[BugFix] Add sync to cudagraph module

[vmoens]

No description provided.

[github-actions]

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

Total Benchmarks: 222. Improved: $\large\color{#35bf28}5$. Worsened: $\large\color{#d91a1a}28$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	73.7580μs	26.4435μs	37.8165 KOps/s	40.9303 KOps/s	$\textbf{\color{#d91a1a}-7.61\%}$
test_plain_set_stack_nested	64.8110μs	26.7570μs	37.3733 KOps/s	40.2900 KOps/s	$\textbf{\color{#d91a1a}-7.24\%}$
test_plain_set_nested_inplace	70.9330μs	29.2945μs	34.1361 KOps/s	37.3383 KOps/s	$\textbf{\color{#d91a1a}-8.58\%}$
test_plain_set_stack_nested_inplace	68.2790μs	28.7535μs	34.7784 KOps/s	37.3494 KOps/s	$\textbf{\color{#d91a1a}-6.88\%}$
test_items	23.0930μs	4.1523μs	240.8323 KOps/s	231.5482 KOps/s	$\color{#35bf28}+4.01\%$
test_items_nested	0.4683ms	0.3881ms	2.5770 KOps/s	2.6132 KOps/s	$\color{#d91a1a}-1.39\%$
test_items_nested_locked	0.5548ms	0.3891ms	2.5701 KOps/s	2.6116 KOps/s	$\color{#d91a1a}-1.59\%$
test_items_nested_leaf	0.1612ms	80.7941μs	12.3771 KOps/s	12.2949 KOps/s	$\color{#35bf28}+0.67\%$
test_items_stack_nested	0.7027ms	0.3951ms	2.5312 KOps/s	2.5774 KOps/s	$\color{#d91a1a}-1.79\%$
test_items_stack_nested_leaf	0.1551ms	84.2178μs	11.8740 KOps/s	12.0376 KOps/s	$\color{#d91a1a}-1.36\%$
test_items_stack_nested_locked	0.7329ms	0.3937ms	2.5399 KOps/s	2.5864 KOps/s	$\color{#d91a1a}-1.80\%$
test_keys	30.3270μs	3.5332μs	283.0297 KOps/s	284.7011 KOps/s	$\color{#d91a1a}-0.59\%$
test_keys_nested	0.2678ms	0.1362ms	7.3430 KOps/s	7.5227 KOps/s	$\color{#d91a1a}-2.39\%$
test_keys_nested_locked	1.5895ms	0.1416ms	7.0631 KOps/s	7.2001 KOps/s	$\color{#d91a1a}-1.90\%$
test_keys_nested_leaf	0.2002ms	0.1193ms	8.3823 KOps/s	8.6125 KOps/s	$\color{#d91a1a}-2.67\%$
test_keys_stack_nested	0.2318ms	0.1344ms	7.4395 KOps/s	7.5322 KOps/s	$\color{#d91a1a}-1.23\%$
test_keys_stack_nested_leaf	0.2098ms	0.1179ms	8.4848 KOps/s	8.6193 KOps/s	$\color{#d91a1a}-1.56\%$
test_keys_stack_nested_locked	0.2492ms	0.1398ms	7.1547 KOps/s	7.2435 KOps/s	$\color{#d91a1a}-1.23\%$
test_values	6.2398μs	1.0726μs	932.3001 KOps/s	937.1496 KOps/s	$\color{#d91a1a}-0.52\%$
test_values_nested	0.1869ms	96.9536μs	10.3142 KOps/s	10.3774 KOps/s	$\color{#d91a1a}-0.61\%$
test_values_nested_locked	0.1698ms	97.4017μs	10.2668 KOps/s	10.4452 KOps/s	$\color{#d91a1a}-1.71\%$
test_values_nested_leaf	0.1618ms	83.6408μs	11.9559 KOps/s	12.3478 KOps/s	$\color{#d91a1a}-3.17\%$
test_values_stack_nested	0.1725ms	98.1995μs	10.1833 KOps/s	10.4195 KOps/s	$\color{#d91a1a}-2.27\%$
test_values_stack_nested_leaf	0.1436ms	82.4443μs	12.1294 KOps/s	12.3271 KOps/s	$\color{#d91a1a}-1.60\%$
test_values_stack_nested_locked	0.1557ms	97.0292μs	10.3062 KOps/s	10.5310 KOps/s	$\color{#d91a1a}-2.13\%$
test_membership	21.3000μs	0.9287μs	1.0768 MOps/s	1.1263 MOps/s	$\color{#d91a1a}-4.40\%$
test_membership_nested	23.1740μs	2.8657μs	348.9513 KOps/s	366.4396 KOps/s	$\color{#d91a1a}-4.77\%$
test_membership_nested_leaf	24.6670μs	2.8847μs	346.6537 KOps/s	364.7127 KOps/s	$\color{#d91a1a}-4.95\%$
test_membership_stacked_nested	22.9630μs	2.8755μs	347.7653 KOps/s	364.9114 KOps/s	$\color{#d91a1a}-4.70\%$
test_membership_stacked_nested_leaf	29.9260μs	2.9144μs	343.1201 KOps/s	368.7271 KOps/s	$\textbf{\color{#d91a1a}-6.94\%}$
test_membership_nested_last	25.4070μs	4.3319μs	230.8475 KOps/s	232.3815 KOps/s	$\color{#d91a1a}-0.66\%$
test_membership_nested_leaf_last	26.6190μs	4.3652μs	229.0871 KOps/s	237.4847 KOps/s	$\color{#d91a1a}-3.54\%$
test_membership_stacked_nested_last	28.3930μs	4.3585μs	229.4387 KOps/s	237.6236 KOps/s	$\color{#d91a1a}-3.44\%$
test_membership_stacked_nested_leaf_last	26.0390μs	4.3346μs	230.7034 KOps/s	235.6261 KOps/s	$\color{#d91a1a}-2.09\%$
test_nested_getleaf	33.7930μs	10.5925μs	94.4068 KOps/s	93.8171 KOps/s	$\color{#35bf28}+0.63\%$
test_nested_get	55.2940μs	9.9542μs	100.4598 KOps/s	98.3939 KOps/s	$\color{#35bf28}+2.10\%$
test_stacked_getleaf	36.0180μs	10.5987μs	94.3512 KOps/s	94.7916 KOps/s	$\color{#d91a1a}-0.46\%$
test_stacked_get	32.6510μs	9.9791μs	100.2095 KOps/s	99.7176 KOps/s	$\color{#35bf28}+0.49\%$
test_nested_getitemleaf	34.3140μs	10.9187μs	91.5858 KOps/s	90.7088 KOps/s	$\color{#35bf28}+0.97\%$
test_nested_getitem	54.3820μs	10.1169μs	98.8447 KOps/s	97.2975 KOps/s	$\color{#35bf28}+1.59\%$
test_stacked_getitemleaf	44.9150μs	10.8791μs	91.9194 KOps/s	90.7819 KOps/s	$\color{#35bf28}+1.25\%$
test_stacked_getitem	30.8270μs	10.0875μs	99.1325 KOps/s	95.8756 KOps/s	$\color{#35bf28}+3.40\%$
test_lock_nested	84.1360ms	0.5978ms	1.6729 KOps/s	1.9214 KOps/s	$\textbf{\color{#d91a1a}-12.93\%}$
test_lock_stack_nested	0.6979ms	0.4749ms	2.1057 KOps/s	2.0698 KOps/s	$\color{#35bf28}+1.73\%$
test_unlock_nested	83.2556ms	0.5150ms	1.9419 KOps/s	2.2917 KOps/s	$\textbf{\color{#d91a1a}-15.27\%}$
test_unlock_stack_nested	0.6588ms	0.3913ms	2.5554 KOps/s	2.4934 KOps/s	$\color{#35bf28}+2.49\%$
test_flatten_speed	0.1911ms	0.1016ms	9.8407 KOps/s	9.9553 KOps/s	$\color{#d91a1a}-1.15\%$
test_unflatten_speed	1.0573ms	0.5350ms	1.8690 KOps/s	1.9370 KOps/s	$\color{#d91a1a}-3.51\%$
test_common_ops	4.5509ms	1.2034ms	830.9866 Ops/s	898.3887 Ops/s	$\textbf{\color{#d91a1a}-7.50\%}$
test_creation	19.5170μs	2.1418μs	466.9060 KOps/s	473.7156 KOps/s	$\color{#d91a1a}-1.44\%$
test_creation_empty	47.5590μs	20.1023μs	49.7456 KOps/s	56.1580 KOps/s	$\textbf{\color{#d91a1a}-11.42\%}$
test_creation_nested_1	55.9050μs	23.4589μs	42.6277 KOps/s	47.7704 KOps/s	$\textbf{\color{#d91a1a}-10.77\%}$
test_creation_nested_2	61.5160μs	27.6225μs	36.2024 KOps/s	39.6664 KOps/s	$\textbf{\color{#d91a1a}-8.73\%}$
test_clone	0.1201ms	17.1299μs	58.3774 KOps/s	58.2338 KOps/s	$\color{#35bf28}+0.25\%$
test_getitem[int]	1.1468ms	16.9050μs	59.1542 KOps/s	57.6708 KOps/s	$\color{#35bf28}+2.57\%$
test_getitem[slice_int]	0.1455ms	31.9062μs	31.3419 KOps/s	32.2207 KOps/s	$\color{#d91a1a}-2.73\%$
test_getitem[range]	0.2710ms	60.5421μs	16.5174 KOps/s	17.2812 KOps/s	$\color{#d91a1a}-4.42\%$
test_getitem[tuple]	0.1414ms	25.8072μs	38.7489 KOps/s	38.8393 KOps/s	$\color{#d91a1a}-0.23\%$
test_getitem[list]	0.1880ms	55.1552μs	18.1307 KOps/s	18.6575 KOps/s	$\color{#d91a1a}-2.82\%$
test_setitem_dim[int]	61.4160μs	34.1248μs	29.3042 KOps/s	30.1376 KOps/s	$\color{#d91a1a}-2.77\%$
test_setitem_dim[slice_int]	0.1097ms	62.7226μs	15.9432 KOps/s	16.2444 KOps/s	$\color{#d91a1a}-1.85\%$
test_setitem_dim[range]	0.1385ms	87.2948μs	11.4554 KOps/s	11.9410 KOps/s	$\color{#d91a1a}-4.07\%$
test_setitem_dim[tuple]	80.2610μs	51.3278μs	19.4826 KOps/s	19.8325 KOps/s	$\color{#d91a1a}-1.76\%$
test_setitem	88.3360μs	32.0764μs	31.1756 KOps/s	32.7089 KOps/s	$\color{#d91a1a}-4.69\%$
test_set	83.0760μs	30.9376μs	32.3231 KOps/s	34.3094 KOps/s	$\textbf{\color{#d91a1a}-5.79\%}$
test_set_shared	3.2701ms	0.2189ms	4.5688 KOps/s	4.5577 KOps/s	$\color{#35bf28}+0.24\%$
test_update	0.1481ms	40.3122μs	24.8064 KOps/s	26.7878 KOps/s	$\textbf{\color{#d91a1a}-7.40\%}$
test_update_nested	0.1257ms	50.9592μs	19.6235 KOps/s	20.8724 KOps/s	$\textbf{\color{#d91a1a}-5.98\%}$
test_update__nested	1.0217ms	37.6594μs	26.5538 KOps/s	26.1721 KOps/s	$\color{#35bf28}+1.46\%$
test_set_nested	0.1714ms	34.9620μs	28.6025 KOps/s	31.5271 KOps/s	$\textbf{\color{#d91a1a}-9.28\%}$
test_set_nested_new	0.1367ms	38.2407μs	26.1502 KOps/s	26.6935 KOps/s	$\color{#d91a1a}-2.04\%$
test_select	0.1340ms	55.8132μs	17.9169 KOps/s	18.5139 KOps/s	$\color{#d91a1a}-3.22\%$
test_select_nested	0.1265ms	60.9997μs	16.3935 KOps/s	16.8152 KOps/s	$\color{#d91a1a}-2.51\%$
test_exclude_nested	0.1776ms	77.1810μs	12.9566 KOps/s	13.4215 KOps/s	$\color{#d91a1a}-3.46\%$
test_empty[True]	0.6525ms	0.3526ms	2.8363 KOps/s	2.8365 KOps/s	$-0.00\%$
test_empty[False]	8.5637μs	1.3037μs	767.0563 KOps/s	801.6773 KOps/s	$\color{#d91a1a}-4.32\%$
test_unbind_speed	0.6510ms	0.3065ms	3.2630 KOps/s	3.1473 KOps/s	$\color{#35bf28}+3.68\%$
test_unbind_speed_stack0	0.5954ms	0.3022ms	3.3090 KOps/s	3.2202 KOps/s	$\color{#35bf28}+2.76\%$
test_unbind_speed_stack1	91.6826ms	0.8020ms	1.2469 KOps/s	1.2813 KOps/s	$\color{#d91a1a}-2.68\%$
test_split	3.2178ms	2.0625ms	484.8526 Ops/s	449.4527 Ops/s	$\textbf{\color{#35bf28}+7.88\%}$
test_chunk	89.9785ms	2.2424ms	445.9494 Ops/s	451.2638 Ops/s	$\color{#d91a1a}-1.18\%$
test_creation[device0]	0.2292ms	0.1166ms	8.5729 KOps/s	8.5724 KOps/s	$+0.01\%$
test_creation_from_tensor	5.7147ms	0.1183ms	8.4529 KOps/s	8.4557 KOps/s	$\color{#d91a1a}-0.03\%$
test_add_one[memmap_tensor0]	0.2123ms	7.4447μs	134.3231 KOps/s	134.9379 KOps/s	$\color{#d91a1a}-0.46\%$
test_contiguous[memmap_tensor0]	17.3220μs	1.9316μs	517.7183 KOps/s	527.0806 KOps/s	$\color{#d91a1a}-1.78\%$
test_stack[memmap_tensor0]	55.4650μs	5.7497μs	173.9212 KOps/s	176.8150 KOps/s	$\color{#d91a1a}-1.64\%$
test_memmaptd_index	1.0988ms	0.4265ms	2.3448 KOps/s	2.4384 KOps/s	$\color{#d91a1a}-3.84\%$
test_memmaptd_index_astensor	1.2452ms	0.5274ms	1.8963 KOps/s	1.9403 KOps/s	$\color{#d91a1a}-2.27\%$
test_memmaptd_index_op	1.7066ms	1.0992ms	909.7751 Ops/s	954.8079 Ops/s	$\color{#d91a1a}-4.72\%$
test_serialize_model	0.2091s	0.1295s	7.7238 Ops/s	8.5527 Ops/s	$\textbf{\color{#d91a1a}-9.69\%}$
test_serialize_model_pickle	0.4730s	0.3917s	2.5529 Ops/s	2.5166 Ops/s	$\color{#35bf28}+1.44\%$
test_serialize_weights	0.1242s	0.1165s	8.5841 Ops/s	8.5972 Ops/s	$\color{#d91a1a}-0.15\%$
test_serialize_weights_returnearly	0.1689s	0.1602s	6.2429 Ops/s	6.4266 Ops/s	$\color{#d91a1a}-2.86\%$
test_serialize_weights_pickle	0.5189s	0.4225s	2.3667 Ops/s	2.4715 Ops/s	$\color{#d91a1a}-4.24\%$
test_serialize_weights_filesystem	0.2231s	0.1524s	6.5611 Ops/s	7.1210 Ops/s	$\textbf{\color{#d91a1a}-7.86\%}$
test_serialize_model_filesystem	0.1568s	0.1455s	6.8721 Ops/s	6.5340 Ops/s	$\textbf{\color{#35bf28}+5.17\%}$
test_reshape_pytree	90.7600μs	39.0870μs	25.5840 KOps/s	25.7282 KOps/s	$\color{#d91a1a}-0.56\%$
test_reshape_td	0.1174ms	45.6259μs	21.9174 KOps/s	21.1107 KOps/s	$\color{#35bf28}+3.82\%$
test_view_pytree	90.5200μs	38.8738μs	25.7243 KOps/s	26.0067 KOps/s	$\color{#d91a1a}-1.09\%$
test_view_td	0.1285ms	52.8314μs	18.9281 KOps/s	18.3564 KOps/s	$\color{#35bf28}+3.11\%$
test_unbind_pytree	78.6080μs	36.5084μs	27.3909 KOps/s	28.1187 KOps/s	$\color{#d91a1a}-2.59\%$
test_unbind_td	0.3059ms	46.3309μs	21.5839 KOps/s	21.3131 KOps/s	$\color{#35bf28}+1.27\%$
test_split_pytree	85.1500μs	38.2810μs	26.1226 KOps/s	26.1316 KOps/s	$\color{#d91a1a}-0.03\%$
test_split_td	0.4566ms	61.0102μs	16.3907 KOps/s	16.7720 KOps/s	$\color{#d91a1a}-2.27\%$
test_add_pytree	98.3750μs	44.9851μs	22.2296 KOps/s	22.2010 KOps/s	$\color{#35bf28}+0.13\%$
test_add_td	0.2719ms	90.4186μs	11.0597 KOps/s	11.5658 KOps/s	$\color{#d91a1a}-4.38\%$
test_compile_add_one_nested[tensordict-compile]	0.1074ms	59.0086μs	16.9467 KOps/s	17.1838 KOps/s	$\color{#d91a1a}-1.38\%$
test_compile_add_one_nested[tensordict-eager]	0.3576ms	0.2013ms	4.9687 KOps/s	5.1075 KOps/s	$\color{#d91a1a}-2.72\%$
test_compile_add_one_nested[pytree-compile]	0.1280ms	56.8126μs	17.6017 KOps/s	17.6212 KOps/s	$\color{#d91a1a}-0.11\%$
test_compile_add_one_nested[pytree-eager]	0.2885ms	0.1403ms	7.1253 KOps/s	7.1658 KOps/s	$\color{#d91a1a}-0.56\%$
test_compile_copy_nested[tensordict-compile]	81.5250μs	23.2872μs	42.9421 KOps/s	43.3749 KOps/s	$\color{#d91a1a}-1.00\%$
test_compile_copy_nested[tensordict-eager]	0.1576ms	73.7437μs	13.5605 KOps/s	13.4352 KOps/s	$\color{#35bf28}+0.93\%$
test_compile_copy_nested[pytree-compile]	0.1457ms	75.8423μs	13.1853 KOps/s	13.3912 KOps/s	$\color{#d91a1a}-1.54\%$
test_compile_copy_nested[pytree-eager]	0.1274ms	68.5130μs	14.5958 KOps/s	14.6828 KOps/s	$\color{#d91a1a}-0.59\%$
test_compile_add_one_flat[tensordict-compile]	0.3864ms	0.1806ms	5.5375 KOps/s	5.5560 KOps/s	$\color{#d91a1a}-0.33\%$
test_compile_add_one_flat[tensordict-eager]	0.4562ms	0.2391ms	4.1821 KOps/s	4.2065 KOps/s	$\color{#d91a1a}-0.58\%$
test_compile_add_one_flat[tensorclass-compile]	0.1087ms	49.0932μs	20.3694 KOps/s	20.6967 KOps/s	$\color{#d91a1a}-1.58\%$
test_compile_add_one_flat[tensorclass-eager]	0.1498ms	76.9514μs	12.9952 KOps/s	12.7903 KOps/s	$\color{#35bf28}+1.60\%$
test_compile_add_one_flat[pytree-compile]	0.2854ms	0.1731ms	5.7763 KOps/s	5.7805 KOps/s	$\color{#d91a1a}-0.07\%$
test_compile_add_one_flat[pytree-eager]	0.4765ms	0.2847ms	3.5121 KOps/s	3.5194 KOps/s	$\color{#d91a1a}-0.21\%$
test_compile_add_self_flat[tensordict-eager]	0.4792ms	0.2761ms	3.6219 KOps/s	3.6121 KOps/s	$\color{#35bf28}+0.27\%$
test_compile_add_self_flat[tensordict-compile]	0.3383ms	0.1819ms	5.4986 KOps/s	5.5951 KOps/s	$\color{#d91a1a}-1.72\%$
test_compile_add_self_flat[tensorclass-eager]	0.1642ms	73.8821μs	13.5351 KOps/s	13.6423 KOps/s	$\color{#d91a1a}-0.79\%$
test_compile_add_self_flat[tensorclass-compile]	0.1157ms	50.3107μs	19.8765 KOps/s	20.8773 KOps/s	$\color{#d91a1a}-4.79\%$
test_compile_add_self_flat[pytree-eager]	0.4557ms	0.2313ms	4.3237 KOps/s	4.3344 KOps/s	$\color{#d91a1a}-0.25\%$
test_compile_add_self_flat[pytree-compile]	0.2840ms	0.1755ms	5.6987 KOps/s	5.8243 KOps/s	$\color{#d91a1a}-2.16\%$
test_compile_copy_flat[tensordict-compile]	0.2102ms	0.1105ms	9.0520 KOps/s	8.9367 KOps/s	$\color{#35bf28}+1.29\%$
test_compile_copy_flat[tensordict-eager]	0.1682ms	78.2182μs	12.7847 KOps/s	12.7389 KOps/s	$\color{#35bf28}+0.36\%$
test_compile_copy_flat[pytree-compile]	0.1617ms	79.1303μs	12.6374 KOps/s	13.0793 KOps/s	$\color{#d91a1a}-3.38\%$
test_compile_copy_flat[pytree-eager]	0.1453ms	68.9800μs	14.4970 KOps/s	14.6847 KOps/s	$\color{#d91a1a}-1.28\%$
test_compile_assign_and_add[tensordict-compile]	0.2933ms	0.1952ms	5.1228 KOps/s	5.1342 KOps/s	$\color{#d91a1a}-0.22\%$
test_compile_assign_and_add[tensordict-eager]	3.0140ms	1.8097ms	552.5834 Ops/s	572.9522 Ops/s	$\color{#d91a1a}-3.56\%$
test_compile_assign_and_add[pytree-compile]	0.4111ms	0.1949ms	5.1300 KOps/s	5.1650 KOps/s	$\color{#d91a1a}-0.68\%$
test_compile_assign_and_add[pytree-eager]	1.8455ms	1.0976ms	911.0601 Ops/s	912.5589 Ops/s	$\color{#d91a1a}-0.16\%$
test_compile_assign_and_add_stack[compile]	0.4990ms	0.4207ms	2.3772 KOps/s	2.4170 KOps/s	$\color{#d91a1a}-1.65\%$
test_compile_assign_and_add_stack[eager]	4.5957ms	4.2028ms	237.9386 Ops/s	252.4610 Ops/s	$\textbf{\color{#d91a1a}-5.75\%}$
test_compile_indexing[tensor-tensordict-compile]	96.1910μs	35.6506μs	28.0500 KOps/s	29.2637 KOps/s	$\color{#d91a1a}-4.15\%$
test_compile_indexing[tensor-tensordict-eager]	1.1608ms	50.8379μs	19.6704 KOps/s	20.5411 KOps/s	$\color{#d91a1a}-4.24\%$
test_compile_indexing[tensor-tensorclass-compile]	96.7720μs	30.5153μs	32.7704 KOps/s	32.4667 KOps/s	$\color{#35bf28}+0.94\%$
test_compile_indexing[tensor-tensorclass-eager]	74.7410μs	30.3705μs	32.9267 KOps/s	34.7078 KOps/s	$\textbf{\color{#d91a1a}-5.13\%}$
test_compile_indexing[tensor-pytree-compile]	95.3890μs	30.4359μs	32.8560 KOps/s	33.0795 KOps/s	$\color{#d91a1a}-0.68\%$
test_compile_indexing[tensor-pytree-eager]	81.4130μs	29.8484μs	33.5026 KOps/s	34.4463 KOps/s	$\color{#d91a1a}-2.74\%$
test_compile_indexing[slice-tensordict-compile]	0.1594ms	75.5160μs	13.2422 KOps/s	13.6777 KOps/s	$\color{#d91a1a}-3.18\%$
test_compile_indexing[slice-tensordict-eager]	0.5549ms	28.7525μs	34.7796 KOps/s	35.2401 KOps/s	$\color{#d91a1a}-1.31\%$
test_compile_indexing[slice-tensorclass-compile]	0.2016ms	70.2774μs	14.2293 KOps/s	14.9017 KOps/s	$\color{#d91a1a}-4.51\%$
test_compile_indexing[slice-tensorclass-eager]	82.1340μs	24.0611μs	41.5608 KOps/s	42.8101 KOps/s	$\color{#d91a1a}-2.92\%$
test_compile_indexing[slice-pytree-compile]	0.1651ms	69.1798μs	14.4551 KOps/s	14.8678 KOps/s	$\color{#d91a1a}-2.78\%$
test_compile_indexing[slice-pytree-eager]	60.7640μs	23.6238μs	42.3301 KOps/s	42.9500 KOps/s	$\color{#d91a1a}-1.44\%$
test_compile_indexing[int-tensordict-compile]	0.1531ms	75.2762μs	13.2844 KOps/s	13.6248 KOps/s	$\color{#d91a1a}-2.50\%$
test_compile_indexing[int-tensordict-eager]	1.1097ms	28.3047μs	35.3298 KOps/s	36.2266 KOps/s	$\color{#d91a1a}-2.48\%$
test_compile_indexing[int-tensorclass-compile]	0.1516ms	68.7121μs	14.5535 KOps/s	14.8571 KOps/s	$\color{#d91a1a}-2.04\%$
test_compile_indexing[int-tensorclass-eager]	70.7230μs	23.6120μs	42.3514 KOps/s	43.0664 KOps/s	$\color{#d91a1a}-1.66\%$
test_compile_indexing[int-pytree-compile]	0.1511ms	68.9939μs	14.4940 KOps/s	15.0056 KOps/s	$\color{#d91a1a}-3.41\%$
test_compile_indexing[int-pytree-eager]	86.2820μs	23.9320μs	41.7850 KOps/s	42.0776 KOps/s	$\color{#d91a1a}-0.70\%$
test_mod_add[eager]	94.0060μs	27.5001μs	36.3635 KOps/s	38.9514 KOps/s	$\textbf{\color{#d91a1a}-6.64\%}$
test_mod_add[compile]	87.1840μs	39.5345μs	25.2944 KOps/s	26.6504 KOps/s	$\textbf{\color{#d91a1a}-5.09\%}$
test_mod_add[compile-overhead]	92.0530μs	39.3325μs	25.4243 KOps/s	25.7760 KOps/s	$\color{#d91a1a}-1.36\%$
test_mod_wrap[eager]	0.4440ms	0.2114ms	4.7307 KOps/s	4.9270 KOps/s	$\color{#d91a1a}-3.98\%$
test_mod_wrap[compile]	0.4385ms	0.2370ms	4.2196 KOps/s	4.4040 KOps/s	$\color{#d91a1a}-4.19\%$
test_mod_wrap[compile-overhead]	0.4142ms	0.2330ms	4.2922 KOps/s	4.4145 KOps/s	$\color{#d91a1a}-2.77\%$
test_mod_wrap_and_backward[eager]	11.9082ms	10.4843ms	95.3804 Ops/s	92.2352 Ops/s	$\color{#35bf28}+3.41\%$
test_mod_wrap_and_backward[compile]	11.9915ms	10.5152ms	95.1002 Ops/s	86.1214 Ops/s	$\textbf{\color{#35bf28}+10.43\%}$
test_mod_wrap_and_backward[compile-overhead]	12.2716ms	10.5610ms	94.6879 Ops/s	87.7345 Ops/s	$\textbf{\color{#35bf28}+7.93\%}$
test_seq_add[eager]	0.1809ms	95.2630μs	10.4972 KOps/s	10.7663 KOps/s	$\color{#d91a1a}-2.50\%$
test_seq_add[compile]	0.1382ms	65.1759μs	15.3431 KOps/s	15.4203 KOps/s	$\color{#d91a1a}-0.50\%$
test_seq_add[compile-overhead]	0.1304ms	64.6524μs	15.4673 KOps/s	15.6688 KOps/s	$\color{#d91a1a}-1.29\%$
test_seq_wrap[eager]	0.6237ms	0.3988ms	2.5074 KOps/s	2.6421 KOps/s	$\textbf{\color{#d91a1a}-5.10\%}$
test_seq_wrap[compile]	1.2107ms	0.2717ms	3.6805 KOps/s	3.7369 KOps/s	$\color{#d91a1a}-1.51\%$
test_seq_wrap[compile-overhead]	1.2315ms	0.2710ms	3.6904 KOps/s	3.7753 KOps/s	$\color{#d91a1a}-2.25\%$
test_func_call_runtime[False-eager]	0.9446ms	0.5309ms	1.8836 KOps/s	1.9678 KOps/s	$\color{#d91a1a}-4.28\%$
test_func_call_runtime[False-compile]	1.0155ms	0.5031ms	1.9876 KOps/s	2.0193 KOps/s	$\color{#d91a1a}-1.57\%$
test_func_call_runtime[False-compile-overhead]	0.8735ms	0.5043ms	1.9830 KOps/s	2.0066 KOps/s	$\color{#d91a1a}-1.18\%$
test_func_call_runtime[True-eager]	1.2074ms	0.7620ms	1.3124 KOps/s	1.3584 KOps/s	$\color{#d91a1a}-3.39\%$
test_func_call_runtime[True-compile]	0.9142ms	0.5172ms	1.9336 KOps/s	1.9845 KOps/s	$\color{#d91a1a}-2.56\%$
test_func_call_runtime[True-compile-overhead]	0.6455ms	0.5165ms	1.9360 KOps/s	1.9711 KOps/s	$\color{#d91a1a}-1.78\%$
test_func_call_cm_runtime[False-eager]	1.0419ms	0.5370ms	1.8621 KOps/s	1.9640 KOps/s	$\textbf{\color{#d91a1a}-5.19\%}$
test_func_call_cm_runtime[False-compile]	0.6824ms	0.5062ms	1.9754 KOps/s	2.0015 KOps/s	$\color{#d91a1a}-1.30\%$
test_func_call_cm_runtime[False-compile-overhead]	0.6391ms	0.5064ms	1.9748 KOps/s	1.9969 KOps/s	$\color{#d91a1a}-1.10\%$
test_func_call_cm_runtime[True-eager]	1.0749ms	0.9103ms	1.0986 KOps/s	1.1304 KOps/s	$\color{#d91a1a}-2.82\%$
test_func_call_cm_runtime[True-compile]	1.1427ms	0.7589ms	1.3177 KOps/s	1.3622 KOps/s	$\color{#d91a1a}-3.26\%$
test_func_call_cm_runtime[True-compile-overhead]	0.8618ms	0.7535ms	1.3271 KOps/s	1.3589 KOps/s	$\color{#d91a1a}-2.34\%$
test_vmap_func_call_cm_runtime[eager]	2.5718ms	1.9410ms	515.2000 Ops/s	525.1234 Ops/s	$\color{#d91a1a}-1.89\%$
test_vmap_func_call_cm_runtime[compile]	2.6922ms	1.9984ms	500.4032 Ops/s	509.5431 Ops/s	$\color{#d91a1a}-1.79\%$
test_vmap_func_call_cm_runtime[compile-overhead]	2.5975ms	1.9978ms	500.5463 Ops/s	513.3802 Ops/s	$\color{#d91a1a}-2.50\%$
test_distributed	0.2711ms	0.1245ms	8.0346 KOps/s	7.8031 KOps/s	$\color{#35bf28}+2.97\%$
test_tdmodule	70.3330μs	19.2502μs	51.9476 KOps/s	58.3347 KOps/s	$\textbf{\color{#d91a1a}-10.95\%}$
test_tdmodule_dispatch	66.3140μs	38.4895μs	25.9811 KOps/s	29.1391 KOps/s	$\textbf{\color{#d91a1a}-10.84\%}$
test_tdseq	49.3630μs	22.0910μs	45.2674 KOps/s	50.8114 KOps/s	$\textbf{\color{#d91a1a}-10.91\%}$
test_tdseq_dispatch	79.7200μs	44.1328μs	22.6589 KOps/s	25.0570 KOps/s	$\textbf{\color{#d91a1a}-9.57\%}$
test_instantiation_functorch	1.7339ms	1.5936ms	627.5120 Ops/s	641.6514 Ops/s	$\color{#d91a1a}-2.20\%$
test_instantiation_td	2.1891ms	1.2216ms	818.5940 Ops/s	853.8919 Ops/s	$\color{#d91a1a}-4.13\%$
test_exec_functorch	0.2867ms	0.1896ms	5.2746 KOps/s	5.3838 KOps/s	$\color{#d91a1a}-2.03\%$
test_exec_functional_call	0.4379ms	0.1755ms	5.6966 KOps/s	5.8665 KOps/s	$\color{#d91a1a}-2.90\%$
test_exec_td	0.3660ms	0.2001ms	4.9968 KOps/s	5.0085 KOps/s	$\color{#d91a1a}-0.23\%$
test_exec_td_decorator	0.8959ms	0.2382ms	4.1974 KOps/s	4.3425 KOps/s	$\color{#d91a1a}-3.34\%$
test_vmap_mlp_speed[True-True]	0.9286ms	0.6968ms	1.4351 KOps/s	1.4463 KOps/s	$\color{#d91a1a}-0.77\%$
test_vmap_mlp_speed[True-False]	1.0887ms	0.6979ms	1.4328 KOps/s	1.4778 KOps/s	$\color{#d91a1a}-3.04\%$
test_vmap_mlp_speed[False-True]	0.6168ms	0.5412ms	1.8479 KOps/s	1.8832 KOps/s	$\color{#d91a1a}-1.88\%$
test_vmap_mlp_speed[False-False]	0.7616ms	0.5421ms	1.8448 KOps/s	1.8745 KOps/s	$\color{#d91a1a}-1.59\%$
test_vmap_mlp_speed_decorator[True-True]	1.3197ms	0.6604ms	1.5142 KOps/s	1.5690 KOps/s	$\color{#d91a1a}-3.49\%$
test_vmap_mlp_speed_decorator[True-False]	1.0489ms	0.6635ms	1.5072 KOps/s	1.5740 KOps/s	$\color{#d91a1a}-4.24\%$
test_vmap_mlp_speed_decorator[False-True]	0.9190ms	0.5462ms	1.8309 KOps/s	1.8892 KOps/s	$\color{#d91a1a}-3.08\%$
test_vmap_mlp_speed_decorator[False-False]	0.8697ms	0.5453ms	1.8340 KOps/s	1.8883 KOps/s	$\color{#d91a1a}-2.88\%$
test_to_module_speed[True]	2.0614ms	1.4555ms	687.0623 Ops/s	718.1580 Ops/s	$\color{#d91a1a}-4.33\%$
test_to_module_speed[False]	2.2297ms	1.4277ms	700.4133 Ops/s	731.4227 Ops/s	$\color{#d91a1a}-4.24\%$
test_tc_init	98.3650μs	47.7083μs	20.9607 KOps/s	21.9232 KOps/s	$\color{#d91a1a}-4.39\%$
test_tc_init_nested	0.1700ms	96.6748μs	10.3440 KOps/s	10.9682 KOps/s	$\textbf{\color{#d91a1a}-5.69\%}$
test_tc_first_layer_tensor	37.0600μs	1.5824μs	631.9673 KOps/s	632.1583 KOps/s	$\color{#d91a1a}-0.03\%$
test_tc_first_layer_nontensor	24.4550μs	4.9329μs	202.7212 KOps/s	210.0437 KOps/s	$\color{#d91a1a}-3.49\%$
test_tc_second_layer_tensor	22.1620μs	2.9379μs	340.3789 KOps/s	347.3818 KOps/s	$\color{#d91a1a}-2.02\%$
test_tc_second_layer_nontensor	28.8440μs	6.1208μs	163.3770 KOps/s	164.7053 KOps/s	$\color{#d91a1a}-0.81\%$
test_unbind	0.4667s	13.1081ms	76.2886 Ops/s	75.7584 Ops/s	$\color{#35bf28}+0.70\%$
test_full_like	8.7797ms	7.2483ms	137.9626 Ops/s	144.9704 Ops/s	$\color{#d91a1a}-4.83\%$
test_zeros_like	3.1614ms	2.7655ms	361.5937 Ops/s	346.6296 Ops/s	$\color{#35bf28}+4.32\%$
test_ones_like	3.5754ms	3.1884ms	313.6374 Ops/s	290.0997 Ops/s	$\textbf{\color{#35bf28}+8.11\%}$
test_clone	5.6838ms	5.0558ms	197.7914 Ops/s	206.7255 Ops/s	$\color{#d91a1a}-4.32\%$
test_squeeze	66.0740μs	12.8179μs	78.0158 KOps/s	78.8672 KOps/s	$\color{#d91a1a}-1.08\%$
test_unsqueeze	0.1600ms	95.0781μs	10.5177 KOps/s	10.8456 KOps/s	$\color{#d91a1a}-3.02\%$
test_split	0.5694ms	0.1959ms	5.1049 KOps/s	5.1302 KOps/s	$\color{#d91a1a}-0.49\%$
test_permute	0.3564ms	0.2208ms	4.5300 KOps/s	4.4661 KOps/s	$\color{#35bf28}+1.43\%$
test_stack	27.3719ms	24.6537ms	40.5619 Ops/s	41.3618 Ops/s	$\color{#d91a1a}-1.93\%$
test_cat	30.6883ms	24.4095ms	40.9677 Ops/s	41.6513 Ops/s	$\color{#d91a1a}-1.64\%$

[github-actions]

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

Total Benchmarks: 228. Improved: $\large\color{#35bf28}23$. Worsened: $\large\color{#d91a1a}8$.

Expand to view detailed results

Name	Max	Mean	Ops	Ops on Repo HEAD	Change
test_plain_set_nested	0.1489ms	16.1417μs	61.9515 KOps/s	58.4373 KOps/s	$\textbf{\color{#35bf28}+6.01\%}$
test_plain_set_stack_nested	35.6500μs	16.2227μs	61.6422 KOps/s	57.7120 KOps/s	$\textbf{\color{#35bf28}+6.81\%}$
test_plain_set_nested_inplace	41.5100μs	17.3759μs	57.5509 KOps/s	54.3644 KOps/s	$\textbf{\color{#35bf28}+5.86\%}$
test_plain_set_stack_nested_inplace	41.8800μs	17.1283μs	58.3830 KOps/s	54.9699 KOps/s	$\textbf{\color{#35bf28}+6.21\%}$
test_items	22.0100μs	2.8591μs	349.7640 KOps/s	348.8000 KOps/s	$\color{#35bf28}+0.28\%$
test_items_nested	0.3748ms	0.3464ms	2.8866 KOps/s	2.8758 KOps/s	$\color{#35bf28}+0.38\%$
test_items_nested_locked	0.4044ms	0.3479ms	2.8741 KOps/s	2.9106 KOps/s	$\color{#d91a1a}-1.25\%$
test_items_nested_leaf	0.1107ms	69.1224μs	14.4671 KOps/s	14.4991 KOps/s	$\color{#d91a1a}-0.22\%$
test_items_stack_nested	0.4012ms	0.3474ms	2.8786 KOps/s	2.8888 KOps/s	$\color{#d91a1a}-0.35\%$
test_items_stack_nested_leaf	0.1071ms	70.1134μs	14.2626 KOps/s	14.1808 KOps/s	$\color{#35bf28}+0.58\%$
test_items_stack_nested_locked	0.3930ms	0.3497ms	2.8593 KOps/s	2.8835 KOps/s	$\color{#d91a1a}-0.84\%$
test_keys	43.1700μs	3.4201μs	292.3907 KOps/s	294.3286 KOps/s	$\color{#d91a1a}-0.66\%$
test_keys_nested	96.4410μs	70.9389μs	14.0966 KOps/s	14.0830 KOps/s	$\color{#35bf28}+0.10\%$
test_keys_nested_locked	2.5071ms	76.1701μs	13.1285 KOps/s	13.0032 KOps/s	$\color{#35bf28}+0.96\%$
test_keys_nested_leaf	92.8710μs	61.1906μs	16.3424 KOps/s	16.3798 KOps/s	$\color{#d91a1a}-0.23\%$
test_keys_stack_nested	97.1720μs	70.9975μs	14.0850 KOps/s	14.0844 KOps/s	$+0.00\%$
test_keys_stack_nested_leaf	93.8720μs	62.3452μs	16.0397 KOps/s	15.7732 KOps/s	$\color{#35bf28}+1.69\%$
test_keys_stack_nested_locked	0.1061ms	76.2984μs	13.1064 KOps/s	12.9315 KOps/s	$\color{#35bf28}+1.35\%$
test_values	6.2502μs	0.8422μs	1.1874 MOps/s	1.1914 MOps/s	$\color{#d91a1a}-0.33\%$
test_values_nested	81.8410μs	48.5034μs	20.6171 KOps/s	20.4728 KOps/s	$\color{#35bf28}+0.70\%$
test_values_nested_locked	76.2710μs	50.2826μs	19.8876 KOps/s	19.8357 KOps/s	$\color{#35bf28}+0.26\%$
test_values_nested_leaf	69.5210μs	42.6050μs	23.4714 KOps/s	23.3568 KOps/s	$\color{#35bf28}+0.49\%$
test_values_stack_nested	77.8110μs	50.4327μs	19.8284 KOps/s	19.6929 KOps/s	$\color{#35bf28}+0.69\%$
test_values_stack_nested_leaf	77.7810μs	43.3359μs	23.0755 KOps/s	22.6558 KOps/s	$\color{#35bf28}+1.85\%$
test_values_stack_nested_locked	79.6810μs	51.0940μs	19.5718 KOps/s	19.1012 KOps/s	$\color{#35bf28}+2.46\%$
test_membership	1.8295μs	0.4979μs	2.0085 MOps/s	1.9956 MOps/s	$\color{#35bf28}+0.65\%$
test_membership_nested	13.0400μs	1.8358μs	544.7291 KOps/s	543.1131 KOps/s	$\color{#35bf28}+0.30\%$
test_membership_nested_leaf	11.2533μs	1.8094μs	552.6595 KOps/s	554.2519 KOps/s	$\color{#d91a1a}-0.29\%$
test_membership_stacked_nested	23.8700μs	1.8810μs	531.6355 KOps/s	537.0805 KOps/s	$\color{#d91a1a}-1.01\%$
test_membership_stacked_nested_leaf	22.7410μs	1.9252μs	519.4236 KOps/s	535.7859 KOps/s	$\color{#d91a1a}-3.05\%$
test_membership_nested_last	32.1010μs	2.9296μs	341.3405 KOps/s	345.5148 KOps/s	$\color{#d91a1a}-1.21\%$
test_membership_nested_leaf_last	32.4210μs	2.9595μs	337.8955 KOps/s	347.3320 KOps/s	$\color{#d91a1a}-2.72\%$
test_membership_stacked_nested_last	37.9900μs	5.6149μs	178.0970 KOps/s	288.9760 KOps/s	$\textbf{\color{#d91a1a}-38.37\%}$
test_membership_stacked_nested_leaf_last	33.9900μs	5.5775μs	179.2902 KOps/s	286.8494 KOps/s	$\textbf{\color{#d91a1a}-37.50\%}$
test_nested_getleaf	32.5900μs	6.0451μs	165.4239 KOps/s	165.6837 KOps/s	$\color{#d91a1a}-0.16\%$
test_nested_get	36.7210μs	5.7204μs	174.8142 KOps/s	176.5633 KOps/s	$\color{#d91a1a}-0.99\%$
test_stacked_getleaf	37.3300μs	5.9741μs	167.3898 KOps/s	165.9591 KOps/s	$\color{#35bf28}+0.86\%$
test_stacked_get	31.8200μs	5.6263μs	177.7378 KOps/s	177.8625 KOps/s	$\color{#d91a1a}-0.07\%$
test_nested_getitemleaf	29.4100μs	6.1413μs	162.8319 KOps/s	162.6734 KOps/s	$\color{#35bf28}+0.10\%$
test_nested_getitem	30.8210μs	5.7666μs	173.4115 KOps/s	175.4934 KOps/s	$\color{#d91a1a}-1.19\%$
test_stacked_getitemleaf	36.0610μs	6.0703μs	164.7370 KOps/s	164.3580 KOps/s	$\color{#35bf28}+0.23\%$
test_stacked_getitem	39.4300μs	5.6938μs	175.6299 KOps/s	176.2203 KOps/s	$\color{#d91a1a}-0.33\%$
test_lock_nested	4.8927ms	0.4302ms	2.3245 KOps/s	2.3745 KOps/s	$\color{#d91a1a}-2.11\%$
test_lock_stack_nested	0.4180ms	0.3802ms	2.6301 KOps/s	2.6640 KOps/s	$\color{#d91a1a}-1.27\%$
test_unlock_nested	0.7546ms	0.3631ms	2.7542 KOps/s	2.8192 KOps/s	$\color{#d91a1a}-2.30\%$
test_unlock_stack_nested	0.3559ms	0.3173ms	3.1516 KOps/s	3.1950 KOps/s	$\color{#d91a1a}-1.36\%$
test_flatten_speed	0.1166ms	83.9826μs	11.9072 KOps/s	12.0913 KOps/s	$\color{#d91a1a}-1.52\%$
test_unflatten_speed	0.3617ms	0.3245ms	3.0814 KOps/s	3.1131 KOps/s	$\color{#d91a1a}-1.02\%$
test_common_ops	1.6489ms	1.3117ms	762.3637 Ops/s	778.9759 Ops/s	$\color{#d91a1a}-2.13\%$
test_creation	26.4000μs	1.4647μs	682.7285 KOps/s	679.5280 KOps/s	$\color{#35bf28}+0.47\%$
test_creation_empty	42.0700μs	14.5315μs	68.8160 KOps/s	62.5276 KOps/s	$\textbf{\color{#35bf28}+10.06\%}$
test_creation_nested_1	65.0310μs	15.9073μs	62.8642 KOps/s	55.5439 KOps/s	$\textbf{\color{#35bf28}+13.18\%}$
test_creation_nested_2	53.9010μs	18.7307μs	53.3883 KOps/s	49.1935 KOps/s	$\textbf{\color{#35bf28}+8.53\%}$
test_clone	71.2410μs	28.0817μs	35.6103 KOps/s	35.1167 KOps/s	$\color{#35bf28}+1.41\%$
test_getitem[int]	92.4959ms	23.3966μs	42.7413 KOps/s	66.7016 KOps/s	$\textbf{\color{#d91a1a}-35.92\%}$
test_getitem[slice_int]	0.1183ms	27.3719μs	36.5339 KOps/s	37.7743 KOps/s	$\color{#d91a1a}-3.28\%$
test_getitem[range]	0.2251ms	0.1081ms	9.2537 KOps/s	9.3656 KOps/s	$\color{#d91a1a}-1.19\%$
test_getitem[tuple]	0.1158ms	24.0477μs	41.5840 KOps/s	43.3538 KOps/s	$\color{#d91a1a}-4.08\%$
test_getitem[list]	0.1923ms	98.2641μs	10.1767 KOps/s	10.4652 KOps/s	$\color{#d91a1a}-2.76\%$
test_setitem_dim[int]	93.1210μs	44.3907μs	22.5272 KOps/s	22.9853 KOps/s	$\color{#d91a1a}-1.99\%$
test_setitem_dim[slice_int]	91.2310μs	66.6790μs	14.9972 KOps/s	15.0369 KOps/s	$\color{#d91a1a}-0.26\%$
test_setitem_dim[range]	0.1610ms	0.1257ms	7.9556 KOps/s	8.0026 KOps/s	$\color{#d91a1a}-0.59\%$
test_setitem_dim[tuple]	85.5510μs	60.2998μs	16.5838 KOps/s	16.7890 KOps/s	$\color{#d91a1a}-1.22\%$
test_setitem	67.1910μs	40.9077μs	24.4453 KOps/s	23.6405 KOps/s	$\color{#35bf28}+3.40\%$
test_set	82.8210μs	41.3750μs	24.1692 KOps/s	22.9953 KOps/s	$\textbf{\color{#35bf28}+5.10\%}$
test_set_shared	0.3515ms	52.8942μs	18.9057 KOps/s	17.7779 KOps/s	$\textbf{\color{#35bf28}+6.34\%}$
test_update	82.6310μs	49.4037μs	20.2414 KOps/s	19.5711 KOps/s	$\color{#35bf28}+3.42\%$
test_update_nested	98.0710μs	58.3691μs	17.1323 KOps/s	16.7788 KOps/s	$\color{#35bf28}+2.11\%$
test_update__nested	96.0610μs	60.0040μs	16.6656 KOps/s	16.3018 KOps/s	$\color{#35bf28}+2.23\%$
test_set_nested	74.6210μs	42.4665μs	23.5480 KOps/s	22.8792 KOps/s	$\color{#35bf28}+2.92\%$
test_set_nested_new	96.2310μs	46.2171μs	21.6370 KOps/s	21.0158 KOps/s	$\color{#35bf28}+2.96\%$
test_select	99.6210μs	59.5547μs	16.7913 KOps/s	16.4820 KOps/s	$\color{#35bf28}+1.88\%$
test_select_nested	0.3466ms	42.5560μs	23.4985 KOps/s	23.6869 KOps/s	$\color{#d91a1a}-0.80\%$
test_exclude_nested	0.1069ms	57.6251μs	17.3535 KOps/s	17.5553 KOps/s	$\color{#d91a1a}-1.15\%$
test_empty[True]	0.2943ms	0.2549ms	3.9239 KOps/s	3.9121 KOps/s	$\color{#35bf28}+0.30\%$
test_empty[False]	3.2490μs	0.7363μs	1.3582 MOps/s	1.3545 MOps/s	$\color{#35bf28}+0.27\%$
test_to	52.0410μs	25.9858μs	38.4826 KOps/s	37.9993 KOps/s	$\color{#35bf28}+1.27\%$
test_to_nonblocking	57.8810μs	24.6455μs	40.5754 KOps/s	40.3062 KOps/s	$\color{#35bf28}+0.67\%$
test_unbind_speed	0.3140ms	0.2768ms	3.6130 KOps/s	3.6484 KOps/s	$\color{#d91a1a}-0.97\%$
test_unbind_speed_stack0	0.3079ms	0.2738ms	3.6527 KOps/s	3.7524 KOps/s	$\color{#d91a1a}-2.66\%$
test_unbind_speed_stack1	91.9810ms	0.7024ms	1.4237 KOps/s	1.4561 KOps/s	$\color{#d91a1a}-2.23\%$
test_split	94.2540ms	2.1321ms	469.0250 Ops/s	475.7444 Ops/s	$\color{#d91a1a}-1.41\%$
test_chunk	94.2802ms	2.1281ms	469.8962 Ops/s	475.1637 Ops/s	$\color{#d91a1a}-1.11\%$
test_creation[device0]	0.3944ms	0.1243ms	8.0435 KOps/s	8.0346 KOps/s	$\color{#35bf28}+0.11\%$
test_creation_from_tensor	0.3510ms	0.1296ms	7.7151 KOps/s	7.8308 KOps/s	$\color{#d91a1a}-1.48\%$
test_add_one[memmap_tensor0]	0.2914ms	8.3668μs	119.5200 KOps/s	118.4392 KOps/s	$\color{#35bf28}+0.91\%$
test_contiguous[memmap_tensor0]	32.7600μs	2.1168μs	472.4078 KOps/s	477.6385 KOps/s	$\color{#d91a1a}-1.10\%$
test_stack[memmap_tensor0]	45.0010μs	6.4359μs	155.3793 KOps/s	158.2423 KOps/s	$\color{#d91a1a}-1.81\%$
test_memmaptd_index	1.2591ms	0.4199ms	2.3814 KOps/s	2.4214 KOps/s	$\color{#d91a1a}-1.65\%$
test_memmaptd_index_astensor	0.9348ms	0.4886ms	2.0468 KOps/s	2.0621 KOps/s	$\color{#d91a1a}-0.74\%$
test_memmaptd_index_op	1.4167ms	0.9911ms	1.0090 KOps/s	979.4465 Ops/s	$\color{#35bf28}+3.02\%$
test_serialize_model	0.1314s	0.1305s	7.6626 Ops/s	7.7008 Ops/s	$\color{#d91a1a}-0.50\%$
test_serialize_model_pickle	1.3725s	1.2174s	0.8215 Ops/s	0.8237 Ops/s	$\color{#d91a1a}-0.28\%$
test_serialize_weights	0.1301s	0.1295s	7.7233 Ops/s	7.6889 Ops/s	$\color{#35bf28}+0.45\%$
test_serialize_weights_returnearly	0.2278s	56.5210ms	17.6925 Ops/s	18.0318 Ops/s	$\color{#d91a1a}-1.88\%$
test_serialize_weights_pickle	1.4282s	1.2258s	0.8158 Ops/s	0.8206 Ops/s	$\color{#d91a1a}-0.59\%$
test_reshape_pytree	67.8110μs	34.1943μs	29.2446 KOps/s	29.9168 KOps/s	$\color{#d91a1a}-2.25\%$
test_reshape_td	81.8010μs	40.7243μs	24.5554 KOps/s	25.2506 KOps/s	$\color{#d91a1a}-2.75\%$
test_view_pytree	69.2310μs	34.7347μs	28.7897 KOps/s	29.9431 KOps/s	$\color{#d91a1a}-3.85\%$
test_view_td	79.0710μs	47.4942μs	21.0552 KOps/s	22.4955 KOps/s	$\textbf{\color{#d91a1a}-6.40\%}$
test_unbind_pytree	66.0510μs	33.2401μs	30.0841 KOps/s	30.9366 KOps/s	$\color{#d91a1a}-2.76\%$
test_unbind_td	0.5378ms	44.3298μs	22.5582 KOps/s	24.9962 KOps/s	$\textbf{\color{#d91a1a}-9.75\%}$
test_split_pytree	0.5233ms	45.5658μs	21.9463 KOps/s	22.7359 KOps/s	$\color{#d91a1a}-3.47\%$
test_split_td	0.1539ms	55.7483μs	17.9378 KOps/s	16.3080 KOps/s	$\textbf{\color{#35bf28}+9.99\%}$
test_add_pytree	92.5310μs	56.1147μs	17.8207 KOps/s	18.6886 KOps/s	$\color{#d91a1a}-4.64\%$
test_add_td	0.1555ms	94.4896μs	10.5832 KOps/s	10.9770 KOps/s	$\color{#d91a1a}-3.59\%$
test_compile_add_one_nested[tensordict-compile]	0.2971ms	0.1597ms	6.2633 KOps/s	6.2578 KOps/s	$\color{#35bf28}+0.09\%$
test_compile_add_one_nested[tensordict-eager]	0.2668ms	0.1673ms	5.9788 KOps/s	6.1568 KOps/s	$\color{#d91a1a}-2.89\%$
test_compile_add_one_nested[pytree-compile]	1.0143ms	0.1415ms	7.0654 KOps/s	7.1066 KOps/s	$\color{#d91a1a}-0.58\%$
test_compile_add_one_nested[pytree-eager]	0.2702ms	0.1765ms	5.6659 KOps/s	5.4382 KOps/s	$\color{#35bf28}+4.19\%$
test_compile_copy_nested[tensordict-compile]	0.1242ms	20.1079μs	49.7318 KOps/s	46.7270 KOps/s	$\textbf{\color{#35bf28}+6.43\%}$
test_compile_copy_nested[tensordict-eager]	0.1405ms	47.8500μs	20.8986 KOps/s	20.3777 KOps/s	$\color{#35bf28}+2.56\%$
test_compile_copy_nested[pytree-compile]	0.2816ms	63.5416μs	15.7377 KOps/s	15.5139 KOps/s	$\color{#35bf28}+1.44\%$
test_compile_copy_nested[pytree-eager]	0.1338ms	49.6463μs	20.1425 KOps/s	20.0131 KOps/s	$\color{#35bf28}+0.65\%$
test_compile_add_one_flat[tensordict-compile]	0.4202ms	0.3120ms	3.2049 KOps/s	3.2212 KOps/s	$\color{#d91a1a}-0.51\%$
test_compile_add_one_flat[tensordict-eager]	0.3318ms	0.2369ms	4.2206 KOps/s	4.3532 KOps/s	$\color{#d91a1a}-3.05\%$
test_compile_add_one_flat[tensorclass-compile]	0.2307ms	0.1246ms	8.0234 KOps/s	7.9244 KOps/s	$\color{#35bf28}+1.25\%$
test_compile_add_one_flat[tensorclass-eager]	0.1637ms	64.1707μs	15.5834 KOps/s	15.1299 KOps/s	$\color{#35bf28}+3.00\%$
test_compile_add_one_flat[pytree-compile]	0.4228ms	0.3128ms	3.1974 KOps/s	3.2165 KOps/s	$\color{#d91a1a}-0.59\%$
test_compile_add_one_flat[pytree-eager]	0.6867ms	0.5936ms	1.6846 KOps/s	1.6294 KOps/s	$\color{#35bf28}+3.39\%$
test_compile_add_self_flat[tensordict-eager]	0.3840ms	0.2825ms	3.5392 KOps/s	3.6012 KOps/s	$\color{#d91a1a}-1.72\%$
test_compile_add_self_flat[tensordict-compile]	0.4280ms	0.3128ms	3.1968 KOps/s	3.1821 KOps/s	$\color{#35bf28}+0.46\%$
test_compile_add_self_flat[tensorclass-eager]	0.1749ms	74.7114μs	13.3848 KOps/s	13.4886 KOps/s	$\color{#d91a1a}-0.77\%$
test_compile_add_self_flat[tensorclass-compile]	0.1829ms	0.1297ms	7.7111 KOps/s	7.8658 KOps/s	$\color{#d91a1a}-1.97\%$
test_compile_add_self_flat[pytree-eager]	0.6185ms	0.5172ms	1.9336 KOps/s	1.8771 KOps/s	$\color{#35bf28}+3.01\%$
test_compile_add_self_flat[pytree-compile]	0.4174ms	0.3121ms	3.2039 KOps/s	3.2231 KOps/s	$\color{#d91a1a}-0.59\%$
test_compile_copy_flat[tensordict-compile]	0.1194ms	17.6752μs	56.5763 KOps/s	51.5416 KOps/s	$\textbf{\color{#35bf28}+9.77\%}$
test_compile_copy_flat[tensordict-eager]	0.1267ms	39.2814μs	25.4573 KOps/s	23.7342 KOps/s	$\textbf{\color{#35bf28}+7.26\%}$
test_compile_copy_flat[pytree-compile]	0.1508ms	70.0508μs	14.2754 KOps/s	14.3238 KOps/s	$\color{#d91a1a}-0.34\%$
test_compile_copy_flat[pytree-eager]	0.1301ms	52.6951μs	18.9771 KOps/s	18.9315 KOps/s	$\color{#35bf28}+0.24\%$
test_compile_assign_and_add[tensordict-compile]	2.2898ms	0.8000ms	1.2500 KOps/s	1.1406 KOps/s	$\textbf{\color{#35bf28}+9.59\%}$
test_compile_assign_and_add[tensordict-eager]	3.1964ms	3.0740ms	325.3119 Ops/s	329.2184 Ops/s	$\color{#d91a1a}-1.19\%$
test_compile_assign_and_add[pytree-compile]	2.2823ms	0.7998ms	1.2502 KOps/s	1.1566 KOps/s	$\textbf{\color{#35bf28}+8.10\%}$
test_compile_assign_and_add[pytree-eager]	3.3232ms	3.1717ms	315.2858 Ops/s	318.5201 Ops/s	$\color{#d91a1a}-1.02\%$
test_compile_indexing[tensor-tensordict-compile]	0.1601ms	0.1090ms	9.1763 KOps/s	9.5085 KOps/s	$\color{#d91a1a}-3.49\%$
test_compile_indexing[tensor-tensordict-eager]	0.2338ms	59.9290μs	16.6864 KOps/s	16.7876 KOps/s	$\color{#d91a1a}-0.60\%$
test_compile_indexing[tensor-tensorclass-compile]	0.1842ms	0.1004ms	9.9649 KOps/s	9.9820 KOps/s	$\color{#d91a1a}-0.17\%$
test_compile_indexing[tensor-tensorclass-eager]	0.1412ms	40.6674μs	24.5897 KOps/s	23.5637 KOps/s	$\color{#35bf28}+4.35\%$
test_compile_indexing[tensor-pytree-compile]	0.1848ms	0.1012ms	9.8825 KOps/s	9.8365 KOps/s	$\color{#35bf28}+0.47\%$
test_compile_indexing[tensor-pytree-eager]	0.1380ms	40.2142μs	24.8669 KOps/s	23.7332 KOps/s	$\color{#35bf28}+4.78\%$
test_compile_indexing[slice-tensordict-compile]	0.1898ms	0.1332ms	7.5080 KOps/s	7.5102 KOps/s	$\color{#d91a1a}-0.03\%$
test_compile_indexing[slice-tensordict-eager]	0.1541ms	23.8995μs	41.8418 KOps/s	42.3625 KOps/s	$\color{#d91a1a}-1.23\%$
test_compile_indexing[slice-tensorclass-compile]	0.2384ms	0.1271ms	7.8681 KOps/s	7.8521 KOps/s	$\color{#35bf28}+0.20\%$
test_compile_indexing[slice-tensorclass-eager]	0.1037ms	19.5834μs	51.0636 KOps/s	50.1381 KOps/s	$\color{#35bf28}+1.85\%$
test_compile_indexing[slice-pytree-compile]	0.2113ms	0.1281ms	7.8072 KOps/s	7.8005 KOps/s	$\color{#35bf28}+0.09\%$
test_compile_indexing[slice-pytree-eager]	70.2110μs	19.5631μs	51.1167 KOps/s	51.3059 KOps/s	$\color{#d91a1a}-0.37\%$
test_compile_indexing[int-tensordict-compile]	0.2250ms	0.1345ms	7.4348 KOps/s	7.4638 KOps/s	$\color{#d91a1a}-0.39\%$
test_compile_indexing[int-tensordict-eager]	0.5175ms	23.7158μs	42.1660 KOps/s	41.6298 KOps/s	$\color{#35bf28}+1.29\%$
test_compile_indexing[int-tensorclass-compile]	0.2178ms	0.1282ms	7.8025 KOps/s	7.8209 KOps/s	$\color{#d91a1a}-0.24\%$
test_compile_indexing[int-tensorclass-eager]	0.1093ms	23.9501μs	41.7534 KOps/s	50.5352 KOps/s	$\textbf{\color{#d91a1a}-17.38\%}$
test_compile_indexing[int-pytree-compile]	0.2246ms	0.1321ms	7.5703 KOps/s	7.8288 KOps/s	$\color{#d91a1a}-3.30\%$
test_compile_indexing[int-pytree-eager]	0.1526ms	19.6071μs	51.0020 KOps/s	40.9872 KOps/s	$\textbf{\color{#35bf28}+24.43\%}$
test_mod_add[eager]	0.1314ms	30.9777μs	32.2813 KOps/s	31.1002 KOps/s	$\color{#35bf28}+3.80\%$
test_mod_add[compile]	0.5138ms	70.1574μs	14.2537 KOps/s	14.3123 KOps/s	$\color{#d91a1a}-0.41\%$
test_mod_add[compile-overhead]	0.2619ms	0.1387ms	7.2096 KOps/s	6.8230 KOps/s	$\textbf{\color{#35bf28}+5.67\%}$
test_mod_wrap[eager]	0.9883ms	0.7984ms	1.2525 KOps/s	1.2489 KOps/s	$\color{#35bf28}+0.29\%$
test_mod_wrap[compile]	2.1132ms	0.8347ms	1.1980 KOps/s	1.2081 KOps/s	$\color{#d91a1a}-0.83\%$
test_mod_wrap[compile-overhead]	4.8848ms	3.0787ms	324.8119 Ops/s	326.8383 Ops/s	$\color{#d91a1a}-0.62\%$
test_mod_wrap_and_backward[eager]	4.6125ms	4.2018ms	237.9909 Ops/s	243.1239 Ops/s	$\color{#d91a1a}-2.11\%$
test_mod_wrap_and_backward[compile]	4.5741ms	4.1308ms	242.0830 Ops/s	244.6037 Ops/s	$\color{#d91a1a}-1.03\%$
test_mod_wrap_and_backward[compile-overhead]	1.3789ms	0.9696ms	1.0314 KOps/s	982.0624 Ops/s	$\textbf{\color{#35bf28}+5.02\%}$
test_seq_add[eager]	0.1638ms	95.4403μs	10.4777 KOps/s	10.2845 KOps/s	$\color{#35bf28}+1.88\%$
test_seq_add[compile]	0.2344ms	79.4675μs	12.5838 KOps/s	12.0156 KOps/s	$\color{#35bf28}+4.73\%$
test_seq_add[compile-overhead]	0.4968ms	0.1113ms	8.9857 KOps/s	8.8688 KOps/s	$\color{#35bf28}+1.32\%$
test_seq_wrap[eager]	1.3082ms	0.9332ms	1.0716 KOps/s	1.0838 KOps/s	$\color{#d91a1a}-1.13\%$
test_seq_wrap[compile]	1.2349ms	0.8468ms	1.1810 KOps/s	1.1952 KOps/s	$\color{#d91a1a}-1.19\%$
test_seq_wrap[compile-overhead]	0.6084ms	0.2158ms	4.6341 KOps/s	4.5977 KOps/s	$\color{#35bf28}+0.79\%$
test_func_call_runtime[False-eager]	2.7724ms	2.3820ms	419.8135 Ops/s	421.5495 Ops/s	$\color{#d91a1a}-0.41\%$
test_func_call_runtime[False-compile]	2.7811ms	2.3999ms	416.6877 Ops/s	422.6779 Ops/s	$\color{#d91a1a}-1.42\%$
test_func_call_runtime[False-compile-overhead]	0.7556ms	0.3523ms	2.8386 KOps/s	2.8527 KOps/s	$\color{#d91a1a}-0.49\%$
test_func_call_runtime[True-eager]	2.7214ms	2.5486ms	392.3697 Ops/s	398.8938 Ops/s	$\color{#d91a1a}-1.64\%$
test_func_call_runtime[True-compile]	2.5880ms	2.4373ms	410.2950 Ops/s	418.7598 Ops/s	$\color{#d91a1a}-2.02\%$
test_func_call_runtime[True-compile-overhead]	0.4239ms	0.3724ms	2.6856 KOps/s	2.6657 KOps/s	$\color{#35bf28}+0.75\%$
test_func_call_cm_runtime[False-eager]	2.7780ms	2.3820ms	419.8170 Ops/s	422.6378 Ops/s	$\color{#d91a1a}-0.67\%$
test_func_call_cm_runtime[False-compile]	2.8126ms	2.3948ms	417.5677 Ops/s	422.0705 Ops/s	$\color{#d91a1a}-1.07\%$
test_func_call_cm_runtime[False-compile-overhead]	0.4084ms	0.3549ms	2.8176 KOps/s	2.8437 KOps/s	$\color{#d91a1a}-0.92\%$
test_func_call_cm_runtime[True-eager]	2.8499ms	2.6494ms	377.4495 Ops/s	382.7642 Ops/s	$\color{#d91a1a}-1.39\%$
test_func_call_cm_runtime[True-compile]	2.6599ms	2.4766ms	403.7804 Ops/s	415.6312 Ops/s	$\color{#d91a1a}-2.85\%$
test_func_call_cm_runtime[True-compile-overhead]	0.5101ms	0.3998ms	2.5012 KOps/s	2.4989 KOps/s	$\color{#35bf28}+0.09\%$
test_vmap_func_call_cm_runtime[eager]	4.2191ms	3.7718ms	265.1249 Ops/s	266.8760 Ops/s	$\color{#d91a1a}-0.66\%$
test_vmap_func_call_cm_runtime[compile]	2.8436ms	2.4492ms	408.2998 Ops/s	410.8199 Ops/s	$\color{#d91a1a}-0.61\%$
test_vmap_func_call_cm_runtime[compile-overhead]	0.5303ms	0.4006ms	2.4961 KOps/s	2.4762 KOps/s	$\color{#35bf28}+0.81\%$
test_distributed	6.3285ms	0.2156ms	4.6385 KOps/s	8.9053 KOps/s	$\textbf{\color{#d91a1a}-47.91\%}$
test_tdmodule	52.0110μs	14.0984μs	70.9302 KOps/s	67.5723 KOps/s	$\color{#35bf28}+4.97\%$
test_tdmodule_dispatch	54.6810μs	27.5461μs	36.3028 KOps/s	34.1814 KOps/s	$\textbf{\color{#35bf28}+6.21\%}$
test_tdseq	35.4800μs	14.8496μs	67.3417 KOps/s	62.9167 KOps/s	$\textbf{\color{#35bf28}+7.03\%}$
test_tdseq_dispatch	52.5510μs	30.4040μs	32.8904 KOps/s	30.9515 KOps/s	$\textbf{\color{#35bf28}+6.26\%}$
test_instantiation_functorch	1.9637ms	1.8014ms	555.1144 Ops/s	555.3556 Ops/s	$\color{#d91a1a}-0.04\%$
test_instantiation_td	1.7056ms	1.1557ms	865.2400 Ops/s	852.9471 Ops/s	$\color{#35bf28}+1.44\%$
test_exec_functorch	1.1037ms	0.9998ms	1.0002 KOps/s	1.0108 KOps/s	$\color{#d91a1a}-1.05\%$
test_exec_functional_call	1.1243ms	1.0110ms	989.1038 Ops/s	1.0079 KOps/s	$\color{#d91a1a}-1.87\%$
test_exec_td	1.1845ms	1.0397ms	961.8200 Ops/s	979.7895 Ops/s	$\color{#d91a1a}-1.83\%$
test_exec_td_decorator	1.5996ms	1.0823ms	923.9622 Ops/s	953.7011 Ops/s	$\color{#d91a1a}-3.12\%$
test_vmap_mlp_speed[True-True]	2.0782ms	1.2748ms	784.4134 Ops/s	798.1068 Ops/s	$\color{#d91a1a}-1.72\%$
test_vmap_mlp_speed[True-False]	1.3599ms	1.2608ms	793.1615 Ops/s	796.1943 Ops/s	$\color{#d91a1a}-0.38\%$
test_vmap_mlp_speed[False-True]	1.2389ms	1.1549ms	865.9086 Ops/s	872.0375 Ops/s	$\color{#d91a1a}-0.70\%$
test_vmap_mlp_speed[False-False]	1.2371ms	1.1540ms	866.5188 Ops/s	868.9582 Ops/s	$\color{#d91a1a}-0.28\%$
test_vmap_mlp_speed_decorator[True-True]	1.3729ms	1.2566ms	795.8073 Ops/s	814.7839 Ops/s	$\color{#d91a1a}-2.33\%$
test_vmap_mlp_speed_decorator[True-False]	1.7842ms	1.2606ms	793.3041 Ops/s	814.5220 Ops/s	$\color{#d91a1a}-2.60\%$
test_vmap_mlp_speed_decorator[False-True]	1.5069ms	1.1828ms	845.4760 Ops/s	872.6298 Ops/s	$\color{#d91a1a}-3.11\%$
test_vmap_mlp_speed_decorator[False-False]	1.3433ms	1.1813ms	846.5034 Ops/s	872.4035 Ops/s	$\color{#d91a1a}-2.97\%$
test_vmap_transformer_speed[True-True]	13.4719ms	13.3353ms	74.9887 Ops/s	76.6320 Ops/s	$\color{#d91a1a}-2.14\%$
test_vmap_transformer_speed[True-False]	13.3946ms	13.3071ms	75.1478 Ops/s	76.8351 Ops/s	$\color{#d91a1a}-2.20\%$
test_vmap_transformer_speed[False-True]	13.2649ms	13.1291ms	76.1669 Ops/s	78.3988 Ops/s	$\color{#d91a1a}-2.85\%$
test_vmap_transformer_speed[False-False]	13.2927ms	13.1431ms	76.0855 Ops/s	78.5312 Ops/s	$\color{#d91a1a}-3.11\%$
test_vmap_transformer_speed_decorator[True-True]	34.4970ms	34.3550ms	29.1078 Ops/s	29.9254 Ops/s	$\color{#d91a1a}-2.73\%$
test_vmap_transformer_speed_decorator[True-False]	34.4677ms	34.3167ms	29.1403 Ops/s	29.8389 Ops/s	$\color{#d91a1a}-2.34\%$
test_vmap_transformer_speed_decorator[False-True]	34.3954ms	34.1311ms	29.2988 Ops/s	30.1020 Ops/s	$\color{#d91a1a}-2.67\%$
test_vmap_transformer_speed_decorator[False-False]	34.4002ms	34.1845ms	29.2530 Ops/s	30.1944 Ops/s	$\color{#d91a1a}-3.12\%$
test_to_module_speed[True]	1.3399ms	0.9720ms	1.0288 KOps/s	1.0140 KOps/s	$\color{#35bf28}+1.46\%$
test_to_module_speed[False]	1.3750ms	0.9536ms	1.0487 KOps/s	1.0491 KOps/s	$\color{#d91a1a}-0.04\%$
test_tc_init	0.1113ms	31.5894μs	31.6562 KOps/s	29.9761 KOps/s	$\textbf{\color{#35bf28}+5.60\%}$
test_tc_init_nested	0.1163ms	65.4467μs	15.2796 KOps/s	14.3754 KOps/s	$\textbf{\color{#35bf28}+6.29\%}$
test_tc_first_layer_tensor	10.8159μs	0.6655μs	1.5026 MOps/s	1.4907 MOps/s	$\color{#35bf28}+0.80\%$
test_tc_first_layer_nontensor	19.1610μs	2.1957μs	455.4258 KOps/s	455.9964 KOps/s	$\color{#d91a1a}-0.13\%$
test_tc_second_layer_tensor	20.3903μs	1.3545μs	738.2763 KOps/s	732.2792 KOps/s	$\color{#35bf28}+0.82\%$
test_tc_second_layer_nontensor	78.6910μs	2.8642μs	349.1427 KOps/s	344.6868 KOps/s	$\color{#35bf28}+1.29\%$
test_unbind	0.1945s	12.1680ms	82.1829 Ops/s	91.3035 Ops/s	$\textbf{\color{#d91a1a}-9.99\%}$
test_full_like	0.6565ms	0.5740ms	1.7423 KOps/s	1.7497 KOps/s	$\color{#d91a1a}-0.42\%$
test_zeros_like	0.2687ms	0.1979ms	5.0523 KOps/s	5.0533 KOps/s	$\color{#d91a1a}-0.02\%$
test_ones_like	0.2809ms	0.1978ms	5.0567 KOps/s	5.0545 KOps/s	$\color{#35bf28}+0.04\%$
test_clone	0.4559ms	0.4137ms	2.4173 KOps/s	2.4158 KOps/s	$\color{#35bf28}+0.06\%$
test_squeeze	39.7300μs	9.4073μs	106.3005 KOps/s	108.3317 KOps/s	$\color{#d91a1a}-1.87\%$
test_unsqueeze	0.2787ms	70.1260μs	14.2600 KOps/s	13.9495 KOps/s	$\color{#35bf28}+2.23\%$
test_split	0.2548ms	0.1498ms	6.6769 KOps/s	6.6782 KOps/s	$\color{#d91a1a}-0.02\%$
test_permute	0.2633ms	0.1707ms	5.8570 KOps/s	5.8643 KOps/s	$\color{#d91a1a}-0.12\%$
test_stack	1.2584ms	0.8481ms	1.1790 KOps/s	1.1633 KOps/s	$\color{#35bf28}+1.35\%$
test_cat	1.2551ms	1.2316ms	811.9654 Ops/s	812.0526 Ops/s	$\color{#d91a1a}-0.01\%$