Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature] Structured dtype #1195

Open
wants to merge 1 commit into
base: gh/vmoens/46/base
Choose a base branch
from
Open

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Jan 30, 2025

Stack from ghstack (oldest at bottom):

[ghstack-poisoned]
vmoens added a commit that referenced this pull request Jan 30, 2025
ghstack-source-id: 46e12fff1a9f76000fc3011c9bf04e0c0e0f5498
Pull Request resolved: #1195
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jan 30, 2025
Copy link

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

Total Benchmarks: 217. Improved: $\large\color{#35bf28}19$. Worsened: $\large\color{#d91a1a}12$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_plain_set_nested 0.1290ms 21.1625μs 47.2535 KOps/s 48.5315 KOps/s $\color{#d91a1a}-2.63\%$
test_plain_set_stack_nested 54.4720μs 21.2543μs 47.0492 KOps/s 47.8553 KOps/s $\color{#d91a1a}-1.68\%$
test_plain_set_nested_inplace 51.8070μs 23.0727μs 43.3412 KOps/s 44.4494 KOps/s $\color{#d91a1a}-2.49\%$
test_plain_set_stack_nested_inplace 62.8790μs 22.8619μs 43.7408 KOps/s 44.5672 KOps/s $\color{#d91a1a}-1.85\%$
test_items 30.3870μs 4.2080μs 237.6451 KOps/s 234.8056 KOps/s $\color{#35bf28}+1.21\%$
test_items_nested 0.5032ms 0.4109ms 2.4336 KOps/s 2.4310 KOps/s $\color{#35bf28}+0.11\%$
test_items_nested_locked 0.7345ms 0.4094ms 2.4425 KOps/s 2.4323 KOps/s $\color{#35bf28}+0.42\%$
test_items_nested_leaf 0.1468ms 76.7814μs 13.0240 KOps/s 12.9105 KOps/s $\color{#35bf28}+0.88\%$
test_items_stack_nested 0.5677ms 0.4069ms 2.4578 KOps/s 2.4219 KOps/s $\color{#35bf28}+1.48\%$
test_items_stack_nested_leaf 0.1626ms 77.4634μs 12.9093 KOps/s 12.0778 KOps/s $\textbf{\color{#35bf28}+6.88\%}$
test_items_stack_nested_locked 0.5674ms 0.4109ms 2.4335 KOps/s 2.4351 KOps/s $\color{#d91a1a}-0.07\%$
test_keys 28.4730μs 3.5426μs 282.2748 KOps/s 281.2367 KOps/s $\color{#35bf28}+0.37\%$
test_keys_nested 0.2711ms 0.1659ms 6.0266 KOps/s 5.9470 KOps/s $\color{#35bf28}+1.34\%$
test_keys_nested_locked 2.2141ms 0.1717ms 5.8255 KOps/s 5.6931 KOps/s $\color{#35bf28}+2.33\%$
test_keys_nested_leaf 0.2270ms 0.1449ms 6.9012 KOps/s 6.7771 KOps/s $\color{#35bf28}+1.83\%$
test_keys_stack_nested 0.2682ms 0.1661ms 6.0191 KOps/s 6.0481 KOps/s $\color{#d91a1a}-0.48\%$
test_keys_stack_nested_leaf 0.2737ms 0.1455ms 6.8729 KOps/s 6.8895 KOps/s $\color{#d91a1a}-0.24\%$
test_keys_stack_nested_locked 0.2471ms 0.1705ms 5.8646 KOps/s 5.7814 KOps/s $\color{#35bf28}+1.44\%$
test_values 4.7738μs 1.0160μs 984.2103 KOps/s 958.4114 KOps/s $\color{#35bf28}+2.69\%$
test_values_nested 0.1169ms 63.2063μs 15.8212 KOps/s 15.8273 KOps/s $\color{#d91a1a}-0.04\%$
test_values_nested_locked 0.1094ms 62.7294μs 15.9415 KOps/s 15.8331 KOps/s $\color{#35bf28}+0.68\%$
test_values_nested_leaf 0.1477ms 72.5012μs 13.7929 KOps/s 13.4347 KOps/s $\color{#35bf28}+2.67\%$
test_values_stack_nested 0.1156ms 63.5202μs 15.7430 KOps/s 15.5171 KOps/s $\color{#35bf28}+1.46\%$
test_values_stack_nested_leaf 0.1371ms 72.1990μs 13.8506 KOps/s 13.7518 KOps/s $\color{#35bf28}+0.72\%$
test_values_stack_nested_locked 0.1163ms 63.0570μs 15.8587 KOps/s 15.5438 KOps/s $\color{#35bf28}+2.03\%$
test_membership 2.2478μs 0.6876μs 1.4543 MOps/s 1.1379 MOps/s $\textbf{\color{#35bf28}+27.81\%}$
test_membership_nested 32.3110μs 2.8850μs 346.6230 KOps/s 341.0793 KOps/s $\color{#35bf28}+1.63\%$
test_membership_nested_leaf 26.0990μs 2.8713μs 348.2772 KOps/s 340.9552 KOps/s $\color{#35bf28}+2.15\%$
test_membership_stacked_nested 27.3620μs 2.8568μs 350.0459 KOps/s 342.5117 KOps/s $\color{#35bf28}+2.20\%$
test_membership_stacked_nested_leaf 22.1920μs 2.8450μs 351.4906 KOps/s 339.4596 KOps/s $\color{#35bf28}+3.54\%$
test_membership_nested_last 24.4460μs 4.3418μs 230.3174 KOps/s 225.4072 KOps/s $\color{#35bf28}+2.18\%$
test_membership_nested_leaf_last 22.9030μs 4.3376μs 230.5433 KOps/s 225.4072 KOps/s $\color{#35bf28}+2.28\%$
test_membership_stacked_nested_last 31.7300μs 4.2840μs 233.4284 KOps/s 172.9251 KOps/s $\textbf{\color{#35bf28}+34.99\%}$
test_membership_stacked_nested_leaf_last 36.7590μs 4.2627μs 234.5914 KOps/s 172.6428 KOps/s $\textbf{\color{#35bf28}+35.88\%}$
test_nested_getleaf 35.5670μs 10.4136μs 96.0282 KOps/s 93.7088 KOps/s $\color{#35bf28}+2.48\%$
test_nested_get 37.0700μs 9.9874μs 100.1260 KOps/s 100.0084 KOps/s $\color{#35bf28}+0.12\%$
test_stacked_getleaf 42.5800μs 10.4805μs 95.4154 KOps/s 95.4364 KOps/s $\color{#d91a1a}-0.02\%$
test_stacked_get 32.6310μs 9.9394μs 100.6093 KOps/s 99.5495 KOps/s $\color{#35bf28}+1.06\%$
test_nested_getitemleaf 31.2590μs 11.1522μs 89.6682 KOps/s 89.6847 KOps/s $\color{#d91a1a}-0.02\%$
test_nested_getitem 41.3580μs 10.5836μs 94.4861 KOps/s 93.6435 KOps/s $\color{#35bf28}+0.90\%$
test_stacked_getitemleaf 36.3380μs 11.3006μs 88.4913 KOps/s 89.8741 KOps/s $\color{#d91a1a}-1.54\%$
test_stacked_getitem 46.0560μs 10.5823μs 94.4975 KOps/s 95.7777 KOps/s $\color{#d91a1a}-1.34\%$
test_lock_nested 0.6531ms 0.4136ms 2.4178 KOps/s 2.4173 KOps/s $\color{#35bf28}+0.02\%$
test_lock_stack_nested 0.6632ms 0.4243ms 2.3570 KOps/s 2.3577 KOps/s $\color{#d91a1a}-0.03\%$
test_unlock_nested 0.4436ms 0.3407ms 2.9355 KOps/s 2.9713 KOps/s $\color{#d91a1a}-1.20\%$
test_unlock_stack_nested 0.5270ms 0.3456ms 2.8938 KOps/s 2.9332 KOps/s $\color{#d91a1a}-1.34\%$
test_flatten_speed 0.1760ms 0.1011ms 9.8924 KOps/s 9.8317 KOps/s $\color{#35bf28}+0.62\%$
test_unflatten_speed 0.6976ms 0.5221ms 1.9154 KOps/s 1.9174 KOps/s $\color{#d91a1a}-0.11\%$
test_common_ops 5.7846ms 0.8270ms 1.2092 KOps/s 1.2776 KOps/s $\textbf{\color{#d91a1a}-5.36\%}$
test_creation 37.9820μs 2.4506μs 408.0616 KOps/s 401.1264 KOps/s $\color{#35bf28}+1.73\%$
test_creation_empty 49.8440μs 13.1398μs 76.1044 KOps/s 85.4883 KOps/s $\textbf{\color{#d91a1a}-10.98\%}$
test_creation_nested_1 42.7210μs 16.2074μs 61.7004 KOps/s 68.6208 KOps/s $\textbf{\color{#d91a1a}-10.08\%}$
test_creation_nested_2 53.4400μs 20.9419μs 47.7512 KOps/s 52.1380 KOps/s $\textbf{\color{#d91a1a}-8.41\%}$
test_clone 48.6810μs 13.3997μs 74.6288 KOps/s 73.8177 KOps/s $\color{#35bf28}+1.10\%$
test_getitem[int] 1.1204ms 12.9302μs 77.3385 KOps/s 77.5185 KOps/s $\color{#d91a1a}-0.23\%$
test_getitem[slice_int] 0.1263ms 24.9258μs 40.1190 KOps/s 41.4902 KOps/s $\color{#d91a1a}-3.30\%$
test_getitem[range] 0.1554ms 49.9562μs 20.0175 KOps/s 20.5218 KOps/s $\color{#d91a1a}-2.46\%$
test_getitem[tuple] 0.1289ms 20.1238μs 49.6923 KOps/s 48.9849 KOps/s $\color{#35bf28}+1.44\%$
test_getitem[list] 0.1512ms 44.8845μs 22.2794 KOps/s 22.8505 KOps/s $\color{#d91a1a}-2.50\%$
test_setitem_dim[int] 59.8620μs 25.3032μs 39.5207 KOps/s 39.8041 KOps/s $\color{#d91a1a}-0.71\%$
test_setitem_dim[slice_int] 0.1169ms 51.0306μs 19.5961 KOps/s 20.5015 KOps/s $\color{#d91a1a}-4.42\%$
test_setitem_dim[range] 0.1277ms 76.8021μs 13.0205 KOps/s 13.1286 KOps/s $\color{#d91a1a}-0.82\%$
test_setitem_dim[tuple] 65.0830μs 39.9739μs 25.0163 KOps/s 24.2869 KOps/s $\color{#35bf28}+3.00\%$
test_setitem 90.9310μs 20.8970μs 47.8538 KOps/s 49.3869 KOps/s $\color{#d91a1a}-3.10\%$
test_set 71.6750μs 20.3554μs 49.1270 KOps/s 50.6344 KOps/s $\color{#d91a1a}-2.98\%$
test_set_shared 0.3332ms 0.1830ms 5.4642 KOps/s 5.4267 KOps/s $\color{#35bf28}+0.69\%$
test_update 0.1053ms 24.2022μs 41.3185 KOps/s 44.2156 KOps/s $\textbf{\color{#d91a1a}-6.55\%}$
test_update_nested 79.5700μs 34.2504μs 29.1968 KOps/s 30.7512 KOps/s $\textbf{\color{#d91a1a}-5.05\%}$
test_update__nested 0.5473ms 33.0833μs 30.2267 KOps/s 29.4742 KOps/s $\color{#35bf28}+2.55\%$
test_set_nested 63.7600μs 22.5665μs 44.3136 KOps/s 45.5490 KOps/s $\color{#d91a1a}-2.71\%$
test_set_nested_new 72.0950μs 27.1238μs 36.8681 KOps/s 38.1387 KOps/s $\color{#d91a1a}-3.33\%$
test_select 99.9880μs 43.0529μs 23.2273 KOps/s 23.8846 KOps/s $\color{#d91a1a}-2.75\%$
test_select_nested 0.1242ms 62.4400μs 16.0154 KOps/s 15.6689 KOps/s $\color{#35bf28}+2.21\%$
test_exclude_nested 0.1577ms 81.0257μs 12.3418 KOps/s 12.1734 KOps/s $\color{#35bf28}+1.38\%$
test_empty[True] 0.7238ms 0.4074ms 2.4546 KOps/s 2.4305 KOps/s $\color{#35bf28}+0.99\%$
test_empty[False] 8.6185μs 1.3962μs 716.2143 KOps/s 712.4475 KOps/s $\color{#35bf28}+0.53\%$
test_unbind_speed 0.5724ms 0.2730ms 3.6636 KOps/s 3.6635 KOps/s $+0.00\%$
test_unbind_speed_stack0 0.5394ms 0.2733ms 3.6583 KOps/s 3.6703 KOps/s $\color{#d91a1a}-0.33\%$
test_unbind_speed_stack1 0.1255s 0.7580ms 1.3192 KOps/s 1.3156 KOps/s $\color{#35bf28}+0.27\%$
test_split 0.1261s 1.7943ms 557.3334 Ops/s 542.3172 Ops/s $\color{#35bf28}+2.77\%$
test_chunk 0.1233s 1.8138ms 551.3269 Ops/s 539.2777 Ops/s $\color{#35bf28}+2.23\%$
test_consolidate_njt[False-None] 9.9146ms 8.3197ms 120.1972 Ops/s 120.9884 Ops/s $\color{#d91a1a}-0.65\%$
test_creation[device0] 4.4780ms 94.6736μs 10.5626 KOps/s 10.9098 KOps/s $\color{#d91a1a}-3.18\%$
test_creation_from_tensor 0.2146ms 96.7224μs 10.3389 KOps/s 10.3534 KOps/s $\color{#d91a1a}-0.14\%$
test_add_one[memmap_tensor0] 0.1083ms 5.1249μs 195.1268 KOps/s 197.7734 KOps/s $\color{#d91a1a}-1.34\%$
test_contiguous[memmap_tensor0] 18.9260μs 0.5066μs 1.9739 MOps/s 1.8982 MOps/s $\color{#35bf28}+3.99\%$
test_stack[memmap_tensor0] 30.4270μs 3.5601μs 280.8891 KOps/s 300.0856 KOps/s $\textbf{\color{#d91a1a}-6.40\%}$
test_memmaptd_index 1.2372ms 0.2278ms 4.3908 KOps/s 4.3701 KOps/s $\color{#35bf28}+0.47\%$
test_memmaptd_index_astensor 0.5677ms 0.3145ms 3.1798 KOps/s 3.1939 KOps/s $\color{#d91a1a}-0.44\%$
test_memmaptd_index_op 0.8334ms 0.6080ms 1.6448 KOps/s 1.7149 KOps/s $\color{#d91a1a}-4.08\%$
test_serialize_model 0.2495s 0.1403s 7.1266 Ops/s 6.8615 Ops/s $\color{#35bf28}+3.86\%$
test_serialize_model_pickle 0.4450s 0.4074s 2.4548 Ops/s 2.4722 Ops/s $\color{#d91a1a}-0.70\%$
test_serialize_weights 0.1271s 0.1221s 8.1877 Ops/s 8.2505 Ops/s $\color{#d91a1a}-0.76\%$
test_serialize_weights_returnearly 0.1913s 0.1726s 5.7928 Ops/s 5.7886 Ops/s $\color{#35bf28}+0.07\%$
test_serialize_weights_pickle 0.6007s 0.4520s 2.2122 Ops/s 1.1994 Ops/s $\textbf{\color{#35bf28}+84.44\%}$
test_serialize_weights_filesystem 0.1505s 0.1456s 6.8682 Ops/s 6.5927 Ops/s $\color{#35bf28}+4.18\%$
test_serialize_model_filesystem 0.1639s 0.1561s 6.4062 Ops/s 6.6781 Ops/s $\color{#d91a1a}-4.07\%$
test_reshape_pytree 67.5970μs 26.1920μs 38.1796 KOps/s 37.7612 KOps/s $\color{#35bf28}+1.11\%$
test_reshape_td 67.1860μs 33.5614μs 29.7961 KOps/s 29.5661 KOps/s $\color{#35bf28}+0.78\%$
test_view_pytree 78.8880μs 26.1215μs 38.2826 KOps/s 37.9821 KOps/s $\color{#35bf28}+0.79\%$
test_view_td 90.6240μs 38.0213μs 26.3010 KOps/s 25.8082 KOps/s $\color{#35bf28}+1.91\%$
test_unbind_pytree 70.9040μs 29.2730μs 34.1612 KOps/s 34.2315 KOps/s $\color{#d91a1a}-0.21\%$
test_unbind_td 0.4766ms 40.6519μs 24.5991 KOps/s 25.1855 KOps/s $\color{#d91a1a}-2.33\%$
test_split_pytree 88.1360μs 29.4425μs 33.9645 KOps/s 34.3901 KOps/s $\color{#d91a1a}-1.24\%$
test_split_td 0.6016ms 45.1503μs 22.1483 KOps/s 21.5537 KOps/s $\color{#35bf28}+2.76\%$
test_add_pytree 73.8790μs 35.5317μs 28.1439 KOps/s 27.3564 KOps/s $\color{#35bf28}+2.88\%$
test_add_td 0.2015ms 60.4544μs 16.5414 KOps/s 16.6828 KOps/s $\color{#d91a1a}-0.85\%$
test_compile_add_one_nested[tensordict-compile] 0.1638ms 67.4592μs 14.8238 KOps/s 14.7753 KOps/s $\color{#35bf28}+0.33\%$
test_compile_add_one_nested[tensordict-eager] 1.7539ms 0.1741ms 5.7441 KOps/s 5.7878 KOps/s $\color{#d91a1a}-0.75\%$
test_compile_add_one_nested[pytree-compile] 0.1370ms 45.4631μs 21.9959 KOps/s 21.4956 KOps/s $\color{#35bf28}+2.33\%$
test_compile_add_one_nested[pytree-eager] 0.2358ms 0.1178ms 8.4895 KOps/s 8.2786 KOps/s $\color{#35bf28}+2.55\%$
test_compile_copy_nested[tensordict-compile] 56.4760μs 28.7155μs 34.8244 KOps/s 35.5302 KOps/s $\color{#d91a1a}-1.99\%$
test_compile_copy_nested[tensordict-eager] 0.1053ms 57.5125μs 17.3875 KOps/s 17.0947 KOps/s $\color{#35bf28}+1.71\%$
test_compile_copy_nested[pytree-compile] 0.1842ms 80.4865μs 12.4244 KOps/s 12.3276 KOps/s $\color{#35bf28}+0.79\%$
test_compile_copy_nested[pytree-eager] 0.1219ms 65.9826μs 15.1555 KOps/s 14.6836 KOps/s $\color{#35bf28}+3.21\%$
test_compile_add_one_flat[tensordict-compile] 0.1657ms 0.1074ms 9.3121 KOps/s 9.1808 KOps/s $\color{#35bf28}+1.43\%$
test_compile_add_one_flat[tensordict-eager] 0.3388ms 0.2148ms 4.6556 KOps/s 4.5941 KOps/s $\color{#35bf28}+1.34\%$
test_compile_add_one_flat[tensorclass-compile] 89.1080μs 46.4910μs 21.5095 KOps/s 20.7493 KOps/s $\color{#35bf28}+3.66\%$
test_compile_add_one_flat[tensorclass-eager] 0.1426ms 66.1971μs 15.1064 KOps/s 14.7846 KOps/s $\color{#35bf28}+2.18\%$
test_compile_add_one_flat[pytree-compile] 0.1631ms 99.3770μs 10.0627 KOps/s 9.8229 KOps/s $\color{#35bf28}+2.44\%$
test_compile_add_one_flat[pytree-eager] 0.3953ms 0.2012ms 4.9707 KOps/s 4.9055 KOps/s $\color{#35bf28}+1.33\%$
test_compile_add_self_flat[tensordict-eager] 0.3017ms 0.2310ms 4.3295 KOps/s 4.2877 KOps/s $\color{#35bf28}+0.98\%$
test_compile_add_self_flat[tensordict-compile] 0.3603ms 0.1124ms 8.8937 KOps/s 9.0643 KOps/s $\color{#d91a1a}-1.88\%$
test_compile_add_self_flat[tensorclass-eager] 0.1225ms 60.9461μs 16.4080 KOps/s 15.9735 KOps/s $\color{#35bf28}+2.72\%$
test_compile_add_self_flat[tensorclass-compile] 0.1017ms 46.6575μs 21.4328 KOps/s 20.2150 KOps/s $\textbf{\color{#35bf28}+6.02\%}$
test_compile_add_self_flat[pytree-eager] 0.2422ms 0.1561ms 6.4081 KOps/s 6.2373 KOps/s $\color{#35bf28}+2.74\%$
test_compile_add_self_flat[pytree-compile] 0.2266ms 0.1027ms 9.7347 KOps/s 9.9516 KOps/s $\color{#d91a1a}-2.18\%$
test_compile_copy_flat[tensordict-compile] 59.9030μs 20.9667μs 47.6946 KOps/s 44.6942 KOps/s $\textbf{\color{#35bf28}+6.71\%}$
test_compile_copy_flat[tensordict-eager] 0.1519ms 68.2992μs 14.6415 KOps/s 14.5630 KOps/s $\color{#35bf28}+0.54\%$
test_compile_copy_flat[pytree-compile] 0.1653ms 82.1439μs 12.1738 KOps/s 11.9999 KOps/s $\color{#35bf28}+1.45\%$
test_compile_copy_flat[pytree-eager] 0.1295ms 67.8722μs 14.7336 KOps/s 14.7710 KOps/s $\color{#d91a1a}-0.25\%$
test_compile_assign_and_add[tensordict-compile] 0.4356ms 0.2144ms 4.6648 KOps/s 4.6237 KOps/s $\color{#35bf28}+0.89\%$
test_compile_assign_and_add[tensordict-eager] 2.6124ms 1.3889ms 719.9866 Ops/s 709.6561 Ops/s $\color{#35bf28}+1.46\%$
test_compile_assign_and_add[pytree-compile] 0.2924ms 0.2123ms 4.7099 KOps/s 4.7185 KOps/s $\color{#d91a1a}-0.18\%$
test_compile_assign_and_add[pytree-eager] 1.6878ms 0.8506ms 1.1756 KOps/s 1.2002 KOps/s $\color{#d91a1a}-2.05\%$
test_compile_assign_and_add_stack[compile] 0.6427ms 0.4666ms 2.1430 KOps/s 2.1522 KOps/s $\color{#d91a1a}-0.43\%$
test_compile_assign_and_add_stack[eager] 4.3629ms 2.8471ms 351.2371 Ops/s 366.1877 Ops/s $\color{#d91a1a}-4.08\%$
test_compile_indexing[tensor-tensordict-compile] 95.7700μs 36.8056μs 27.1698 KOps/s 25.2520 KOps/s $\textbf{\color{#35bf28}+7.59\%}$
test_compile_indexing[tensor-tensordict-eager] 0.6328ms 32.6688μs 30.6102 KOps/s 30.9894 KOps/s $\color{#d91a1a}-1.22\%$
test_compile_indexing[tensor-tensorclass-compile] 0.1094ms 29.5331μs 33.8603 KOps/s 32.1771 KOps/s $\textbf{\color{#35bf28}+5.23\%}$
test_compile_indexing[tensor-tensorclass-eager] 0.1054ms 22.7763μs 43.9054 KOps/s 44.2368 KOps/s $\color{#d91a1a}-0.75\%$
test_compile_indexing[tensor-pytree-compile] 86.5120μs 30.0724μs 33.2530 KOps/s 31.0036 KOps/s $\textbf{\color{#35bf28}+7.26\%}$
test_compile_indexing[tensor-pytree-eager] 70.5330μs 22.6361μs 44.1773 KOps/s 44.1916 KOps/s $\color{#d91a1a}-0.03\%$
test_compile_indexing[slice-tensordict-compile] 0.1363ms 51.5010μs 19.4171 KOps/s 17.9348 KOps/s $\textbf{\color{#35bf28}+8.27\%}$
test_compile_indexing[slice-tensordict-eager] 0.3851ms 19.6095μs 50.9957 KOps/s 48.7038 KOps/s $\color{#35bf28}+4.71\%$
test_compile_indexing[slice-tensorclass-compile] 0.1093ms 43.7054μs 22.8804 KOps/s 21.3797 KOps/s $\textbf{\color{#35bf28}+7.02\%}$
test_compile_indexing[slice-tensorclass-eager] 91.3580μs 18.4203μs 54.2880 KOps/s 52.6898 KOps/s $\color{#35bf28}+3.03\%$
test_compile_indexing[slice-pytree-compile] 0.1023ms 44.8723μs 22.2855 KOps/s 20.7242 KOps/s $\textbf{\color{#35bf28}+7.53\%}$
test_compile_indexing[slice-pytree-eager] 73.4880μs 18.4594μs 54.1730 KOps/s 52.8174 KOps/s $\color{#35bf28}+2.57\%$
test_compile_indexing[int-tensordict-compile] 0.1369ms 53.3514μs 18.7436 KOps/s 17.4795 KOps/s $\textbf{\color{#35bf28}+7.23\%}$
test_compile_indexing[int-tensordict-eager] 1.0584ms 19.8224μs 50.4481 KOps/s 49.2006 KOps/s $\color{#35bf28}+2.54\%$
test_compile_indexing[int-tensorclass-compile] 0.1156ms 45.2225μs 22.1129 KOps/s 20.6991 KOps/s $\textbf{\color{#35bf28}+6.83\%}$
test_compile_indexing[int-tensorclass-eager] 74.2690μs 18.5929μs 53.7840 KOps/s 53.8680 KOps/s $\color{#d91a1a}-0.16\%$
test_compile_indexing[int-pytree-compile] 0.1268ms 46.0014μs 21.7384 KOps/s 20.9144 KOps/s $\color{#35bf28}+3.94\%$
test_compile_indexing[int-pytree-eager] 55.1240μs 18.4179μs 54.2950 KOps/s 52.8511 KOps/s $\color{#35bf28}+2.73\%$
test_mod_add[eager] 92.1630μs 35.0665μs 28.5172 KOps/s 29.0726 KOps/s $\color{#d91a1a}-1.91\%$
test_mod_add[compile] 0.1279ms 63.3773μs 15.7785 KOps/s 14.8744 KOps/s $\textbf{\color{#35bf28}+6.08\%}$
test_mod_add[compile-overhead] 0.1178ms 63.8115μs 15.6712 KOps/s 14.9212 KOps/s $\textbf{\color{#35bf28}+5.03\%}$
test_mod_wrap[eager] 0.3675ms 0.2209ms 4.5275 KOps/s 4.5392 KOps/s $\color{#d91a1a}-0.26\%$
test_mod_wrap[compile] 1.3687ms 0.2282ms 4.3826 KOps/s 4.3215 KOps/s $\color{#35bf28}+1.41\%$
test_mod_wrap[compile-overhead] 0.3409ms 0.2245ms 4.4534 KOps/s 4.3082 KOps/s $\color{#35bf28}+3.37\%$
test_mod_wrap_and_backward[eager] 15.0941ms 12.6457ms 79.0780 Ops/s 73.3156 Ops/s $\textbf{\color{#35bf28}+7.86\%}$
test_mod_wrap_and_backward[compile] 15.3941ms 12.2651ms 81.5323 Ops/s 78.7070 Ops/s $\color{#35bf28}+3.59\%$
test_mod_wrap_and_backward[compile-overhead] 14.7557ms 12.3266ms 81.1256 Ops/s 78.6663 Ops/s $\color{#35bf28}+3.13\%$
test_seq_add[eager] 0.2131ms 0.1165ms 8.5856 KOps/s 8.5371 KOps/s $\color{#35bf28}+0.57\%$
test_seq_add[compile] 0.1686ms 77.1222μs 12.9664 KOps/s 12.8636 KOps/s $\color{#35bf28}+0.80\%$
test_seq_add[compile-overhead] 0.1484ms 74.9357μs 13.3448 KOps/s 13.3834 KOps/s $\color{#d91a1a}-0.29\%$
test_seq_wrap[eager] 0.8034ms 0.4452ms 2.2464 KOps/s 2.2667 KOps/s $\color{#d91a1a}-0.90\%$
test_seq_wrap[compile] 0.3778ms 0.2425ms 4.1245 KOps/s 4.0744 KOps/s $\color{#35bf28}+1.23\%$
test_seq_wrap[compile-overhead] 0.4749ms 0.2417ms 4.1366 KOps/s 4.0444 KOps/s $\color{#35bf28}+2.28\%$
test_func_call_runtime[False-eager] 0.8724ms 0.5411ms 1.8480 KOps/s 1.8680 KOps/s $\color{#d91a1a}-1.07\%$
test_func_call_runtime[False-compile] 0.5918ms 0.4430ms 2.2572 KOps/s 2.2641 KOps/s $\color{#d91a1a}-0.30\%$
test_func_call_runtime[False-compile-overhead] 0.5602ms 0.4456ms 2.2440 KOps/s 2.2670 KOps/s $\color{#d91a1a}-1.02\%$
test_func_call_runtime[True-eager] 0.9736ms 0.7479ms 1.3370 KOps/s 1.3180 KOps/s $\color{#35bf28}+1.44\%$
test_func_call_runtime[True-compile] 0.8406ms 0.4637ms 2.1566 KOps/s 2.1337 KOps/s $\color{#35bf28}+1.07\%$
test_func_call_runtime[True-compile-overhead] 0.8492ms 0.4755ms 2.1031 KOps/s 2.1458 KOps/s $\color{#d91a1a}-1.99\%$
test_func_call_cm_runtime[False-eager] 0.9655ms 0.5348ms 1.8699 KOps/s 1.8647 KOps/s $\color{#35bf28}+0.28\%$
test_func_call_cm_runtime[False-compile] 0.7242ms 0.4427ms 2.2588 KOps/s 2.2505 KOps/s $\color{#35bf28}+0.37\%$
test_func_call_cm_runtime[False-compile-overhead] 0.6686ms 0.4439ms 2.2527 KOps/s 2.2488 KOps/s $\color{#35bf28}+0.17\%$
test_func_call_cm_runtime[True-eager] 1.3605ms 0.9001ms 1.1110 KOps/s 1.1033 KOps/s $\color{#35bf28}+0.70\%$
test_func_call_cm_runtime[True-compile] 1.1908ms 0.8028ms 1.2457 KOps/s 1.2471 KOps/s $\color{#d91a1a}-0.12\%$
test_func_call_cm_runtime[True-compile-overhead] 0.9272ms 0.8008ms 1.2487 KOps/s 1.2597 KOps/s $\color{#d91a1a}-0.87\%$
test_vmap_func_call_cm_runtime[eager] 2.7333ms 1.9157ms 522.0080 Ops/s 515.2443 Ops/s $\color{#35bf28}+1.31\%$
test_vmap_func_call_cm_runtime[compile] 0.8851ms 0.5523ms 1.8106 KOps/s 1.8326 KOps/s $\color{#d91a1a}-1.20\%$
test_vmap_func_call_cm_runtime[compile-overhead] 0.9505ms 0.5499ms 1.8184 KOps/s 1.8222 KOps/s $\color{#d91a1a}-0.21\%$
test_distributed 0.3025ms 0.1275ms 7.8440 KOps/s 7.7441 KOps/s $\color{#35bf28}+1.29\%$
test_tdmodule 59.0920μs 27.4810μs 36.3888 KOps/s 38.2068 KOps/s $\color{#d91a1a}-4.76\%$
test_tdmodule_dispatch 90.4710μs 49.6297μs 20.1492 KOps/s 20.9467 KOps/s $\color{#d91a1a}-3.81\%$
test_tdseq 61.5960μs 29.7645μs 33.5970 KOps/s 34.8363 KOps/s $\color{#d91a1a}-3.56\%$
test_tdseq_dispatch 0.1352ms 58.3372μs 17.1417 KOps/s 18.7195 KOps/s $\textbf{\color{#d91a1a}-8.43\%}$
test_instantiation_functorch 2.5917ms 1.5031ms 665.2813 Ops/s 662.8615 Ops/s $\color{#35bf28}+0.37\%$
test_exec_functorch 0.2565ms 0.1766ms 5.6624 KOps/s 5.6353 KOps/s $\color{#35bf28}+0.48\%$
test_exec_functional_call 0.4291ms 0.1669ms 5.9923 KOps/s 5.9499 KOps/s $\color{#35bf28}+0.71\%$
test_exec_td_decorator 0.4186ms 0.2273ms 4.4002 KOps/s 4.2619 KOps/s $\color{#35bf28}+3.25\%$
test_vmap_mlp_speed_decorator[True-True] 0.8432ms 0.6553ms 1.5261 KOps/s 1.4743 KOps/s $\color{#35bf28}+3.51\%$
test_vmap_mlp_speed_decorator[True-False] 0.9744ms 0.6567ms 1.5227 KOps/s 1.4983 KOps/s $\color{#35bf28}+1.62\%$
test_vmap_mlp_speed_decorator[False-True] 0.7540ms 0.5235ms 1.9103 KOps/s 1.8563 KOps/s $\color{#35bf28}+2.91\%$
test_vmap_mlp_speed_decorator[False-False] 0.7189ms 0.5233ms 1.9110 KOps/s 1.8594 KOps/s $\color{#35bf28}+2.77\%$
test_to_module_speed[True] 2.4613ms 1.3348ms 749.1974 Ops/s 733.0247 Ops/s $\color{#35bf28}+2.21\%$
test_to_module_speed[False] 1.8320ms 1.2929ms 773.4644 Ops/s 754.6943 Ops/s $\color{#35bf28}+2.49\%$
test_tc_init 0.1111ms 48.6389μs 20.5597 KOps/s 21.6307 KOps/s $\color{#d91a1a}-4.95\%$
test_tc_init_nested 0.1916ms 96.4346μs 10.3697 KOps/s 10.8074 KOps/s $\color{#d91a1a}-4.05\%$
test_tc_first_layer_tensor 15.9200μs 1.5272μs 654.7760 KOps/s 651.0296 KOps/s $\color{#35bf28}+0.58\%$
test_tc_first_layer_nontensor 24.6470μs 4.6668μs 214.2804 KOps/s 209.8080 KOps/s $\color{#35bf28}+2.13\%$
test_tc_second_layer_tensor 38.7440μs 2.7989μs 357.2854 KOps/s 345.3572 KOps/s $\color{#35bf28}+3.45\%$
test_tc_second_layer_nontensor 50.1720μs 6.0497μs 165.2983 KOps/s 166.7856 KOps/s $\color{#d91a1a}-0.89\%$
test_unbind 0.3072s 15.6907ms 63.7322 Ops/s 68.5165 Ops/s $\textbf{\color{#d91a1a}-6.98\%}$
test_full_like 14.4197ms 11.7004ms 85.4671 Ops/s 90.3027 Ops/s $\textbf{\color{#d91a1a}-5.35\%}$
test_zeros_like 7.6664ms 4.0684ms 245.7993 Ops/s 236.9288 Ops/s $\color{#35bf28}+3.74\%$
test_ones_like 5.5254ms 4.2180ms 237.0803 Ops/s 222.3398 Ops/s $\textbf{\color{#35bf28}+6.63\%}$
test_clone 14.4434ms 10.6617ms 93.7934 Ops/s 116.3627 Ops/s $\textbf{\color{#d91a1a}-19.40\%}$
test_squeeze 57.0380μs 12.1871μs 82.0540 KOps/s 79.3038 KOps/s $\color{#35bf28}+3.47\%$
test_unsqueeze 0.1615ms 90.7234μs 11.0225 KOps/s 10.7433 KOps/s $\color{#35bf28}+2.60\%$
test_split 0.5186ms 0.1925ms 5.1953 KOps/s 4.9723 KOps/s $\color{#35bf28}+4.48\%$
test_permute 0.2738ms 0.2014ms 4.9654 KOps/s 4.9546 KOps/s $\color{#35bf28}+0.22\%$
test_stack 39.5592ms 33.9969ms 29.4144 Ops/s 29.3882 Ops/s $\color{#35bf28}+0.09\%$
test_cat 46.8132ms 35.9370ms 27.8265 Ops/s 31.2812 Ops/s $\textbf{\color{#d91a1a}-11.04\%}$

Copy link

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

Total Benchmarks: 229. Improved: $\large\color{#35bf28}50$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_plain_set_nested 0.2025ms 11.7631μs 85.0118 KOps/s 76.5164 KOps/s $\textbf{\color{#35bf28}+11.10\%}$
test_plain_set_stack_nested 34.3000μs 11.9640μs 83.5838 KOps/s 75.4498 KOps/s $\textbf{\color{#35bf28}+10.78\%}$
test_plain_set_nested_inplace 44.3600μs 12.8188μs 78.0101 KOps/s 70.2042 KOps/s $\textbf{\color{#35bf28}+11.12\%}$
test_plain_set_stack_nested_inplace 69.7910μs 12.8719μs 77.6886 KOps/s 70.2842 KOps/s $\textbf{\color{#35bf28}+10.53\%}$
test_items 30.7000μs 2.9232μs 342.0924 KOps/s 340.7743 KOps/s $\color{#35bf28}+0.39\%$
test_items_nested 0.5029ms 0.3803ms 2.6296 KOps/s 2.7023 KOps/s $\color{#d91a1a}-2.69\%$
test_items_nested_locked 0.4530ms 0.3817ms 2.6197 KOps/s 2.7172 KOps/s $\color{#d91a1a}-3.59\%$
test_items_nested_leaf 90.8020μs 59.1672μs 16.9012 KOps/s 17.0708 KOps/s $\color{#d91a1a}-0.99\%$
test_items_stack_nested 0.5143ms 0.3814ms 2.6217 KOps/s 2.7124 KOps/s $\color{#d91a1a}-3.34\%$
test_items_stack_nested_leaf 89.4910μs 58.7487μs 17.0217 KOps/s 17.0575 KOps/s $\color{#d91a1a}-0.21\%$
test_items_stack_nested_locked 0.4496ms 0.3804ms 2.6290 KOps/s 2.7030 KOps/s $\color{#d91a1a}-2.74\%$
test_keys 28.2010μs 3.4931μs 286.2827 KOps/s 289.5137 KOps/s $\color{#d91a1a}-1.12\%$
test_keys_nested 0.2024ms 88.6639μs 11.2785 KOps/s 11.2024 KOps/s $\color{#35bf28}+0.68\%$
test_keys_nested_locked 0.7885ms 94.6641μs 10.5637 KOps/s 10.5506 KOps/s $\color{#35bf28}+0.12\%$
test_keys_nested_leaf 0.1159ms 79.7547μs 12.5384 KOps/s 12.4960 KOps/s $\color{#35bf28}+0.34\%$
test_keys_stack_nested 0.1358ms 88.3093μs 11.3238 KOps/s 11.1607 KOps/s $\color{#35bf28}+1.46\%$
test_keys_stack_nested_leaf 0.1154ms 79.4011μs 12.5943 KOps/s 12.4492 KOps/s $\color{#35bf28}+1.17\%$
test_keys_stack_nested_locked 0.1447ms 95.5239μs 10.4686 KOps/s 10.4396 KOps/s $\color{#35bf28}+0.28\%$
test_values 5.0567μs 0.8514μs 1.1745 MOps/s 1.1674 MOps/s $\color{#35bf28}+0.61\%$
test_values_nested 0.1594ms 37.7360μs 26.4999 KOps/s 26.3154 KOps/s $\color{#35bf28}+0.70\%$
test_values_nested_locked 64.7410μs 39.2749μs 25.4616 KOps/s 25.2265 KOps/s $\color{#35bf28}+0.93\%$
test_values_nested_leaf 0.2360ms 42.1409μs 23.7299 KOps/s 23.4958 KOps/s $\color{#35bf28}+1.00\%$
test_values_stack_nested 0.2251ms 37.5702μs 26.6168 KOps/s 26.1282 KOps/s $\color{#35bf28}+1.87\%$
test_values_stack_nested_leaf 0.2317ms 42.2596μs 23.6632 KOps/s 23.3142 KOps/s $\color{#35bf28}+1.50\%$
test_values_stack_nested_locked 81.3610μs 39.3446μs 25.4164 KOps/s 24.9759 KOps/s $\color{#35bf28}+1.76\%$
test_membership 10.0767μs 0.5022μs 1.9914 MOps/s 1.9771 MOps/s $\color{#35bf28}+0.72\%$
test_membership_nested 34.8310μs 2.0866μs 479.2599 KOps/s 484.8121 KOps/s $\color{#d91a1a}-1.15\%$
test_membership_nested_leaf 13.9250μs 2.0239μs 494.1042 KOps/s 477.3825 KOps/s $\color{#35bf28}+3.50\%$
test_membership_stacked_nested 34.3400μs 2.1353μs 468.3196 KOps/s 474.4567 KOps/s $\color{#d91a1a}-1.29\%$
test_membership_stacked_nested_leaf 44.1310μs 2.0967μs 476.9383 KOps/s 470.3627 KOps/s $\color{#35bf28}+1.40\%$
test_membership_nested_last 34.2510μs 3.1262μs 319.8725 KOps/s 316.0795 KOps/s $\color{#35bf28}+1.20\%$
test_membership_nested_leaf_last 27.6300μs 3.1330μs 319.1808 KOps/s 313.9993 KOps/s $\color{#35bf28}+1.65\%$
test_membership_stacked_nested_last 69.6310μs 3.1259μs 319.9031 KOps/s 318.2817 KOps/s $\color{#35bf28}+0.51\%$
test_membership_stacked_nested_leaf_last 0.1453ms 3.1006μs 322.5214 KOps/s 318.9730 KOps/s $\color{#35bf28}+1.11\%$
test_nested_getleaf 40.6110μs 6.2045μs 161.1729 KOps/s 161.6759 KOps/s $\color{#d91a1a}-0.31\%$
test_nested_get 32.9910μs 5.9382μs 168.4018 KOps/s 170.4635 KOps/s $\color{#d91a1a}-1.21\%$
test_stacked_getleaf 40.9900μs 6.2505μs 159.9884 KOps/s 159.9400 KOps/s $\color{#35bf28}+0.03\%$
test_stacked_get 56.8610μs 5.9300μs 168.6341 KOps/s 168.4627 KOps/s $\color{#35bf28}+0.10\%$
test_nested_getitemleaf 38.0110μs 6.6365μs 150.6829 KOps/s 151.3346 KOps/s $\color{#d91a1a}-0.43\%$
test_nested_getitem 35.8910μs 6.2214μs 160.7361 KOps/s 161.4392 KOps/s $\color{#d91a1a}-0.44\%$
test_stacked_getitemleaf 36.0210μs 6.4311μs 155.4952 KOps/s 153.4586 KOps/s $\color{#35bf28}+1.33\%$
test_stacked_getitem 31.3100μs 6.1270μs 163.2132 KOps/s 161.1615 KOps/s $\color{#35bf28}+1.27\%$
test_lock_nested 9.0050ms 0.3477ms 2.8763 KOps/s 2.8025 KOps/s $\color{#35bf28}+2.63\%$
test_lock_stack_nested 0.4139ms 0.3440ms 2.9072 KOps/s 2.8342 KOps/s $\color{#35bf28}+2.58\%$
test_unlock_nested 0.4122ms 0.2821ms 3.5454 KOps/s 3.4461 KOps/s $\color{#35bf28}+2.88\%$
test_unlock_stack_nested 0.4309ms 0.2797ms 3.5749 KOps/s 3.4442 KOps/s $\color{#35bf28}+3.79\%$
test_flatten_speed 98.4920μs 75.9383μs 13.1686 KOps/s 12.9366 KOps/s $\color{#35bf28}+1.79\%$
test_unflatten_speed 0.5230ms 0.3256ms 3.0716 KOps/s 3.0188 KOps/s $\color{#35bf28}+1.75\%$
test_common_ops 0.8363ms 0.6133ms 1.6306 KOps/s 1.4980 KOps/s $\textbf{\color{#35bf28}+8.85\%}$
test_creation 85.2110μs 1.7729μs 564.0516 KOps/s 566.5516 KOps/s $\color{#d91a1a}-0.44\%$
test_creation_empty 29.8400μs 7.3880μs 135.3546 KOps/s 101.8340 KOps/s $\textbf{\color{#35bf28}+32.92\%}$
test_creation_nested_1 51.1610μs 9.1483μs 109.3100 KOps/s 86.5160 KOps/s $\textbf{\color{#35bf28}+26.35\%}$
test_creation_nested_2 39.3910μs 11.9039μs 84.0061 KOps/s 69.4563 KOps/s $\textbf{\color{#35bf28}+20.95\%}$
test_clone 55.7110μs 10.6534μs 93.8665 KOps/s 86.7530 KOps/s $\textbf{\color{#35bf28}+8.20\%}$
test_getitem[int] 1.2977ms 10.7554μs 92.9764 KOps/s 88.8491 KOps/s $\color{#35bf28}+4.65\%$
test_getitem[slice_int] 0.1073ms 21.0540μs 47.4970 KOps/s 45.4354 KOps/s $\color{#35bf28}+4.54\%$
test_getitem[range] 0.2150ms 38.2768μs 26.1255 KOps/s 25.2081 KOps/s $\color{#35bf28}+3.64\%$
test_getitem[tuple] 0.1586ms 18.4048μs 54.3336 KOps/s 52.0462 KOps/s $\color{#35bf28}+4.40\%$
test_getitem[list] 0.1556ms 33.7935μs 29.5915 KOps/s 28.1279 KOps/s $\textbf{\color{#35bf28}+5.20\%}$
test_setitem_dim[int] 43.5410μs 19.9760μs 50.0600 KOps/s 46.5204 KOps/s $\textbf{\color{#35bf28}+7.61\%}$
test_setitem_dim[slice_int] 61.7210μs 39.8390μs 25.1010 KOps/s 24.6016 KOps/s $\color{#35bf28}+2.03\%$
test_setitem_dim[range] 78.0110μs 54.6430μs 18.3006 KOps/s 17.7719 KOps/s $\color{#35bf28}+2.97\%$
test_setitem_dim[tuple] 81.7310μs 32.8300μs 30.4599 KOps/s 29.1433 KOps/s $\color{#35bf28}+4.52\%$
test_setitem 0.1329ms 15.1837μs 65.8603 KOps/s 58.8012 KOps/s $\textbf{\color{#35bf28}+12.01\%}$
test_set 0.1018ms 14.6841μs 68.1011 KOps/s 59.7663 KOps/s $\textbf{\color{#35bf28}+13.95\%}$
test_set_shared 0.5183ms 0.1604ms 6.2351 KOps/s 6.1938 KOps/s $\color{#35bf28}+0.67\%$
test_update 0.4230ms 16.7616μs 59.6602 KOps/s 49.2193 KOps/s $\textbf{\color{#35bf28}+21.21\%}$
test_update_nested 0.1179ms 22.6684μs 44.1142 KOps/s 38.0209 KOps/s $\textbf{\color{#35bf28}+16.03\%}$
test_update__nested 0.5103ms 26.0930μs 38.3244 KOps/s 37.2269 KOps/s $\color{#35bf28}+2.95\%$
test_set_nested 52.7010μs 15.9446μs 62.7170 KOps/s 55.4049 KOps/s $\textbf{\color{#35bf28}+13.20\%}$
test_set_nested_new 59.4910μs 18.2553μs 54.7786 KOps/s 49.1448 KOps/s $\textbf{\color{#35bf28}+11.46\%}$
test_select 0.1620ms 30.7154μs 32.5570 KOps/s 31.3827 KOps/s $\color{#35bf28}+3.74\%$
test_select_nested 0.1355ms 44.9268μs 22.2584 KOps/s 22.4298 KOps/s $\color{#d91a1a}-0.76\%$
test_exclude_nested 0.1045ms 65.1544μs 15.3482 KOps/s 15.6268 KOps/s $\color{#d91a1a}-1.78\%$
test_empty[True] 0.3636ms 0.3034ms 3.2958 KOps/s 3.3856 KOps/s $\color{#d91a1a}-2.65\%$
test_empty[False] 3.6520μs 0.8380μs 1.1933 MOps/s 1.2005 MOps/s $\color{#d91a1a}-0.60\%$
test_to 95.7310μs 57.7293μs 17.3222 KOps/s 17.6236 KOps/s $\color{#d91a1a}-1.71\%$
test_to_nonblocking 0.2101ms 47.8234μs 20.9103 KOps/s 20.6132 KOps/s $\color{#35bf28}+1.44\%$
test_unbind_speed 0.3991ms 0.2397ms 4.1724 KOps/s 4.0416 KOps/s $\color{#35bf28}+3.24\%$
test_unbind_speed_stack0 0.3167ms 0.2374ms 4.2120 KOps/s 4.0634 KOps/s $\color{#35bf28}+3.66\%$
test_unbind_speed_stack1 93.7684ms 0.7406ms 1.3503 KOps/s 1.3371 KOps/s $\color{#35bf28}+0.98\%$
test_split 95.0709ms 1.5975ms 625.9828 Ops/s 602.2711 Ops/s $\color{#35bf28}+3.94\%$
test_chunk 96.6371ms 1.6071ms 622.2288 Ops/s 611.5082 Ops/s $\color{#35bf28}+1.75\%$
test_consolidate[False-None] 97.1860ms 2.9946ms 333.9344 Ops/s 363.2108 Ops/s $\textbf{\color{#d91a1a}-8.06\%}$
test_consolidate[default-None] 1.9394ms 1.7203ms 581.3078 Ops/s 570.0188 Ops/s $\color{#35bf28}+1.98\%$
test_consolidate[reduce-overhead-None] 2.0259ms 1.7687ms 565.3906 Ops/s 552.7475 Ops/s $\color{#35bf28}+2.29\%$
test_consolidate_njt[False-None] 7.0347ms 6.6166ms 151.1348 Ops/s 149.5414 Ops/s $\color{#35bf28}+1.07\%$
test_to[False-False-None] 2.0280ms 1.7266ms 579.1707 Ops/s 564.7705 Ops/s $\color{#35bf28}+2.55\%$
test_to[True-False-None] 1.6058ms 1.3805ms 724.3683 Ops/s 705.9302 Ops/s $\color{#35bf28}+2.61\%$
test_to[within-False-None] 4.4841ms 4.2263ms 236.6120 Ops/s 231.7497 Ops/s $\color{#35bf28}+2.10\%$
test_to[True-default-None] 5.7141ms 5.3757ms 186.0226 Ops/s 173.2164 Ops/s $\textbf{\color{#35bf28}+7.39\%}$
test_to_njt[False-False-None] 7.3587ms 7.0002ms 142.8524 Ops/s 133.4900 Ops/s $\textbf{\color{#35bf28}+7.01\%}$
test_to_njt[True-False-None] 6.0660ms 5.6640ms 176.5535 Ops/s 163.7970 Ops/s $\textbf{\color{#35bf28}+7.79\%}$
test_to_njt[within-False-None] 12.6382ms 12.3263ms 81.1272 Ops/s 73.8366 Ops/s $\textbf{\color{#35bf28}+9.87\%}$
test_creation[device0] 0.4638ms 82.6624μs 12.0974 KOps/s 11.8339 KOps/s $\color{#35bf28}+2.23\%$
test_creation_from_tensor 0.4574ms 85.4418μs 11.7039 KOps/s 11.6826 KOps/s $\color{#35bf28}+0.18\%$
test_add_one[memmap_tensor0] 0.2330ms 6.9349μs 144.1973 KOps/s 137.1265 KOps/s $\textbf{\color{#35bf28}+5.16\%}$
test_contiguous[memmap_tensor0] 1.8990μs 0.4254μs 2.3509 MOps/s 2.3636 MOps/s $\color{#d91a1a}-0.54\%$
test_stack[memmap_tensor0] 26.5000μs 4.3924μs 227.6643 KOps/s 219.9112 KOps/s $\color{#35bf28}+3.53\%$
test_memmaptd_index 1.7746ms 0.2459ms 4.0670 KOps/s 3.9226 KOps/s $\color{#35bf28}+3.68\%$
test_memmaptd_index_astensor 0.4505ms 0.3066ms 3.2612 KOps/s 2.9807 KOps/s $\textbf{\color{#35bf28}+9.41\%}$
test_memmaptd_index_op 0.7619ms 0.5708ms 1.7519 KOps/s 1.5794 KOps/s $\textbf{\color{#35bf28}+10.93\%}$
test_serialize_model 0.1313s 0.1302s 7.6779 Ops/s 7.6269 Ops/s $\color{#35bf28}+0.67\%$
test_serialize_model_pickle 1.3526s 1.2135s 0.8241 Ops/s 0.8248 Ops/s $\color{#d91a1a}-0.09\%$
test_serialize_weights 0.4084s 0.1691s 5.9142 Ops/s 7.6931 Ops/s $\textbf{\color{#d91a1a}-23.12\%}$
test_serialize_weights_returnearly 0.3359s 55.9273ms 17.8804 Ops/s 22.8434 Ops/s $\textbf{\color{#d91a1a}-21.73\%}$
test_serialize_weights_pickle 1.3748s 1.2186s 0.8206 Ops/s 0.8213 Ops/s $\color{#d91a1a}-0.08\%$
test_reshape_pytree 72.4210μs 22.0891μs 45.2713 KOps/s 42.9875 KOps/s $\textbf{\color{#35bf28}+5.31\%}$
test_reshape_td 0.1435ms 26.8712μs 37.2145 KOps/s 32.1782 KOps/s $\textbf{\color{#35bf28}+15.65\%}$
test_view_pytree 0.1494ms 22.0009μs 45.4528 KOps/s 42.4116 KOps/s $\textbf{\color{#35bf28}+7.17\%}$
test_view_td 0.2274ms 31.2282μs 32.0224 KOps/s 27.0679 KOps/s $\textbf{\color{#35bf28}+18.30\%}$
test_unbind_pytree 0.2244ms 28.1180μs 35.5644 KOps/s 34.5726 KOps/s $\color{#35bf28}+2.87\%$
test_unbind_td 0.8190ms 37.4827μs 26.6789 KOps/s 25.1623 KOps/s $\textbf{\color{#35bf28}+6.03\%}$
test_split_pytree 0.1487ms 29.5101μs 33.8867 KOps/s 29.4456 KOps/s $\textbf{\color{#35bf28}+15.08\%}$
test_split_td 0.9869ms 38.4026μs 26.0399 KOps/s 23.5432 KOps/s $\textbf{\color{#35bf28}+10.60\%}$
test_add_pytree 0.2218ms 35.2939μs 28.3335 KOps/s 25.9894 KOps/s $\textbf{\color{#35bf28}+9.02\%}$
test_add_td 0.1844ms 47.0318μs 21.2622 KOps/s 17.3949 KOps/s $\textbf{\color{#35bf28}+22.23\%}$
test_compile_add_one_nested[tensordict-compile] 0.2683ms 0.1228ms 8.1460 KOps/s 7.4185 KOps/s $\textbf{\color{#35bf28}+9.81\%}$
test_compile_add_one_nested[tensordict-eager] 0.2781ms 0.1352ms 7.3986 KOps/s 7.3799 KOps/s $\color{#35bf28}+0.25\%$
test_compile_add_one_nested[pytree-compile] 0.2400ms 96.1524μs 10.4002 KOps/s 10.0744 KOps/s $\color{#35bf28}+3.23\%$
test_compile_add_one_nested[pytree-eager] 1.7974ms 0.1501ms 6.6619 KOps/s 6.5135 KOps/s $\color{#35bf28}+2.28\%$
test_compile_copy_nested[tensordict-compile] 0.1609ms 24.9928μs 40.0115 KOps/s 40.9436 KOps/s $\color{#d91a1a}-2.28\%$
test_compile_copy_nested[tensordict-eager] 0.1553ms 29.6111μs 33.7711 KOps/s 33.3065 KOps/s $\color{#35bf28}+1.39\%$
test_compile_copy_nested[pytree-compile] 0.1887ms 64.7451μs 15.4452 KOps/s 15.3134 KOps/s $\color{#35bf28}+0.86\%$
test_compile_copy_nested[pytree-eager] 0.1589ms 49.1057μs 20.3642 KOps/s 20.0815 KOps/s $\color{#35bf28}+1.41\%$
test_compile_add_one_flat[tensordict-compile] 0.2780ms 0.1419ms 7.0463 KOps/s 7.0401 KOps/s $\color{#35bf28}+0.09\%$
test_compile_add_one_flat[tensordict-eager] 0.3677ms 0.2212ms 4.5208 KOps/s 4.5621 KOps/s $\color{#d91a1a}-0.91\%$
test_compile_add_one_flat[tensorclass-compile] 0.3010ms 99.6999μs 10.0301 KOps/s 10.1640 KOps/s $\color{#d91a1a}-1.32\%$
test_compile_add_one_flat[tensorclass-eager] 0.2023ms 56.4217μs 17.7237 KOps/s 17.0890 KOps/s $\color{#35bf28}+3.71\%$
test_compile_add_one_flat[pytree-compile] 0.2638ms 0.1350ms 7.4080 KOps/s 7.2816 KOps/s $\color{#35bf28}+1.73\%$
test_compile_add_one_flat[pytree-eager] 0.6614ms 0.4777ms 2.0932 KOps/s 2.0133 KOps/s $\color{#35bf28}+3.97\%$
test_compile_add_self_flat[tensordict-eager] 0.4152ms 0.2635ms 3.7946 KOps/s 3.7939 KOps/s $\color{#35bf28}+0.02\%$
test_compile_add_self_flat[tensordict-compile] 0.2666ms 0.1439ms 6.9475 KOps/s 6.8724 KOps/s $\color{#35bf28}+1.09\%$
test_compile_add_self_flat[tensorclass-eager] 0.2616ms 68.6130μs 14.5745 KOps/s 13.9033 KOps/s $\color{#35bf28}+4.83\%$
test_compile_add_self_flat[tensorclass-compile] 0.3000ms 98.3276μs 10.1701 KOps/s 9.9746 KOps/s $\color{#35bf28}+1.96\%$
test_compile_add_self_flat[pytree-eager] 0.5838ms 0.4008ms 2.4951 KOps/s 2.4174 KOps/s $\color{#35bf28}+3.21\%$
test_compile_add_self_flat[pytree-compile] 0.2755ms 0.1344ms 7.4414 KOps/s 6.9329 KOps/s $\textbf{\color{#35bf28}+7.33\%}$
test_compile_copy_flat[tensordict-compile] 0.1515ms 19.0911μs 52.3803 KOps/s 50.5182 KOps/s $\color{#35bf28}+3.69\%$
test_compile_copy_flat[tensordict-eager] 61.0510μs 31.8018μs 31.4448 KOps/s 31.0067 KOps/s $\color{#35bf28}+1.41\%$
test_compile_copy_flat[pytree-compile] 0.1810ms 70.8666μs 14.1110 KOps/s 14.2354 KOps/s $\color{#d91a1a}-0.87\%$
test_compile_copy_flat[pytree-eager] 80.5210μs 51.8201μs 19.2975 KOps/s 19.3338 KOps/s $\color{#d91a1a}-0.19\%$
test_compile_assign_and_add[tensordict-compile] 1.7947ms 0.4172ms 2.3971 KOps/s 2.2183 KOps/s $\textbf{\color{#35bf28}+8.06\%}$
test_compile_assign_and_add[tensordict-eager] 3.0217ms 2.6563ms 376.4681 Ops/s 365.6573 Ops/s $\color{#35bf28}+2.96\%$
test_compile_assign_and_add[pytree-compile] 1.6236ms 0.3935ms 2.5413 KOps/s 2.2030 KOps/s $\textbf{\color{#35bf28}+15.36\%}$
test_compile_assign_and_add[pytree-eager] 2.9157ms 2.6419ms 378.5133 Ops/s 369.7289 Ops/s $\color{#35bf28}+2.38\%$
test_compile_indexing[tensor-tensordict-compile] 0.6068ms 0.1187ms 8.4228 KOps/s 8.2242 KOps/s $\color{#35bf28}+2.42\%$
test_compile_indexing[tensor-tensordict-eager] 0.5645ms 81.0686μs 12.3352 KOps/s 12.2920 KOps/s $\color{#35bf28}+0.35\%$
test_compile_indexing[tensor-tensorclass-compile] 0.5114ms 0.1067ms 9.3703 KOps/s 9.3553 KOps/s $\color{#35bf28}+0.16\%$
test_compile_indexing[tensor-tensorclass-eager] 0.2647ms 67.3857μs 14.8399 KOps/s 14.3498 KOps/s $\color{#35bf28}+3.42\%$
test_compile_indexing[tensor-pytree-compile] 0.2586ms 0.1071ms 9.3347 KOps/s 9.2876 KOps/s $\color{#35bf28}+0.51\%$
test_compile_indexing[tensor-pytree-eager] 0.2192ms 67.5588μs 14.8019 KOps/s 14.3824 KOps/s $\color{#35bf28}+2.92\%$
test_compile_indexing[slice-tensordict-compile] 0.2525ms 0.1002ms 9.9808 KOps/s 9.7668 KOps/s $\color{#35bf28}+2.19\%$
test_compile_indexing[slice-tensordict-eager] 0.1386ms 17.4926μs 57.1670 KOps/s 54.1399 KOps/s $\textbf{\color{#35bf28}+5.59\%}$
test_compile_indexing[slice-tensorclass-compile] 0.2406ms 96.4624μs 10.3667 KOps/s 10.2013 KOps/s $\color{#35bf28}+1.62\%$
test_compile_indexing[slice-tensorclass-eager] 0.1245ms 16.1630μs 61.8696 KOps/s 60.6079 KOps/s $\color{#35bf28}+2.08\%$
test_compile_indexing[slice-pytree-compile] 0.2424ms 96.4921μs 10.3635 KOps/s 10.1825 KOps/s $\color{#35bf28}+1.78\%$
test_compile_indexing[slice-pytree-eager] 99.7020μs 16.0934μs 62.1372 KOps/s 61.6131 KOps/s $\color{#35bf28}+0.85\%$
test_compile_indexing[int-tensordict-compile] 0.2520ms 0.1015ms 9.8543 KOps/s 9.7303 KOps/s $\color{#35bf28}+1.27\%$
test_compile_indexing[int-tensordict-eager] 0.5976ms 17.4655μs 57.2558 KOps/s 54.6987 KOps/s $\color{#35bf28}+4.67\%$
test_compile_indexing[int-tensorclass-compile] 0.5051ms 97.0826μs 10.3005 KOps/s 10.1463 KOps/s $\color{#35bf28}+1.52\%$
test_compile_indexing[int-tensorclass-eager] 0.4088ms 16.1858μs 61.7826 KOps/s 61.1610 KOps/s $\color{#35bf28}+1.02\%$
test_compile_indexing[int-pytree-compile] 0.5071ms 97.0448μs 10.3045 KOps/s 10.0838 KOps/s $\color{#35bf28}+2.19\%$
test_compile_indexing[int-pytree-eager] 0.4089ms 18.4235μs 54.2785 KOps/s 61.5039 KOps/s $\textbf{\color{#d91a1a}-11.75\%}$
test_mod_add[eager] 0.4509ms 38.0316μs 26.2939 KOps/s 24.8985 KOps/s $\textbf{\color{#35bf28}+5.60\%}$
test_mod_add[compile] 0.3457ms 85.0074μs 11.7637 KOps/s 11.9152 KOps/s $\color{#d91a1a}-1.27\%$
test_mod_add[compile-overhead] 0.3202ms 0.1644ms 6.0836 KOps/s 5.5388 KOps/s $\textbf{\color{#35bf28}+9.84\%}$
test_mod_wrap[eager] 0.4473ms 0.2554ms 3.9156 KOps/s 3.8293 KOps/s $\color{#35bf28}+2.25\%$
test_mod_wrap[compile] 0.4666ms 0.3019ms 3.3123 KOps/s 3.3900 KOps/s $\color{#d91a1a}-2.29\%$
test_mod_wrap[compile-overhead] 7.1064ms 3.7611ms 265.8783 Ops/s 274.5140 Ops/s $\color{#d91a1a}-3.15\%$
test_mod_wrap_and_backward[eager] 1.6328ms 1.3879ms 720.5165 Ops/s 672.6422 Ops/s $\textbf{\color{#35bf28}+7.12\%}$
test_mod_wrap_and_backward[compile] 1.4961ms 1.2903ms 774.9919 Ops/s 709.8042 Ops/s $\textbf{\color{#35bf28}+9.18\%}$
test_mod_wrap_and_backward[compile-overhead] 1.3894ms 0.9327ms 1.0722 KOps/s 952.0123 Ops/s $\textbf{\color{#35bf28}+12.62\%}$
test_seq_add[eager] 0.2698ms 0.1152ms 8.6791 KOps/s 8.0118 KOps/s $\textbf{\color{#35bf28}+8.33\%}$
test_seq_add[compile] 0.2429ms 88.7779μs 11.2641 KOps/s 10.9913 KOps/s $\color{#35bf28}+2.48\%$
test_seq_add[compile-overhead] 0.2809ms 0.1290ms 7.7503 KOps/s 7.5941 KOps/s $\color{#35bf28}+2.06\%$
test_seq_wrap[eager] 0.6308ms 0.4267ms 2.3434 KOps/s 2.2641 KOps/s $\color{#35bf28}+3.50\%$
test_seq_wrap[compile] 0.4753ms 0.3081ms 3.2455 KOps/s 3.1998 KOps/s $\color{#35bf28}+1.43\%$
test_seq_wrap[compile-overhead] 0.4171ms 0.2285ms 4.3760 KOps/s 4.3769 KOps/s $\color{#d91a1a}-0.02\%$
test_func_call_runtime[False-eager] 0.9917ms 0.7719ms 1.2954 KOps/s 1.3031 KOps/s $\color{#d91a1a}-0.59\%$
test_func_call_runtime[False-compile] 0.9065ms 0.7510ms 1.3316 KOps/s 1.2984 KOps/s $\color{#35bf28}+2.56\%$
test_func_call_runtime[False-compile-overhead] 0.5118ms 0.3692ms 2.7088 KOps/s 2.7158 KOps/s $\color{#d91a1a}-0.26\%$
test_func_call_runtime[True-eager] 1.0849ms 0.9039ms 1.1064 KOps/s 1.0683 KOps/s $\color{#35bf28}+3.56\%$
test_func_call_runtime[True-compile] 0.9812ms 0.7861ms 1.2721 KOps/s 1.2613 KOps/s $\color{#35bf28}+0.86\%$
test_func_call_runtime[True-compile-overhead] 0.5870ms 0.3898ms 2.5655 KOps/s 2.5645 KOps/s $\color{#35bf28}+0.04\%$
test_func_call_cm_runtime[False-eager] 0.9862ms 0.7826ms 1.2778 KOps/s 1.3077 KOps/s $\color{#d91a1a}-2.29\%$
test_func_call_cm_runtime[False-compile] 0.9837ms 0.7825ms 1.2779 KOps/s 1.2574 KOps/s $\color{#35bf28}+1.64\%$
test_func_call_cm_runtime[False-compile-overhead] 0.5274ms 0.3748ms 2.6682 KOps/s 2.6832 KOps/s $\color{#d91a1a}-0.56\%$
test_func_call_cm_runtime[True-eager] 1.2727ms 1.0203ms 980.1441 Ops/s 944.6622 Ops/s $\color{#35bf28}+3.76\%$
test_func_call_cm_runtime[True-compile] 1.2691ms 0.9978ms 1.0022 KOps/s 975.2865 Ops/s $\color{#35bf28}+2.76\%$
test_func_call_cm_runtime[True-compile-overhead] 1.1717ms 0.9996ms 1.0004 KOps/s 930.4723 Ops/s $\textbf{\color{#35bf28}+7.51\%}$
test_vmap_func_call_cm_runtime[eager] 2.5813ms 2.1230ms 471.0405 Ops/s 462.0476 Ops/s $\color{#35bf28}+1.95\%$
test_vmap_func_call_cm_runtime[compile] 1.0530ms 0.8232ms 1.2148 KOps/s 1.1707 KOps/s $\color{#35bf28}+3.77\%$
test_vmap_func_call_cm_runtime[compile-overhead] 0.6083ms 0.4201ms 2.3802 KOps/s 2.3606 KOps/s $\color{#35bf28}+0.83\%$
test_distributed 5.4565ms 0.1794ms 5.5746 KOps/s 8.5703 KOps/s $\textbf{\color{#d91a1a}-34.95\%}$
test_tdmodule 31.5010μs 19.6413μs 50.9131 KOps/s 45.1128 KOps/s $\textbf{\color{#35bf28}+12.86\%}$
test_tdmodule_dispatch 77.3610μs 35.1785μs 28.4265 KOps/s 26.1903 KOps/s $\textbf{\color{#35bf28}+8.54\%}$
test_tdseq 0.1656ms 20.8037μs 48.0683 KOps/s 45.9449 KOps/s $\color{#35bf28}+4.62\%$
test_tdseq_dispatch 59.8210μs 37.6990μs 26.5259 KOps/s 24.5810 KOps/s $\textbf{\color{#35bf28}+7.91\%}$
test_instantiation_functorch 1.8815ms 1.5891ms 629.2720 Ops/s 623.2841 Ops/s $\color{#35bf28}+0.96\%$
test_exec_functorch 0.3432ms 0.1467ms 6.8146 KOps/s 6.6762 KOps/s $\color{#35bf28}+2.07\%$
test_exec_functional_call 0.2878ms 0.1392ms 7.1865 KOps/s 6.9738 KOps/s $\color{#35bf28}+3.05\%$
test_exec_td_decorator 0.3937ms 0.1876ms 5.3301 KOps/s 5.1269 KOps/s $\color{#35bf28}+3.96\%$
test_vmap_mlp_speed_decorator[True-True] 0.8492ms 0.6895ms 1.4503 KOps/s 1.3898 KOps/s $\color{#35bf28}+4.36\%$
test_vmap_mlp_speed_decorator[True-False] 0.8456ms 0.6878ms 1.4539 KOps/s 1.4020 KOps/s $\color{#35bf28}+3.70\%$
test_vmap_mlp_speed_decorator[False-True] 0.7893ms 0.6033ms 1.6576 KOps/s 1.6126 KOps/s $\color{#35bf28}+2.79\%$
test_vmap_mlp_speed_decorator[False-False] 0.8010ms 0.6163ms 1.6227 KOps/s 1.6192 KOps/s $\color{#35bf28}+0.21\%$
test_vmap_transformer_speed_decorator[True-True] 20.5312ms 19.5540ms 51.1403 Ops/s 50.6251 Ops/s $\color{#35bf28}+1.02\%$
test_vmap_transformer_speed_decorator[True-False] 20.0038ms 19.5156ms 51.2410 Ops/s 50.5777 Ops/s $\color{#35bf28}+1.31\%$
test_vmap_transformer_speed_decorator[False-True] 20.5086ms 19.4690ms 51.3637 Ops/s 51.2495 Ops/s $\color{#35bf28}+0.22\%$
test_vmap_transformer_speed_decorator[False-False] 19.6518ms 19.3053ms 51.7993 Ops/s 51.3001 Ops/s $\color{#35bf28}+0.97\%$
test_to_module_speed[True] 1.4402ms 0.9656ms 1.0357 KOps/s 1.0240 KOps/s $\color{#35bf28}+1.14\%$
test_to_module_speed[False] 1.0414ms 0.9544ms 1.0478 KOps/s 1.0395 KOps/s $\color{#35bf28}+0.80\%$
test_tc_init 0.1669ms 35.1647μs 28.4376 KOps/s 26.8260 KOps/s $\textbf{\color{#35bf28}+6.01\%}$
test_tc_init_nested 0.1936ms 72.2466μs 13.8415 KOps/s 13.6279 KOps/s $\color{#35bf28}+1.57\%$
test_tc_first_layer_tensor 4.4844μs 0.6995μs 1.4295 MOps/s 1.4330 MOps/s $\color{#d91a1a}-0.24\%$
test_tc_first_layer_nontensor 33.6800μs 2.2917μs 436.3589 KOps/s 444.0048 KOps/s $\color{#d91a1a}-1.72\%$
test_tc_second_layer_tensor 8.6152μs 1.3981μs 715.2589 KOps/s 709.7961 KOps/s $\color{#35bf28}+0.77\%$
test_tc_second_layer_nontensor 28.1600μs 3.0453μs 328.3719 KOps/s 337.2764 KOps/s $\color{#d91a1a}-2.64\%$
test_unbind 7.3806ms 7.0767ms 141.3098 Ops/s 142.3378 Ops/s $\color{#d91a1a}-0.72\%$
test_full_like 13.2256ms 9.3360ms 107.1117 Ops/s 103.2216 Ops/s $\color{#35bf28}+3.77\%$
test_zeros_like 6.0294ms 4.2792ms 233.6904 Ops/s 115.0534 Ops/s $\textbf{\color{#35bf28}+103.11\%}$
test_ones_like 4.7293ms 4.2847ms 233.3887 Ops/s 229.1815 Ops/s $\color{#35bf28}+1.84\%$
test_clone 12.0113ms 9.3294ms 107.1886 Ops/s 152.0920 Ops/s $\textbf{\color{#d91a1a}-29.52\%}$
test_squeeze 96.7710μs 9.6214μs 103.9350 KOps/s 99.0609 KOps/s $\color{#35bf28}+4.92\%$
test_unsqueeze 0.1916ms 73.8453μs 13.5418 KOps/s 13.0732 KOps/s $\color{#35bf28}+3.58\%$
test_split 0.3713ms 0.1631ms 6.1323 KOps/s 5.9581 KOps/s $\color{#35bf28}+2.92\%$
test_permute 0.2952ms 0.1777ms 5.6272 KOps/s 5.4017 KOps/s $\color{#35bf28}+4.17\%$
test_stack 52.9821ms 52.6881ms 18.9796 Ops/s 19.6896 Ops/s $\color{#d91a1a}-3.61\%$
test_cat 51.1395ms 50.4223ms 19.8325 Ops/s 19.9077 Ops/s $\color{#d91a1a}-0.38\%$

@vmoens vmoens added the enhancement New feature or request label Feb 3, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants