μs	55.0862μs	18.1534 KOps/s	17.9007 KOps/s	$\color{#35bf28}+1.41\%$
test_setitem	0.1812ms	37.2510μs	26.8449 KOps/s	26.8327 KOps/s	$\color{#35bf28}+0.05\%$
test_set	0.1992ms	35.5712μs	28.1126 KOps/s	27.8132 KOps/s	$\color{#35bf28}+1.08\%$
test_set_shared	4.1377ms	0.2234ms	4.4767 KOps/s	4.8119 KOps/s	$\textbf{\color{#d91a1a}-6.97\%}$
test_update	0.2271ms	40.0433μs	24.9730 KOps/s	24.6456 KOps/s	$\color{#35bf28}+1.33\%$
test_update_nested	0.2576ms	61.0419μs	16.3822 KOps/s	16.8677 KOps/s	$\color{#d91a1a}-2.88\%$
test_set_nested	0.4589ms	39.3370μs	25.4214 KOps/s	25.4828 KOps/s	$\color{#d91a1a}-0.24\%$
test_set_nested_new	0.2094ms	60.9467μs	16.4078 KOps/s	16.3356 KOps/s	$\color{#35bf28}+0.44\%$
test_select	0.3102ms	0.1134ms	8.8204 KOps/s	8.8583 KOps/s	$\color{#d91a1a}-0.43\%$
test_unbind_speed	0.8877ms	0.7597ms	1.3163 KOps/s	1.3169 KOps/s	$\color{#d91a1a}-0.05\%$
test_unbind_speed_stack0	89.9474ms	10.1297ms	98.7197 Ops/s	94.4127 Ops/s	$\color{#35bf28}+4.56\%$
test_unbind_speed_stack1	65.1040μs	1.3258μs	754.2401 KOps/s	742.8277 KOps/s	$\color{#35bf28}+1.54\%$
test_creation[device0]	0.6542ms	0.5329ms	1.8766 KOps/s	1.8998 KOps/s	$\color{#d91a1a}-1.22\%$
test_creation_from_tensor	3.2590ms	0.5982ms	1.6716 KOps/s	1.6948 KOps/s	$\color{#d91a1a}-1.37\%$
test_add_one[memmap_tensor0]	2.0440ms	37.4521μs	26.7007 KOps/s	26.7348 KOps/s	$\color{#d91a1a}-0.13\%$
test_contiguous[memmap_tensor0]	38.6020μs	10.0739μs	99.2666 KOps/s	98.5086 KOps/s	$\color{#35bf28}+0.77\%$
test_stack[memmap_tensor0]	0.1084ms	30.8451μs	32.4201 KOps/s	32.1379 KOps/s	$\color{#35bf28}+0.88\%$
test_memmaptd_index	0.3957ms	0.3557ms	2.8114 KOps/s	2.7885 KOps/s	$\color{#35bf28}+0.82\%$
test_memmaptd_index_astensor	1.6554ms	1.5387ms	649.9028 Ops/s	628.8021 Ops/s	$\color{#35bf28}+3.36\%$
test_memmaptd_index_op	3.1664ms	3.0770ms	324.9870 Ops/s	325.1571 Ops/s	$\color{#d91a1a}-0.05\%$
test_reshape_pytree	0.1152ms	43.8971μs	22.7805 KOps/s	23.3772 KOps/s	$\color{#d91a1a}-2.55\%$
test_reshape_td	95.8050μs	53.2095μs	18.7936 KOps/s	19.0766 KOps/s	$\color{#d91a1a}-1.48\%$
test_view_pytree	0.1136ms	40.6615μs	24.5933 KOps/s	24.8859 KOps/s	$\color{#d91a1a}-1.18\%$
test_view_td	44.3020μs	10.3083μs	97.0094 KOps/s	94.8785 KOps/s	$\color{#35bf28}+2.25\%$
test_unbind_pytree	90.5050μs	43.9358μs	22.7605 KOps/s	22.3752 KOps/s	$\color{#35bf28}+1.72\%$
test_unbind_td	0.2120ms	0.1119ms	8.9353 KOps/s	8.6993 KOps/s	$\color{#35bf28}+2.71\%$
test_split_pytree	0.1032ms	51.1334μs	19.5567 KOps/s	19.6074 KOps/s	$\color{#d91a1a}-0.26\%$
test_split_td	0.8744ms	0.1327ms	7.5362 KOps/s	7.4375 KOps/s	$\color{#35bf28}+1.33\%$
test_add_pytree	0.1022ms	53.6324μs	18.6455 KOps/s	18.6907 KOps/s	$\color{#d91a1a}-0.24\%$
test_add_td	0.2226ms	88.3086μs	11.3239 KOps/s	11.7482 KOps/s	$\color{#d91a1a}-3.61\%$
test_distributed	30.6020μs	10.7842μs	92.7282 KOps/s	91.9091 KOps/s	$\color{#35bf28}+0.89\%$
test_tdmodule	0.2437ms	34.2725μs	29.1779 KOps/s	29.1944 KOps/s	$\color{#d91a1a}-0.06\%$
test_tdmodule_dispatch	0.3220ms	66.1936μs	15.1072 KOps/s	15.4186 KOps/s	$\color{#d91a1a}-2.02\%$
test_tdseq	0.6258ms	36.9557μs	27.0594 KOps/s	26.3952 KOps/s	$\color{#35bf28}+2.52\%$
test_tdseq_dispatch	0.2512ms	79.3622μs	12.6005 KOps/s	12.7412 KOps/s	$\color{#d91a1a}-1.10\%$
test_instantiation_functorch	2.0355ms	1.8941ms	527.9662 Ops/s	519.6814 Ops/s	$\color{#35bf28}+1.59\%$
test_instantiation_td	2.3724ms	1.5814ms	632.3625 Ops/s	628.4234 Ops/s	$\color{#35bf28}+0.63\%$
test_exec_functorch	0.2872ms	0.2204ms	4.5367 KOps/s	4.5408 KOps/s	$\color{#d91a1a}-0.09\%$
test_exec_td	0.2568ms	0.2060ms	4.8554 KOps/s	4.7973 KOps/s	$\color{#35bf28}+1.21\%$
test_vmap_mlp_speed[True-True]	7.7727ms	1.4112ms	708.6087 Ops/s	666.8419 Ops/s	$\textbf{\color{#35bf28}+6.26\%}$
test_vmap_mlp_speed[True-False]	3.5301ms	0.7291ms	1.3716 KOps/s	1.3779 KOps/s	$\color{#d91a1a}-0.46\%$
test_vmap_mlp_speed[False-True]	7.1178ms	1.1734ms	852.2384 Ops/s	840.3489 Ops/s	$\color{#35bf28}+1.41\%$
test_vmap_mlp_speed[False-False]	3.6553ms	0.5406ms	1.8497 KOps/s	1.8232 KOps/s	$\color{#35bf28}+1.46\%$
test_vmap_transformer_speed[True-True]	22.7771ms	16.6291ms	60.1357 Ops/s	58.0827 Ops/s	$\color{#35bf28}+3.53\%$
test_vmap_transformer_speed[True-False]	17.2549ms	10.6403ms	93.9821 Ops/s	94.4267 Ops/s	$\color{#d91a1a}-0.47\%$
test_vmap_transformer_speed[False-True]	21.2921ms	16.0851ms	62.1694 Ops/s	62.6164 Ops/s	$\color{#d91a1a}-0.71\%$
test_vmap_transformer_speed[False-False]	17.6441ms	10.6320ms	94.0556 Ops/s	95.4953 Ops/s	$\color{#d91a1a}-1.51\%$