[Feature] min, amin, max, amax, cummin, cummax

[vmoens]

Stack from ghstack (oldest at bottom):

• -> [Feature] min, amin, max, amax, cummin, cummax #1057

Closes #1012

[github-actions]

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

Total Benchmarks: 216. Improved: $\large\color{#35bf28}28$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	80.8200μs	24.8738μs	40.2029 KOps/s	38.1416 KOps/s	$\textbf{\color{#35bf28}+5.40\%}$
test_plain_set_stack_nested	61.0240μs	24.2618μs	41.2171 KOps/s	37.0299 KOps/s	$\textbf{\color{#35bf28}+11.31\%}$
test_plain_set_nested_inplace	95.1790μs	26.6998μs	37.4535 KOps/s	34.7699 KOps/s	$\textbf{\color{#35bf28}+7.72\%}$
test_plain_set_stack_nested_inplace	68.2680μs	26.6896μs	37.4678 KOps/s	34.9215 KOps/s	$\textbf{\color{#35bf28}+7.29\%}$
test_items	28.4830μs	4.3293μs	230.9850 KOps/s	238.6433 KOps/s	$\color{#d91a1a}-3.21\%$
test_items_nested	0.8919ms	0.3883ms	2.5751 KOps/s	2.5980 KOps/s	$\color{#d91a1a}-0.88\%$
test_items_nested_locked	0.4767ms	0.3830ms	2.6107 KOps/s	2.6048 KOps/s	$\color{#35bf28}+0.22\%$
test_items_nested_leaf	0.1841ms	80.2784μs	12.4567 KOps/s	12.2857 KOps/s	$\color{#35bf28}+1.39\%$
test_items_stack_nested	0.4898ms	0.3867ms	2.5861 KOps/s	2.5736 KOps/s	$\color{#35bf28}+0.49\%$
test_items_stack_nested_leaf	0.1696ms	84.2929μs	11.8634 KOps/s	11.7554 KOps/s	$\color{#35bf28}+0.92\%$
test_items_stack_nested_locked	0.7109ms	0.3856ms	2.5932 KOps/s	2.6069 KOps/s	$\color{#d91a1a}-0.52\%$
test_keys	28.9840μs	3.5646μs	280.5377 KOps/s	284.4190 KOps/s	$\color{#d91a1a}-1.36\%$
test_keys_nested	0.2332ms	0.1340ms	7.4601 KOps/s	7.3556 KOps/s	$\color{#35bf28}+1.42\%$
test_keys_nested_locked	0.8160ms	0.1393ms	7.1772 KOps/s	7.0223 KOps/s	$\color{#35bf28}+2.20\%$
test_keys_nested_leaf	0.2357ms	0.1172ms	8.5297 KOps/s	8.4019 KOps/s	$\color{#35bf28}+1.52\%$
test_keys_stack_nested	0.2803ms	0.1316ms	7.5976 KOps/s	7.4974 KOps/s	$\color{#35bf28}+1.34\%$
test_keys_stack_nested_leaf	0.1819ms	0.1136ms	8.8045 KOps/s	8.6583 KOps/s	$\color{#35bf28}+1.69\%$
test_keys_stack_nested_locked	0.2480ms	0.1369ms	7.3064 KOps/s	7.1795 KOps/s	$\color{#35bf28}+1.77\%$
test_values	6.7004μs	1.0471μs	955.0241 KOps/s	956.6369 KOps/s	$\color{#d91a1a}-0.17\%$
test_values_nested	0.1531ms	92.5387μs	10.8063 KOps/s	10.6994 KOps/s	$\color{#35bf28}+1.00\%$
test_values_nested_locked	0.1899ms	92.7506μs	10.7816 KOps/s	10.8286 KOps/s	$\color{#d91a1a}-0.43\%$
test_values_nested_leaf	0.1410ms	78.5008μs	12.7387 KOps/s	12.3817 KOps/s	$\color{#35bf28}+2.88\%$
test_values_stack_nested	0.1701ms	92.7135μs	10.7859 KOps/s	10.5926 KOps/s	$\color{#35bf28}+1.82\%$
test_values_stack_nested_leaf	0.1521ms	77.4112μs	12.9180 KOps/s	12.9399 KOps/s	$\color{#d91a1a}-0.17\%$
test_values_stack_nested_locked	0.1847ms	93.4132μs	10.7051 KOps/s	10.6959 KOps/s	$\color{#35bf28}+0.09\%$
test_membership	2.6785μs	0.7011μs	1.4262 MOps/s	1.3288 MOps/s	$\textbf{\color{#35bf28}+7.33\%}$
test_membership_nested	41.1060μs	2.7548μs	363.0000 KOps/s	366.2470 KOps/s	$\color{#d91a1a}-0.89\%$
test_membership_nested_leaf	20.5980μs	2.7388μs	365.1259 KOps/s	365.7059 KOps/s	$\color{#d91a1a}-0.16\%$
test_membership_stacked_nested	19.0760μs	2.7161μs	368.1800 KOps/s	365.1172 KOps/s	$\color{#35bf28}+0.84\%$
test_membership_stacked_nested_leaf	18.7040μs	2.7184μs	367.8601 KOps/s	369.5620 KOps/s	$\color{#d91a1a}-0.46\%$
test_membership_nested_last	25.7480μs	4.1976μs	238.2334 KOps/s	238.5418 KOps/s	$\color{#d91a1a}-0.13\%$
test_membership_nested_leaf_last	32.6900μs	4.1512μs	240.8967 KOps/s	235.1664 KOps/s	$\color{#35bf28}+2.44\%$
test_membership_stacked_nested_last	39.3940μs	5.7551μs	173.7588 KOps/s	73.6325 KOps/s	$\textbf{\color{#35bf28}+135.98\%}$
test_membership_stacked_nested_leaf_last	38.6920μs	5.8710μs	170.3274 KOps/s	73.9068 KOps/s	$\textbf{\color{#35bf28}+130.46\%}$
test_nested_getleaf	34.6440μs	10.5247μs	95.0150 KOps/s	92.6471 KOps/s	$\color{#35bf28}+2.56\%$
test_nested_get	33.9940μs	10.1039μs	98.9720 KOps/s	98.1226 KOps/s	$\color{#35bf28}+0.87\%$
test_stacked_getleaf	43.8920μs	10.4177μs	95.9902 KOps/s	94.2424 KOps/s	$\color{#35bf28}+1.85\%$
test_stacked_get	33.6530μs	9.9055μs	100.9540 KOps/s	100.2111 KOps/s	$\color{#35bf28}+0.74\%$
test_nested_getitemleaf	36.2780μs	11.0463μs	90.5284 KOps/s	89.8072 KOps/s	$\color{#35bf28}+0.80\%$
test_nested_getitem	38.4820μs	10.3544μs	96.5771 KOps/s	97.0245 KOps/s	$\color{#d91a1a}-0.46\%$
test_stacked_getitemleaf	33.2420μs	10.8006μs	92.5874 KOps/s	89.5253 KOps/s	$\color{#35bf28}+3.42\%$
test_stacked_getitem	46.2970μs	10.1854μs	98.1801 KOps/s	95.9760 KOps/s	$\color{#35bf28}+2.30\%$
test_lock_nested	5.4136ms	0.5064ms	1.9749 KOps/s	1.9792 KOps/s	$\color{#d91a1a}-0.22\%$
test_lock_stack_nested	0.5409ms	0.4630ms	2.1600 KOps/s	2.1764 KOps/s	$\color{#d91a1a}-0.75\%$
test_unlock_nested	0.7365ms	0.4188ms	2.3879 KOps/s	2.3843 KOps/s	$\color{#35bf28}+0.15\%$
test_unlock_stack_nested	0.4472ms	0.3780ms	2.6456 KOps/s	2.6828 KOps/s	$\color{#d91a1a}-1.39\%$
test_flatten_speed	0.2005ms	0.1014ms	9.8649 KOps/s	9.8479 KOps/s	$\color{#35bf28}+0.17\%$
test_unflatten_speed	0.7690ms	0.5058ms	1.9769 KOps/s	1.9800 KOps/s	$\color{#d91a1a}-0.16\%$
test_common_ops	4.9806ms	1.1379ms	878.8295 Ops/s	820.4995 Ops/s	$\textbf{\color{#35bf28}+7.11\%}$
test_creation	65.0510μs	2.1042μs	475.2401 KOps/s	460.7967 KOps/s	$\color{#35bf28}+3.13\%$
test_creation_empty	54.0810μs	18.6351μs	53.6621 KOps/s	46.8922 KOps/s	$\textbf{\color{#35bf28}+14.44\%}$
test_creation_nested_1	57.3370μs	21.9153μs	45.6303 KOps/s	41.1053 KOps/s	$\textbf{\color{#35bf28}+11.01\%}$
test_creation_nested_2	63.1680μs	26.4452μs	37.8140 KOps/s	34.8768 KOps/s	$\textbf{\color{#35bf28}+8.42\%}$
test_clone	0.1126ms	17.2454μs	57.9865 KOps/s	56.7440 KOps/s	$\color{#35bf28}+2.19\%$
test_getitem[int]	0.9803ms	16.7527μs	59.6919 KOps/s	57.8250 KOps/s	$\color{#35bf28}+3.23\%$
test_getitem[slice_int]	0.1345ms	30.6450μs	32.6318 KOps/s	32.1665 KOps/s	$\color{#35bf28}+1.45\%$
test_getitem[range]	0.1743ms	59.6479μs	16.7651 KOps/s	17.1348 KOps/s	$\color{#d91a1a}-2.16\%$
test_getitem[tuple]	0.1334ms	25.8796μs	38.6405 KOps/s	39.4358 KOps/s	$\color{#d91a1a}-2.02\%$
test_getitem[list]	0.3137ms	54.4238μs	18.3743 KOps/s	18.2967 KOps/s	$\color{#35bf28}+0.42\%$
test_setitem_dim[int]	68.1560μs	32.7686μs	30.5171 KOps/s	29.8508 KOps/s	$\color{#35bf28}+2.23\%$
test_setitem_dim[slice_int]	0.1213ms	61.7022μs	16.2069 KOps/s	15.9555 KOps/s	$\color{#35bf28}+1.58\%$
test_setitem_dim[range]	0.1388ms	85.9252μs	11.6380 KOps/s	11.6084 KOps/s	$\color{#35bf28}+0.26\%$
test_setitem_dim[tuple]	87.8940μs	49.2598μs	20.3005 KOps/s	20.1541 KOps/s	$\color{#35bf28}+0.73\%$
test_setitem	0.1270ms	30.4710μs	32.8181 KOps/s	30.7981 KOps/s	$\textbf{\color{#35bf28}+6.56\%}$
test_set	0.1212ms	29.4551μs	33.9500 KOps/s	31.8904 KOps/s	$\textbf{\color{#35bf28}+6.46\%}$
test_set_shared	3.4782ms	0.2199ms	4.5473 KOps/s	4.5624 KOps/s	$\color{#d91a1a}-0.33\%$
test_update	0.1197ms	38.6262μs	25.8892 KOps/s	24.3735 KOps/s	$\textbf{\color{#35bf28}+6.22\%}$
test_update_nested	0.1403ms	48.8872μs	20.4553 KOps/s	18.9668 KOps/s	$\textbf{\color{#35bf28}+7.85\%}$
test_update__nested	0.6574ms	44.4991μs	22.4723 KOps/s	21.7260 KOps/s	$\color{#35bf28}+3.44\%$
test_set_nested	92.9540μs	32.7330μs	30.5502 KOps/s	28.5744 KOps/s	$\textbf{\color{#35bf28}+6.91\%}$
test_set_nested_new	0.1999ms	37.3013μs	26.8087 KOps/s	25.0244 KOps/s	$\textbf{\color{#35bf28}+7.13\%}$
test_select	0.1680ms	54.5526μs	18.3309 KOps/s	17.5538 KOps/s	$\color{#35bf28}+4.43\%$
test_select_nested	0.1271ms	59.1730μs	16.8996 KOps/s	17.1009 KOps/s	$\color{#d91a1a}-1.18\%$
test_exclude_nested	0.1854ms	74.7454μs	13.3787 KOps/s	13.3150 KOps/s	$\color{#35bf28}+0.48\%$
test_empty[True]	0.4752ms	0.3460ms	2.8900 KOps/s	2.8233 KOps/s	$\color{#35bf28}+2.36\%$
test_empty[False]	11.2110μs	1.2195μs	819.9949 KOps/s	795.1101 KOps/s	$\color{#35bf28}+3.13\%$
test_unbind_speed	0.4875ms	0.3003ms	3.3296 KOps/s	3.3035 KOps/s	$\color{#35bf28}+0.79\%$
test_unbind_speed_stack0	0.4709ms	0.2900ms	3.4488 KOps/s	3.4610 KOps/s	$\color{#d91a1a}-0.35\%$
test_unbind_speed_stack1	0.1023s	0.7965ms	1.2555 KOps/s	1.3938 KOps/s	$\textbf{\color{#d91a1a}-9.92\%}$
test_split	98.3290ms	2.2902ms	436.6375 Ops/s	448.1760 Ops/s	$\color{#d91a1a}-2.57\%$
test_chunk	2.9358ms	2.0763ms	481.6369 Ops/s	451.3595 Ops/s	$\textbf{\color{#35bf28}+6.71\%}$
test_creation[device0]	0.2292ms	0.1161ms	8.6166 KOps/s	8.4441 KOps/s	$\color{#35bf28}+2.04\%$
test_creation_from_tensor	3.8964ms	0.1183ms	8.4562 KOps/s	8.2994 KOps/s	$\color{#35bf28}+1.89\%$
test_add_one[memmap_tensor0]	0.2446ms	7.3116μs	136.7698 KOps/s	135.0742 KOps/s	$\color{#35bf28}+1.26\%$
test_contiguous[memmap_tensor0]	15.1580μs	1.8728μs	533.9549 KOps/s	508.5743 KOps/s	$\color{#35bf28}+4.99\%$
test_stack[memmap_tensor0]	81.4510μs	5.9593μs	167.8039 KOps/s	172.4387 KOps/s	$\color{#d91a1a}-2.69\%$
test_memmaptd_index	1.2143ms	0.4241ms	2.3577 KOps/s	2.3975 KOps/s	$\color{#d91a1a}-1.66\%$
test_memmaptd_index_astensor	1.0403ms	0.5280ms	1.8941 KOps/s	1.9225 KOps/s	$\color{#d91a1a}-1.48\%$
test_memmaptd_index_op	1.6940ms	1.0764ms	929.0028 Ops/s	882.9120 Ops/s	$\textbf{\color{#35bf28}+5.22\%}$
test_serialize_model	0.1281s	0.1210s	8.2649 Ops/s	8.3473 Ops/s	$\color{#d91a1a}-0.99\%$
test_serialize_model_pickle	0.4729s	0.4025s	2.4847 Ops/s	2.5109 Ops/s	$\color{#d91a1a}-1.04\%$
test_serialize_weights	0.1231s	0.1151s	8.6907 Ops/s	8.4485 Ops/s	$\color{#35bf28}+2.87\%$
test_serialize_weights_returnearly	0.1783s	0.1634s	6.1191 Ops/s	5.6906 Ops/s	$\textbf{\color{#35bf28}+7.53\%}$
test_serialize_weights_pickle	0.5621s	0.4345s	2.3015 Ops/s	2.5002 Ops/s	$\textbf{\color{#d91a1a}-7.95\%}$
test_serialize_weights_filesystem	0.1457s	0.1424s	7.0207 Ops/s	6.9906 Ops/s	$\color{#35bf28}+0.43\%$
test_serialize_model_filesystem	0.1540s	0.1486s	6.7290 Ops/s	6.6587 Ops/s	$\color{#35bf28}+1.06\%$
test_reshape_pytree	93.2940μs	40.3193μs	24.8020 KOps/s	25.1808 KOps/s	$\color{#d91a1a}-1.50\%$
test_reshape_td	0.1014ms	46.0406μs	21.7200 KOps/s	21.3635 KOps/s	$\color{#35bf28}+1.67\%$
test_view_pytree	90.0280μs	39.8432μs	25.0984 KOps/s	25.4769 KOps/s	$\color{#d91a1a}-1.49\%$
test_view_td	0.1130ms	52.1905μs	19.1606 KOps/s	19.1512 KOps/s	$\color{#35bf28}+0.05\%$
test_unbind_pytree	78.9270μs	36.3020μs	27.5467 KOps/s	27.6698 KOps/s	$\color{#d91a1a}-0.44\%$
test_unbind_td	0.3428ms	45.0481μs	22.1985 KOps/s	22.0803 KOps/s	$\color{#35bf28}+0.54\%$
test_split_pytree	87.6930μs	39.5729μs	25.2698 KOps/s	25.7645 KOps/s	$\color{#d91a1a}-1.92\%$
test_split_td	0.5036ms	59.5073μs	16.8047 KOps/s	16.9942 KOps/s	$\color{#d91a1a}-1.12\%$
test_add_pytree	97.6820μs	44.6342μs	22.4044 KOps/s	21.6099 KOps/s	$\color{#35bf28}+3.68\%$
test_add_td	0.1666ms	87.6358μs	11.4109 KOps/s	10.8695 KOps/s	$\color{#35bf28}+4.98\%$
test_compile_add_one_nested[tensordict-compile]	0.1481ms	71.9530μs	13.8980 KOps/s	13.7429 KOps/s	$\color{#35bf28}+1.13\%$
test_compile_add_one_nested[tensordict-eager]	0.3880ms	0.2027ms	4.9338 KOps/s	4.8230 KOps/s	$\color{#35bf28}+2.30\%$
test_compile_add_one_nested[pytree-compile]	0.1221ms	53.8809μs	18.5594 KOps/s	18.4141 KOps/s	$\color{#35bf28}+0.79\%$
test_compile_add_one_nested[pytree-eager]	0.2531ms	0.1443ms	6.9283 KOps/s	6.7837 KOps/s	$\color{#35bf28}+2.13\%$
test_compile_copy_nested[tensordict-compile]	61.8160μs	27.3031μs	36.6259 KOps/s	36.0389 KOps/s	$\color{#35bf28}+1.63\%$
test_compile_copy_nested[tensordict-eager]	0.1631ms	77.3431μs	12.9294 KOps/s	12.9525 KOps/s	$\color{#d91a1a}-0.18\%$
test_compile_copy_nested[pytree-compile]	0.1744ms	78.4973μs	12.7393 KOps/s	12.7642 KOps/s	$\color{#d91a1a}-0.20\%$
test_compile_copy_nested[pytree-eager]	0.1285ms	66.8890μs	14.9501 KOps/s	14.6926 KOps/s	$\color{#35bf28}+1.75\%$
test_compile_add_one_flat[tensordict-compile]	0.1960ms	0.1234ms	8.1021 KOps/s	8.2778 KOps/s	$\color{#d91a1a}-2.12\%$
test_compile_add_one_flat[tensordict-eager]	0.4540ms	0.2443ms	4.0936 KOps/s	3.9967 KOps/s	$\color{#35bf28}+2.43\%$
test_compile_add_one_flat[tensorclass-compile]	0.1250ms	54.1595μs	18.4640 KOps/s	18.7516 KOps/s	$\color{#d91a1a}-1.53\%$
test_compile_add_one_flat[tensorclass-eager]	0.5036ms	80.7356μs	12.3861 KOps/s	12.3497 KOps/s	$\color{#35bf28}+0.29\%$
test_compile_add_one_flat[pytree-compile]	0.1968ms	0.1143ms	8.7504 KOps/s	8.8341 KOps/s	$\color{#d91a1a}-0.95\%$
test_compile_add_one_flat[pytree-eager]	0.4496ms	0.2970ms	3.3664 KOps/s	3.3632 KOps/s	$\color{#35bf28}+0.10\%$
test_compile_add_self_flat[tensordict-eager]	0.4992ms	0.2735ms	3.6558 KOps/s	3.5215 KOps/s	$\color{#35bf28}+3.81\%$
test_compile_add_self_flat[tensordict-compile]	0.2220ms	0.1241ms	8.0567 KOps/s	8.2012 KOps/s	$\color{#d91a1a}-1.76\%$
test_compile_add_self_flat[tensorclass-eager]	0.2823ms	79.0420μs	12.6515 KOps/s	13.2501 KOps/s	$\color{#d91a1a}-4.52\%$
test_compile_add_self_flat[tensorclass-compile]	0.1298ms	54.5176μs	18.3427 KOps/s	18.3105 KOps/s	$\color{#35bf28}+0.18\%$
test_compile_add_self_flat[pytree-eager]	0.3471ms	0.2479ms	4.0341 KOps/s	4.1247 KOps/s	$\color{#d91a1a}-2.20\%$
test_compile_add_self_flat[pytree-compile]	0.2186ms	0.1141ms	8.7610 KOps/s	8.9671 KOps/s	$\color{#d91a1a}-2.30\%$
test_compile_copy_flat[tensordict-compile]	84.4180μs	29.7848μs	33.5742 KOps/s	34.9469 KOps/s	$\color{#d91a1a}-3.93\%$
test_compile_copy_flat[tensordict-eager]	0.1744ms	79.3100μs	12.6087 KOps/s	12.6792 KOps/s	$\color{#d91a1a}-0.56\%$
test_compile_copy_flat[pytree-compile]	0.2083ms	81.5853μs	12.2571 KOps/s	12.2759 KOps/s	$\color{#d91a1a}-0.15\%$
test_compile_copy_flat[pytree-eager]	0.1437ms	68.6606μs	14.5644 KOps/s	14.6348 KOps/s	$\color{#d91a1a}-0.48\%$
test_compile_assign_and_add[tensordict-compile]	0.3302ms	0.2176ms	4.5959 KOps/s	4.6389 KOps/s	$\color{#d91a1a}-0.93\%$
test_compile_assign_and_add[tensordict-eager]	4.0210ms	1.8743ms	533.5238 Ops/s	544.9516 Ops/s	$\color{#d91a1a}-2.10\%$
test_compile_assign_and_add[pytree-compile]	0.8474ms	0.2100ms	4.7623 KOps/s	4.7610 KOps/s	$\color{#35bf28}+0.03\%$
test_compile_assign_and_add[pytree-eager]	1.4786ms	1.1649ms	858.4318 Ops/s	850.5284 Ops/s	$\color{#35bf28}+0.93\%$
test_compile_assign_and_add_stack[compile]	0.8301ms	0.4584ms	2.1816 KOps/s	2.1859 KOps/s	$\color{#d91a1a}-0.19\%$
test_compile_assign_and_add_stack[eager]	4.5991ms	4.2397ms	235.8658 Ops/s	223.7308 Ops/s	$\textbf{\color{#35bf28}+5.42\%}$
test_compile_indexing[tensor-tensordict-compile]	0.1666ms	42.6887μs	23.4254 KOps/s	23.6008 KOps/s	$\color{#d91a1a}-0.74\%$
test_compile_indexing[tensor-tensordict-eager]	0.5269ms	51.4292μs	19.4442 KOps/s	19.6222 KOps/s	$\color{#d91a1a}-0.91\%$
test_compile_indexing[tensor-tensorclass-compile]	84.6490μs	37.3766μs	26.7547 KOps/s	27.2941 KOps/s	$\color{#d91a1a}-1.98\%$
test_compile_indexing[tensor-tensorclass-eager]	0.1327ms	29.9266μs	33.4151 KOps/s	33.0680 KOps/s	$\color{#35bf28}+1.05\%$
test_compile_indexing[tensor-pytree-compile]	98.5040μs	38.5169μs	25.9626 KOps/s	26.9083 KOps/s	$\color{#d91a1a}-3.51\%$
test_compile_indexing[tensor-pytree-eager]	87.7940μs	29.8838μs	33.4629 KOps/s	34.1898 KOps/s	$\color{#d91a1a}-2.13\%$
test_compile_indexing[slice-tensordict-compile]	0.1821ms	77.3448μs	12.9291 KOps/s	13.0706 KOps/s	$\color{#d91a1a}-1.08\%$
test_compile_indexing[slice-tensordict-eager]	0.5992ms	29.4288μs	33.9804 KOps/s	33.3500 KOps/s	$\color{#35bf28}+1.89\%$
test_compile_indexing[slice-tensorclass-compile]	0.1466ms	71.0086μs	14.0828 KOps/s	13.7379 KOps/s	$\color{#35bf28}+2.51\%$
test_compile_indexing[slice-tensorclass-eager]	87.4930μs	24.5511μs	40.7315 KOps/s	41.6839 KOps/s	$\color{#d91a1a}-2.28\%$
test_compile_indexing[slice-pytree-compile]	0.1417ms	71.8166μs	13.9244 KOps/s	14.2429 KOps/s	$\color{#d91a1a}-2.24\%$
test_compile_indexing[slice-pytree-eager]	89.7470μs	24.4305μs	40.9325 KOps/s	42.3524 KOps/s	$\color{#d91a1a}-3.35\%$
test_compile_indexing[int-tensordict-compile]	0.1658ms	79.5327μs	12.5734 KOps/s	12.9144 KOps/s	$\color{#d91a1a}-2.64\%$
test_compile_indexing[int-tensordict-eager]	0.8854ms	28.8011μs	34.7209 KOps/s	35.0253 KOps/s	$\color{#d91a1a}-0.87\%$
test_compile_indexing[int-tensorclass-compile]	0.1321ms	71.2169μs	14.0416 KOps/s	14.1915 KOps/s	$\color{#d91a1a}-1.06\%$
test_compile_indexing[int-tensorclass-eager]	70.0600μs	24.1029μs	41.4887 KOps/s	42.0545 KOps/s	$\color{#d91a1a}-1.35\%$
test_compile_indexing[int-pytree-compile]	0.1511ms	71.0323μs	14.0781 KOps/s	14.2638 KOps/s	$\color{#d91a1a}-1.30\%$
test_compile_indexing[int-pytree-eager]	61.7440μs	24.0595μs	41.5636 KOps/s	41.7689 KOps/s	$\color{#d91a1a}-0.49\%$
test_mod_add[eager]	94.5060μs	25.9491μs	38.5371 KOps/s	34.4218 KOps/s	$\textbf{\color{#35bf28}+11.96\%}$
test_mod_add[compile]	99.9240μs	44.2640μs	22.5917 KOps/s	22.9207 KOps/s	$\color{#d91a1a}-1.44\%$
test_mod_add[compile-overhead]	97.5120μs	43.4492μs	23.0154 KOps/s	22.6765 KOps/s	$\color{#35bf28}+1.49\%$
test_mod_wrap[eager]	0.4315ms	0.2155ms	4.6403 KOps/s	4.5602 KOps/s	$\color{#35bf28}+1.76\%$
test_mod_wrap[compile]	1.4398ms	0.2036ms	4.9115 KOps/s	4.8533 KOps/s	$\color{#35bf28}+1.20\%$
test_mod_wrap[compile-overhead]	1.8230ms	0.2002ms	4.9961 KOps/s	4.8124 KOps/s	$\color{#35bf28}+3.82\%$
test_mod_wrap_and_backward[eager]	20.6022ms	11.5034ms	86.9311 Ops/s	90.8855 Ops/s	$\color{#d91a1a}-4.35\%$
test_mod_wrap_and_backward[compile]	19.1959ms	13.5943ms	73.5604 Ops/s	92.4096 Ops/s	$\textbf{\color{#d91a1a}-20.40\%}$
test_mod_wrap_and_backward[compile-overhead]	20.2974ms	13.7381ms	72.7902 Ops/s	92.4205 Ops/s	$\textbf{\color{#d91a1a}-21.24\%}$
test_seq_add[eager]	0.1706ms	92.3161μs	10.8324 KOps/s	10.0743 KOps/s	$\textbf{\color{#35bf28}+7.52\%}$
test_seq_add[compile]	0.1114ms	57.5781μs	17.3677 KOps/s	17.2576 KOps/s	$\color{#35bf28}+0.64\%$
test_seq_add[compile-overhead]	0.1308ms	57.2955μs	17.4534 KOps/s	17.3301 KOps/s	$\color{#35bf28}+0.71\%$
test_seq_wrap[eager]	0.6460ms	0.3923ms	2.5488 KOps/s	2.4907 KOps/s	$\color{#35bf28}+2.33\%$
test_seq_wrap[compile]	0.4216ms	0.2239ms	4.4670 KOps/s	4.3748 KOps/s	$\color{#35bf28}+2.11\%$
test_seq_wrap[compile-overhead]	0.4710ms	0.2241ms	4.4624 KOps/s	4.3962 KOps/s	$\color{#35bf28}+1.51\%$
test_func_call_runtime[False-eager]	1.3061ms	0.5417ms	1.8462 KOps/s	1.8692 KOps/s	$\color{#d91a1a}-1.23\%$
test_func_call_runtime[False-compile]	0.8019ms	0.4310ms	2.3200 KOps/s	2.3035 KOps/s	$\color{#35bf28}+0.72\%$
test_func_call_runtime[False-compile-overhead]	0.6424ms	0.4254ms	2.3507 KOps/s	2.3004 KOps/s	$\color{#35bf28}+2.19\%$
test_func_call_runtime[True-eager]	1.5993ms	0.7758ms	1.2891 KOps/s	1.3360 KOps/s	$\color{#d91a1a}-3.51\%$
test_func_call_runtime[True-compile]	0.5707ms	0.4653ms	2.1493 KOps/s	2.1155 KOps/s	$\color{#35bf28}+1.60\%$
test_func_call_runtime[True-compile-overhead]	0.8215ms	0.4707ms	2.1246 KOps/s	2.1259 KOps/s	$\color{#d91a1a}-0.06\%$
test_func_call_cm_runtime[False-eager]	0.7082ms	0.5355ms	1.8674 KOps/s	1.8588 KOps/s	$\color{#35bf28}+0.46\%$
test_func_call_cm_runtime[False-compile]	0.6336ms	0.4270ms	2.3419 KOps/s	2.3087 KOps/s	$\color{#35bf28}+1.44\%$
test_func_call_cm_runtime[False-compile-overhead]	0.6680ms	0.4274ms	2.3397 KOps/s	2.3122 KOps/s	$\color{#35bf28}+1.19\%$
test_func_call_cm_runtime[True-eager]	1.3091ms	0.9108ms	1.0979 KOps/s	1.1114 KOps/s	$\color{#d91a1a}-1.21\%$
test_func_call_cm_runtime[True-compile]	0.6423ms	0.4897ms	2.0420 KOps/s	2.0086 KOps/s	$\color{#35bf28}+1.66\%$
test_func_call_cm_runtime[True-compile-overhead]	0.6571ms	0.4891ms	2.0444 KOps/s	2.0216 KOps/s	$\color{#35bf28}+1.13\%$
test_vmap_func_call_cm_runtime[eager]	2.4298ms	1.8875ms	529.8133 Ops/s	529.8946 Ops/s	$\color{#d91a1a}-0.02\%$
test_vmap_func_call_cm_runtime[compile]	0.8918ms	0.5160ms	1.9379 KOps/s	1.9179 KOps/s	$\color{#35bf28}+1.04\%$
test_vmap_func_call_cm_runtime[compile-overhead]	1.0712ms	0.5240ms	1.9083 KOps/s	1.9129 KOps/s	$\color{#d91a1a}-0.24\%$
test_distributed	0.3737ms	0.1285ms	7.7810 KOps/s	7.6826 KOps/s	$\color{#35bf28}+1.28\%$
test_tdmodule	0.1315ms	18.7597μs	53.3058 KOps/s	47.9951 KOps/s	$\textbf{\color{#35bf28}+11.07\%}$
test_tdmodule_dispatch	67.1150μs	37.4269μs	26.7188 KOps/s	24.9897 KOps/s	$\textbf{\color{#35bf28}+6.92\%}$
test_tdseq	47.1780μs	21.7676μs	45.9399 KOps/s	43.2167 KOps/s	$\textbf{\color{#35bf28}+6.30\%}$
test_tdseq_dispatch	69.2790μs	42.8889μs	23.3160 KOps/s	22.0054 KOps/s	$\textbf{\color{#35bf28}+5.96\%}$
test_instantiation_functorch	1.6924ms	1.5519ms	644.3874 Ops/s	642.1684 Ops/s	$\color{#35bf28}+0.35\%$
test_exec_functorch	0.3373ms	0.1869ms	5.3497 KOps/s	5.4963 KOps/s	$\color{#d91a1a}-2.67\%$
test_exec_functional_call	0.3434ms	0.1749ms	5.7190 KOps/s	5.6805 KOps/s	$\color{#35bf28}+0.68\%$
test_exec_td_decorator	0.5000ms	0.2395ms	4.1754 KOps/s	4.1915 KOps/s	$\color{#d91a1a}-0.38\%$
test_vmap_mlp_speed_decorator[True-True]	0.9015ms	0.6522ms	1.5332 KOps/s	1.5425 KOps/s	$\color{#d91a1a}-0.60\%$
test_vmap_mlp_speed_decorator[True-False]	1.0774ms	0.6532ms	1.5309 KOps/s	1.5393 KOps/s	$\color{#d91a1a}-0.54\%$
test_vmap_mlp_speed_decorator[False-True]	0.7486ms	0.5334ms	1.8749 KOps/s	1.9012 KOps/s	$\color{#d91a1a}-1.38\%$
test_vmap_mlp_speed_decorator[False-False]	0.8004ms	0.5344ms	1.8714 KOps/s	1.9065 KOps/s	$\color{#d91a1a}-1.84\%$
test_to_module_speed[True]	1.6322ms	1.3820ms	723.5672 Ops/s	727.8412 Ops/s	$\color{#d91a1a}-0.59\%$
test_to_module_speed[False]	1.6302ms	1.3536ms	738.7529 Ops/s	741.2892 Ops/s	$\color{#d91a1a}-0.34\%$
test_tc_init	90.6490μs	47.7111μs	20.9595 KOps/s	20.2611 KOps/s	$\color{#35bf28}+3.45\%$
test_tc_init_nested	0.1766ms	96.5399μs	10.3584 KOps/s	10.6482 KOps/s	$\color{#d91a1a}-2.72\%$
test_tc_first_layer_tensor	21.9710μs	1.5084μs	662.9561 KOps/s	620.6781 KOps/s	$\textbf{\color{#35bf28}+6.81\%}$
test_tc_first_layer_nontensor	25.4070μs	4.6731μs	213.9888 KOps/s	209.7039 KOps/s	$\color{#35bf28}+2.04\%$
test_tc_second_layer_tensor	19.8270μs	2.8129μs	355.5100 KOps/s	343.9121 KOps/s	$\color{#35bf28}+3.37\%$
test_tc_second_layer_nontensor	27.7910μs	5.9038μs	169.3824 KOps/s	163.2997 KOps/s	$\color{#35bf28}+3.72\%$
test_unbind	0.2016s	14.8310ms	67.4264 Ops/s	73.1319 Ops/s	$\textbf{\color{#d91a1a}-7.80\%}$
test_full_like	7.5195ms	6.9575ms	143.7290 Ops/s	141.4805 Ops/s	$\color{#35bf28}+1.59\%$
test_zeros_like	3.3122ms	2.7660ms	361.5292 Ops/s	345.2295 Ops/s	$\color{#35bf28}+4.72\%$
test_ones_like	3.5787ms	3.1648ms	315.9744 Ops/s	315.6943 Ops/s	$\color{#35bf28}+0.09\%$
test_clone	5.6472ms	4.9007ms	204.0530 Ops/s	195.4796 Ops/s	$\color{#35bf28}+4.39\%$
test_squeeze	59.3610μs	13.2481μs	75.4827 KOps/s	79.4543 KOps/s	$\color{#d91a1a}-5.00\%$
test_unsqueeze	0.2283ms	95.6541μs	10.4543 KOps/s	10.3523 KOps/s	$\color{#35bf28}+0.99\%$
test_split	0.5196ms	0.2010ms	4.9759 KOps/s	5.1256 KOps/s	$\color{#d91a1a}-2.92\%$
test_permute	0.3792ms	0.2266ms	4.4129 KOps/s	4.4732 KOps/s	$\color{#d91a1a}-1.35\%$
test_stack	33.3412ms	25.7638ms	38.8142 Ops/s	38.7542 Ops/s	$\color{#35bf28}+0.15\%$
test_cat	32.0384ms	25.1208ms	39.8077 Ops/s	38.3516 Ops/s	$\color{#35bf28}+3.80\%$

[github-actions]

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

Total Benchmarks: 222. Improved: $\large\color{#35bf28}25$. Worsened: $\large\color{#d91a1a}12$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	47.0120μs	15.7275μs	63.5830 KOps/s	57.7559 KOps/s	$\textbf{\color{#35bf28}+10.09\%}$
test_plain_set_stack_nested	91.9930μs	15.9854μs	62.5570 KOps/s	56.4621 KOps/s	$\textbf{\color{#35bf28}+10.79\%}$
test_plain_set_nested_inplace	0.1288ms	17.2320μs	58.0314 KOps/s	52.9912 KOps/s	$\textbf{\color{#35bf28}+9.51\%}$
test_plain_set_stack_nested_inplace	43.1510μs	16.9996μs	58.8248 KOps/s	53.3358 KOps/s	$\textbf{\color{#35bf28}+10.29\%}$
test_items	21.4610μs	2.8370μs	352.4898 KOps/s	338.3812 KOps/s	$\color{#35bf28}+4.17\%$
test_items_nested	0.5229ms	0.3418ms	2.9254 KOps/s	2.9788 KOps/s	$\color{#d91a1a}-1.79\%$
test_items_nested_locked	0.3749ms	0.3472ms	2.8800 KOps/s	2.9853 KOps/s	$\color{#d91a1a}-3.53\%$
test_items_nested_leaf	89.0140μs	63.3747μs	15.7792 KOps/s	15.8145 KOps/s	$\color{#d91a1a}-0.22\%$
test_items_stack_nested	0.3957ms	0.3450ms	2.8990 KOps/s	2.9461 KOps/s	$\color{#d91a1a}-1.60\%$
test_items_stack_nested_leaf	0.1006ms	64.9274μs	15.4018 KOps/s	15.1933 KOps/s	$\color{#35bf28}+1.37\%$
test_items_stack_nested_locked	0.3779ms	0.3478ms	2.8753 KOps/s	2.9259 KOps/s	$\color{#d91a1a}-1.73\%$
test_keys	30.0320μs	3.4554μs	289.4009 KOps/s	288.7332 KOps/s	$\color{#35bf28}+0.23\%$
test_keys_nested	0.1059ms	70.6350μs	14.1573 KOps/s	14.2932 KOps/s	$\color{#d91a1a}-0.95\%$
test_keys_nested_locked	2.2945ms	77.0369μs	12.9808 KOps/s	13.0977 KOps/s	$\color{#d91a1a}-0.89\%$
test_keys_nested_leaf	0.1168ms	61.5244μs	16.2537 KOps/s	16.4754 KOps/s	$\color{#d91a1a}-1.35\%$
test_keys_stack_nested	0.1014ms	71.7528μs	13.9367 KOps/s	14.0708 KOps/s	$\color{#d91a1a}-0.95\%$
test_keys_stack_nested_leaf	91.2340μs	63.1154μs	15.8440 KOps/s	15.9903 KOps/s	$\color{#d91a1a}-0.91\%$
test_keys_stack_nested_locked	0.1266ms	77.2378μs	12.9470 KOps/s	12.8557 KOps/s	$\color{#35bf28}+0.71\%$
test_values	10.4204μs	1.0112μs	988.9269 KOps/s	1.1780 MOps/s	$\textbf{\color{#d91a1a}-16.05\%}$
test_values_nested	0.1401ms	48.8937μs	20.4525 KOps/s	20.2461 KOps/s	$\color{#35bf28}+1.02\%$
test_values_nested_locked	0.3661ms	50.7428μs	19.7072 KOps/s	19.6688 KOps/s	$\color{#35bf28}+0.20\%$
test_values_nested_leaf	88.5540μs	42.6543μs	23.4443 KOps/s	23.6519 KOps/s	$\color{#d91a1a}-0.88\%$
test_values_stack_nested	0.1061ms	50.3224μs	19.8718 KOps/s	20.0183 KOps/s	$\color{#d91a1a}-0.73\%$
test_values_stack_nested_leaf	75.0330μs	43.5396μs	22.9676 KOps/s	22.6922 KOps/s	$\color{#35bf28}+1.21\%$
test_values_stack_nested_locked	87.9030μs	51.6692μs	19.3539 KOps/s	19.3573 KOps/s	$\color{#d91a1a}-0.02\%$
test_membership	1.6545μs	0.5156μs	1.9395 MOps/s	1.9320 MOps/s	$\color{#35bf28}+0.39\%$
test_membership_nested	16.2460μs	1.8970μs	527.1556 KOps/s	519.9297 KOps/s	$\color{#35bf28}+1.39\%$
test_membership_nested_leaf	13.9460μs	1.9049μs	524.9612 KOps/s	533.2200 KOps/s	$\color{#d91a1a}-1.55\%$
test_membership_stacked_nested	25.3810μs	1.9594μs	510.3562 KOps/s	505.2893 KOps/s	$\color{#35bf28}+1.00\%$
test_membership_stacked_nested_leaf	30.2810μs	1.9599μs	510.2283 KOps/s	508.6088 KOps/s	$\color{#35bf28}+0.32\%$
test_membership_nested_last	25.8710μs	2.9921μs	334.2164 KOps/s	334.8123 KOps/s	$\color{#d91a1a}-0.18\%$
test_membership_nested_leaf_last	0.1741ms	2.9692μs	336.7926 KOps/s	336.6753 KOps/s	$\color{#35bf28}+0.03\%$
test_membership_stacked_nested_last	0.1952ms	2.9895μs	334.5033 KOps/s	284.4880 KOps/s	$\textbf{\color{#35bf28}+17.58\%}$
test_membership_stacked_nested_leaf_last	24.3610μs	2.9878μs	334.6950 KOps/s	281.2309 KOps/s	$\textbf{\color{#35bf28}+19.01\%}$
test_nested_getleaf	0.2032ms	6.0376μs	165.6288 KOps/s	166.6058 KOps/s	$\color{#d91a1a}-0.59\%$
test_nested_get	32.8010μs	5.6627μs	176.5929 KOps/s	174.8829 KOps/s	$\color{#35bf28}+0.98\%$
test_stacked_getleaf	43.0020μs	5.9843μs	167.1048 KOps/s	166.6690 KOps/s	$\color{#35bf28}+0.26\%$
test_stacked_get	29.8310μs	5.7094μs	175.1498 KOps/s	175.5582 KOps/s	$\color{#d91a1a}-0.23\%$
test_nested_getitemleaf	44.4420μs	6.1369μs	162.9497 KOps/s	164.1046 KOps/s	$\color{#d91a1a}-0.70\%$
test_nested_getitem	0.4552ms	5.7853μs	172.8512 KOps/s	173.4094 KOps/s	$\color{#d91a1a}-0.32\%$
test_stacked_getitemleaf	41.2220μs	6.1345μs	163.0122 KOps/s	163.6158 KOps/s	$\color{#d91a1a}-0.37\%$
test_stacked_getitem	36.6720μs	5.7289μs	174.5530 KOps/s	172.4516 KOps/s	$\color{#35bf28}+1.22\%$
test_lock_nested	3.0757ms	0.4277ms	2.3381 KOps/s	2.3483 KOps/s	$\color{#d91a1a}-0.44\%$
test_lock_stack_nested	0.4255ms	0.3934ms	2.5421 KOps/s	2.5197 KOps/s	$\color{#35bf28}+0.89\%$
test_unlock_nested	0.7641ms	0.3653ms	2.7377 KOps/s	2.7483 KOps/s	$\color{#d91a1a}-0.38\%$
test_unlock_stack_nested	0.4449ms	0.3318ms	3.0138 KOps/s	2.9960 KOps/s	$\color{#35bf28}+0.59\%$
test_flatten_speed	0.2076ms	76.7762μs	13.0249 KOps/s	12.9133 KOps/s	$\color{#35bf28}+0.86\%$
test_unflatten_speed	0.3821ms	0.3178ms	3.1467 KOps/s	3.1581 KOps/s	$\color{#d91a1a}-0.36\%$
test_common_ops	1.5973ms	1.3003ms	769.0390 Ops/s	786.6347 Ops/s	$\color{#d91a1a}-2.24\%$
test_creation	30.1110μs	1.4738μs	678.5006 KOps/s	666.8863 KOps/s	$\color{#35bf28}+1.74\%$
test_creation_empty	48.5620μs	13.7053μs	72.9643 KOps/s	57.8129 KOps/s	$\textbf{\color{#35bf28}+26.21\%}$
test_creation_nested_1	38.7610μs	15.3413μs	65.1833 KOps/s	52.2257 KOps/s	$\textbf{\color{#35bf28}+24.81\%}$
test_creation_nested_2	0.2021ms	17.9253μs	55.7871 KOps/s	45.6581 KOps/s	$\textbf{\color{#35bf28}+22.18\%}$
test_clone	0.2230ms	29.5049μs	33.8926 KOps/s	35.2483 KOps/s	$\color{#d91a1a}-3.85\%$
test_getitem[int]	1.3176ms	16.9135μs	59.1244 KOps/s	60.1410 KOps/s	$\color{#d91a1a}-1.69\%$
test_getitem[slice_int]	0.1308ms	29.1526μs	34.3023 KOps/s	34.6980 KOps/s	$\color{#d91a1a}-1.14\%$
test_getitem[range]	0.1527ms	0.1137ms	8.7961 KOps/s	8.6547 KOps/s	$\color{#35bf28}+1.63\%$
test_getitem[tuple]	0.1550ms	25.1521μs	39.7581 KOps/s	40.0709 KOps/s	$\color{#d91a1a}-0.78\%$
test_getitem[list]	0.2835ms	0.1044ms	9.5776 KOps/s	9.6809 KOps/s	$\color{#d91a1a}-1.07\%$
test_setitem_dim[int]	0.1294ms	45.9186μs	21.7776 KOps/s	22.0786 KOps/s	$\color{#d91a1a}-1.36\%$
test_setitem_dim[slice_int]	0.2440ms	71.0050μs	14.0835 KOps/s	14.8738 KOps/s	$\textbf{\color{#d91a1a}-5.31\%}$
test_setitem_dim[range]	0.2840ms	0.1371ms	7.2942 KOps/s	7.6920 KOps/s	$\textbf{\color{#d91a1a}-5.17\%}$
test_setitem_dim[tuple]	0.1967ms	65.6416μs	15.2342 KOps/s	16.3344 KOps/s	$\textbf{\color{#d91a1a}-6.74\%}$
test_setitem	0.2196ms	45.0523μs	22.1964 KOps/s	24.1783 KOps/s	$\textbf{\color{#d91a1a}-8.20\%}$
test_set	0.1891ms	43.4741μs	23.0022 KOps/s	24.5440 KOps/s	$\textbf{\color{#d91a1a}-6.28\%}$
test_set_shared	0.3534ms	54.9851μs	18.1867 KOps/s	19.2498 KOps/s	$\textbf{\color{#d91a1a}-5.52\%}$
test_update	0.2406ms	50.6948μs	19.7259 KOps/s	19.5764 KOps/s	$\color{#35bf28}+0.76\%$
test_update_nested	0.2161ms	58.5464μs	17.0805 KOps/s	17.2219 KOps/s	$\color{#d91a1a}-0.82\%$
test_update__nested	0.1916ms	63.5019μs	15.7476 KOps/s	16.0669 KOps/s	$\color{#d91a1a}-1.99\%$
test_set_nested	0.1934ms	43.1788μs	23.1595 KOps/s	22.4823 KOps/s	$\color{#35bf28}+3.01\%$
test_set_nested_new	0.2015ms	46.5000μs	21.5054 KOps/s	21.0329 KOps/s	$\color{#35bf28}+2.25\%$
test_select	0.2701ms	62.8936μs	15.8999 KOps/s	16.4481 KOps/s	$\color{#d91a1a}-3.33\%$
test_select_nested	63.1830μs	42.8078μs	23.3603 KOps/s	23.6891 KOps/s	$\color{#d91a1a}-1.39\%$
test_exclude_nested	0.1064ms	60.2437μs	16.5993 KOps/s	16.8079 KOps/s	$\color{#d91a1a}-1.24\%$
test_empty[True]	0.3201ms	0.2545ms	3.9292 KOps/s	3.9310 KOps/s	$\color{#d91a1a}-0.05\%$
test_empty[False]	3.7952μs	0.7452μs	1.3419 MOps/s	1.3250 MOps/s	$\color{#35bf28}+1.28\%$
test_to	54.2820μs	25.2429μs	39.6152 KOps/s	38.4432 KOps/s	$\color{#35bf28}+3.05\%$
test_to_nonblocking	0.1468ms	25.6469μs	38.9911 KOps/s	39.8736 KOps/s	$\color{#d91a1a}-2.21\%$
test_unbind_speed	0.3263ms	0.2764ms	3.6177 KOps/s	3.5419 KOps/s	$\color{#35bf28}+2.14\%$
test_unbind_speed_stack0	0.3881ms	0.2754ms	3.6314 KOps/s	3.5863 KOps/s	$\color{#35bf28}+1.26\%$
test_unbind_speed_stack1	92.2914ms	0.7050ms	1.4184 KOps/s	1.4114 KOps/s	$\color{#35bf28}+0.50\%$
test_split	97.0081ms	2.2469ms	445.0510 Ops/s	447.7308 Ops/s	$\color{#d91a1a}-0.60\%$
test_chunk	96.9768ms	2.2372ms	446.9858 Ops/s	447.9506 Ops/s	$\color{#d91a1a}-0.22\%$
test_to[False]	3.6479ms	3.4290ms	291.6294 Ops/s	293.7832 Ops/s	$\color{#d91a1a}-0.73\%$
test_to[True]	4.8360ms	4.4760ms	223.4147 Ops/s	224.5444 Ops/s	$\color{#d91a1a}-0.50\%$
test_to_njt[False]	0.3362s	0.2545s	3.9298 Ops/s	3.9031 Ops/s	$\color{#35bf28}+0.69\%$
test_to_njt[True]	0.3644s	0.2821s	3.5442 Ops/s	3.7646 Ops/s	$\textbf{\color{#d91a1a}-5.85\%}$
test_creation[device0]	0.3862ms	0.1294ms	7.7268 KOps/s	7.7018 KOps/s	$\color{#35bf28}+0.32\%$
test_creation_from_tensor	0.3459ms	0.1307ms	7.6493 KOps/s	7.6267 KOps/s	$\color{#35bf28}+0.30\%$
test_add_one[memmap_tensor0]	0.1780ms	9.1570μs	109.2060 KOps/s	108.3935 KOps/s	$\color{#35bf28}+0.75\%$
test_contiguous[memmap_tensor0]	48.7520μs	2.1973μs	455.1126 KOps/s	445.9453 KOps/s	$\color{#35bf28}+2.06\%$
test_stack[memmap_tensor0]	0.1618ms	7.0901μs	141.0416 KOps/s	140.0040 KOps/s	$\color{#35bf28}+0.74\%$
test_memmaptd_index	1.2337ms	0.4485ms	2.2298 KOps/s	2.2437 KOps/s	$\color{#d91a1a}-0.62\%$
test_memmaptd_index_astensor	0.8379ms	0.5145ms	1.9438 KOps/s	1.9467 KOps/s	$\color{#d91a1a}-0.15\%$
test_memmaptd_index_op	1.4161ms	1.0186ms	981.7077 Ops/s	917.0062 Ops/s	$\textbf{\color{#35bf28}+7.06\%}$
test_serialize_model	0.1325s	0.1312s	7.6215 Ops/s	7.6877 Ops/s	$\color{#d91a1a}-0.86\%$
test_serialize_model_pickle	1.3494s	1.1896s	0.8406 Ops/s	0.8406 Ops/s	$+0.00\%$
test_serialize_weights	0.1318s	0.1307s	7.6507 Ops/s	7.7107 Ops/s	$\color{#d91a1a}-0.78\%$
test_serialize_weights_returnearly	0.2488s	63.3641ms	15.7818 Ops/s	17.4167 Ops/s	$\textbf{\color{#d91a1a}-9.39\%}$
test_serialize_weights_pickle	1.3563s	1.1950s	0.8368 Ops/s	0.8386 Ops/s	$\color{#d91a1a}-0.20\%$
test_reshape_pytree	0.1713ms	36.0762μs	27.7191 KOps/s	27.4854 KOps/s	$\color{#35bf28}+0.85\%$
test_reshape_td	0.1522ms	41.1270μs	24.3149 KOps/s	25.0910 KOps/s	$\color{#d91a1a}-3.09\%$
test_view_pytree	0.4154ms	36.0455μs	27.7427 KOps/s	28.1493 KOps/s	$\color{#d91a1a}-1.44\%$
test_view_td	0.4443ms	45.0787μs	22.1834 KOps/s	22.0744 KOps/s	$\color{#35bf28}+0.49\%$
test_unbind_pytree	99.7140μs	35.2835μs	28.3418 KOps/s	28.7105 KOps/s	$\color{#d91a1a}-1.28\%$
test_unbind_td	0.5152ms	41.9081μs	23.8618 KOps/s	23.8499 KOps/s	$\color{#35bf28}+0.05\%$
test_split_pytree	0.1375ms	45.1970μs	22.1254 KOps/s	21.9955 KOps/s	$\color{#35bf28}+0.59\%$
test_split_td	0.6822ms	56.4657μs	17.7099 KOps/s	15.3319 KOps/s	$\textbf{\color{#35bf28}+15.51\%}$
test_add_pytree	0.2038ms	56.7578μs	17.6187 KOps/s	17.7956 KOps/s	$\color{#d91a1a}-0.99\%$
test_add_td	0.4734ms	88.2053μs	11.3372 KOps/s	10.6951 KOps/s	$\textbf{\color{#35bf28}+6.00\%}$
test_compile_add_one_nested[tensordict-compile]	0.3232ms	0.1607ms	6.2222 KOps/s	6.1129 KOps/s	$\color{#35bf28}+1.79\%$
test_compile_add_one_nested[tensordict-eager]	0.3160ms	0.1611ms	6.2074 KOps/s	6.2188 KOps/s	$\color{#d91a1a}-0.18\%$
test_compile_add_one_nested[pytree-compile]	0.3364ms	0.1540ms	6.4940 KOps/s	6.2833 KOps/s	$\color{#35bf28}+3.35\%$
test_compile_add_one_nested[pytree-eager]	0.3623ms	0.1838ms	5.4414 KOps/s	5.4192 KOps/s	$\color{#35bf28}+0.41\%$
test_compile_copy_nested[tensordict-compile]	0.2185ms	20.6400μs	48.4496 KOps/s	47.3058 KOps/s	$\color{#35bf28}+2.42\%$
test_compile_copy_nested[tensordict-eager]	0.1129ms	48.6021μs	20.5752 KOps/s	20.8985 KOps/s	$\color{#d91a1a}-1.55\%$
test_compile_copy_nested[pytree-compile]	0.3309ms	66.3979μs	15.0607 KOps/s	15.2322 KOps/s	$\color{#d91a1a}-1.13\%$
test_compile_copy_nested[pytree-eager]	85.3430μs	50.1262μs	19.9496 KOps/s	19.9321 KOps/s	$\color{#35bf28}+0.09\%$
test_compile_add_one_flat[tensordict-compile]	0.4354ms	0.3181ms	3.1432 KOps/s	3.1036 KOps/s	$\color{#35bf28}+1.27\%$
test_compile_add_one_flat[tensordict-eager]	0.3831ms	0.2355ms	4.2467 KOps/s	4.2694 KOps/s	$\color{#d91a1a}-0.53\%$
test_compile_add_one_flat[tensorclass-compile]	0.3369ms	0.1278ms	7.8234 KOps/s	7.7372 KOps/s	$\color{#35bf28}+1.11\%$
test_compile_add_one_flat[tensorclass-eager]	0.2478ms	64.7993μs	15.4323 KOps/s	15.4954 KOps/s	$\color{#d91a1a}-0.41\%$
test_compile_add_one_flat[pytree-compile]	0.4565ms	0.3245ms	3.0815 KOps/s	3.0402 KOps/s	$\color{#35bf28}+1.36\%$
test_compile_add_one_flat[pytree-eager]	0.7944ms	0.6183ms	1.6174 KOps/s	1.6131 KOps/s	$\color{#35bf28}+0.27\%$
test_compile_add_self_flat[tensordict-eager]	0.7259ms	0.2863ms	3.4925 KOps/s	3.5270 KOps/s	$\color{#d91a1a}-0.98\%$
test_compile_add_self_flat[tensordict-compile]	0.4242ms	0.3258ms	3.0691 KOps/s	3.0772 KOps/s	$\color{#d91a1a}-0.26\%$
test_compile_add_self_flat[tensorclass-eager]	0.4933ms	78.2379μs	12.7815 KOps/s	12.9451 KOps/s	$\color{#d91a1a}-1.26\%$
test_compile_add_self_flat[tensorclass-compile]	0.5366ms	0.1326ms	7.5394 KOps/s	7.7018 KOps/s	$\color{#d91a1a}-2.11\%$
test_compile_add_self_flat[pytree-eager]	0.9157ms	0.5363ms	1.8648 KOps/s	1.8915 KOps/s	$\color{#d91a1a}-1.41\%$
test_compile_add_self_flat[pytree-compile]	0.4547ms	0.3314ms	3.0178 KOps/s	3.0275 KOps/s	$\color{#d91a1a}-0.32\%$
test_compile_copy_flat[tensordict-compile]	0.4132ms	18.6343μs	53.6646 KOps/s	51.1831 KOps/s	$\color{#35bf28}+4.85\%$
test_compile_copy_flat[tensordict-eager]	0.4260ms	39.5028μs	25.3147 KOps/s	25.6537 KOps/s	$\color{#d91a1a}-1.32\%$
test_compile_copy_flat[pytree-compile]	0.4596ms	71.3130μs	14.0227 KOps/s	14.3621 KOps/s	$\color{#d91a1a}-2.36\%$
test_compile_copy_flat[pytree-eager]	0.1847ms	51.0046μs	19.6061 KOps/s	19.5009 KOps/s	$\color{#35bf28}+0.54\%$
test_compile_assign_and_add[tensordict-compile]	2.3725ms	0.8224ms	1.2159 KOps/s	1.1104 KOps/s	$\textbf{\color{#35bf28}+9.50\%}$
test_compile_assign_and_add[tensordict-eager]	3.5006ms	3.1629ms	316.1633 Ops/s	310.1779 Ops/s	$\color{#35bf28}+1.93\%$
test_compile_assign_and_add[pytree-compile]	2.4445ms	0.8455ms	1.1827 KOps/s	1.0274 KOps/s	$\textbf{\color{#35bf28}+15.12\%}$
test_compile_assign_and_add[pytree-eager]	3.6032ms	3.2657ms	306.2106 Ops/s	311.1345 Ops/s	$\color{#d91a1a}-1.58\%$
test_compile_indexing[tensor-tensordict-compile]	0.2889ms	0.1200ms	8.3328 KOps/s	8.3937 KOps/s	$\color{#d91a1a}-0.73\%$
test_compile_indexing[tensor-tensordict-eager]	0.2216ms	64.5154μs	15.5002 KOps/s	16.0292 KOps/s	$\color{#d91a1a}-3.30\%$
test_compile_indexing[tensor-tensorclass-compile]	0.2694ms	0.1149ms	8.7044 KOps/s	8.7784 KOps/s	$\color{#d91a1a}-0.84\%$
test_compile_indexing[tensor-tensorclass-eager]	0.1975ms	43.5857μs	22.9433 KOps/s	23.6099 KOps/s	$\color{#d91a1a}-2.82\%$
test_compile_indexing[tensor-pytree-compile]	0.2718ms	0.1187ms	8.4280 KOps/s	8.6789 KOps/s	$\color{#d91a1a}-2.89\%$
test_compile_indexing[tensor-pytree-eager]	0.2070ms	43.1841μs	23.1567 KOps/s	23.8046 KOps/s	$\color{#d91a1a}-2.72\%$
test_compile_indexing[slice-tensordict-compile]	0.3440ms	0.1497ms	6.6809 KOps/s	6.7489 KOps/s	$\color{#d91a1a}-1.01\%$
test_compile_indexing[slice-tensordict-eager]	0.2107ms	26.8515μs	37.2418 KOps/s	38.4628 KOps/s	$\color{#d91a1a}-3.17\%$
test_compile_indexing[slice-tensorclass-compile]	0.3408ms	0.1458ms	6.8572 KOps/s	6.9782 KOps/s	$\color{#d91a1a}-1.73\%$
test_compile_indexing[slice-tensorclass-eager]	0.1532ms	21.1239μs	47.3398 KOps/s	47.8995 KOps/s	$\color{#d91a1a}-1.17\%$
test_compile_indexing[slice-pytree-compile]	0.3221ms	0.1490ms	6.7103 KOps/s	6.9466 KOps/s	$\color{#d91a1a}-3.40\%$
test_compile_indexing[slice-pytree-eager]	72.4530μs	20.9488μs	47.7354 KOps/s	47.2359 KOps/s	$\color{#35bf28}+1.06\%$
test_compile_indexing[int-tensordict-compile]	0.3039ms	0.1540ms	6.4950 KOps/s	6.5742 KOps/s	$\color{#d91a1a}-1.20\%$
test_compile_indexing[int-tensordict-eager]	0.4571ms	27.2079μs	36.7541 KOps/s	38.1884 KOps/s	$\color{#d91a1a}-3.76\%$
test_compile_indexing[int-tensorclass-compile]	0.2869ms	0.1446ms	6.9166 KOps/s	6.8813 KOps/s	$\color{#35bf28}+0.51\%$
test_compile_indexing[int-tensorclass-eager]	0.2011ms	21.0318μs	47.5470 KOps/s	46.9874 KOps/s	$\color{#35bf28}+1.19\%$
test_compile_indexing[int-pytree-compile]	0.3081ms	0.1470ms	6.8027 KOps/s	6.8894 KOps/s	$\color{#d91a1a}-1.26\%$
test_compile_indexing[int-pytree-eager]	0.1309ms	21.1120μs	47.3664 KOps/s	47.3113 KOps/s	$\color{#35bf28}+0.12\%$
test_mod_add[eager]	0.1736ms	30.6863μs	32.5878 KOps/s	31.3462 KOps/s	$\color{#35bf28}+3.96\%$
test_mod_add[compile]	0.2302ms	81.3044μs	12.2995 KOps/s	11.9226 KOps/s	$\color{#35bf28}+3.16\%$
test_mod_add[compile-overhead]	0.3181ms	0.1535ms	6.5130 KOps/s	5.9049 KOps/s	$\textbf{\color{#35bf28}+10.30\%}$
test_mod_wrap[eager]	0.4177ms	0.2494ms	4.0099 KOps/s	4.0307 KOps/s	$\color{#d91a1a}-0.52\%$
test_mod_wrap[compile]	0.4622ms	0.3037ms	3.2930 KOps/s	3.2959 KOps/s	$\color{#d91a1a}-0.09\%$
test_mod_wrap[compile-overhead]	7.8179ms	4.1551ms	240.6663 Ops/s	231.4114 Ops/s	$\color{#35bf28}+4.00\%$
test_mod_wrap_and_backward[eager]	1.8484ms	1.4453ms	691.9018 Ops/s	667.6841 Ops/s	$\color{#35bf28}+3.63\%$
test_mod_wrap_and_backward[compile]	1.7579ms	1.4412ms	693.8468 Ops/s	676.7680 Ops/s	$\color{#35bf28}+2.52\%$
test_mod_wrap_and_backward[compile-overhead]	1.5851ms	1.0337ms	967.3749 Ops/s	953.7849 Ops/s	$\color{#35bf28}+1.42\%$
test_seq_add[eager]	0.2420ms	94.0083μs	10.6374 KOps/s	9.8631 KOps/s	$\textbf{\color{#35bf28}+7.85\%}$
test_seq_add[compile]	0.2648ms	90.4355μs	11.0576 KOps/s	10.7143 KOps/s	$\color{#35bf28}+3.20\%$
test_seq_add[compile-overhead]	0.2591ms	0.1250ms	7.9980 KOps/s	7.7500 KOps/s	$\color{#35bf28}+3.20\%$
test_seq_wrap[eager]	0.5368ms	0.3745ms	2.6705 KOps/s	2.5297 KOps/s	$\textbf{\color{#35bf28}+5.57\%}$
test_seq_wrap[compile]	0.4814ms	0.3134ms	3.1907 KOps/s	3.1029 KOps/s	$\color{#35bf28}+2.83\%$
test_seq_wrap[compile-overhead]	0.3409ms	0.2219ms	4.5056 KOps/s	4.3817 KOps/s	$\color{#35bf28}+2.83\%$
test_func_call_runtime[False-eager]	0.9124ms	0.7384ms	1.3543 KOps/s	1.3320 KOps/s	$\color{#35bf28}+1.68\%$
test_func_call_runtime[False-compile]	0.9483ms	0.7890ms	1.2674 KOps/s	1.2330 KOps/s	$\color{#35bf28}+2.79\%$
test_func_call_runtime[False-compile-overhead]	0.5430ms	0.3616ms	2.7655 KOps/s	2.7149 KOps/s	$\color{#35bf28}+1.86\%$
test_func_call_runtime[True-eager]	1.0442ms	0.8923ms	1.1207 KOps/s	1.0880 KOps/s	$\color{#35bf28}+3.00\%$
test_func_call_runtime[True-compile]	0.9621ms	0.8053ms	1.2417 KOps/s	1.1996 KOps/s	$\color{#35bf28}+3.51\%$
test_func_call_runtime[True-compile-overhead]	0.5136ms	0.3821ms	2.6172 KOps/s	2.6024 KOps/s	$\color{#35bf28}+0.57\%$
test_func_call_cm_runtime[False-eager]	0.9240ms	0.7331ms	1.3641 KOps/s	1.3677 KOps/s	$\color{#d91a1a}-0.26\%$
test_func_call_cm_runtime[False-compile]	0.9806ms	0.7922ms	1.2622 KOps/s	1.2530 KOps/s	$\color{#35bf28}+0.74\%$
test_func_call_cm_runtime[False-compile-overhead]	0.5058ms	0.3642ms	2.7459 KOps/s	2.7574 KOps/s	$\color{#d91a1a}-0.41\%$
test_func_call_cm_runtime[True-eager]	1.1814ms	1.0066ms	993.4325 Ops/s	985.8510 Ops/s	$\color{#35bf28}+0.77\%$
test_func_call_cm_runtime[True-compile]	1.0117ms	0.8407ms	1.1895 KOps/s	1.1810 KOps/s	$\color{#35bf28}+0.72\%$
test_func_call_cm_runtime[True-compile-overhead]	0.5926ms	0.4079ms	2.4517 KOps/s	2.4244 KOps/s	$\color{#35bf28}+1.12\%$
test_vmap_func_call_cm_runtime[eager]	2.5904ms	2.1191ms	471.8947 Ops/s	474.0683 Ops/s	$\color{#d91a1a}-0.46\%$
test_vmap_func_call_cm_runtime[compile]	1.0013ms	0.8543ms	1.1705 KOps/s	1.1672 KOps/s	$\color{#35bf28}+0.28\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.5555ms	0.4115ms	2.4302 KOps/s	2.4171 KOps/s	$\color{#35bf28}+0.54\%$
test_distributed	4.4568ms	0.2111ms	4.7372 KOps/s	8.6453 KOps/s	$\textbf{\color{#d91a1a}-45.20\%}$
test_tdmodule	0.2732ms	13.6145μs	73.4513 KOps/s	64.3387 KOps/s	$\textbf{\color{#35bf28}+14.16\%}$
test_tdmodule_dispatch	49.4020μs	26.2735μs	38.0612 KOps/s	31.9734 KOps/s	$\textbf{\color{#35bf28}+19.04\%}$
test_tdseq	36.7420μs	14.6519μs	68.2506 KOps/s	59.4697 KOps/s	$\textbf{\color{#35bf28}+14.77\%}$
test_tdseq_dispatch	49.5310μs	29.0501μs	34.4233 KOps/s	28.9674 KOps/s	$\textbf{\color{#35bf28}+18.83\%}$
test_instantiation_functorch	2.0404ms	1.8479ms	541.1586 Ops/s	539.9477 Ops/s	$\color{#35bf28}+0.22\%$
test_exec_functorch	0.3608ms	0.2084ms	4.7984 KOps/s	4.8292 KOps/s	$\color{#d91a1a}-0.64\%$
test_exec_functional_call	0.3914ms	0.2127ms	4.7006 KOps/s	4.7835 KOps/s	$\color{#d91a1a}-1.73\%$
test_exec_td_decorator	0.4269ms	0.2596ms	3.8525 KOps/s	3.8421 KOps/s	$\color{#35bf28}+0.27\%$
test_vmap_mlp_speed_decorator[True-True]	0.8436ms	0.6799ms	1.4709 KOps/s	1.4278 KOps/s	$\color{#35bf28}+3.02\%$
test_vmap_mlp_speed_decorator[True-False]	0.8272ms	0.6809ms	1.4687 KOps/s	1.4303 KOps/s	$\color{#35bf28}+2.68\%$
test_vmap_mlp_speed_decorator[False-True]	0.7822ms	0.6036ms	1.6568 KOps/s	1.6266 KOps/s	$\color{#35bf28}+1.85\%$
test_vmap_mlp_speed_decorator[False-False]	0.7694ms	0.6062ms	1.6497 KOps/s	1.6260 KOps/s	$\color{#35bf28}+1.45\%$
test_vmap_transformer_speed_decorator[True-True]	19.9795ms	19.7426ms	50.6518 Ops/s	50.0874 Ops/s	$\color{#35bf28}+1.13\%$
test_vmap_transformer_speed_decorator[True-False]	20.0210ms	19.7240ms	50.6997 Ops/s	50.0186 Ops/s	$\color{#35bf28}+1.36\%$
test_vmap_transformer_speed_decorator[False-True]	19.9837ms	19.6440ms	50.9061 Ops/s	50.4895 Ops/s	$\color{#35bf28}+0.83\%$
test_vmap_transformer_speed_decorator[False-False]	19.9457ms	19.6407ms	50.9148 Ops/s	50.4533 Ops/s	$\color{#35bf28}+0.91\%$
test_to_module_speed[True]	1.4305ms	0.9857ms	1.0145 KOps/s	1.0084 KOps/s	$\color{#35bf28}+0.61\%$
test_to_module_speed[False]	1.3882ms	0.9665ms	1.0347 KOps/s	1.0285 KOps/s	$\color{#35bf28}+0.60\%$
test_tc_init	85.9940μs	32.7452μs	30.5388 KOps/s	26.8656 KOps/s	$\textbf{\color{#35bf28}+13.67\%}$
test_tc_init_nested	0.1000ms	66.4162μs	15.0566 KOps/s	12.7091 KOps/s	$\textbf{\color{#35bf28}+18.47\%}$
test_tc_first_layer_tensor	4.2601μs	0.6996μs	1.4294 MOps/s	1.3811 MOps/s	$\color{#35bf28}+3.50\%$
test_tc_first_layer_nontensor	21.3410μs	2.3205μs	430.9356 KOps/s	434.1369 KOps/s	$\color{#d91a1a}-0.74\%$
test_tc_second_layer_tensor	9.1953μs	1.4289μs	699.8390 KOps/s	663.6834 KOps/s	$\textbf{\color{#35bf28}+5.45\%}$
test_tc_second_layer_nontensor	29.0210μs	3.0678μs	325.9692 KOps/s	332.4894 KOps/s	$\color{#d91a1a}-1.96\%$
test_unbind	0.1954s	9.4629ms	105.6764 Ops/s	87.4656 Ops/s	$\textbf{\color{#35bf28}+20.82\%}$
test_full_like	0.7895ms	0.5743ms	1.7414 KOps/s	1.7357 KOps/s	$\color{#35bf28}+0.33\%$
test_zeros_like	0.4022ms	0.1984ms	5.0402 KOps/s	5.0520 KOps/s	$\color{#d91a1a}-0.23\%$
test_ones_like	0.3757ms	0.1981ms	5.0487 KOps/s	5.0524 KOps/s	$\color{#d91a1a}-0.07\%$
test_clone	0.5602ms	0.4152ms	2.4083 KOps/s	2.4144 KOps/s	$\color{#d91a1a}-0.25\%$
test_squeeze	0.1194ms	9.5768μs	104.4186 KOps/s	101.6772 KOps/s	$\color{#35bf28}+2.70\%$
test_unsqueeze	0.2575ms	75.2091μs	13.2963 KOps/s	13.7013 KOps/s	$\color{#d91a1a}-2.96\%$
test_split	0.1800s	0.2041ms	4.8998 KOps/s	6.1254 KOps/s	$\textbf{\color{#d91a1a}-20.01\%}$
test_permute	0.3181ms	0.1868ms	5.3539 KOps/s	5.6576 KOps/s	$\textbf{\color{#d91a1a}-5.37\%}$
test_stack	1.3563ms	0.8429ms	1.1864 KOps/s	1.1811 KOps/s	$\color{#35bf28}+0.45\%$
test_cat	1.3808ms	1.2320ms	811.6713 Ops/s	811.7781 Ops/s	$\color{#d91a1a}-0.01\%$