[Doc] Refactor README and add GETTING_STARTED.md

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 219. Improved: $\large\color{#35bf28}49$. Worsened: $\large\color{#d91a1a}15$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	41.7570μs	21.0089μs	47.5990 KOps/s	46.0472 KOps/s	$\color{#35bf28}+3.37\%$
test_plain_set_stack_nested	87.7130μs	20.9159μs	47.8104 KOps/s	45.4024 KOps/s	$\textbf{\color{#35bf28}+5.30\%}$
test_plain_set_nested_inplace	69.8790μs	22.5150μs	44.4148 KOps/s	41.5126 KOps/s	$\textbf{\color{#35bf28}+6.99\%}$
test_plain_set_stack_nested_inplace	0.1744ms	22.7979μs	43.8637 KOps/s	41.7856 KOps/s	$\color{#35bf28}+4.97\%$
test_items	18.2940μs	2.7665μs	361.4738 KOps/s	379.6571 KOps/s	$\color{#d91a1a}-4.79\%$
test_items_nested	2.2101ms	0.3373ms	2.9650 KOps/s	2.8995 KOps/s	$\color{#35bf28}+2.26\%$
test_items_nested_locked	0.7276ms	0.3347ms	2.9875 KOps/s	2.8679 KOps/s	$\color{#35bf28}+4.17\%$
test_items_nested_leaf	0.1593ms	85.2780μs	11.7264 KOps/s	11.9219 KOps/s	$\color{#d91a1a}-1.64\%$
test_items_stack_nested	0.5351ms	0.3386ms	2.9534 KOps/s	2.9272 KOps/s	$\color{#35bf28}+0.89\%$
test_items_stack_nested_leaf	0.1624ms	85.5231μs	11.6927 KOps/s	11.8386 KOps/s	$\color{#d91a1a}-1.23\%$
test_items_stack_nested_locked	0.5613ms	0.3379ms	2.9595 KOps/s	2.9187 KOps/s	$\color{#35bf28}+1.40\%$
test_keys	85.2880μs	4.0211μs	248.6862 KOps/s	249.2284 KOps/s	$\color{#d91a1a}-0.22\%$
test_keys_nested	0.2858ms	0.1485ms	6.7361 KOps/s	6.9487 KOps/s	$\color{#d91a1a}-3.06\%$
test_keys_nested_locked	0.7730ms	0.1535ms	6.5142 KOps/s	6.7014 KOps/s	$\color{#d91a1a}-2.79\%$
test_keys_nested_leaf	0.2246ms	0.1264ms	7.9098 KOps/s	8.0437 KOps/s	$\color{#d91a1a}-1.66\%$
test_keys_stack_nested	0.2479ms	0.1483ms	6.7431 KOps/s	6.9304 KOps/s	$\color{#d91a1a}-2.70\%$
test_keys_stack_nested_leaf	0.2135ms	0.1253ms	7.9831 KOps/s	8.1375 KOps/s	$\color{#d91a1a}-1.90\%$
test_keys_stack_nested_locked	0.2861ms	0.1534ms	6.5179 KOps/s	6.7158 KOps/s	$\color{#d91a1a}-2.95\%$
test_values	7.2660μs	1.1625μs	860.1933 KOps/s	863.5963 KOps/s	$\color{#d91a1a}-0.39\%$
test_values_nested	0.1115ms	51.6787μs	19.3503 KOps/s	19.7878 KOps/s	$\color{#d91a1a}-2.21\%$
test_values_nested_locked	0.1131ms	51.7553μs	19.3217 KOps/s	19.6924 KOps/s	$\color{#d91a1a}-1.88\%$
test_values_nested_leaf	82.4530μs	46.4232μs	21.5410 KOps/s	21.9337 KOps/s	$\color{#d91a1a}-1.79\%$
test_values_stack_nested	0.1005ms	52.7748μs	18.9484 KOps/s	19.4349 KOps/s	$\color{#d91a1a}-2.50\%$
test_values_stack_nested_leaf	92.5220μs	46.1306μs	21.6776 KOps/s	21.9362 KOps/s	$\color{#d91a1a}-1.18\%$
test_values_stack_nested_locked	0.1009ms	52.3765μs	19.0925 KOps/s	19.3985 KOps/s	$\color{#d91a1a}-1.58\%$
test_membership	13.9460μs	0.9103μs	1.0986 MOps/s	1.1085 MOps/s	$\color{#d91a1a}-0.90\%$
test_membership_nested	32.5410μs	2.5935μs	385.5863 KOps/s	384.1627 KOps/s	$\color{#35bf28}+0.37\%$
test_membership_nested_leaf	24.4960μs	2.6016μs	384.3743 KOps/s	381.0226 KOps/s	$\color{#35bf28}+0.88\%$
test_membership_stacked_nested	14.8670μs	2.6103μs	383.0980 KOps/s	386.1694 KOps/s	$\color{#d91a1a}-0.80\%$
test_membership_stacked_nested_leaf	24.4760μs	2.6199μs	381.6868 KOps/s	381.5614 KOps/s	$\color{#35bf28}+0.03\%$
test_membership_nested_last	22.1410μs	4.0597μs	246.3235 KOps/s	255.1281 KOps/s	$\color{#d91a1a}-3.45\%$
test_membership_nested_leaf_last	29.0940μs	4.0879μs	244.6215 KOps/s	254.7181 KOps/s	$\color{#d91a1a}-3.96\%$
test_membership_stacked_nested_last	40.0840μs	10.1315μs	98.7021 KOps/s	253.5154 KOps/s	$\textbf{\color{#d91a1a}-61.07\%}$
test_membership_stacked_nested_leaf_last	37.0890μs	10.3241μs	96.8607 KOps/s	254.6078 KOps/s	$\textbf{\color{#d91a1a}-61.96\%}$
test_nested_getleaf	35.0850μs	10.6713μs	93.7094 KOps/s	94.5559 KOps/s	$\color{#d91a1a}-0.90\%$
test_nested_get	39.2930μs	9.9504μs	100.4982 KOps/s	99.0310 KOps/s	$\color{#35bf28}+1.48\%$
test_stacked_getleaf	32.9310μs	10.5405μs	94.8719 KOps/s	93.6451 KOps/s	$\color{#35bf28}+1.31\%$
test_stacked_get	37.0890μs	10.0050μs	99.9505 KOps/s	99.1876 KOps/s	$\color{#35bf28}+0.77\%$
test_nested_getitemleaf	34.5440μs	11.0335μs	90.6332 KOps/s	90.9504 KOps/s	$\color{#d91a1a}-0.35\%$
test_nested_getitem	34.8740μs	10.1631μs	98.3953 KOps/s	97.1085 KOps/s	$\color{#35bf28}+1.33\%$
test_stacked_getitemleaf	41.3070μs	11.0293μs	90.6677 KOps/s	84.6354 KOps/s	$\textbf{\color{#35bf28}+7.13\%}$
test_stacked_getitem	37.6000μs	10.2111μs	97.9322 KOps/s	99.4285 KOps/s	$\color{#d91a1a}-1.50\%$
test_lock_nested	93.9347ms	0.6074ms	1.6463 KOps/s	1.9890 KOps/s	$\textbf{\color{#d91a1a}-17.23\%}$
test_lock_stack_nested	0.9850ms	0.4668ms	2.1424 KOps/s	2.1170 KOps/s	$\color{#35bf28}+1.20\%$
test_unlock_nested	89.6095ms	0.5150ms	1.9419 KOps/s	2.3974 KOps/s	$\textbf{\color{#d91a1a}-19.00\%}$
test_unlock_stack_nested	0.6624ms	0.3759ms	2.6603 KOps/s	2.5850 KOps/s	$\color{#35bf28}+2.91\%$
test_flatten_speed	0.3024ms	0.1063ms	9.4089 KOps/s	9.6266 KOps/s	$\color{#d91a1a}-2.26\%$
test_unflatten_speed	0.7576ms	0.4345ms	2.3012 KOps/s	2.2619 KOps/s	$\color{#35bf28}+1.74\%$
test_common_ops	5.3939ms	1.0566ms	946.4623 Ops/s	915.1459 Ops/s	$\color{#35bf28}+3.42\%$
test_creation	22.8320μs	2.2273μs	448.9809 KOps/s	483.9152 KOps/s	$\textbf{\color{#d91a1a}-7.22\%}$
test_creation_empty	70.7610μs	16.4672μs	60.7267 KOps/s	56.6363 KOps/s	$\textbf{\color{#35bf28}+7.22\%}$
test_creation_nested_1	0.1872ms	19.9087μs	50.2293 KOps/s	47.0832 KOps/s	$\textbf{\color{#35bf28}+6.68\%}$
test_creation_nested_2	0.1014ms	23.6333μs	42.3132 KOps/s	39.4152 KOps/s	$\textbf{\color{#35bf28}+7.35\%}$
test_clone	58.6280μs	16.3517μs	61.1556 KOps/s	57.5967 KOps/s	$\textbf{\color{#35bf28}+6.18\%}$
test_getitem[int]	1.2857ms	16.8443μs	59.3674 KOps/s	59.5671 KOps/s	$\color{#d91a1a}-0.34\%$
test_getitem[slice_int]	0.1533ms	30.8042μs	32.4631 KOps/s	31.6547 KOps/s	$\color{#35bf28}+2.55\%$
test_getitem[range]	0.1535ms	56.3553μs	17.7446 KOps/s	17.3098 KOps/s	$\color{#35bf28}+2.51\%$
test_getitem[tuple]	0.1213ms	25.3464μs	39.4533 KOps/s	39.4787 KOps/s	$\color{#d91a1a}-0.06\%$
test_getitem[list]	0.1681ms	52.1032μs	19.1927 KOps/s	19.3045 KOps/s	$\color{#d91a1a}-0.58\%$
test_setitem_dim[int]	77.6540μs	39.3475μs	25.4146 KOps/s	23.9137 KOps/s	$\textbf{\color{#35bf28}+6.28\%}$
test_setitem_dim[slice_int]	0.1307ms	68.4296μs	14.6136 KOps/s	13.6398 KOps/s	$\textbf{\color{#35bf28}+7.14\%}$
test_setitem_dim[range]	0.1216ms	89.5726μs	11.1641 KOps/s	10.6451 KOps/s	$\color{#35bf28}+4.88\%$
test_setitem_dim[tuple]	78.0050μs	56.0221μs	17.8501 KOps/s	16.7791 KOps/s	$\textbf{\color{#35bf28}+6.38\%}$
test_setitem	85.7290μs	27.5554μs	36.2906 KOps/s	34.9820 KOps/s	$\color{#35bf28}+3.74\%$
test_set	70.7820μs	26.3857μs	37.8994 KOps/s	35.5767 KOps/s	$\textbf{\color{#35bf28}+6.53\%}$
test_set_shared	2.5280ms	0.2133ms	4.6890 KOps/s	4.6762 KOps/s	$\color{#35bf28}+0.27\%$
test_update	0.2329ms	32.8012μs	30.4867 KOps/s	28.3934 KOps/s	$\textbf{\color{#35bf28}+7.37\%}$
test_update_nested	95.3770μs	42.7250μs	23.4055 KOps/s	22.0878 KOps/s	$\textbf{\color{#35bf28}+5.97\%}$
test_update__nested	85.6490μs	33.9311μs	29.4715 KOps/s	28.7782 KOps/s	$\color{#35bf28}+2.41\%$
test_set_nested	81.3410μs	28.8626μs	34.6470 KOps/s	32.7663 KOps/s	$\textbf{\color{#35bf28}+5.74\%}$
test_set_nested_new	0.1062ms	33.9586μs	29.4477 KOps/s	28.0801 KOps/s	$\color{#35bf28}+4.87\%$
test_select	0.1117ms	50.7285μs	19.7128 KOps/s	19.0279 KOps/s	$\color{#35bf28}+3.60\%$
test_select_nested	0.1413ms	60.4661μs	16.5382 KOps/s	16.8501 KOps/s	$\color{#d91a1a}-1.85\%$
test_exclude_nested	0.1631ms	78.2602μs	12.7779 KOps/s	12.7268 KOps/s	$\color{#35bf28}+0.40\%$
test_empty[True]	0.4105ms	0.3224ms	3.1014 KOps/s	3.0788 KOps/s	$\color{#35bf28}+0.73\%$
test_empty[False]	8.8040μs	1.2947μs	772.4064 KOps/s	858.4736 KOps/s	$\textbf{\color{#d91a1a}-10.03\%}$
test_unbind_speed	0.3859ms	0.3138ms	3.1864 KOps/s	3.2868 KOps/s	$\color{#d91a1a}-3.06\%$
test_unbind_speed_stack0	0.4530ms	0.3000ms	3.3329 KOps/s	3.3040 KOps/s	$\color{#35bf28}+0.88\%$
test_unbind_speed_stack1	86.5968ms	0.7843ms	1.2751 KOps/s	1.3485 KOps/s	$\textbf{\color{#d91a1a}-5.45\%}$
test_split	83.1186ms	2.1216ms	471.3329 Ops/s	429.7214 Ops/s	$\textbf{\color{#35bf28}+9.68\%}$
test_chunk	88.0909ms	2.0937ms	477.6300 Ops/s	511.0147 Ops/s	$\textbf{\color{#d91a1a}-6.53\%}$
test_creation[device0]	0.2281ms	0.1190ms	8.4029 KOps/s	8.1436 KOps/s	$\color{#35bf28}+3.18\%$
test_creation_from_tensor	3.9487ms	0.1210ms	8.2664 KOps/s	8.3380 KOps/s	$\color{#d91a1a}-0.86\%$
test_add_one[memmap_tensor0]	0.1525ms	7.2189μs	138.5253 KOps/s	127.9073 KOps/s	$\textbf{\color{#35bf28}+8.30\%}$
test_contiguous[memmap_tensor0]	28.5430μs	2.0001μs	499.9720 KOps/s	498.6507 KOps/s	$\color{#35bf28}+0.26\%$
test_stack[memmap_tensor0]	56.0240μs	5.6935μs	175.6404 KOps/s	164.3435 KOps/s	$\textbf{\color{#35bf28}+6.87\%}$
test_memmaptd_index	1.0516ms	0.4059ms	2.4636 KOps/s	2.4211 KOps/s	$\color{#35bf28}+1.75\%$
test_memmaptd_index_astensor	0.8199ms	0.4821ms	2.0741 KOps/s	2.0310 KOps/s	$\color{#35bf28}+2.12\%$
test_memmaptd_index_op	1.3184ms	0.9796ms	1.0208 KOps/s	958.2056 Ops/s	$\textbf{\color{#35bf28}+6.53\%}$
test_serialize_model	0.1232s	0.1173s	8.5232 Ops/s	7.3741 Ops/s	$\textbf{\color{#35bf28}+15.58\%}$
test_serialize_model_pickle	0.4544s	0.3952s	2.5301 Ops/s	2.4701 Ops/s	$\color{#35bf28}+2.43\%$
test_serialize_weights	0.1246s	0.1171s	8.5421 Ops/s	8.4700 Ops/s	$\color{#35bf28}+0.85\%$
test_serialize_weights_returnearly	0.1755s	0.1579s	6.3328 Ops/s	6.4139 Ops/s	$\color{#d91a1a}-1.27\%$
test_serialize_weights_pickle	1.1080s	0.7093s	1.4097 Ops/s	1.0960 Ops/s	$\textbf{\color{#35bf28}+28.63\%}$
test_serialize_weights_filesystem	0.2268s	0.1520s	6.5788 Ops/s	6.9871 Ops/s	$\textbf{\color{#d91a1a}-5.84\%}$
test_serialize_model_filesystem	0.1558s	0.1441s	6.9382 Ops/s	6.9018 Ops/s	$\color{#35bf28}+0.53\%$
test_reshape_pytree	0.1122ms	40.6293μs	24.6128 KOps/s	24.4717 KOps/s	$\color{#35bf28}+0.58\%$
test_reshape_td	0.1728ms	46.8488μs	21.3453 KOps/s	20.9386 KOps/s	$\color{#35bf28}+1.94\%$
test_view_pytree	0.1200ms	39.7823μs	25.1368 KOps/s	24.6604 KOps/s	$\color{#35bf28}+1.93\%$
test_view_td	0.1359ms	53.1137μs	18.8275 KOps/s	18.5523 KOps/s	$\color{#35bf28}+1.48\%$
test_unbind_pytree	93.8540μs	37.2727μs	26.8293 KOps/s	26.3804 KOps/s	$\color{#35bf28}+1.70\%$
test_unbind_td	0.3704ms	46.4242μs	21.5405 KOps/s	21.6778 KOps/s	$\color{#d91a1a}-0.63\%$
test_split_pytree	88.4640μs	40.2496μs	24.8450 KOps/s	24.5959 KOps/s	$\color{#35bf28}+1.01\%$
test_split_td	0.5052ms	58.1405μs	17.1997 KOps/s	17.1290 KOps/s	$\color{#35bf28}+0.41\%$
test_add_pytree	0.1294ms	46.1563μs	21.6655 KOps/s	20.7838 KOps/s	$\color{#35bf28}+4.24\%$
test_add_td	0.1846ms	78.7418μs	12.6997 KOps/s	11.8192 KOps/s	$\textbf{\color{#35bf28}+7.45\%}$
test_compile_add_one_nested[tensordict-compile]	0.1085ms	55.2013μs	18.1155 KOps/s	18.2170 KOps/s	$\color{#d91a1a}-0.56\%$
test_compile_add_one_nested[tensordict-eager]	1.0844ms	0.1956ms	5.1122 KOps/s	4.8808 KOps/s	$\color{#35bf28}+4.74\%$
test_compile_add_one_nested[pytree-compile]	0.1208ms	54.0953μs	18.4859 KOps/s	17.9355 KOps/s	$\color{#35bf28}+3.07\%$
test_compile_add_one_nested[pytree-eager]	0.2684ms	0.1441ms	6.9418 KOps/s	6.8134 KOps/s	$\color{#35bf28}+1.89\%$
test_compile_copy_nested[tensordict-compile]	62.4860μs	21.4948μs	46.5229 KOps/s	48.6538 KOps/s	$\color{#d91a1a}-4.38\%$
test_compile_copy_nested[tensordict-eager]	0.1299ms	65.0590μs	15.3707 KOps/s	15.2523 KOps/s	$\color{#35bf28}+0.78\%$
test_compile_copy_nested[pytree-compile]	0.1610ms	79.9651μs	12.5055 KOps/s	12.3905 KOps/s	$\color{#35bf28}+0.93\%$
test_compile_copy_nested[pytree-eager]	0.1623ms	74.0619μs	13.5022 KOps/s	13.6881 KOps/s	$\color{#d91a1a}-1.36\%$
test_compile_add_one_flat[tensordict-compile]	0.3823ms	0.1773ms	5.6414 KOps/s	5.6183 KOps/s	$\color{#35bf28}+0.41\%$
test_compile_add_one_flat[tensordict-eager]	0.4307ms	0.1925ms	5.1940 KOps/s	5.0751 KOps/s	$\color{#35bf28}+2.34\%$
test_compile_add_one_flat[tensorclass-compile]	0.1289ms	39.3789μs	25.3943 KOps/s	25.3716 KOps/s	$\color{#35bf28}+0.09\%$
test_compile_add_one_flat[tensorclass-eager]	0.7826ms	70.6722μs	14.1498 KOps/s	13.7328 KOps/s	$\color{#35bf28}+3.04\%$
test_compile_add_one_flat[pytree-compile]	0.2779ms	0.1768ms	5.6571 KOps/s	5.6287 KOps/s	$\color{#35bf28}+0.51\%$
test_compile_add_one_flat[pytree-eager]	0.4461ms	0.2857ms	3.5003 KOps/s	3.3255 KOps/s	$\textbf{\color{#35bf28}+5.26\%}$
test_compile_add_self_flat[tensordict-eager]	0.4364ms	0.2115ms	4.7271 KOps/s	4.8034 KOps/s	$\color{#d91a1a}-1.59\%$
test_compile_add_self_flat[tensordict-compile]	0.5536ms	0.1786ms	5.5995 KOps/s	5.5490 KOps/s	$\color{#35bf28}+0.91\%$
test_compile_add_self_flat[tensorclass-eager]	0.7860ms	63.2575μs	15.8084 KOps/s	15.8569 KOps/s	$\color{#d91a1a}-0.31\%$
test_compile_add_self_flat[tensorclass-compile]	0.1396ms	38.9250μs	25.6904 KOps/s	24.9268 KOps/s	$\color{#35bf28}+3.06\%$
test_compile_add_self_flat[pytree-eager]	0.4736ms	0.2357ms	4.2433 KOps/s	4.1524 KOps/s	$\color{#35bf28}+2.19\%$
test_compile_add_self_flat[pytree-compile]	0.3620ms	0.1731ms	5.7768 KOps/s	5.7754 KOps/s	$\color{#35bf28}+0.02\%$
test_compile_copy_flat[tensordict-compile]	0.3538ms	0.1125ms	8.8905 KOps/s	8.9585 KOps/s	$\color{#d91a1a}-0.76\%$
test_compile_copy_flat[tensordict-eager]	90.6680μs	55.1509μs	18.1321 KOps/s	17.8017 KOps/s	$\color{#35bf28}+1.86\%$
test_compile_copy_flat[pytree-compile]	4.9492ms	80.8197μs	12.3732 KOps/s	12.3991 KOps/s	$\color{#d91a1a}-0.21\%$
test_compile_copy_flat[pytree-eager]	0.1499ms	72.2704μs	13.8369 KOps/s	14.0514 KOps/s	$\color{#d91a1a}-1.53\%$
test_compile_assign_and_add[tensordict-compile]	0.2561ms	0.1897ms	5.2704 KOps/s	5.1694 KOps/s	$\color{#35bf28}+1.95\%$
test_compile_assign_and_add[tensordict-eager]	1.7154ms	1.6189ms	617.7154 Ops/s	612.3055 Ops/s	$\color{#35bf28}+0.88\%$
test_compile_assign_and_add[pytree-compile]	0.2738ms	0.1878ms	5.3243 KOps/s	5.2158 KOps/s	$\color{#35bf28}+2.08\%$
test_compile_assign_and_add[pytree-eager]	1.5376ms	1.0740ms	931.0693 Ops/s	914.5966 Ops/s	$\color{#35bf28}+1.80\%$
test_compile_assign_and_add_stack[compile]	0.5081ms	0.4115ms	2.4299 KOps/s	2.4139 KOps/s	$\color{#35bf28}+0.66\%$
test_compile_assign_and_add_stack[eager]	3.9350ms	3.7778ms	264.7069 Ops/s	255.6445 Ops/s	$\color{#35bf28}+3.54\%$
test_compile_indexing[tensor-tensordict-compile]	79.2970μs	32.1510μs	31.1033 KOps/s	30.0287 KOps/s	$\color{#35bf28}+3.58\%$
test_compile_indexing[tensor-tensordict-eager]	1.3699ms	48.1190μs	20.7818 KOps/s	19.6434 KOps/s	$\textbf{\color{#35bf28}+5.80\%}$
test_compile_indexing[tensor-tensorclass-compile]	0.1859ms	27.6503μs	36.1660 KOps/s	34.4018 KOps/s	$\textbf{\color{#35bf28}+5.13\%}$
test_compile_indexing[tensor-tensorclass-eager]	0.2138ms	33.3934μs	29.9460 KOps/s	31.8706 KOps/s	$\textbf{\color{#d91a1a}-6.04\%}$
test_compile_indexing[tensor-pytree-compile]	0.1747ms	28.0280μs	35.6786 KOps/s	34.6681 KOps/s	$\color{#35bf28}+2.91\%$
test_compile_indexing[tensor-pytree-eager]	0.1897ms	31.7135μs	31.5323 KOps/s	31.0594 KOps/s	$\color{#35bf28}+1.52\%$
test_compile_indexing[slice-tensordict-compile]	0.1391ms	72.7876μs	13.7386 KOps/s	13.6525 KOps/s	$\color{#35bf28}+0.63\%$
test_compile_indexing[slice-tensordict-eager]	0.5567ms	28.5123μs	35.0725 KOps/s	34.9903 KOps/s	$\color{#35bf28}+0.23\%$
test_compile_indexing[slice-tensorclass-compile]	0.1705ms	68.0500μs	14.6951 KOps/s	14.6218 KOps/s	$\color{#35bf28}+0.50\%$
test_compile_indexing[slice-tensorclass-eager]	59.9610μs	24.9723μs	40.0444 KOps/s	39.9621 KOps/s	$\color{#35bf28}+0.21\%$
test_compile_indexing[slice-pytree-compile]	0.1490ms	67.9241μs	14.7223 KOps/s	14.5821 KOps/s	$\color{#35bf28}+0.96\%$
test_compile_indexing[slice-pytree-eager]	72.9350μs	24.8616μs	40.2227 KOps/s	40.3698 KOps/s	$\color{#d91a1a}-0.36\%$
test_compile_indexing[int-tensordict-compile]	0.1457ms	73.4601μs	13.6128 KOps/s	13.6285 KOps/s	$\color{#d91a1a}-0.12\%$
test_compile_indexing[int-tensordict-eager]	0.9180ms	28.3715μs	35.2466 KOps/s	35.2564 KOps/s	$\color{#d91a1a}-0.03\%$
test_compile_indexing[int-tensorclass-compile]	0.1431ms	67.1607μs	14.8897 KOps/s	14.5037 KOps/s	$\color{#35bf28}+2.66\%$
test_compile_indexing[int-tensorclass-eager]	69.2090μs	24.7984μs	40.3252 KOps/s	40.8137 KOps/s	$\color{#d91a1a}-1.20\%$
test_compile_indexing[int-pytree-compile]	0.1478ms	67.0284μs	14.9191 KOps/s	14.6148 KOps/s	$\color{#35bf28}+2.08\%$
test_compile_indexing[int-pytree-eager]	77.6440μs	24.4791μs	40.8512 KOps/s	40.4158 KOps/s	$\color{#35bf28}+1.08\%$
test_mod_add[eager]	0.1067ms	22.8650μs	43.7350 KOps/s	40.4093 KOps/s	$\textbf{\color{#35bf28}+8.23\%}$
test_mod_add[compile]	80.8000μs	36.2625μs	27.5767 KOps/s	25.7428 KOps/s	$\textbf{\color{#35bf28}+7.12\%}$
test_mod_add[compile-overhead]	0.1006ms	36.0654μs	27.7274 KOps/s	26.4618 KOps/s	$\color{#35bf28}+4.78\%$
test_mod_wrap[eager]	0.3194ms	0.1976ms	5.0596 KOps/s	4.6446 KOps/s	$\textbf{\color{#35bf28}+8.93\%}$
test_mod_wrap[compile]	1.4281ms	0.2224ms	4.4961 KOps/s	4.2760 KOps/s	$\textbf{\color{#35bf28}+5.15\%}$
test_mod_wrap[compile-overhead]	0.3171ms	0.2186ms	4.5742 KOps/s	4.3448 KOps/s	$\textbf{\color{#35bf28}+5.28\%}$
test_mod_wrap_and_backward[eager]	14.5050ms	11.5872ms	86.3021 Ops/s	92.6757 Ops/s	$\textbf{\color{#d91a1a}-6.88\%}$
test_mod_wrap_and_backward[compile]	14.3398ms	12.1999ms	81.9679 Ops/s	91.4620 Ops/s	$\textbf{\color{#d91a1a}-10.38\%}$
test_mod_wrap_and_backward[compile-overhead]	15.1735ms	11.8168ms	84.6255 Ops/s	89.5268 Ops/s	$\textbf{\color{#d91a1a}-5.47\%}$
test_seq_add[eager]	0.1503ms	80.2665μs	12.4585 KOps/s	11.3627 KOps/s	$\textbf{\color{#35bf28}+9.64\%}$
test_seq_add[compile]	0.1921ms	61.0208μs	16.3879 KOps/s	15.5509 KOps/s	$\textbf{\color{#35bf28}+5.38\%}$
test_seq_add[compile-overhead]	0.2175ms	59.0830μs	16.9253 KOps/s	15.6268 KOps/s	$\textbf{\color{#35bf28}+8.31\%}$
test_seq_wrap[eager]	0.4917ms	0.3583ms	2.7909 KOps/s	2.6260 KOps/s	$\textbf{\color{#35bf28}+6.28\%}$
test_seq_wrap[compile]	0.4176ms	0.2573ms	3.8867 KOps/s	3.7988 KOps/s	$\color{#35bf28}+2.31\%$
test_seq_wrap[compile-overhead]	0.3807ms	0.2555ms	3.9138 KOps/s	3.8028 KOps/s	$\color{#35bf28}+2.92\%$
test_func_call_runtime[False-eager]	0.7738ms	0.5110ms	1.9569 KOps/s	1.8347 KOps/s	$\textbf{\color{#35bf28}+6.66\%}$
test_func_call_runtime[False-compile]	0.5899ms	0.4858ms	2.0583 KOps/s	1.9689 KOps/s	$\color{#35bf28}+4.54\%$
test_func_call_runtime[False-compile-overhead]	1.0079ms	0.4894ms	2.0433 KOps/s	1.9705 KOps/s	$\color{#35bf28}+3.70\%$
test_func_call_runtime[True-eager]	1.3085ms	0.7422ms	1.3474 KOps/s	1.2672 KOps/s	$\textbf{\color{#35bf28}+6.33\%}$
test_func_call_runtime[True-compile]	0.6217ms	0.5052ms	1.9793 KOps/s	1.9300 KOps/s	$\color{#35bf28}+2.55\%$
test_func_call_runtime[True-compile-overhead]	1.0138ms	0.4996ms	2.0015 KOps/s	1.9191 KOps/s	$\color{#35bf28}+4.30\%$
test_func_call_cm_runtime[False-eager]	0.9419ms	0.5137ms	1.9467 KOps/s	1.8197 KOps/s	$\textbf{\color{#35bf28}+6.98\%}$
test_func_call_cm_runtime[False-compile]	1.1146ms	0.4808ms	2.0800 KOps/s	1.9988 KOps/s	$\color{#35bf28}+4.06\%$
test_func_call_cm_runtime[False-compile-overhead]	0.5896ms	0.4828ms	2.0711 KOps/s	1.9802 KOps/s	$\color{#35bf28}+4.59\%$
test_func_call_cm_runtime[True-eager]	1.4094ms	0.8659ms	1.1549 KOps/s	1.1079 KOps/s	$\color{#35bf28}+4.24\%$
test_func_call_cm_runtime[True-compile]	1.2648ms	0.8023ms	1.2465 KOps/s	1.1780 KOps/s	$\textbf{\color{#35bf28}+5.81\%}$
test_func_call_cm_runtime[True-compile-overhead]	1.0672ms	0.8026ms	1.2460 KOps/s	1.1703 KOps/s	$\textbf{\color{#35bf28}+6.46\%}$
test_distributed	0.2639ms	0.1322ms	7.5628 KOps/s	7.6378 KOps/s	$\color{#d91a1a}-0.98\%$
test_tdmodule	30.7270μs	15.5880μs	64.1518 KOps/s	60.1386 KOps/s	$\textbf{\color{#35bf28}+6.67\%}$
test_tdmodule_dispatch	53.1390μs	32.8310μs	30.4591 KOps/s	28.0099 KOps/s	$\textbf{\color{#35bf28}+8.74\%}$
test_tdseq	31.9190μs	17.7768μs	56.2531 KOps/s	53.7132 KOps/s	$\color{#35bf28}+4.73\%$
test_tdseq_dispatch	58.2380μs	37.6526μs	26.5586 KOps/s	25.0608 KOps/s	$\textbf{\color{#35bf28}+5.98\%}$
test_instantiation_functorch	2.2128ms	1.6200ms	617.2671 Ops/s	598.0252 Ops/s	$\color{#35bf28}+3.22\%$
test_instantiation_td	1.7638ms	1.1791ms	848.0911 Ops/s	840.5334 Ops/s	$\color{#35bf28}+0.90\%$
test_exec_functorch	0.4519ms	0.1786ms	5.6006 KOps/s	5.5404 KOps/s	$\color{#35bf28}+1.09\%$
test_exec_functional_call	0.2431ms	0.1618ms	6.1822 KOps/s	5.7679 KOps/s	$\textbf{\color{#35bf28}+7.18\%}$
test_exec_td	0.2543ms	0.1655ms	6.0427 KOps/s	5.6197 KOps/s	$\textbf{\color{#35bf28}+7.53\%}$
test_exec_td_decorator	0.6853ms	0.2212ms	4.5208 KOps/s	4.3801 KOps/s	$\color{#35bf28}+3.21\%$
test_vmap_mlp_speed[True-True]	0.7698ms	0.5527ms	1.8095 KOps/s	1.7103 KOps/s	$\textbf{\color{#35bf28}+5.80\%}$
test_vmap_mlp_speed[True-False]	0.8165ms	0.5516ms	1.8130 KOps/s	1.7083 KOps/s	$\textbf{\color{#35bf28}+6.13\%}$
test_vmap_mlp_speed[False-True]	0.6404ms	0.4555ms	2.1952 KOps/s	2.0699 KOps/s	$\textbf{\color{#35bf28}+6.05\%}$
test_vmap_mlp_speed[False-False]	0.7936ms	0.4599ms	2.1744 KOps/s	2.0626 KOps/s	$\textbf{\color{#35bf28}+5.42\%}$
test_vmap_mlp_speed_decorator[True-True]	1.2914ms	0.6098ms	1.6399 KOps/s	1.5609 KOps/s	$\textbf{\color{#35bf28}+5.06\%}$
test_vmap_mlp_speed_decorator[True-False]	1.0071ms	0.6153ms	1.6253 KOps/s	1.5573 KOps/s	$\color{#35bf28}+4.37\%$
test_vmap_mlp_speed_decorator[False-True]	0.7730ms	0.5101ms	1.9602 KOps/s	1.9112 KOps/s	$\color{#35bf28}+2.57\%$
test_vmap_mlp_speed_decorator[False-False]	0.8123ms	0.5127ms	1.9505 KOps/s	1.9137 KOps/s	$\color{#35bf28}+1.92\%$
test_to_module_speed[True]	1.5814ms	1.3477ms	742.0216 Ops/s	756.4579 Ops/s	$\color{#d91a1a}-1.91\%$
test_to_module_speed[False]	1.7696ms	1.3229ms	755.8880 Ops/s	774.3673 Ops/s	$\color{#d91a1a}-2.39\%$
test_tc_init	69.8800μs	41.2640μs	24.2342 KOps/s	22.9649 KOps/s	$\textbf{\color{#35bf28}+5.53\%}$
test_tc_init_nested	0.1224ms	83.8810μs	11.9217 KOps/s	11.4917 KOps/s	$\color{#35bf28}+3.74\%$
test_tc_first_layer_tensor	19.3760μs	1.5147μs	660.1910 KOps/s	683.1671 KOps/s	$\color{#d91a1a}-3.36\%$
test_tc_first_layer_nontensor	25.4370μs	4.4383μs	225.3113 KOps/s	231.5567 KOps/s	$\color{#d91a1a}-2.70\%$
test_tc_second_layer_tensor	22.8220μs	2.8279μs	353.6229 KOps/s	358.1952 KOps/s	$\color{#d91a1a}-1.28\%$
test_tc_second_layer_nontensor	27.3200μs	5.7741μs	173.1878 KOps/s	180.3509 KOps/s	$\color{#d91a1a}-3.97\%$
test_unbind	0.4411s	14.8331ms	67.4167 Ops/s	75.2191 Ops/s	$\textbf{\color{#d91a1a}-10.37\%}$
test_full_like	8.5383ms	7.4416ms	134.3790 Ops/s	142.0631 Ops/s	$\textbf{\color{#d91a1a}-5.41\%}$
test_zeros_like	12.7889ms	7.0823ms	141.1969 Ops/s	134.9231 Ops/s	$\color{#35bf28}+4.65\%$
test_ones_like	13.6768ms	7.5625ms	132.2317 Ops/s	133.2122 Ops/s	$\color{#d91a1a}-0.74\%$
test_clone	12.5242ms	9.5596ms	104.6071 Ops/s	107.6676 Ops/s	$\color{#d91a1a}-2.84\%$
test_squeeze	60.9530μs	13.3043μs	75.1638 KOps/s	76.4405 KOps/s	$\color{#d91a1a}-1.67\%$
test_unsqueeze	0.3463ms	95.2771μs	10.4957 KOps/s	10.3222 KOps/s	$\color{#35bf28}+1.68\%$
test_split	0.3567ms	0.1989ms	5.0283 KOps/s	4.9044 KOps/s	$\color{#35bf28}+2.53\%$
test_permute	0.3245ms	0.2191ms	4.5651 KOps/s	4.5132 KOps/s	$\color{#35bf28}+1.15\%$
test_stack	31.9042ms	25.6356ms	39.0082 Ops/s	39.9487 Ops/s	$\color{#d91a1a}-2.35\%$
test_cat	32.3892ms	25.3715ms	39.4143 Ops/s	40.1178 Ops/s	$\color{#d91a1a}-1.75\%$

[github-actions]

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

Total Benchmarks: 225. Improved: $\large\color{#35bf28}22$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	51.1110μs	16.9872μs	58.8677 KOps/s	59.2678 KOps/s	$\color{#d91a1a}-0.68\%$
test_plain_set_stack_nested	76.0510μs	16.9726μs	58.9184 KOps/s	59.2233 KOps/s	$\color{#d91a1a}-0.51\%$
test_plain_set_nested_inplace	40.1910μs	18.0954μs	55.2628 KOps/s	56.2346 KOps/s	$\color{#d91a1a}-1.73\%$
test_plain_set_stack_nested_inplace	37.6700μs	18.1473μs	55.1045 KOps/s	55.8108 KOps/s	$\color{#d91a1a}-1.27\%$
test_items	1.0614ms	4.7825μs	209.0936 KOps/s	212.4668 KOps/s	$\color{#d91a1a}-1.59\%$
test_items_nested	0.4020ms	0.3662ms	2.7307 KOps/s	2.7507 KOps/s	$\color{#d91a1a}-0.73\%$
test_items_nested_locked	0.4055ms	0.3701ms	2.7023 KOps/s	2.7404 KOps/s	$\color{#d91a1a}-1.39\%$
test_items_nested_leaf	0.1464ms	84.3136μs	11.8605 KOps/s	11.8630 KOps/s	$\color{#d91a1a}-0.02\%$
test_items_stack_nested	0.4195ms	0.3661ms	2.7315 KOps/s	2.7413 KOps/s	$\color{#d91a1a}-0.36\%$
test_items_stack_nested_leaf	0.2489ms	86.0632μs	11.6194 KOps/s	11.6747 KOps/s	$\color{#d91a1a}-0.47\%$
test_items_stack_nested_locked	0.5622ms	0.3674ms	2.7222 KOps/s	2.7338 KOps/s	$\color{#d91a1a}-0.42\%$
test_keys	18.7110μs	4.3911μs	227.7350 KOps/s	229.9627 KOps/s	$\color{#d91a1a}-0.97\%$
test_keys_nested	85.5710μs	67.2453μs	14.8709 KOps/s	14.9541 KOps/s	$\color{#d91a1a}-0.56\%$
test_keys_nested_locked	2.3706ms	72.9824μs	13.7019 KOps/s	13.4798 KOps/s	$\color{#35bf28}+1.65\%$
test_keys_nested_leaf	78.8210μs	56.1436μs	17.8115 KOps/s	17.5363 KOps/s	$\color{#35bf28}+1.57\%$
test_keys_stack_nested	85.4820μs	67.3941μs	14.8381 KOps/s	14.7023 KOps/s	$\color{#35bf28}+0.92\%$
test_keys_stack_nested_leaf	0.1148ms	58.3943μs	17.1250 KOps/s	16.8745 KOps/s	$\color{#35bf28}+1.48\%$
test_keys_stack_nested_locked	93.2020μs	72.9940μs	13.6998 KOps/s	13.4899 KOps/s	$\color{#35bf28}+1.56\%$
test_values	9.1300μs	1.7534μs	570.3121 KOps/s	571.2918 KOps/s	$\color{#d91a1a}-0.17\%$
test_values_nested	51.0810μs	33.7688μs	29.6131 KOps/s	29.5826 KOps/s	$\color{#35bf28}+0.10\%$
test_values_nested_locked	50.6610μs	35.7732μs	27.9539 KOps/s	28.0173 KOps/s	$\color{#d91a1a}-0.23\%$
test_values_nested_leaf	94.3030μs	30.1154μs	33.2055 KOps/s	33.2004 KOps/s	$\color{#35bf28}+0.02\%$
test_values_stack_nested	0.1752ms	34.7050μs	28.8143 KOps/s	28.9963 KOps/s	$\color{#d91a1a}-0.63\%$
test_values_stack_nested_leaf	55.8710μs	30.9492μs	32.3111 KOps/s	32.4112 KOps/s	$\color{#d91a1a}-0.31\%$
test_values_stack_nested_locked	0.1731ms	36.6233μs	27.3051 KOps/s	27.4643 KOps/s	$\color{#d91a1a}-0.58\%$
test_membership	1.3325μs	0.5556μs	1.7999 MOps/s	1.8297 MOps/s	$\color{#d91a1a}-1.63\%$
test_membership_nested	10.3900μs	1.9273μs	518.8710 KOps/s	508.8953 KOps/s	$\color{#35bf28}+1.96\%$
test_membership_nested_leaf	10.3755μs	1.9300μs	518.1394 KOps/s	506.6780 KOps/s	$\color{#35bf28}+2.26\%$
test_membership_stacked_nested	27.7600μs	2.0131μs	496.7520 KOps/s	501.8830 KOps/s	$\color{#d91a1a}-1.02\%$
test_membership_stacked_nested_leaf	16.0010μs	1.9882μs	502.9758 KOps/s	501.3084 KOps/s	$\color{#35bf28}+0.33\%$
test_membership_nested_last	16.2700μs	2.9693μs	336.7814 KOps/s	333.4635 KOps/s	$\color{#35bf28}+0.99\%$
test_membership_nested_leaf_last	21.7400μs	2.9802μs	335.5430 KOps/s	340.4351 KOps/s	$\color{#d91a1a}-1.44\%$
test_membership_stacked_nested_last	16.8800μs	4.2905μs	233.0719 KOps/s	244.1763 KOps/s	$\color{#d91a1a}-4.55\%$
test_membership_stacked_nested_leaf_last	17.3510μs	4.3410μs	230.3600 KOps/s	245.6241 KOps/s	$\textbf{\color{#d91a1a}-6.21\%}$
test_nested_getleaf	24.6500μs	7.8998μs	126.5860 KOps/s	126.1441 KOps/s	$\color{#35bf28}+0.35\%$
test_nested_get	0.1789ms	7.4886μs	133.5361 KOps/s	133.9137 KOps/s	$\color{#d91a1a}-0.28\%$
test_stacked_getleaf	30.5510μs	7.9938μs	125.0971 KOps/s	125.2412 KOps/s	$\color{#d91a1a}-0.12\%$
test_stacked_get	24.3700μs	7.4612μs	134.0262 KOps/s	133.7786 KOps/s	$\color{#35bf28}+0.19\%$
test_nested_getitemleaf	26.2610μs	8.0870μs	123.6546 KOps/s	122.9143 KOps/s	$\color{#35bf28}+0.60\%$
test_nested_getitem	73.6020μs	7.6081μs	131.4395 KOps/s	130.8830 KOps/s	$\color{#35bf28}+0.43\%$
test_stacked_getitemleaf	28.4110μs	8.1148μs	123.2314 KOps/s	123.2350 KOps/s	$-0.00\%$
test_stacked_getitem	20.9910μs	7.6118μs	131.3742 KOps/s	130.8945 KOps/s	$\color{#35bf28}+0.37\%$
test_lock_nested	7.6275ms	0.4908ms	2.0375 KOps/s	2.0724 KOps/s	$\color{#d91a1a}-1.69\%$
test_lock_stack_nested	0.4985ms	0.4400ms	2.2728 KOps/s	2.2747 KOps/s	$\color{#d91a1a}-0.08\%$
test_unlock_nested	0.8841ms	0.4028ms	2.4826 KOps/s	2.4872 KOps/s	$\color{#d91a1a}-0.19\%$
test_unlock_stack_nested	0.3801ms	0.3591ms	2.7845 KOps/s	2.7861 KOps/s	$\color{#d91a1a}-0.06\%$
test_flatten_speed	0.4678ms	0.1062ms	9.4156 KOps/s	9.5528 KOps/s	$\color{#d91a1a}-1.44\%$
test_unflatten_speed	0.3082ms	0.2863ms	3.4923 KOps/s	3.4739 KOps/s	$\color{#35bf28}+0.53\%$
test_common_ops	1.5774ms	1.3540ms	738.5430 Ops/s	726.1331 Ops/s	$\color{#35bf28}+1.71\%$
test_creation	18.7500μs	1.6590μs	602.7718 KOps/s	614.2082 KOps/s	$\color{#d91a1a}-1.86\%$
test_creation_empty	40.9900μs	17.6928μs	56.5202 KOps/s	58.9461 KOps/s	$\color{#d91a1a}-4.12\%$
test_creation_nested_1	35.8500μs	19.5156μs	51.2411 KOps/s	52.8126 KOps/s	$\color{#d91a1a}-2.98\%$
test_creation_nested_2	41.5510μs	22.2775μs	44.8884 KOps/s	45.8456 KOps/s	$\color{#d91a1a}-2.09\%$
test_clone	69.7120μs	30.6959μs	32.5776 KOps/s	30.9289 KOps/s	$\textbf{\color{#35bf28}+5.33\%}$
test_getitem[int]	1.2028ms	18.0351μs	55.4474 KOps/s	56.1452 KOps/s	$\color{#d91a1a}-1.24\%$
test_getitem[slice_int]	0.1475ms	30.7660μs	32.5034 KOps/s	31.9559 KOps/s	$\color{#35bf28}+1.71\%$
test_getitem[range]	0.2618ms	0.1175ms	8.5102 KOps/s	8.4740 KOps/s	$\color{#35bf28}+0.43\%$
test_getitem[tuple]	0.1711ms	26.8290μs	37.2731 KOps/s	38.3551 KOps/s	$\color{#d91a1a}-2.82\%$
test_getitem[list]	0.2568ms	0.1072ms	9.3285 KOps/s	9.3811 KOps/s	$\color{#d91a1a}-0.56\%$
test_setitem_dim[int]	84.2720μs	55.2288μs	18.1065 KOps/s	18.0852 KOps/s	$\color{#35bf28}+0.12\%$
test_setitem_dim[slice_int]	0.1125ms	81.2640μs	12.3056 KOps/s	11.8157 KOps/s	$\color{#35bf28}+4.15\%$
test_setitem_dim[range]	0.1774ms	0.1453ms	6.8828 KOps/s	6.8887 KOps/s	$\color{#d91a1a}-0.09\%$
test_setitem_dim[tuple]	94.9830μs	73.1290μs	13.6745 KOps/s	13.6385 KOps/s	$\color{#35bf28}+0.26\%$
test_setitem	77.2020μs	44.4757μs	22.4842 KOps/s	22.3227 KOps/s	$\color{#35bf28}+0.72\%$
test_set	0.1921ms	43.6122μs	22.9294 KOps/s	22.9323 KOps/s	$\color{#d91a1a}-0.01\%$
test_set_shared	92.8482ms	64.3766μs	15.5336 KOps/s	16.9147 KOps/s	$\textbf{\color{#d91a1a}-8.17\%}$
test_update	0.2030ms	52.6586μs	18.9902 KOps/s	18.0354 KOps/s	$\textbf{\color{#35bf28}+5.29\%}$
test_update_nested	87.7920μs	60.2132μs	16.6076 KOps/s	15.4883 KOps/s	$\textbf{\color{#35bf28}+7.23\%}$
test_update__nested	0.2248ms	63.2596μs	15.8079 KOps/s	14.3822 KOps/s	$\textbf{\color{#35bf28}+9.91\%}$
test_set_nested	76.7820μs	46.2426μs	21.6251 KOps/s	20.0655 KOps/s	$\textbf{\color{#35bf28}+7.77\%}$
test_set_nested_new	78.6010μs	49.3098μs	20.2799 KOps/s	18.3427 KOps/s	$\textbf{\color{#35bf28}+10.56\%}$
test_select	0.2130ms	65.4404μs	15.2811 KOps/s	14.3881 KOps/s	$\textbf{\color{#35bf28}+6.21\%}$
test_select_nested	0.4744ms	52.6962μs	18.9767 KOps/s	18.9178 KOps/s	$\color{#35bf28}+0.31\%$
test_exclude_nested	89.7320μs	69.6060μs	14.3666 KOps/s	14.3589 KOps/s	$\color{#35bf28}+0.05\%$
test_empty[True]	0.3245ms	0.2839ms	3.5227 KOps/s	3.5161 KOps/s	$\color{#35bf28}+0.19\%$
test_empty[False]	2.3621μs	0.8699μs	1.1495 MOps/s	1.1711 MOps/s	$\color{#d91a1a}-1.84\%$
test_to	76.3910μs	27.8737μs	35.8761 KOps/s	34.6155 KOps/s	$\color{#35bf28}+3.64\%$
test_to_nonblocking	56.4710μs	27.4727μs	36.3998 KOps/s	35.7038 KOps/s	$\color{#35bf28}+1.95\%$
test_unbind_speed	0.3578ms	0.3093ms	3.2330 KOps/s	3.2485 KOps/s	$\color{#d91a1a}-0.48\%$
test_unbind_speed_stack0	0.3608ms	0.3047ms	3.2824 KOps/s	3.2565 KOps/s	$\color{#35bf28}+0.80\%$
test_unbind_speed_stack1	88.8981ms	0.7771ms	1.2868 KOps/s	1.2775 KOps/s	$\color{#35bf28}+0.72\%$
test_split	2.3604ms	2.2274ms	448.9600 Ops/s	408.5836 Ops/s	$\textbf{\color{#35bf28}+9.88\%}$
test_chunk	92.3050ms	2.4178ms	413.6060 Ops/s	407.1768 Ops/s	$\color{#35bf28}+1.58\%$
test_creation[device0]	0.1575ms	0.1066ms	9.3807 KOps/s	9.3215 KOps/s	$\color{#35bf28}+0.63\%$
test_creation_from_tensor	0.2132ms	0.1028ms	9.7237 KOps/s	9.6132 KOps/s	$\color{#35bf28}+1.15\%$
test_add_one[memmap_tensor0]	0.1639ms	9.2762μs	107.8024 KOps/s	106.1754 KOps/s	$\color{#35bf28}+1.53\%$
test_contiguous[memmap_tensor0]	17.0900μs	2.2517μs	444.1035 KOps/s	433.7992 KOps/s	$\color{#35bf28}+2.38\%$
test_stack[memmap_tensor0]	32.7700μs	6.9420μs	144.0513 KOps/s	143.3806 KOps/s	$\color{#35bf28}+0.47\%$
test_memmaptd_index	1.1968ms	0.4444ms	2.2500 KOps/s	2.2054 KOps/s	$\color{#35bf28}+2.02\%$
test_memmaptd_index_astensor	91.1267ms	0.5673ms	1.7627 KOps/s	1.9095 KOps/s	$\textbf{\color{#d91a1a}-7.69\%}$
test_memmaptd_index_op	1.5104ms	1.0961ms	912.3599 Ops/s	904.8244 Ops/s	$\color{#35bf28}+0.83\%$
test_serialize_model	94.8484ms	89.7708ms	11.1395 Ops/s	10.8388 Ops/s	$\color{#35bf28}+2.77\%$
test_serialize_model_pickle	1.3501s	1.2363s	0.8089 Ops/s	0.8056 Ops/s	$\color{#35bf28}+0.41\%$
test_serialize_weights	91.7652ms	86.8370ms	11.5158 Ops/s	9.5768 Ops/s	$\textbf{\color{#35bf28}+20.25\%}$
test_serialize_weights_returnearly	0.2409s	67.2808ms	14.8631 Ops/s	14.8410 Ops/s	$\color{#35bf28}+0.15\%$
test_serialize_weights_pickle	1.3473s	1.2369s	0.8084 Ops/s	0.8085 Ops/s	$-0.01\%$
test_reshape_pytree	94.7620μs	39.2543μs	25.4749 KOps/s	24.7756 KOps/s	$\color{#35bf28}+2.82\%$
test_reshape_td	0.1453ms	45.8461μs	21.8121 KOps/s	21.7647 KOps/s	$\color{#35bf28}+0.22\%$
test_view_pytree	73.9110μs	39.1259μs	25.5585 KOps/s	24.9676 KOps/s	$\color{#35bf28}+2.37\%$
test_view_td	95.0220μs	52.4838μs	19.0535 KOps/s	19.3221 KOps/s	$\color{#d91a1a}-1.39\%$
test_unbind_pytree	0.1692ms	38.3101μs	26.1028 KOps/s	26.0336 KOps/s	$\color{#35bf28}+0.27\%$
test_unbind_td	0.4764ms	48.8572μs	20.4678 KOps/s	21.1522 KOps/s	$\color{#d91a1a}-3.24\%$
test_split_pytree	92.4420μs	51.7083μs	19.3393 KOps/s	18.9474 KOps/s	$\color{#35bf28}+2.07\%$
test_split_td	91.1885ms	73.2289μs	13.6558 KOps/s	15.6067 KOps/s	$\textbf{\color{#d91a1a}-12.50\%}$
test_add_pytree	0.1060ms	61.1990μs	16.3401 KOps/s	16.3619 KOps/s	$\color{#d91a1a}-0.13\%$
test_add_td	0.1709ms	97.8045μs	10.2245 KOps/s	10.1190 KOps/s	$\color{#35bf28}+1.04\%$
test_compile_add_one_nested[tensordict-compile]	0.4202ms	0.2172ms	4.6050 KOps/s	4.5428 KOps/s	$\color{#35bf28}+1.37\%$
test_compile_add_one_nested[tensordict-eager]	0.3293ms	0.1817ms	5.5036 KOps/s	5.6213 KOps/s	$\color{#d91a1a}-2.09\%$
test_compile_add_one_nested[pytree-compile]	0.1843ms	0.1511ms	6.6201 KOps/s	6.5140 KOps/s	$\color{#35bf28}+1.63\%$
test_compile_add_one_nested[pytree-eager]	0.3490ms	0.2026ms	4.9359 KOps/s	4.9447 KOps/s	$\color{#d91a1a}-0.18\%$
test_compile_copy_nested[tensordict-compile]	0.1715ms	23.6831μs	42.2241 KOps/s	42.9527 KOps/s	$\color{#d91a1a}-1.70\%$
test_compile_copy_nested[tensordict-eager]	91.4020μs	49.4809μs	20.2098 KOps/s	20.5489 KOps/s	$\color{#d91a1a}-1.65\%$
test_compile_copy_nested[pytree-compile]	0.1147ms	74.6962μs	13.3876 KOps/s	13.5133 KOps/s	$\color{#d91a1a}-0.93\%$
test_compile_copy_nested[pytree-eager]	0.1220ms	59.8512μs	16.7081 KOps/s	16.6691 KOps/s	$\color{#35bf28}+0.23\%$
test_compile_add_one_flat[tensordict-compile]	0.4979ms	0.3361ms	2.9755 KOps/s	2.9015 KOps/s	$\color{#35bf28}+2.55\%$
test_compile_add_one_flat[tensordict-eager]	0.3450ms	0.2244ms	4.4571 KOps/s	4.3024 KOps/s	$\color{#35bf28}+3.60\%$
test_compile_add_one_flat[tensorclass-compile]	0.1935ms	0.1386ms	7.2152 KOps/s	7.3426 KOps/s	$\color{#d91a1a}-1.74\%$
test_compile_add_one_flat[tensorclass-eager]	0.2504ms	68.1122μs	14.6817 KOps/s	15.5954 KOps/s	$\textbf{\color{#d91a1a}-5.86\%}$
test_compile_add_one_flat[pytree-compile]	0.3852ms	0.3337ms	2.9965 KOps/s	2.9121 KOps/s	$\color{#35bf28}+2.90\%$
test_compile_add_one_flat[pytree-eager]	0.8254ms	0.6568ms	1.5226 KOps/s	1.5266 KOps/s	$\color{#d91a1a}-0.27\%$
test_compile_add_self_flat[tensordict-eager]	0.3908ms	0.2724ms	3.6713 KOps/s	3.6774 KOps/s	$\color{#d91a1a}-0.17\%$
test_compile_add_self_flat[tensordict-compile]	0.5117ms	0.3387ms	2.9524 KOps/s	2.8718 KOps/s	$\color{#35bf28}+2.81\%$
test_compile_add_self_flat[tensorclass-eager]	0.2277ms	78.0206μs	12.8171 KOps/s	13.0225 KOps/s	$\color{#d91a1a}-1.58\%$
test_compile_add_self_flat[tensorclass-compile]	0.2803ms	0.1364ms	7.3294 KOps/s	7.2660 KOps/s	$\color{#35bf28}+0.87\%$
test_compile_add_self_flat[pytree-eager]	0.7541ms	0.5582ms	1.7914 KOps/s	1.7877 KOps/s	$\color{#35bf28}+0.20\%$
test_compile_add_self_flat[pytree-compile]	0.3980ms	0.3342ms	2.9920 KOps/s	2.9165 KOps/s	$\color{#35bf28}+2.59\%$
test_compile_copy_flat[tensordict-compile]	0.1549ms	19.6147μs	50.9821 KOps/s	51.0869 KOps/s	$\color{#d91a1a}-0.21\%$
test_compile_copy_flat[tensordict-eager]	54.8510μs	31.7837μs	31.4626 KOps/s	31.6272 KOps/s	$\color{#d91a1a}-0.52\%$
test_compile_copy_flat[pytree-compile]	0.1449ms	76.1653μs	13.1293 KOps/s	13.0966 KOps/s	$\color{#35bf28}+0.25\%$
test_compile_copy_flat[pytree-eager]	0.1354ms	60.7829μs	16.4520 KOps/s	16.5140 KOps/s	$\color{#d91a1a}-0.38\%$
test_compile_assign_and_add[tensordict-compile]	2.5630ms	0.8742ms	1.1440 KOps/s	1.0487 KOps/s	$\textbf{\color{#35bf28}+9.08\%}$
test_compile_assign_and_add[tensordict-eager]	3.8421ms	3.5597ms	280.9191 Ops/s	286.6593 Ops/s	$\color{#d91a1a}-2.00\%$
test_compile_assign_and_add[pytree-compile]	2.5179ms	0.8627ms	1.1592 KOps/s	1.0580 KOps/s	$\textbf{\color{#35bf28}+9.56\%}$
test_compile_assign_and_add[pytree-eager]	4.0876ms	3.5786ms	279.4397 Ops/s	285.9077 Ops/s	$\color{#d91a1a}-2.26\%$
test_compile_indexing[tensor-tensordict-compile]	0.2529ms	0.1176ms	8.5066 KOps/s	8.6092 KOps/s	$\color{#d91a1a}-1.19\%$
test_compile_indexing[tensor-tensordict-eager]	0.2609ms	66.9056μs	14.9464 KOps/s	14.4206 KOps/s	$\color{#35bf28}+3.65\%$
test_compile_indexing[tensor-tensorclass-compile]	0.2579ms	0.1072ms	9.3270 KOps/s	8.8436 KOps/s	$\textbf{\color{#35bf28}+5.47\%}$
test_compile_indexing[tensor-tensorclass-eager]	0.2033ms	46.8257μs	21.3558 KOps/s	19.6788 KOps/s	$\textbf{\color{#35bf28}+8.52\%}$
test_compile_indexing[tensor-pytree-compile]	0.2578ms	0.1069ms	9.3558 KOps/s	8.8499 KOps/s	$\textbf{\color{#35bf28}+5.72\%}$
test_compile_indexing[tensor-pytree-eager]	0.2001ms	46.8771μs	21.3324 KOps/s	19.7034 KOps/s	$\textbf{\color{#35bf28}+8.27\%}$
test_compile_indexing[slice-tensordict-compile]	0.2139ms	0.1441ms	6.9384 KOps/s	6.8403 KOps/s	$\color{#35bf28}+1.44\%$
test_compile_indexing[slice-tensordict-eager]	0.1856ms	27.5238μs	36.3322 KOps/s	36.7002 KOps/s	$\color{#d91a1a}-1.00\%$
test_compile_indexing[slice-tensorclass-compile]	0.2769ms	0.1360ms	7.3514 KOps/s	7.2978 KOps/s	$\color{#35bf28}+0.73\%$
test_compile_indexing[slice-tensorclass-eager]	60.4020μs	23.7789μs	42.0541 KOps/s	42.4256 KOps/s	$\color{#d91a1a}-0.88\%$
test_compile_indexing[slice-pytree-compile]	0.2887ms	0.1361ms	7.3468 KOps/s	7.2157 KOps/s	$\color{#35bf28}+1.82\%$
test_compile_indexing[slice-pytree-eager]	42.6710μs	23.2284μs	43.0508 KOps/s	42.1467 KOps/s	$\color{#35bf28}+2.15\%$
test_compile_indexing[int-tensordict-compile]	0.3089ms	0.1436ms	6.9631 KOps/s	6.8633 KOps/s	$\color{#35bf28}+1.45\%$
test_compile_indexing[int-tensordict-eager]	0.4635ms	29.5088μs	33.8882 KOps/s	35.7877 KOps/s	$\textbf{\color{#d91a1a}-5.31\%}$
test_compile_indexing[int-tensorclass-compile]	0.3191ms	0.1363ms	7.3385 KOps/s	6.9803 KOps/s	$\textbf{\color{#35bf28}+5.13\%}$
test_compile_indexing[int-tensorclass-eager]	0.2205ms	23.4452μs	42.6527 KOps/s	42.1985 KOps/s	$\color{#35bf28}+1.08\%$
test_compile_indexing[int-pytree-compile]	0.2832ms	0.1358ms	7.3660 KOps/s	7.0743 KOps/s	$\color{#35bf28}+4.12\%$
test_compile_indexing[int-pytree-eager]	48.6210μs	23.7252μs	42.1493 KOps/s	42.2862 KOps/s	$\color{#d91a1a}-0.32\%$
test_mod_add[eager]	0.2086ms	35.0775μs	28.5083 KOps/s	29.4625 KOps/s	$\color{#d91a1a}-3.24\%$
test_mod_add[compile]	0.2263ms	74.4199μs	13.4373 KOps/s	13.1021 KOps/s	$\color{#35bf28}+2.56\%$
test_mod_add[compile-overhead]	0.2821ms	0.1422ms	7.0307 KOps/s	6.5918 KOps/s	$\textbf{\color{#35bf28}+6.66\%}$
test_mod_wrap[eager]	0.7874ms	0.2495ms	4.0087 KOps/s	3.9837 KOps/s	$\color{#35bf28}+0.63\%$
test_mod_wrap[compile]	1.1201ms	0.3030ms	3.3003 KOps/s	3.1516 KOps/s	$\color{#35bf28}+4.72\%$
test_mod_wrap[compile-overhead]	8.4001ms	4.3759ms	228.5253 Ops/s	227.7910 Ops/s	$\color{#35bf28}+0.32\%$
test_mod_wrap_and_backward[eager]	1.5490ms	1.3768ms	726.3313 Ops/s	723.7334 Ops/s	$\color{#35bf28}+0.36\%$
test_mod_wrap_and_backward[compile]	1.5462ms	1.3700ms	729.9323 Ops/s	670.8849 Ops/s	$\textbf{\color{#35bf28}+8.80\%}$
test_mod_wrap_and_backward[compile-overhead]	1.3685ms	0.9247ms	1.0815 KOps/s	969.8205 Ops/s	$\textbf{\color{#35bf28}+11.51\%}$
test_seq_add[eager]	0.3431ms	0.1034ms	9.6727 KOps/s	9.1732 KOps/s	$\textbf{\color{#35bf28}+5.45\%}$
test_seq_add[compile]	0.3142ms	85.5263μs	11.6923 KOps/s	11.7435 KOps/s	$\color{#d91a1a}-0.44\%$
test_seq_add[compile-overhead]	0.1685ms	0.1206ms	8.2891 KOps/s	7.9638 KOps/s	$\color{#35bf28}+4.08\%$
test_seq_wrap[eager]	0.6270ms	0.3949ms	2.5323 KOps/s	2.3865 KOps/s	$\textbf{\color{#35bf28}+6.11\%}$
test_seq_wrap[compile]	0.5264ms	0.3267ms	3.0605 KOps/s	2.9956 KOps/s	$\color{#35bf28}+2.17\%$
test_seq_wrap[compile-overhead]	0.3769ms	0.2319ms	4.3115 KOps/s	4.2119 KOps/s	$\color{#35bf28}+2.37\%$
test_func_call_runtime[False-eager]	1.0009ms	0.7606ms	1.3148 KOps/s	1.2883 KOps/s	$\color{#35bf28}+2.06\%$
test_func_call_runtime[False-compile]	1.0618ms	0.8258ms	1.2109 KOps/s	1.1877 KOps/s	$\color{#35bf28}+1.95\%$
test_func_call_runtime[False-compile-overhead]	0.4915ms	0.3775ms	2.6490 KOps/s	2.6099 KOps/s	$\color{#35bf28}+1.50\%$
test_func_call_runtime[True-eager]	1.1723ms	0.9492ms	1.0535 KOps/s	1.0438 KOps/s	$\color{#35bf28}+0.94\%$
test_func_call_runtime[True-compile]	1.2029ms	0.8706ms	1.1486 KOps/s	1.1277 KOps/s	$\color{#35bf28}+1.85\%$
test_func_call_runtime[True-compile-overhead]	0.6701ms	0.4219ms	2.3705 KOps/s	2.3353 KOps/s	$\color{#35bf28}+1.51\%$
test_func_call_cm_runtime[False-eager]	0.9855ms	0.7616ms	1.3130 KOps/s	1.2520 KOps/s	$\color{#35bf28}+4.87\%$
test_func_call_cm_runtime[False-compile]	1.0382ms	0.8251ms	1.2119 KOps/s	1.1736 KOps/s	$\color{#35bf28}+3.27\%$
test_func_call_cm_runtime[False-compile-overhead]	0.6109ms	0.3783ms	2.6436 KOps/s	2.5955 KOps/s	$\color{#35bf28}+1.85\%$
test_func_call_cm_runtime[True-eager]	1.2956ms	1.0610ms	942.5493 Ops/s	931.8896 Ops/s	$\color{#35bf28}+1.14\%$
test_func_call_cm_runtime[True-compile]	1.2487ms	1.0318ms	969.1706 Ops/s	951.8879 Ops/s	$\color{#35bf28}+1.82\%$
test_func_call_cm_runtime[True-compile-overhead]	1.2749ms	1.0318ms	969.1884 Ops/s	928.9400 Ops/s	$\color{#35bf28}+4.33\%$
test_distributed	1.3981ms	72.5012μs	13.7929 KOps/s	13.2175 KOps/s	$\color{#35bf28}+4.35\%$
test_tdmodule	33.3610μs	16.3014μs	61.3444 KOps/s	65.0903 KOps/s	$\textbf{\color{#d91a1a}-5.75\%}$
test_tdmodule_dispatch	48.6510μs	32.8124μs	30.4763 KOps/s	31.2829 KOps/s	$\color{#d91a1a}-2.58\%$
test_tdseq	31.1010μs	16.9835μs	58.8806 KOps/s	60.3847 KOps/s	$\color{#d91a1a}-2.49\%$
test_tdseq_dispatch	52.8010μs	35.1033μs	28.4874 KOps/s	28.8406 KOps/s	$\color{#d91a1a}-1.22\%$
test_instantiation_functorch	2.1813ms	2.0534ms	487.0024 Ops/s	479.4185 Ops/s	$\color{#35bf28}+1.58\%$
test_instantiation_td	2.0989ms	1.3347ms	749.2114 Ops/s	741.5780 Ops/s	$\color{#35bf28}+1.03\%$
test_exec_functorch	0.3614ms	0.2220ms	4.5047 KOps/s	4.5426 KOps/s	$\color{#d91a1a}-0.83\%$
test_exec_functional_call	0.2967ms	0.2151ms	4.6486 KOps/s	4.5352 KOps/s	$\color{#35bf28}+2.50\%$
test_exec_td	0.3580ms	0.2253ms	4.4385 KOps/s	4.5131 KOps/s	$\color{#d91a1a}-1.65\%$
test_exec_td_decorator	1.0308ms	0.2766ms	3.6147 KOps/s	3.5840 KOps/s	$\color{#35bf28}+0.86\%$
test_vmap_mlp_speed[True-True]	0.8300ms	0.6672ms	1.4988 KOps/s	1.4876 KOps/s	$\color{#35bf28}+0.75\%$
test_vmap_mlp_speed[True-False]	0.8116ms	0.6646ms	1.5047 KOps/s	1.5089 KOps/s	$\color{#d91a1a}-0.28\%$
test_vmap_mlp_speed[False-True]	0.7331ms	0.5841ms	1.7120 KOps/s	1.6757 KOps/s	$\color{#35bf28}+2.17\%$
test_vmap_mlp_speed[False-False]	0.7192ms	0.5847ms	1.7102 KOps/s	1.6979 KOps/s	$\color{#35bf28}+0.73\%$
test_vmap_mlp_speed_decorator[True-True]	1.3305ms	0.7161ms	1.3965 KOps/s	1.4065 KOps/s	$\color{#d91a1a}-0.71\%$
test_vmap_mlp_speed_decorator[True-False]	0.8814ms	0.7178ms	1.3931 KOps/s	1.3960 KOps/s	$\color{#d91a1a}-0.21\%$
test_vmap_mlp_speed_decorator[False-True]	0.7756ms	0.6258ms	1.5979 KOps/s	1.5993 KOps/s	$\color{#d91a1a}-0.09\%$
test_vmap_mlp_speed_decorator[False-False]	0.7977ms	0.6257ms	1.5983 KOps/s	1.6056 KOps/s	$\color{#d91a1a}-0.45\%$
test_vmap_transformer_speed[True-True]	9.2002ms	8.9089ms	112.2471 Ops/s	112.1532 Ops/s	$\color{#35bf28}+0.08\%$
test_vmap_transformer_speed[True-False]	10.0895ms	8.8888ms	112.5009 Ops/s	112.2736 Ops/s	$\color{#35bf28}+0.20\%$
test_vmap_transformer_speed[False-True]	8.9898ms	8.8233ms	113.3368 Ops/s	112.8560 Ops/s	$\color{#35bf28}+0.43\%$
test_vmap_transformer_speed[False-False]	9.0024ms	8.8113ms	113.4908 Ops/s	113.3285 Ops/s	$\color{#35bf28}+0.14\%$
test_vmap_transformer_speed_decorator[True-True]	21.3862ms	21.1412ms	47.3011 Ops/s	47.8253 Ops/s	$\color{#d91a1a}-1.10\%$
test_vmap_transformer_speed_decorator[True-False]	21.2396ms	21.0655ms	47.4709 Ops/s	47.7114 Ops/s	$\color{#d91a1a}-0.50\%$
test_vmap_transformer_speed_decorator[False-True]	21.1678ms	21.0183ms	47.5775 Ops/s	48.2246 Ops/s	$\color{#d91a1a}-1.34\%$
test_vmap_transformer_speed_decorator[False-False]	21.1171ms	20.9466ms	47.7405 Ops/s	48.0682 Ops/s	$\color{#d91a1a}-0.68\%$
test_to_module_speed[True]	1.5716ms	1.1531ms	867.2531 Ops/s	870.5024 Ops/s	$\color{#d91a1a}-0.37\%$
test_to_module_speed[False]	1.6237ms	1.1306ms	884.5010 Ops/s	884.4466 Ops/s	$+0.01\%$
test_tc_init	59.2610μs	41.5989μs	24.0391 KOps/s	26.1934 KOps/s	$\textbf{\color{#d91a1a}-8.22\%}$
test_tc_init_nested	0.1628ms	81.6315μs	12.2502 KOps/s	13.0267 KOps/s	$\textbf{\color{#d91a1a}-5.96\%}$
test_tc_first_layer_tensor	5.9650μs	0.7862μs	1.2719 MOps/s	1.2866 MOps/s	$\color{#d91a1a}-1.15\%$
test_tc_first_layer_nontensor	15.3900μs	2.5587μs	390.8296 KOps/s	392.9382 KOps/s	$\color{#d91a1a}-0.54\%$
test_tc_second_layer_tensor	47.3410μs	1.6094μs	621.3590 KOps/s	627.9435 KOps/s	$\color{#d91a1a}-1.05\%$
test_tc_second_layer_nontensor	28.7200μs	3.3725μs	296.5125 KOps/s	296.7085 KOps/s	$\color{#d91a1a}-0.07\%$
test_unbind	0.1865s	10.6193ms	94.1677 Ops/s	83.0125 Ops/s	$\textbf{\color{#35bf28}+13.44\%}$
test_full_like	0.7940ms	0.5757ms	1.7369 KOps/s	1.7342 KOps/s	$\color{#35bf28}+0.16\%$
test_zeros_like	0.2654ms	0.1976ms	5.0602 KOps/s	5.0503 KOps/s	$\color{#35bf28}+0.20\%$
test_ones_like	0.3811ms	0.1976ms	5.0602 KOps/s	5.0605 KOps/s	$-0.00\%$
test_clone	0.5556ms	0.4143ms	2.4136 KOps/s	2.4087 KOps/s	$\color{#35bf28}+0.20\%$
test_squeeze	28.6710μs	10.9595μs	91.2449 KOps/s	90.7734 KOps/s	$\color{#35bf28}+0.52\%$
test_unsqueeze	0.2556ms	82.3649μs	12.1411 KOps/s	12.2743 KOps/s	$\color{#d91a1a}-1.09\%$
test_split	0.4678ms	0.1810ms	5.5263 KOps/s	5.4642 KOps/s	$\color{#35bf28}+1.14\%$
test_permute	0.2563ms	0.1929ms	5.1829 KOps/s	5.0951 KOps/s	$\color{#35bf28}+1.72\%$
test_stack	1.3518ms	0.9148ms	1.0931 KOps/s	1.1103 KOps/s	$\color{#d91a1a}-1.55\%$
test_cat	1.3789ms	1.2317ms	811.9127 Ops/s	811.4290 Ops/s	$\color{#35bf28}+0.06\%$