[Refactor] Update nn inline_inbuilt check

[vmoens]

Stack from ghstack (oldest at bottom):

• -> [Refactor] Update nn inline_inbuilt check #1029

[github-actions]

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

Total Benchmarks: 216. Improved: $\large\color{#35bf28}36$. Worsened: $\large\color{#d91a1a}10$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	64.0890μs	23.9661μs	41.7256 KOps/s	40.3761 KOps/s	$\color{#35bf28}+3.34\%$
test_plain_set_stack_nested	73.7470μs	24.6015μs	40.6480 KOps/s	40.8406 KOps/s	$\color{#d91a1a}-0.47\%$
test_plain_set_nested_inplace	77.2440μs	26.4248μs	37.8432 KOps/s	37.3285 KOps/s	$\color{#35bf28}+1.38\%$
test_plain_set_stack_nested_inplace	81.2710μs	26.4190μs	37.8516 KOps/s	37.2078 KOps/s	$\color{#35bf28}+1.73\%$
test_items	0.1354ms	4.2297μs	236.4251 KOps/s	238.7453 KOps/s	$\color{#d91a1a}-0.97\%$
test_items_nested	0.5751ms	0.3822ms	2.6162 KOps/s	2.6025 KOps/s	$\color{#35bf28}+0.53\%$
test_items_nested_locked	0.5694ms	0.3790ms	2.6383 KOps/s	2.5933 KOps/s	$\color{#35bf28}+1.74\%$
test_items_nested_leaf	0.1598ms	79.3146μs	12.6080 KOps/s	12.5147 KOps/s	$\color{#35bf28}+0.75\%$
test_items_stack_nested	0.5390ms	0.3851ms	2.5964 KOps/s	2.5693 KOps/s	$\color{#35bf28}+1.06\%$
test_items_stack_nested_leaf	0.1761ms	82.4420μs	12.1297 KOps/s	12.2046 KOps/s	$\color{#d91a1a}-0.61\%$
test_items_stack_nested_locked	0.5896ms	0.3824ms	2.6150 KOps/s	2.5636 KOps/s	$\color{#35bf28}+2.01\%$
test_keys	20.5390μs	3.4953μs	286.1013 KOps/s	287.6261 KOps/s	$\color{#d91a1a}-0.53\%$
test_keys_nested	0.2521ms	0.1342ms	7.4533 KOps/s	7.3909 KOps/s	$\color{#35bf28}+0.84\%$
test_keys_nested_locked	1.6490ms	0.1397ms	7.1603 KOps/s	7.1198 KOps/s	$\color{#35bf28}+0.57\%$
test_keys_nested_leaf	0.2389ms	0.1172ms	8.5293 KOps/s	8.4294 KOps/s	$\color{#35bf28}+1.18\%$
test_keys_stack_nested	0.2369ms	0.1339ms	7.4660 KOps/s	7.1847 KOps/s	$\color{#35bf28}+3.92\%$
test_keys_stack_nested_leaf	0.2041ms	0.1166ms	8.5730 KOps/s	8.4934 KOps/s	$\color{#35bf28}+0.94\%$
test_keys_stack_nested_locked	0.2102ms	0.1392ms	7.1827 KOps/s	7.1148 KOps/s	$\color{#35bf28}+0.95\%$
test_values	7.0372μs	1.0538μs	948.9887 KOps/s	956.7748 KOps/s	$\color{#d91a1a}-0.81\%$
test_values_nested	0.1607ms	91.4858μs	10.9307 KOps/s	10.4355 KOps/s	$\color{#35bf28}+4.74\%$
test_values_nested_locked	0.1697ms	92.3886μs	10.8238 KOps/s	10.4335 KOps/s	$\color{#35bf28}+3.74\%$
test_values_nested_leaf	0.1576ms	78.9885μs	12.6601 KOps/s	12.4123 KOps/s	$\color{#35bf28}+2.00\%$
test_values_stack_nested	0.1677ms	93.6781μs	10.6748 KOps/s	10.5921 KOps/s	$\color{#35bf28}+0.78\%$
test_values_stack_nested_leaf	0.1484ms	78.7848μs	12.6928 KOps/s	12.3894 KOps/s	$\color{#35bf28}+2.45\%$
test_values_stack_nested_locked	0.1739ms	94.1023μs	10.6267 KOps/s	10.4923 KOps/s	$\color{#35bf28}+1.28\%$
test_membership	5.8080μs	0.7497μs	1.3339 MOps/s	1.3105 MOps/s	$\color{#35bf28}+1.79\%$
test_membership_nested	36.9790μs	2.7681μs	361.2581 KOps/s	357.1578 KOps/s	$\color{#35bf28}+1.15\%$
test_membership_nested_leaf	19.9670μs	2.8113μs	355.7023 KOps/s	354.8912 KOps/s	$\color{#35bf28}+0.23\%$
test_membership_stacked_nested	42.1080μs	2.7424μs	364.6423 KOps/s	366.8093 KOps/s	$\color{#d91a1a}-0.59\%$
test_membership_stacked_nested_leaf	17.3120μs	2.8084μs	356.0708 KOps/s	358.8642 KOps/s	$\color{#d91a1a}-0.78\%$
test_membership_nested_last	28.1830μs	4.1773μs	239.3869 KOps/s	237.5539 KOps/s	$\color{#35bf28}+0.77\%$
test_membership_nested_leaf_last	48.8330μs	4.1660μs	240.0393 KOps/s	237.4130 KOps/s	$\color{#35bf28}+1.11\%$
test_membership_stacked_nested_last	28.0020μs	4.1825μs	239.0910 KOps/s	185.6407 KOps/s	$\textbf{\color{#35bf28}+28.79\%}$
test_membership_stacked_nested_leaf_last	22.2620μs	4.1400μs	241.5430 KOps/s	184.0590 KOps/s	$\textbf{\color{#35bf28}+31.23\%}$
test_nested_getleaf	33.2120μs	10.7899μs	92.6794 KOps/s	90.8161 KOps/s	$\color{#35bf28}+2.05\%$
test_nested_get	35.2260μs	10.2591μs	97.4746 KOps/s	96.2255 KOps/s	$\color{#35bf28}+1.30\%$
test_stacked_getleaf	34.5350μs	10.7765μs	92.7943 KOps/s	92.7374 KOps/s	$\color{#35bf28}+0.06\%$
test_stacked_get	32.7110μs	10.3686μs	96.4453 KOps/s	97.6266 KOps/s	$\color{#d91a1a}-1.21\%$
test_nested_getitemleaf	36.6180μs	11.1818μs	89.4310 KOps/s	88.1563 KOps/s	$\color{#35bf28}+1.45\%$
test_nested_getitem	32.6510μs	10.5160μs	95.0934 KOps/s	96.3982 KOps/s	$\color{#d91a1a}-1.35\%$
test_stacked_getitemleaf	47.1070μs	11.0728μs	90.3113 KOps/s	88.5544 KOps/s	$\color{#35bf28}+1.98\%$
test_stacked_getitem	28.2420μs	10.5025μs	95.2150 KOps/s	94.5041 KOps/s	$\color{#35bf28}+0.75\%$
test_lock_nested	84.7239ms	0.5904ms	1.6937 KOps/s	1.9593 KOps/s	$\textbf{\color{#d91a1a}-13.56\%}$
test_lock_stack_nested	0.7325ms	0.4687ms	2.1337 KOps/s	2.0730 KOps/s	$\color{#35bf28}+2.93\%$
test_unlock_nested	86.6992ms	0.5091ms	1.9644 KOps/s	2.3078 KOps/s	$\textbf{\color{#d91a1a}-14.88\%}$
test_unlock_stack_nested	0.5943ms	0.3842ms	2.6029 KOps/s	2.4853 KOps/s	$\color{#35bf28}+4.74\%$
test_flatten_speed	0.2195ms	0.1007ms	9.9281 KOps/s	10.0569 KOps/s	$\color{#d91a1a}-1.28\%$
test_unflatten_speed	2.0164ms	0.5277ms	1.8951 KOps/s	1.9564 KOps/s	$\color{#d91a1a}-3.13\%$
test_common_ops	2.1111ms	1.1379ms	878.8005 Ops/s	846.8160 Ops/s	$\color{#35bf28}+3.78\%$
test_creation	36.4280μs	2.0915μs	478.1262 KOps/s	478.1387 KOps/s	$-0.00\%$
test_creation_empty	43.3610μs	18.6163μs	53.7165 KOps/s	50.0477 KOps/s	$\textbf{\color{#35bf28}+7.33\%}$
test_creation_nested_1	54.3910μs	21.6710μs	46.1447 KOps/s	41.3428 KOps/s	$\textbf{\color{#35bf28}+11.61\%}$
test_creation_nested_2	69.6400μs	25.6862μs	38.9313 KOps/s	36.3043 KOps/s	$\textbf{\color{#35bf28}+7.24\%}$
test_clone	66.9250μs	16.7563μs	59.6790 KOps/s	57.7686 KOps/s	$\color{#35bf28}+3.31\%$
test_getitem[int]	0.9382ms	16.5254μs	60.5131 KOps/s	58.3927 KOps/s	$\color{#35bf28}+3.63\%$
test_getitem[slice_int]	0.1475ms	31.5774μs	31.6682 KOps/s	31.7434 KOps/s	$\color{#d91a1a}-0.24\%$
test_getitem[range]	0.2197ms	56.5663μs	17.6784 KOps/s	17.1964 KOps/s	$\color{#35bf28}+2.80\%$
test_getitem[tuple]	0.1304ms	24.7855μs	40.3462 KOps/s	37.8213 KOps/s	$\textbf{\color{#35bf28}+6.68\%}$
test_getitem[list]	0.2013ms	51.9310μs	19.2563 KOps/s	18.8820 KOps/s	$\color{#35bf28}+1.98\%$
test_setitem_dim[int]	63.4390μs	32.9364μs	30.3616 KOps/s	30.5474 KOps/s	$\color{#d91a1a}-0.61\%$
test_setitem_dim[slice_int]	0.1053ms	61.7111μs	16.2046 KOps/s	16.0739 KOps/s	$\color{#35bf28}+0.81\%$
test_setitem_dim[range]	0.1370ms	85.2504μs	11.7301 KOps/s	11.5804 KOps/s	$\color{#35bf28}+1.29\%$
test_setitem_dim[tuple]	80.2400μs	49.2941μs	20.2864 KOps/s	20.0254 KOps/s	$\color{#35bf28}+1.30\%$
test_setitem	0.1042ms	29.4194μs	33.9912 KOps/s	32.4766 KOps/s	$\color{#35bf28}+4.66\%$
test_set	0.3065ms	29.0613μs	34.4100 KOps/s	32.5231 KOps/s	$\textbf{\color{#35bf28}+5.80\%}$
test_set_shared	3.2905ms	0.2184ms	4.5791 KOps/s	4.4839 KOps/s	$\color{#35bf28}+2.12\%$
test_update	0.8359ms	37.0764μs	26.9714 KOps/s	25.8934 KOps/s	$\color{#35bf28}+4.16\%$
test_update_nested	0.1293ms	48.4159μs	20.6544 KOps/s	20.1594 KOps/s	$\color{#35bf28}+2.46\%$
test_update__nested	0.1330ms	43.9742μs	22.7406 KOps/s	21.6187 KOps/s	$\textbf{\color{#35bf28}+5.19\%}$
test_set_nested	85.6000μs	31.4443μs	31.8023 KOps/s	30.1097 KOps/s	$\textbf{\color{#35bf28}+5.62\%}$
test_set_nested_new	0.1109ms	36.8005μs	27.1735 KOps/s	25.7628 KOps/s	$\textbf{\color{#35bf28}+5.48\%}$
test_select	0.2092ms	54.0201μs	18.5116 KOps/s	17.7929 KOps/s	$\color{#35bf28}+4.04\%$
test_select_nested	0.1418ms	60.6544μs	16.4868 KOps/s	16.7796 KOps/s	$\color{#d91a1a}-1.74\%$
test_exclude_nested	0.1455ms	75.1523μs	13.3063 KOps/s	13.5030 KOps/s	$\color{#d91a1a}-1.46\%$
test_empty[True]	0.7295ms	0.3499ms	2.8577 KOps/s	2.8488 KOps/s	$\color{#35bf28}+0.31\%$
test_empty[False]	9.8110μs	1.2329μs	811.1221 KOps/s	824.3601 KOps/s	$\color{#d91a1a}-1.61\%$
test_unbind_speed	1.4136ms	0.3379ms	2.9594 KOps/s	3.2658 KOps/s	$\textbf{\color{#d91a1a}-9.38\%}$
test_unbind_speed_stack0	0.5989ms	0.2937ms	3.4045 KOps/s	3.3223 KOps/s	$\color{#35bf28}+2.47\%$
test_unbind_speed_stack1	0.1104s	0.8363ms	1.1958 KOps/s	1.3301 KOps/s	$\textbf{\color{#d91a1a}-10.10\%}$
test_split	3.2342ms	2.0093ms	497.6841 Ops/s	449.9728 Ops/s	$\textbf{\color{#35bf28}+10.60\%}$
test_chunk	89.8989ms	2.1997ms	454.6139 Ops/s	446.4661 Ops/s	$\color{#35bf28}+1.82\%$
test_creation[device0]	0.2629ms	0.1174ms	8.5212 KOps/s	8.4460 KOps/s	$\color{#35bf28}+0.89\%$
test_creation_from_tensor	3.8417ms	0.1177ms	8.4984 KOps/s	8.4137 KOps/s	$\color{#35bf28}+1.01\%$
test_add_one[memmap_tensor0]	0.1582ms	7.4960μs	133.4041 KOps/s	132.8800 KOps/s	$\color{#35bf28}+0.39\%$
test_contiguous[memmap_tensor0]	30.3460μs	1.9300μs	518.1456 KOps/s	465.3993 KOps/s	$\textbf{\color{#35bf28}+11.33\%}$
test_stack[memmap_tensor0]	35.0760μs	5.6633μs	176.5753 KOps/s	150.0957 KOps/s	$\textbf{\color{#35bf28}+17.64\%}$
test_memmaptd_index	1.6005ms	0.4138ms	2.4167 KOps/s	2.3914 KOps/s	$\color{#35bf28}+1.06\%$
test_memmaptd_index_astensor	0.9947ms	0.5073ms	1.9712 KOps/s	1.9239 KOps/s	$\color{#35bf28}+2.46\%$
test_memmaptd_index_op	90.3606ms	1.1525ms	867.6830 Ops/s	889.1527 Ops/s	$\color{#d91a1a}-2.41\%$
test_serialize_model	0.1218s	0.1166s	8.5735 Ops/s	8.3267 Ops/s	$\color{#35bf28}+2.96\%$
test_serialize_model_pickle	0.4489s	0.3887s	2.5724 Ops/s	2.5057 Ops/s	$\color{#35bf28}+2.66\%$
test_serialize_weights	0.1254s	0.1161s	8.6108 Ops/s	8.3722 Ops/s	$\color{#35bf28}+2.85\%$
test_serialize_weights_returnearly	0.2459s	0.1725s	5.7959 Ops/s	5.4556 Ops/s	$\textbf{\color{#35bf28}+6.24\%}$
test_serialize_weights_pickle	0.5484s	0.4450s	2.2470 Ops/s	2.5153 Ops/s	$\textbf{\color{#d91a1a}-10.67\%}$
test_serialize_weights_filesystem	0.1492s	0.1433s	6.9773 Ops/s	6.8180 Ops/s	$\color{#35bf28}+2.34\%$
test_serialize_model_filesystem	0.1650s	0.1459s	6.8560 Ops/s	6.4744 Ops/s	$\textbf{\color{#35bf28}+5.89\%}$
test_reshape_pytree	0.1029ms	38.0168μs	26.3042 KOps/s	24.9960 KOps/s	$\textbf{\color{#35bf28}+5.23\%}$
test_reshape_td	0.1006ms	44.8181μs	22.3124 KOps/s	21.0375 KOps/s	$\textbf{\color{#35bf28}+6.06\%}$
test_view_pytree	84.2860μs	37.9034μs	26.3828 KOps/s	25.1871 KOps/s	$\color{#35bf28}+4.75\%$
test_view_td	0.1210ms	50.2218μs	19.9117 KOps/s	19.1661 KOps/s	$\color{#35bf28}+3.89\%$
test_unbind_pytree	72.0140μs	35.6204μs	28.0738 KOps/s	26.6773 KOps/s	$\textbf{\color{#35bf28}+5.24\%}$
test_unbind_td	0.3047ms	45.7753μs	21.8458 KOps/s	21.5765 KOps/s	$\color{#35bf28}+1.25\%$
test_split_pytree	76.4520μs	37.6788μs	26.5401 KOps/s	25.2278 KOps/s	$\textbf{\color{#35bf28}+5.20\%}$
test_split_td	0.4320ms	58.7542μs	17.0201 KOps/s	17.0215 KOps/s	$-0.01\%$
test_add_pytree	0.1597ms	44.6452μs	22.3988 KOps/s	20.9342 KOps/s	$\textbf{\color{#35bf28}+7.00\%}$
test_add_td	0.1690ms	85.1300μs	11.7467 KOps/s	10.9216 KOps/s	$\textbf{\color{#35bf28}+7.56\%}$
test_compile_add_one_nested[tensordict-compile]	0.1122ms	57.6173μs	17.3559 KOps/s	16.7746 KOps/s	$\color{#35bf28}+3.47\%$
test_compile_add_one_nested[tensordict-eager]	0.3398ms	0.1976ms	5.0619 KOps/s	5.0930 KOps/s	$\color{#d91a1a}-0.61\%$
test_compile_add_one_nested[pytree-compile]	0.1305ms	55.5317μs	18.0077 KOps/s	17.0056 KOps/s	$\textbf{\color{#35bf28}+5.89\%}$
test_compile_add_one_nested[pytree-eager]	0.2897ms	0.1386ms	7.2132 KOps/s	6.8934 KOps/s	$\color{#35bf28}+4.64\%$
test_compile_copy_nested[tensordict-compile]	58.8400μs	23.5511μs	42.4608 KOps/s	40.8461 KOps/s	$\color{#35bf28}+3.95\%$
test_compile_copy_nested[tensordict-eager]	0.1508ms	74.6404μs	13.3976 KOps/s	13.3393 KOps/s	$\color{#35bf28}+0.44\%$
test_compile_copy_nested[pytree-compile]	0.1478ms	75.7931μs	13.1938 KOps/s	13.0894 KOps/s	$\color{#35bf28}+0.80\%$
test_compile_copy_nested[pytree-eager]	0.1345ms	69.5641μs	14.3752 KOps/s	14.3488 KOps/s	$\color{#35bf28}+0.18\%$
test_compile_add_one_flat[tensordict-compile]	0.3489ms	0.1800ms	5.5560 KOps/s	5.3803 KOps/s	$\color{#35bf28}+3.27\%$
test_compile_add_one_flat[tensordict-eager]	0.4300ms	0.2376ms	4.2080 KOps/s	4.1440 KOps/s	$\color{#35bf28}+1.54\%$
test_compile_add_one_flat[tensorclass-compile]	0.1233ms	48.6206μs	20.5674 KOps/s	20.7572 KOps/s	$\color{#d91a1a}-0.91\%$
test_compile_add_one_flat[tensorclass-eager]	0.4347ms	78.1734μs	12.7921 KOps/s	12.5643 KOps/s	$\color{#35bf28}+1.81\%$
test_compile_add_one_flat[pytree-compile]	0.3849ms	0.1738ms	5.7549 KOps/s	5.6772 KOps/s	$\color{#35bf28}+1.37\%$
test_compile_add_one_flat[pytree-eager]	0.5749ms	0.2892ms	3.4575 KOps/s	3.3694 KOps/s	$\color{#35bf28}+2.61\%$
test_compile_add_self_flat[tensordict-eager]	0.4253ms	0.2728ms	3.6651 KOps/s	3.6260 KOps/s	$\color{#35bf28}+1.08\%$
test_compile_add_self_flat[tensordict-compile]	0.4071ms	0.1850ms	5.4062 KOps/s	5.4962 KOps/s	$\color{#d91a1a}-1.64\%$
test_compile_add_self_flat[tensorclass-eager]	0.1747ms	74.1267μs	13.4904 KOps/s	13.4113 KOps/s	$\color{#35bf28}+0.59\%$
test_compile_add_self_flat[tensorclass-compile]	0.1618ms	48.6236μs	20.5662 KOps/s	20.1605 KOps/s	$\color{#35bf28}+2.01\%$
test_compile_add_self_flat[pytree-eager]	0.4216ms	0.2316ms	4.3177 KOps/s	4.1964 KOps/s	$\color{#35bf28}+2.89\%$
test_compile_add_self_flat[pytree-compile]	0.3186ms	0.1733ms	5.7692 KOps/s	5.5874 KOps/s	$\color{#35bf28}+3.25\%$
test_compile_copy_flat[tensordict-compile]	0.1999ms	0.1093ms	9.1529 KOps/s	8.9306 KOps/s	$\color{#35bf28}+2.49\%$
test_compile_copy_flat[tensordict-eager]	0.1357ms	78.7564μs	12.6974 KOps/s	12.6309 KOps/s	$\color{#35bf28}+0.53\%$
test_compile_copy_flat[pytree-compile]	0.1999ms	77.3830μs	12.9227 KOps/s	12.3939 KOps/s	$\color{#35bf28}+4.27\%$
test_compile_copy_flat[pytree-eager]	0.1303ms	69.2095μs	14.4489 KOps/s	13.9759 KOps/s	$\color{#35bf28}+3.38\%$
test_compile_assign_and_add[tensordict-compile]	0.2735ms	0.1906ms	5.2469 KOps/s	5.0593 KOps/s	$\color{#35bf28}+3.71\%$
test_compile_assign_and_add[tensordict-eager]	1.9582ms	1.7168ms	582.4645 Ops/s	553.2107 Ops/s	$\textbf{\color{#35bf28}+5.29\%}$
test_compile_assign_and_add[pytree-compile]	0.2647ms	0.1868ms	5.3526 KOps/s	5.1567 KOps/s	$\color{#35bf28}+3.80\%$
test_compile_assign_and_add[pytree-eager]	1.1949ms	1.0837ms	922.7596 Ops/s	882.5285 Ops/s	$\color{#35bf28}+4.56\%$
test_compile_assign_and_add_stack[compile]	0.7385ms	0.4175ms	2.3950 KOps/s	2.3853 KOps/s	$\color{#35bf28}+0.41\%$
test_compile_assign_and_add_stack[eager]	4.4990ms	3.9828ms	251.0822 Ops/s	233.9889 Ops/s	$\textbf{\color{#35bf28}+7.31\%}$
test_compile_indexing[tensor-tensordict-compile]	91.4110μs	34.3573μs	29.1059 KOps/s	27.5405 KOps/s	$\textbf{\color{#35bf28}+5.68\%}$
test_compile_indexing[tensor-tensordict-eager]	0.8402ms	48.8481μs	20.4716 KOps/s	20.3399 KOps/s	$\color{#35bf28}+0.65\%$
test_compile_indexing[tensor-tensorclass-compile]	72.2540μs	29.4927μs	33.9067 KOps/s	32.9239 KOps/s	$\color{#35bf28}+2.98\%$
test_compile_indexing[tensor-tensorclass-eager]	91.7810μs	28.3711μs	35.2471 KOps/s	34.1182 KOps/s	$\color{#35bf28}+3.31\%$
test_compile_indexing[tensor-pytree-compile]	97.7220μs	29.3376μs	34.0860 KOps/s	32.2247 KOps/s	$\textbf{\color{#35bf28}+5.78\%}$
test_compile_indexing[tensor-pytree-eager]	95.9590μs	29.3369μs	34.0867 KOps/s	34.2779 KOps/s	$\color{#d91a1a}-0.56\%$
test_compile_indexing[slice-tensordict-compile]	0.1314ms	73.0659μs	13.6863 KOps/s	13.3190 KOps/s	$\color{#35bf28}+2.76\%$
test_compile_indexing[slice-tensordict-eager]	0.5662ms	28.1992μs	35.4620 KOps/s	35.7222 KOps/s	$\color{#d91a1a}-0.73\%$
test_compile_indexing[slice-tensorclass-compile]	0.1407ms	66.9021μs	14.9472 KOps/s	14.1491 KOps/s	$\textbf{\color{#35bf28}+5.64\%}$
test_compile_indexing[slice-tensorclass-eager]	0.2201ms	23.1681μs	43.1628 KOps/s	42.2880 KOps/s	$\color{#35bf28}+2.07\%$
test_compile_indexing[slice-pytree-compile]	0.1881ms	67.2834μs	14.8625 KOps/s	14.3009 KOps/s	$\color{#35bf28}+3.93\%$
test_compile_indexing[slice-pytree-eager]	0.1123ms	23.1584μs	43.1810 KOps/s	42.6605 KOps/s	$\color{#35bf28}+1.22\%$
test_compile_indexing[int-tensordict-compile]	0.1485ms	72.6371μs	13.7671 KOps/s	13.2564 KOps/s	$\color{#35bf28}+3.85\%$
test_compile_indexing[int-tensordict-eager]	0.7744ms	27.8788μs	35.8696 KOps/s	35.8777 KOps/s	$\color{#d91a1a}-0.02\%$
test_compile_indexing[int-tensorclass-compile]	0.1360ms	66.6136μs	15.0119 KOps/s	14.4074 KOps/s	$\color{#35bf28}+4.20\%$
test_compile_indexing[int-tensorclass-eager]	62.1050μs	23.0207μs	43.4391 KOps/s	42.6022 KOps/s	$\color{#35bf28}+1.96\%$
test_compile_indexing[int-pytree-compile]	0.1323ms	66.6007μs	15.0149 KOps/s	14.3659 KOps/s	$\color{#35bf28}+4.52\%$
test_compile_indexing[int-pytree-eager]	78.4160μs	22.9420μs	43.5882 KOps/s	42.4524 KOps/s	$\color{#35bf28}+2.68\%$
test_mod_add[eager]	87.6930μs	25.2302μs	39.6350 KOps/s	37.7281 KOps/s	$\textbf{\color{#35bf28}+5.05\%}$
test_mod_add[compile]	0.1067ms	36.9729μs	27.0468 KOps/s	25.8018 KOps/s	$\color{#35bf28}+4.83\%$
test_mod_add[compile-overhead]	83.8960μs	37.8328μs	26.4321 KOps/s	24.4321 KOps/s	$\textbf{\color{#35bf28}+8.19\%}$
test_mod_wrap[eager]	0.4428ms	0.2089ms	4.7864 KOps/s	4.6731 KOps/s	$\color{#35bf28}+2.42\%$
test_mod_wrap[compile]	0.4514ms	0.2337ms	4.2785 KOps/s	4.2124 KOps/s	$\color{#35bf28}+1.57\%$
test_mod_wrap[compile-overhead]	0.3788ms	0.2297ms	4.3529 KOps/s	4.2489 KOps/s	$\color{#35bf28}+2.45\%$
test_mod_wrap_and_backward[eager]	12.4185ms	10.5751ms	94.5619 Ops/s	92.4932 Ops/s	$\color{#35bf28}+2.24\%$
test_mod_wrap_and_backward[compile]	11.9743ms	10.7013ms	93.4463 Ops/s	87.1146 Ops/s	$\textbf{\color{#35bf28}+7.27\%}$
test_mod_wrap_and_backward[compile-overhead]	12.2038ms	10.6834ms	93.6033 Ops/s	86.3893 Ops/s	$\textbf{\color{#35bf28}+8.35\%}$
test_seq_add[eager]	0.1666ms	91.0391μs	10.9843 KOps/s	10.7831 KOps/s	$\color{#35bf28}+1.87\%$
test_seq_add[compile]	0.1342ms	63.5729μs	15.7300 KOps/s	14.9877 KOps/s	$\color{#35bf28}+4.95\%$
test_seq_add[compile-overhead]	0.1291ms	62.4616μs	16.0098 KOps/s	15.2277 KOps/s	$\textbf{\color{#35bf28}+5.14\%}$
test_seq_wrap[eager]	0.6591ms	0.3824ms	2.6151 KOps/s	2.5640 KOps/s	$\color{#35bf28}+2.00\%$
test_seq_wrap[compile]	0.5007ms	0.2681ms	3.7303 KOps/s	3.6496 KOps/s	$\color{#35bf28}+2.21\%$
test_seq_wrap[compile-overhead]	0.5164ms	0.2665ms	3.7528 KOps/s	3.4635 KOps/s	$\textbf{\color{#35bf28}+8.35\%}$
test_func_call_runtime[False-eager]	0.7732ms	0.5091ms	1.9642 KOps/s	1.8603 KOps/s	$\textbf{\color{#35bf28}+5.59\%}$
test_func_call_runtime[False-compile]	0.7447ms	0.4972ms	2.0112 KOps/s	1.9555 KOps/s	$\color{#35bf28}+2.85\%$
test_func_call_runtime[False-compile-overhead]	1.0914ms	0.5016ms	1.9935 KOps/s	1.9817 KOps/s	$\color{#35bf28}+0.59\%$
test_func_call_runtime[True-eager]	1.2038ms	0.7301ms	1.3697 KOps/s	1.3187 KOps/s	$\color{#35bf28}+3.87\%$
test_func_call_runtime[True-compile]	0.6756ms	0.5114ms	1.9554 KOps/s	1.9543 KOps/s	$\color{#35bf28}+0.06\%$
test_func_call_runtime[True-compile-overhead]	0.5962ms	0.5130ms	1.9492 KOps/s	1.9603 KOps/s	$\color{#d91a1a}-0.57\%$
test_func_call_cm_runtime[False-eager]	0.6270ms	0.5240ms	1.9082 KOps/s	1.8816 KOps/s	$\color{#35bf28}+1.42\%$
test_func_call_cm_runtime[False-compile]	0.9662ms	0.5003ms	1.9990 KOps/s	1.9904 KOps/s	$\color{#35bf28}+0.43\%$
test_func_call_cm_runtime[False-compile-overhead]	0.5764ms	0.4969ms	2.0123 KOps/s	1.8786 KOps/s	$\textbf{\color{#35bf28}+7.12\%}$
test_func_call_cm_runtime[True-eager]	1.2083ms	0.8732ms	1.1452 KOps/s	1.1160 KOps/s	$\color{#35bf28}+2.62\%$
test_func_call_cm_runtime[True-compile]	1.0264ms	0.7283ms	1.3731 KOps/s	1.3318 KOps/s	$\color{#35bf28}+3.11\%$
test_func_call_cm_runtime[True-compile-overhead]	0.8243ms	0.7291ms	1.3716 KOps/s	1.3321 KOps/s	$\color{#35bf28}+2.96\%$
test_vmap_func_call_cm_runtime[eager]	2.5895ms	1.9023ms	525.6888 Ops/s	523.2335 Ops/s	$\color{#35bf28}+0.47\%$
test_vmap_func_call_cm_runtime[compile]	2.5312ms	1.9587ms	510.5526 Ops/s	508.8822 Ops/s	$\color{#35bf28}+0.33\%$
test_vmap_func_call_cm_runtime[compile-overhead]	2.5837ms	1.9396ms	515.5668 Ops/s	509.7985 Ops/s	$\color{#35bf28}+1.13\%$
test_distributed	0.4947ms	0.1278ms	7.8246 KOps/s	7.8451 KOps/s	$\color{#d91a1a}-0.26\%$
test_tdmodule	0.2842ms	23.7915μs	42.0319 KOps/s	52.9710 KOps/s	$\textbf{\color{#d91a1a}-20.65\%}$
test_tdmodule_dispatch	60.6830μs	36.9570μs	27.0584 KOps/s	26.7151 KOps/s	$\color{#35bf28}+1.29\%$
test_tdseq	36.5680μs	21.6241μs	46.2447 KOps/s	46.6775 KOps/s	$\color{#d91a1a}-0.93\%$
test_tdseq_dispatch	73.5970μs	42.5673μs	23.4922 KOps/s	23.4616 KOps/s	$\color{#35bf28}+0.13\%$
test_instantiation_functorch	1.8050ms	1.5725ms	635.9184 Ops/s	630.8680 Ops/s	$\color{#35bf28}+0.80\%$
test_exec_functorch	0.4128ms	0.1858ms	5.3810 KOps/s	5.3545 KOps/s	$\color{#35bf28}+0.49\%$
test_exec_functional_call	0.2728ms	0.1737ms	5.7556 KOps/s	5.6733 KOps/s	$\color{#35bf28}+1.45\%$
test_exec_td_decorator	0.5114ms	0.2328ms	4.2956 KOps/s	4.2058 KOps/s	$\color{#35bf28}+2.14\%$
test_vmap_mlp_speed_decorator[True-True]	1.0147ms	0.6537ms	1.5297 KOps/s	1.5414 KOps/s	$\color{#d91a1a}-0.76\%$
test_vmap_mlp_speed_decorator[True-False]	1.1178ms	0.6517ms	1.5344 KOps/s	1.5192 KOps/s	$\color{#35bf28}+1.00\%$
test_vmap_mlp_speed_decorator[False-True]	1.2588ms	0.5340ms	1.8728 KOps/s	1.8160 KOps/s	$\color{#35bf28}+3.13\%$
test_vmap_mlp_speed_decorator[False-False]	0.7187ms	0.5258ms	1.9018 KOps/s	1.8629 KOps/s	$\color{#35bf28}+2.09\%$
test_to_module_speed[True]	2.0204ms	1.4247ms	701.9266 Ops/s	689.3084 Ops/s	$\color{#35bf28}+1.83\%$
test_to_module_speed[False]	1.6355ms	1.3803ms	724.4924 Ops/s	712.2248 Ops/s	$\color{#35bf28}+1.72\%$
test_tc_init	86.2220μs	46.2579μs	21.6180 KOps/s	21.1119 KOps/s	$\color{#35bf28}+2.40\%$
test_tc_init_nested	0.1412ms	92.3927μs	10.8234 KOps/s	10.3748 KOps/s	$\color{#35bf28}+4.32\%$
test_tc_first_layer_tensor	42.2180μs	1.5099μs	662.3011 KOps/s	654.3074 KOps/s	$\color{#35bf28}+1.22\%$
test_tc_first_layer_nontensor	15.7590μs	4.7053μs	212.5261 KOps/s	211.9877 KOps/s	$\color{#35bf28}+0.25\%$
test_tc_second_layer_tensor	25.0770μs	2.8662μs	348.8888 KOps/s	352.4934 KOps/s	$\color{#d91a1a}-1.02\%$
test_tc_second_layer_nontensor	26.1190μs	6.0727μs	164.6724 KOps/s	163.3894 KOps/s	$\color{#35bf28}+0.79\%$
test_unbind	7.7108ms	7.4688ms	133.8897 Ops/s	76.3632 Ops/s	$\textbf{\color{#35bf28}+75.33\%}$
test_full_like	20.5934ms	11.7054ms	85.4307 Ops/s	133.2378 Ops/s	$\textbf{\color{#d91a1a}-35.88\%}$
test_zeros_like	14.5310ms	7.3173ms	136.6618 Ops/s	353.9653 Ops/s	$\textbf{\color{#d91a1a}-61.39\%}$
test_ones_like	15.9134ms	7.4007ms	135.1233 Ops/s	301.3796 Ops/s	$\textbf{\color{#d91a1a}-55.17\%}$
test_clone	14.5969ms	9.0662ms	110.2992 Ops/s	192.8710 Ops/s	$\textbf{\color{#d91a1a}-42.81\%}$
test_squeeze	54.1110μs	12.2571μs	81.5856 KOps/s	81.4313 KOps/s	$\color{#35bf28}+0.19\%$
test_unsqueeze	0.2009ms	93.5313μs	10.6916 KOps/s	10.7040 KOps/s	$\color{#d91a1a}-0.12\%$
test_split	0.4403ms	0.1906ms	5.2462 KOps/s	5.0596 KOps/s	$\color{#35bf28}+3.69\%$
test_permute	0.4817ms	0.2178ms	4.5907 KOps/s	4.4733 KOps/s	$\color{#35bf28}+2.63\%$
test_stack	29.8145ms	25.3905ms	39.3849 Ops/s	40.4738 Ops/s	$\color{#d91a1a}-2.69\%$
test_cat	32.3179ms	25.4359ms	39.3146 Ops/s	40.5863 Ops/s	$\color{#d91a1a}-3.13\%$

[github-actions]

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

Total Benchmarks: 218. Improved: $\large\color{#35bf28}13$. Worsened: $\large\color{#d91a1a}8$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	0.4651ms	16.0175μs	62.4317 KOps/s	61.1340 KOps/s	$\color{#35bf28}+2.12\%$
test_plain_set_stack_nested	35.1510μs	16.1743μs	61.8265 KOps/s	60.6548 KOps/s	$\color{#35bf28}+1.93\%$
test_plain_set_nested_inplace	40.9900μs	17.3547μs	57.6212 KOps/s	57.1083 KOps/s	$\color{#35bf28}+0.90\%$
test_plain_set_stack_nested_inplace	47.0610μs	17.3988μs	57.4752 KOps/s	57.7637 KOps/s	$\color{#d91a1a}-0.50\%$
test_items	25.5310μs	2.8586μs	349.8193 KOps/s	344.1908 KOps/s	$\color{#35bf28}+1.64\%$
test_items_nested	0.4337ms	0.3393ms	2.9475 KOps/s	2.9659 KOps/s	$\color{#d91a1a}-0.62\%$
test_items_nested_locked	0.3823ms	0.3397ms	2.9441 KOps/s	2.9438 KOps/s	$+0.01\%$
test_items_nested_leaf	94.2510μs	62.1990μs	16.0774 KOps/s	16.0599 KOps/s	$\color{#35bf28}+0.11\%$
test_items_stack_nested	0.5323ms	0.3400ms	2.9409 KOps/s	2.9290 KOps/s	$\color{#35bf28}+0.41\%$
test_items_stack_nested_leaf	99.0120μs	64.3025μs	15.5515 KOps/s	15.6135 KOps/s	$\color{#d91a1a}-0.40\%$
test_items_stack_nested_locked	0.3778ms	0.3426ms	2.9192 KOps/s	2.8856 KOps/s	$\color{#35bf28}+1.17\%$
test_keys	30.7300μs	3.4216μs	292.2626 KOps/s	292.7639 KOps/s	$\color{#d91a1a}-0.17\%$
test_keys_nested	95.3020μs	69.1842μs	14.4542 KOps/s	14.2743 KOps/s	$\color{#35bf28}+1.26\%$
test_keys_nested_locked	2.1457ms	76.3915μs	13.0905 KOps/s	13.0672 KOps/s	$\color{#35bf28}+0.18\%$
test_keys_nested_leaf	92.0610μs	60.6503μs	16.4880 KOps/s	16.2137 KOps/s	$\color{#35bf28}+1.69\%$
test_keys_stack_nested	0.1160ms	71.1627μs	14.0523 KOps/s	14.0010 KOps/s	$\color{#35bf28}+0.37\%$
test_keys_stack_nested_leaf	91.7120μs	62.4053μs	16.0243 KOps/s	15.9083 KOps/s	$\color{#35bf28}+0.73\%$
test_keys_stack_nested_locked	0.1025ms	75.9725μs	13.1627 KOps/s	12.9873 KOps/s	$\color{#35bf28}+1.35\%$
test_values	5.2500μs	0.8399μs	1.1906 MOps/s	1.1463 MOps/s	$\color{#35bf28}+3.86\%$
test_values_nested	78.4710μs	48.2796μs	20.7127 KOps/s	20.4650 KOps/s	$\color{#35bf28}+1.21\%$
test_values_nested_locked	0.1785ms	49.5703μs	20.1734 KOps/s	20.0132 KOps/s	$\color{#35bf28}+0.80\%$
test_values_nested_leaf	72.5910μs	42.3864μs	23.5925 KOps/s	23.5299 KOps/s	$\color{#35bf28}+0.27\%$
test_values_stack_nested	89.2720μs	49.2802μs	20.2921 KOps/s	20.0262 KOps/s	$\color{#35bf28}+1.33\%$
test_values_stack_nested_leaf	73.7710μs	43.2941μs	23.0978 KOps/s	22.8597 KOps/s	$\color{#35bf28}+1.04\%$
test_values_stack_nested_locked	0.1200ms	51.5432μs	19.4012 KOps/s	19.4273 KOps/s	$\color{#d91a1a}-0.13\%$
test_membership	1.9161μs	0.4993μs	2.0028 MOps/s	2.0045 MOps/s	$\color{#d91a1a}-0.09\%$
test_membership_nested	14.9000μs	1.8386μs	543.8962 KOps/s	552.1392 KOps/s	$\color{#d91a1a}-1.49\%$
test_membership_nested_leaf	10.9233μs	1.8247μs	548.0455 KOps/s	561.1668 KOps/s	$\color{#d91a1a}-2.34\%$
test_membership_stacked_nested	49.0510μs	1.8798μs	531.9577 KOps/s	540.8289 KOps/s	$\color{#d91a1a}-1.64\%$
test_membership_stacked_nested_leaf	30.2610μs	1.8856μs	530.3333 KOps/s	529.3785 KOps/s	$\color{#35bf28}+0.18\%$
test_membership_nested_last	0.7403ms	2.9111μs	343.5151 KOps/s	346.5344 KOps/s	$\color{#d91a1a}-0.87\%$
test_membership_nested_leaf_last	50.2710μs	2.9451μs	339.5423 KOps/s	336.3437 KOps/s	$\color{#35bf28}+0.95\%$
test_membership_stacked_nested_last	48.6610μs	3.4476μs	290.0540 KOps/s	339.7419 KOps/s	$\textbf{\color{#d91a1a}-14.63\%}$
test_membership_stacked_nested_leaf_last	42.4910μs	3.4422μs	290.5083 KOps/s	339.7646 KOps/s	$\textbf{\color{#d91a1a}-14.50\%}$
test_nested_getleaf	38.2010μs	5.9968μs	166.7554 KOps/s	165.9710 KOps/s	$\color{#35bf28}+0.47\%$
test_nested_get	34.3910μs	5.7103μs	175.1212 KOps/s	176.4739 KOps/s	$\color{#d91a1a}-0.77\%$
test_stacked_getleaf	36.4510μs	5.9934μs	166.8493 KOps/s	167.4392 KOps/s	$\color{#d91a1a}-0.35\%$
test_stacked_get	55.5410μs	5.6890μs	175.7779 KOps/s	179.7282 KOps/s	$\color{#d91a1a}-2.20\%$
test_nested_getitemleaf	50.9110μs	6.1026μs	163.8650 KOps/s	164.5363 KOps/s	$\color{#d91a1a}-0.41\%$
test_nested_getitem	31.1600μs	5.6953μs	175.5828 KOps/s	176.2546 KOps/s	$\color{#d91a1a}-0.38\%$
test_stacked_getitemleaf	38.6300μs	6.0966μs	164.0255 KOps/s	166.3484 KOps/s	$\color{#d91a1a}-1.40\%$
test_stacked_getitem	34.6900μs	5.6958μs	175.5665 KOps/s	177.1762 KOps/s	$\color{#d91a1a}-0.91\%$
test_lock_nested	2.7275ms	0.4220ms	2.3697 KOps/s	2.3914 KOps/s	$\color{#d91a1a}-0.90\%$
test_lock_stack_nested	0.5777ms	0.3849ms	2.5982 KOps/s	2.5941 KOps/s	$\color{#35bf28}+0.16\%$
test_unlock_nested	0.7457ms	0.3529ms	2.8335 KOps/s	2.7913 KOps/s	$\color{#35bf28}+1.51\%$
test_unlock_stack_nested	0.4447ms	0.3225ms	3.1011 KOps/s	3.0663 KOps/s	$\color{#35bf28}+1.13\%$
test_flatten_speed	0.2006ms	75.9088μs	13.1737 KOps/s	13.1477 KOps/s	$\color{#35bf28}+0.20\%$
test_unflatten_speed	0.3805ms	0.3181ms	3.1432 KOps/s	3.1821 KOps/s	$\color{#d91a1a}-1.22\%$
test_common_ops	1.9099ms	1.1932ms	838.0774 Ops/s	819.7017 Ops/s	$\color{#35bf28}+2.24\%$
test_creation	27.0500μs	1.4437μs	692.6726 KOps/s	694.5520 KOps/s	$\color{#d91a1a}-0.27\%$
test_creation_empty	47.6610μs	14.2092μs	70.3767 KOps/s	68.4076 KOps/s	$\color{#35bf28}+2.88\%$
test_creation_nested_1	54.7710μs	15.8734μs	62.9985 KOps/s	61.0120 KOps/s	$\color{#35bf28}+3.26\%$
test_creation_nested_2	54.6410μs	18.4775μs	54.1199 KOps/s	53.2510 KOps/s	$\color{#35bf28}+1.63\%$
test_clone	0.1677ms	27.4142μs	36.4775 KOps/s	35.2810 KOps/s	$\color{#35bf28}+3.39\%$
test_getitem[int]	1.5362ms	15.8704μs	63.0105 KOps/s	65.3548 KOps/s	$\color{#d91a1a}-3.59\%$
test_getitem[slice_int]	0.1314ms	27.3205μs	36.6025 KOps/s	38.4363 KOps/s	$\color{#d91a1a}-4.77\%$
test_getitem[range]	0.1479ms	0.1082ms	9.2464 KOps/s	9.2107 KOps/s	$\color{#35bf28}+0.39\%$
test_getitem[tuple]	0.1358ms	23.4498μs	42.6443 KOps/s	43.6489 KOps/s	$\color{#d91a1a}-2.30\%$
test_getitem[list]	0.2475ms	97.6664μs	10.2389 KOps/s	10.2136 KOps/s	$\color{#35bf28}+0.25\%$
test_setitem_dim[int]	0.1800ms	43.6915μs	22.8878 KOps/s	23.1985 KOps/s	$\color{#d91a1a}-1.34\%$
test_setitem_dim[slice_int]	0.1127ms	66.7762μs	14.9754 KOps/s	15.3396 KOps/s	$\color{#d91a1a}-2.37\%$
test_setitem_dim[range]	0.1730ms	0.1254ms	7.9741 KOps/s	7.9609 KOps/s	$\color{#35bf28}+0.17\%$
test_setitem_dim[tuple]	91.1910μs	59.7714μs	16.7304 KOps/s	17.1201 KOps/s	$\color{#d91a1a}-2.28\%$
test_setitem	0.1939ms	39.9659μs	25.0213 KOps/s	24.4391 KOps/s	$\color{#35bf28}+2.38\%$
test_set	0.1884ms	39.0371μs	25.6167 KOps/s	25.2460 KOps/s	$\color{#35bf28}+1.47\%$
test_set_shared	94.7575ms	61.9604μs	16.1393 KOps/s	18.8269 KOps/s	$\textbf{\color{#d91a1a}-14.28\%}$
test_update	0.1963ms	47.1200μs	21.2224 KOps/s	20.5427 KOps/s	$\color{#35bf28}+3.31\%$
test_update_nested	0.2052ms	55.3277μs	18.0741 KOps/s	17.7319 KOps/s	$\color{#35bf28}+1.93\%$
test_update__nested	0.1482ms	60.7228μs	16.4683 KOps/s	15.5127 KOps/s	$\textbf{\color{#35bf28}+6.16\%}$
test_set_nested	0.1920ms	41.5181μs	24.0859 KOps/s	23.8710 KOps/s	$\color{#35bf28}+0.90\%$
test_set_nested_new	0.1943ms	44.6157μs	22.4136 KOps/s	22.0164 KOps/s	$\color{#35bf28}+1.80\%$
test_select	0.2108ms	57.3158μs	17.4472 KOps/s	16.9840 KOps/s	$\color{#35bf28}+2.73\%$
test_select_nested	64.9100μs	42.9482μs	23.2839 KOps/s	24.0423 KOps/s	$\color{#d91a1a}-3.15\%$
test_exclude_nested	0.1106ms	57.3866μs	17.4257 KOps/s	17.1854 KOps/s	$\color{#35bf28}+1.40\%$
test_empty[True]	0.3480ms	0.2538ms	3.9403 KOps/s	3.9257 KOps/s	$\color{#35bf28}+0.37\%$
test_empty[False]	0.4702ms	0.7383μs	1.3545 MOps/s	1.3252 MOps/s	$\color{#35bf28}+2.21\%$
test_to	47.6310μs	25.0287μs	39.9541 KOps/s	37.8234 KOps/s	$\textbf{\color{#35bf28}+5.63\%}$
test_to_nonblocking	60.2510μs	23.9575μs	41.7406 KOps/s	42.5862 KOps/s	$\color{#d91a1a}-1.99\%$
test_unbind_speed	1.5355ms	0.2642ms	3.7848 KOps/s	3.7524 KOps/s	$\color{#35bf28}+0.86\%$
test_unbind_speed_stack0	0.3702ms	0.2624ms	3.8109 KOps/s	3.7244 KOps/s	$\color{#35bf28}+2.32\%$
test_unbind_speed_stack1	97.6042ms	0.6959ms	1.4369 KOps/s	1.5572 KOps/s	$\textbf{\color{#d91a1a}-7.73\%}$
test_split	0.1003s	2.1253ms	470.5145 Ops/s	482.8425 Ops/s	$\color{#d91a1a}-2.55\%$
test_chunk	0.1015s	2.1396ms	467.3728 Ops/s	481.4057 Ops/s	$\color{#d91a1a}-2.91\%$
test_creation[device0]	0.3408ms	0.1244ms	8.0415 KOps/s	7.9292 KOps/s	$\color{#35bf28}+1.42\%$
test_creation_from_tensor	0.3424ms	0.1311ms	7.6284 KOps/s	7.8101 KOps/s	$\color{#d91a1a}-2.33\%$
test_add_one[memmap_tensor0]	0.1310ms	8.5129μs	117.4683 KOps/s	116.5889 KOps/s	$\color{#35bf28}+0.75\%$
test_contiguous[memmap_tensor0]	31.1200μs	2.0590μs	485.6624 KOps/s	468.8325 KOps/s	$\color{#35bf28}+3.59\%$
test_stack[memmap_tensor0]	36.4200μs	6.3710μs	156.9617 KOps/s	153.3419 KOps/s	$\color{#35bf28}+2.36\%$
test_memmaptd_index	1.2295ms	0.4087ms	2.4469 KOps/s	2.4183 KOps/s	$\color{#35bf28}+1.19\%$
test_memmaptd_index_astensor	0.7360ms	0.4770ms	2.0964 KOps/s	2.0842 KOps/s	$\color{#35bf28}+0.59\%$
test_memmaptd_index_op	1.3637ms	0.9782ms	1.0223 KOps/s	1.0249 KOps/s	$\color{#d91a1a}-0.25\%$
test_serialize_model	0.1318s	0.1303s	7.6773 Ops/s	7.6575 Ops/s	$\color{#35bf28}+0.26\%$
test_serialize_model_pickle	1.3518s	1.2128s	0.8245 Ops/s	0.8241 Ops/s	$\color{#35bf28}+0.06\%$
test_serialize_weights	0.1304s	0.1300s	7.6915 Ops/s	6.9669 Ops/s	$\textbf{\color{#35bf28}+10.40\%}$
test_serialize_weights_returnearly	0.2357s	55.8417ms	17.9078 Ops/s	17.6846 Ops/s	$\color{#35bf28}+1.26\%$
test_serialize_weights_pickle	1.3522s	1.2142s	0.8236 Ops/s	0.8246 Ops/s	$\color{#d91a1a}-0.12\%$
test_reshape_pytree	66.9610μs	33.8416μs	29.5494 KOps/s	29.6018 KOps/s	$\color{#d91a1a}-0.18\%$
test_reshape_td	71.2910μs	38.2308μs	26.1570 KOps/s	25.5033 KOps/s	$\color{#35bf28}+2.56\%$
test_view_pytree	0.1275ms	33.4760μs	29.8721 KOps/s	30.1517 KOps/s	$\color{#d91a1a}-0.93\%$
test_view_td	78.4610μs	44.4581μs	22.4931 KOps/s	23.3986 KOps/s	$\color{#d91a1a}-3.87\%$
test_unbind_pytree	0.1702ms	33.0335μs	30.2723 KOps/s	30.6705 KOps/s	$\color{#d91a1a}-1.30\%$
test_unbind_td	0.7813ms	40.7140μs	24.5616 KOps/s	24.8852 KOps/s	$\color{#d91a1a}-1.30\%$
test_split_pytree	0.1218ms	42.5929μs	23.4781 KOps/s	23.4412 KOps/s	$\color{#35bf28}+0.16\%$
test_split_td	0.1797ms	51.9119μs	19.2634 KOps/s	19.4737 KOps/s	$\color{#d91a1a}-1.08\%$
test_add_pytree	0.2323ms	55.6553μs	17.9678 KOps/s	18.8980 KOps/s	$\color{#d91a1a}-4.92\%$
test_add_td	0.2694ms	85.4505μs	11.7027 KOps/s	11.3933 KOps/s	$\color{#35bf28}+2.72\%$
test_compile_add_one_nested[tensordict-compile]	0.3092ms	0.1591ms	6.2837 KOps/s	6.3645 KOps/s	$\color{#d91a1a}-1.27\%$
test_compile_add_one_nested[tensordict-eager]	0.3027ms	0.1557ms	6.4205 KOps/s	6.2272 KOps/s	$\color{#35bf28}+3.10\%$
test_compile_add_one_nested[pytree-compile]	0.2909ms	0.1392ms	7.1819 KOps/s	7.1332 KOps/s	$\color{#35bf28}+0.68\%$
test_compile_add_one_nested[pytree-eager]	0.3230ms	0.1797ms	5.5654 KOps/s	5.6550 KOps/s	$\color{#d91a1a}-1.58\%$
test_compile_copy_nested[tensordict-compile]	0.1573ms	20.0154μs	49.9615 KOps/s	48.1259 KOps/s	$\color{#35bf28}+3.81\%$
test_compile_copy_nested[tensordict-eager]	88.0610μs	47.6839μs	20.9714 KOps/s	21.2174 KOps/s	$\color{#d91a1a}-1.16\%$
test_compile_copy_nested[pytree-compile]	0.2556ms	63.9410μs	15.6394 KOps/s	16.1012 KOps/s	$\color{#d91a1a}-2.87\%$
test_compile_copy_nested[pytree-eager]	0.1459ms	49.3807μs	20.2508 KOps/s	20.4020 KOps/s	$\color{#d91a1a}-0.74\%$
test_compile_add_one_flat[tensordict-compile]	0.4575ms	0.3088ms	3.2387 KOps/s	3.2107 KOps/s	$\color{#35bf28}+0.87\%$
test_compile_add_one_flat[tensordict-eager]	0.3257ms	0.2310ms	4.3291 KOps/s	4.1796 KOps/s	$\color{#35bf28}+3.57\%$
test_compile_add_one_flat[tensorclass-compile]	0.2476ms	0.1228ms	8.1459 KOps/s	8.1369 KOps/s	$\color{#35bf28}+0.11\%$
test_compile_add_one_flat[tensorclass-eager]	0.2112ms	63.0335μs	15.8646 KOps/s	15.4340 KOps/s	$\color{#35bf28}+2.79\%$
test_compile_add_one_flat[pytree-compile]	0.4629ms	0.3080ms	3.2471 KOps/s	3.2320 KOps/s	$\color{#35bf28}+0.47\%$
test_compile_add_one_flat[pytree-eager]	0.8102ms	0.6147ms	1.6269 KOps/s	1.6779 KOps/s	$\color{#d91a1a}-3.04\%$
test_compile_add_self_flat[tensordict-eager]	0.4291ms	0.2851ms	3.5075 KOps/s	3.4813 KOps/s	$\color{#35bf28}+0.75\%$
test_compile_add_self_flat[tensordict-compile]	0.5227ms	0.3227ms	3.0988 KOps/s	3.2014 KOps/s	$\color{#d91a1a}-3.20\%$
test_compile_add_self_flat[tensorclass-eager]	0.2551ms	76.5139μs	13.0695 KOps/s	13.2271 KOps/s	$\color{#d91a1a}-1.19\%$
test_compile_add_self_flat[tensorclass-compile]	0.2723ms	0.1310ms	7.6342 KOps/s	7.8977 KOps/s	$\color{#d91a1a}-3.34\%$
test_compile_add_self_flat[pytree-eager]	0.7073ms	0.5194ms	1.9253 KOps/s	1.9982 KOps/s	$\color{#d91a1a}-3.65\%$
test_compile_add_self_flat[pytree-compile]	0.4509ms	0.3132ms	3.1930 KOps/s	3.2422 KOps/s	$\color{#d91a1a}-1.52\%$
test_compile_copy_flat[tensordict-compile]	0.1476ms	18.0794μs	55.3116 KOps/s	54.9604 KOps/s	$\color{#35bf28}+0.64\%$
test_compile_copy_flat[tensordict-eager]	0.1370ms	37.9037μs	26.3827 KOps/s	25.7580 KOps/s	$\color{#35bf28}+2.43\%$
test_compile_copy_flat[pytree-compile]	0.1788ms	68.6372μs	14.5694 KOps/s	14.6590 KOps/s	$\color{#d91a1a}-0.61\%$
test_compile_copy_flat[pytree-eager]	0.1440ms	50.9162μs	19.6401 KOps/s	19.7956 KOps/s	$\color{#d91a1a}-0.79\%$
test_compile_assign_and_add[tensordict-compile]	2.3938ms	0.8305ms	1.2042 KOps/s	1.1260 KOps/s	$\textbf{\color{#35bf28}+6.95\%}$
test_compile_assign_and_add[tensordict-eager]	3.4080ms	3.1671ms	315.7433 Ops/s	305.2655 Ops/s	$\color{#35bf28}+3.43\%$
test_compile_assign_and_add[pytree-compile]	2.2425ms	0.7948ms	1.2582 KOps/s	1.1653 KOps/s	$\textbf{\color{#35bf28}+7.97\%}$
test_compile_assign_and_add[pytree-eager]	3.4133ms	3.1347ms	319.0100 Ops/s	327.4789 Ops/s	$\color{#d91a1a}-2.59\%$
test_compile_indexing[tensor-tensordict-compile]	0.2592ms	0.1105ms	9.0457 KOps/s	9.3177 KOps/s	$\color{#d91a1a}-2.92\%$
test_compile_indexing[tensor-tensordict-eager]	0.2083ms	61.3271μs	16.3060 KOps/s	16.6586 KOps/s	$\color{#d91a1a}-2.12\%$
test_compile_indexing[tensor-tensorclass-compile]	0.2735ms	0.1048ms	9.5452 KOps/s	9.8848 KOps/s	$\color{#d91a1a}-3.44\%$
test_compile_indexing[tensor-tensorclass-eager]	0.2299ms	42.5957μs	23.4766 KOps/s	24.2241 KOps/s	$\color{#d91a1a}-3.09\%$
test_compile_indexing[tensor-pytree-compile]	0.2809ms	0.1036ms	9.6516 KOps/s	9.8020 KOps/s	$\color{#d91a1a}-1.53\%$
test_compile_indexing[tensor-pytree-eager]	0.2127ms	42.9054μs	23.3071 KOps/s	24.5340 KOps/s	$\textbf{\color{#d91a1a}-5.00\%}$
test_compile_indexing[slice-tensordict-compile]	0.2696ms	0.1358ms	7.3626 KOps/s	7.5655 KOps/s	$\color{#d91a1a}-2.68\%$
test_compile_indexing[slice-tensordict-eager]	0.2076ms	23.0023μs	43.4739 KOps/s	42.8211 KOps/s	$\color{#35bf28}+1.52\%$
test_compile_indexing[slice-tensorclass-compile]	0.2368ms	0.1315ms	7.6056 KOps/s	7.9693 KOps/s	$\color{#d91a1a}-4.56\%$
test_compile_indexing[slice-tensorclass-eager]	0.1918ms	19.5640μs	51.1143 KOps/s	51.6139 KOps/s	$\color{#d91a1a}-0.97\%$
test_compile_indexing[slice-pytree-compile]	0.2740ms	0.1272ms	7.8646 KOps/s	7.9248 KOps/s	$\color{#d91a1a}-0.76\%$
test_compile_indexing[slice-pytree-eager]	0.1700ms	19.8318μs	50.4240 KOps/s	51.9054 KOps/s	$\color{#d91a1a}-2.85\%$
test_compile_indexing[int-tensordict-compile]	0.2647ms	0.1339ms	7.4696 KOps/s	7.5328 KOps/s	$\color{#d91a1a}-0.84\%$
test_compile_indexing[int-tensordict-eager]	0.5062ms	24.4477μs	40.9037 KOps/s	42.9370 KOps/s	$\color{#d91a1a}-4.74\%$
test_compile_indexing[int-tensorclass-compile]	0.2945ms	0.1277ms	7.8292 KOps/s	7.9037 KOps/s	$\color{#d91a1a}-0.94\%$
test_compile_indexing[int-tensorclass-eager]	62.1710μs	19.9359μs	50.1607 KOps/s	51.7495 KOps/s	$\color{#d91a1a}-3.07\%$
test_compile_indexing[int-pytree-compile]	0.2693ms	0.1293ms	7.7345 KOps/s	7.9269 KOps/s	$\color{#d91a1a}-2.43\%$
test_compile_indexing[int-pytree-eager]	48.4110μs	19.6502μs	50.8900 KOps/s	51.8060 KOps/s	$\color{#d91a1a}-1.77\%$
test_mod_add[eager]	0.2155ms	29.9449μs	33.3947 KOps/s	33.7344 KOps/s	$\color{#d91a1a}-1.01\%$
test_mod_add[compile]	0.2122ms	66.9858μs	14.9285 KOps/s	14.0748 KOps/s	$\textbf{\color{#35bf28}+6.07\%}$
test_mod_add[compile-overhead]	0.2750ms	0.1339ms	7.4668 KOps/s	6.2950 KOps/s	$\textbf{\color{#35bf28}+18.61\%}$
test_mod_wrap[eager]	0.4361ms	0.2366ms	4.2263 KOps/s	4.0120 KOps/s	$\textbf{\color{#35bf28}+5.34\%}$
test_mod_wrap[compile]	1.3683ms	0.2852ms	3.5064 KOps/s	3.3274 KOps/s	$\textbf{\color{#35bf28}+5.38\%}$
test_mod_wrap[compile-overhead]	7.6884ms	4.0758ms	245.3513 Ops/s	249.3888 Ops/s	$\color{#d91a1a}-1.62\%$
test_mod_wrap_and_backward[eager]	1.5110ms	1.3197ms	757.7320 Ops/s	699.8025 Ops/s	$\textbf{\color{#35bf28}+8.28\%}$
test_mod_wrap_and_backward[compile]	1.5315ms	1.2864ms	777.3465 Ops/s	698.4912 Ops/s	$\textbf{\color{#35bf28}+11.29\%}$
test_mod_wrap_and_backward[compile-overhead]	1.3309ms	0.8943ms	1.1182 KOps/s	935.3359 Ops/s	$\textbf{\color{#35bf28}+19.55\%}$
test_seq_add[eager]	0.2475ms	93.6599μs	10.6769 KOps/s	10.2619 KOps/s	$\color{#35bf28}+4.04\%$
test_seq_add[compile]	0.2533ms	79.5275μs	12.5743 KOps/s	12.5875 KOps/s	$\color{#d91a1a}-0.11\%$
test_seq_add[compile-overhead]	0.2590ms	0.1124ms	8.8974 KOps/s	8.8932 KOps/s	$\color{#35bf28}+0.05\%$
test_seq_wrap[eager]	0.5427ms	0.3907ms	2.5598 KOps/s	2.6222 KOps/s	$\color{#d91a1a}-2.38\%$
test_seq_wrap[compile]	0.4625ms	0.3054ms	3.2746 KOps/s	3.2494 KOps/s	$\color{#35bf28}+0.78\%$
test_seq_wrap[compile-overhead]	0.3628ms	0.2172ms	4.6040 KOps/s	4.6354 KOps/s	$\color{#d91a1a}-0.68\%$
test_func_call_runtime[False-eager]	0.9439ms	0.7615ms	1.3132 KOps/s	1.3908 KOps/s	$\textbf{\color{#d91a1a}-5.58\%}$
test_func_call_runtime[False-compile]	0.9439ms	0.7650ms	1.3071 KOps/s	1.2876 KOps/s	$\color{#35bf28}+1.51\%$
test_func_call_runtime[False-compile-overhead]	0.4955ms	0.3501ms	2.8567 KOps/s	2.8073 KOps/s	$\color{#35bf28}+1.76\%$
test_func_call_runtime[True-eager]	1.0800ms	0.8803ms	1.1360 KOps/s	1.0840 KOps/s	$\color{#35bf28}+4.80\%$
test_func_call_runtime[True-compile]	0.9795ms	0.7886ms	1.2681 KOps/s	1.2538 KOps/s	$\color{#35bf28}+1.13\%$
test_func_call_runtime[True-compile-overhead]	0.5091ms	0.3716ms	2.6908 KOps/s	2.6391 KOps/s	$\color{#35bf28}+1.96\%$
test_func_call_cm_runtime[False-eager]	0.8780ms	0.7156ms	1.3973 KOps/s	1.3064 KOps/s	$\textbf{\color{#35bf28}+6.96\%}$
test_func_call_cm_runtime[False-compile]	0.9497ms	0.7663ms	1.3049 KOps/s	1.2785 KOps/s	$\color{#35bf28}+2.07\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4848ms	0.3519ms	2.8417 KOps/s	2.7930 KOps/s	$\color{#35bf28}+1.74\%$
test_func_call_cm_runtime[True-eager]	1.2187ms	0.9928ms	1.0072 KOps/s	962.1117 Ops/s	$\color{#35bf28}+4.69\%$
test_func_call_cm_runtime[True-compile]	0.9582ms	0.8074ms	1.2386 KOps/s	1.1890 KOps/s	$\color{#35bf28}+4.17\%$
test_func_call_cm_runtime[True-compile-overhead]	0.6089ms	0.3967ms	2.5210 KOps/s	2.4704 KOps/s	$\color{#35bf28}+2.05\%$
test_vmap_func_call_cm_runtime[eager]	2.5344ms	2.0814ms	480.4474 Ops/s	467.7112 Ops/s	$\color{#35bf28}+2.72\%$
test_vmap_func_call_cm_runtime[compile]	1.0269ms	0.8279ms	1.2079 KOps/s	1.1618 KOps/s	$\color{#35bf28}+3.97\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.5368ms	0.4004ms	2.4978 KOps/s	2.4922 KOps/s	$\color{#35bf28}+0.22\%$
test_distributed	5.1631ms	0.2240ms	4.4635 KOps/s	8.8117 KOps/s	$\textbf{\color{#d91a1a}-49.35\%}$
test_tdmodule	0.1838ms	14.2997μs	69.9316 KOps/s	67.2915 KOps/s	$\color{#35bf28}+3.92\%$
test_tdmodule_dispatch	47.8810μs	27.1065μs	36.8915 KOps/s	36.6041 KOps/s	$\color{#35bf28}+0.79\%$
test_tdseq	35.5010μs	15.0847μs	66.2924 KOps/s	66.9264 KOps/s	$\color{#d91a1a}-0.95\%$
test_tdseq_dispatch	0.1553ms	30.3672μs	32.9302 KOps/s	33.2084 KOps/s	$\color{#d91a1a}-0.84\%$
test_instantiation_functorch	2.2430ms	1.8542ms	539.3125 Ops/s	556.8718 Ops/s	$\color{#d91a1a}-3.15\%$
test_exec_functorch	0.3420ms	0.2083ms	4.8008 KOps/s	4.9443 KOps/s	$\color{#d91a1a}-2.90\%$
test_exec_functional_call	0.6058ms	0.2115ms	4.7282 KOps/s	4.9112 KOps/s	$\color{#d91a1a}-3.73\%$
test_exec_td_decorator	0.6501ms	0.2657ms	3.7632 KOps/s	3.8859 KOps/s	$\color{#d91a1a}-3.16\%$
test_vmap_mlp_speed_decorator[True-True]	1.0820ms	0.6890ms	1.4513 KOps/s	1.5028 KOps/s	$\color{#d91a1a}-3.43\%$
test_vmap_mlp_speed_decorator[True-False]	1.1148ms	0.6899ms	1.4494 KOps/s	1.5032 KOps/s	$\color{#d91a1a}-3.58\%$
test_vmap_mlp_speed_decorator[False-True]	1.0279ms	0.6104ms	1.6383 KOps/s	1.7048 KOps/s	$\color{#d91a1a}-3.90\%$
test_vmap_mlp_speed_decorator[False-False]	1.0088ms	0.6109ms	1.6368 KOps/s	1.7041 KOps/s	$\color{#d91a1a}-3.95\%$
test_vmap_transformer_speed_decorator[True-True]	20.3087ms	19.9815ms	50.0464 Ops/s	51.9532 Ops/s	$\color{#d91a1a}-3.67\%$
test_vmap_transformer_speed_decorator[True-False]	20.3744ms	19.9635ms	50.0915 Ops/s	51.1774 Ops/s	$\color{#d91a1a}-2.12\%$
test_vmap_transformer_speed_decorator[False-True]	20.4420ms	19.8273ms	50.4356 Ops/s	50.8844 Ops/s	$\color{#d91a1a}-0.88\%$
test_vmap_transformer_speed_decorator[False-False]	20.1504ms	19.8320ms	50.4234 Ops/s	50.5182 Ops/s	$\color{#d91a1a}-0.19\%$
test_to_module_speed[True]	1.4234ms	0.9939ms	1.0062 KOps/s	1.0238 KOps/s	$\color{#d91a1a}-1.72\%$
test_to_module_speed[False]	1.3984ms	0.9669ms	1.0342 KOps/s	1.0502 KOps/s	$\color{#d91a1a}-1.52\%$
test_tc_init	54.7910μs	31.4816μs	31.7646 KOps/s	31.0970 KOps/s	$\color{#35bf28}+2.15\%$
test_tc_init_nested	0.4651ms	65.3516μs	15.3019 KOps/s	15.0107 KOps/s	$\color{#35bf28}+1.94\%$
test_tc_first_layer_tensor	54.9736μs	0.6690μs	1.4947 MOps/s	1.4885 MOps/s	$\color{#35bf28}+0.41\%$
test_tc_first_layer_nontensor	24.3800μs	2.1917μs	456.2684 KOps/s	454.5519 KOps/s	$\color{#35bf28}+0.38\%$
test_tc_second_layer_tensor	0.1008ms	1.3446μs	743.7366 KOps/s	741.1637 KOps/s	$\color{#35bf28}+0.35\%$
test_tc_second_layer_nontensor	30.3000μs	2.9124μs	343.3651 KOps/s	345.6805 KOps/s	$\color{#d91a1a}-0.67\%$
test_unbind	0.1961s	12.2904ms	81.3642 Ops/s	93.3283 Ops/s	$\textbf{\color{#d91a1a}-12.82\%}$
test_full_like	0.7763ms	0.5732ms	1.7446 KOps/s	1.7419 KOps/s	$\color{#35bf28}+0.15\%$
test_zeros_like	0.3193ms	0.1980ms	5.0502 KOps/s	5.0556 KOps/s	$\color{#d91a1a}-0.11\%$
test_ones_like	0.5599ms	0.1980ms	5.0513 KOps/s	5.0513 KOps/s	$+0.00\%$
test_clone	1.2068ms	0.4151ms	2.4090 KOps/s	2.4117 KOps/s	$\color{#d91a1a}-0.11\%$
test_squeeze	51.1310μs	9.1823μs	108.9050 KOps/s	107.6735 KOps/s	$\color{#35bf28}+1.14\%$
test_unsqueeze	0.2696ms	71.1274μs	14.0593 KOps/s	14.1359 KOps/s	$\color{#d91a1a}-0.54\%$
test_split	0.2823ms	0.1487ms	6.7231 KOps/s	6.6899 KOps/s	$\color{#35bf28}+0.50\%$
test_permute	0.3379ms	0.1706ms	5.8604 KOps/s	5.8035 KOps/s	$\color{#35bf28}+0.98\%$
test_stack	1.3801ms	0.8603ms	1.1624 KOps/s	1.1762 KOps/s	$\color{#d91a1a}-1.17\%$
test_cat	1.3576ms	1.2315ms	811.9999 Ops/s	811.9906 Ops/s	$+0.00\%$