[BugFix] num_samples=None fix#1292
Merged
vmoens merged 2 commits intogh/vmoens/52/basefrom Apr 23, 2025
Merged
Conversation
Contributor
|
| Name | Max | Mean | Ops | Ops on Repo HEAD
|
Change |
|---|---|---|---|---|---|
| test_plain_set_nested | 47.7610μs | 11.5496μs | 86.5828 KOps/s | 87.7811 KOps/s | |
| test_plain_set_stack_nested | 40.8910μs | 11.5753μs | 86.3906 KOps/s | 86.8288 KOps/s | |
| test_plain_set_nested_inplace | 39.9000μs | 12.7155μs | 78.6442 KOps/s | 78.9726 KOps/s | |
| test_plain_set_stack_nested_inplace | 40.3710μs | 12.6541μs | 79.0258 KOps/s | 79.4279 KOps/s | |
| test_items | 40.5810μs | 2.9226μs | 342.1583 KOps/s | 336.7217 KOps/s | |
| test_items_nested | 1.4547ms | 0.3624ms | 2.7595 KOps/s | 2.7437 KOps/s | |
| test_items_nested_locked | 0.5335ms | 0.3635ms | 2.7513 KOps/s | 2.7265 KOps/s | |
| test_items_nested_leaf | 0.1022ms | 60.8742μs | 16.4273 KOps/s | 16.5184 KOps/s | |
| test_items_stack_nested | 0.5065ms | 0.3655ms | 2.7361 KOps/s | 2.7333 KOps/s | |
| test_items_stack_nested_leaf | 0.1116ms | 60.9966μs | 16.3944 KOps/s | 16.4799 KOps/s | |
| test_items_stack_nested_locked | 0.5429ms | 0.3662ms | 2.7311 KOps/s | 2.7565 KOps/s | |
| test_keys | 32.0110μs | 3.4563μs | 289.3266 KOps/s | 290.2443 KOps/s | |
| test_keys_nested | 0.1406ms | 89.1274μs | 11.2199 KOps/s | 11.1173 KOps/s | |
| test_keys_nested_locked | 2.4687ms | 94.5542μs | 10.5759 KOps/s | 10.4296 KOps/s | |
| test_keys_nested_leaf | 0.1305ms | 79.5424μs | 12.5719 KOps/s | 12.4162 KOps/s | |
| test_keys_stack_nested | 0.1342ms | 89.5541μs | 11.1664 KOps/s | 11.2169 KOps/s | |
| test_keys_stack_nested_leaf | 0.1045ms | 79.5347μs | 12.5731 KOps/s | 12.5035 KOps/s | |
| test_keys_stack_nested_locked | 0.1400ms | 94.1055μs | 10.6264 KOps/s | 10.4537 KOps/s | |
| test_values | 11.9618μs | 0.8545μs | 1.1702 MOps/s | 1.1770 MOps/s | |
| test_values_nested | 82.0810μs | 37.5859μs | 26.6057 KOps/s | 26.3430 KOps/s | |
| test_values_nested_locked | 87.0320μs | 39.8801μs | 25.0752 KOps/s | 25.1304 KOps/s | |
| test_values_nested_leaf | 86.5710μs | 43.2671μs | 23.1122 KOps/s | 23.3172 KOps/s | |
| test_values_stack_nested | 99.4120μs | 37.6951μs | 26.5286 KOps/s | 26.2307 KOps/s | |
| test_values_stack_nested_leaf | 0.5311ms | 43.1929μs | 23.1520 KOps/s | 23.0891 KOps/s | |
| test_values_stack_nested_locked | 70.1820μs | 39.9303μs | 25.0437 KOps/s | 25.0205 KOps/s | |
| test_membership | 1.7480μs | 0.5041μs | 1.9839 MOps/s | 2.0086 MOps/s | |
| test_membership_nested | 14.1555μs | 2.0359μs | 491.1881 KOps/s | 493.7813 KOps/s | |
| test_membership_nested_leaf | 34.6360μs | 2.0274μs | 493.2473 KOps/s | 494.1348 KOps/s | |
| test_membership_stacked_nested | 29.5410μs | 2.0761μs | 481.6789 KOps/s | 475.0638 KOps/s | |
| test_membership_stacked_nested_leaf | 32.4400μs | 2.1092μs | 474.1171 KOps/s | 475.9177 KOps/s | |
| test_membership_nested_last | 33.5300μs | 3.0819μs | 324.4721 KOps/s | 325.6003 KOps/s | |
| test_membership_nested_leaf_last | 26.7710μs | 3.0734μs | 325.3748 KOps/s | 326.3891 KOps/s | |
| test_membership_stacked_nested_last | 32.6600μs | 3.0748μs | 325.2211 KOps/s | 327.9335 KOps/s | |
| test_membership_stacked_nested_leaf_last | 22.8200μs | 3.0497μs | 327.8970 KOps/s | 326.1569 KOps/s | |
| test_nested_getleaf | 38.8500μs | 13.0655μs | 76.5374 KOps/s | 76.7504 KOps/s | |
| test_nested_get | 46.8510μs | 12.4854μs | 80.0936 KOps/s | 80.9789 KOps/s | |
| test_stacked_getleaf | 43.9610μs | 13.0476μs | 76.6425 KOps/s | 76.7543 KOps/s | |
| test_stacked_get | 42.6010μs | 12.4750μs | 80.1606 KOps/s | 81.0133 KOps/s | |
| test_nested_getitemleaf | 34.3500μs | 13.4647μs | 74.2682 KOps/s | 74.4949 KOps/s | |
| test_nested_getitem | 48.0210μs | 12.7807μs | 78.2429 KOps/s | 78.8093 KOps/s | |
| test_stacked_getitemleaf | 38.8310μs | 13.4479μs | 74.3608 KOps/s | 74.7511 KOps/s | |
| test_stacked_getitem | 56.0800μs | 12.6745μs | 78.8986 KOps/s | 79.2070 KOps/s | |
| test_lock_nested | 1.6981ms | 0.3574ms | 2.7981 KOps/s | 2.7899 KOps/s | |
| test_lock_stack_nested | 0.3805ms | 0.3463ms | 2.8874 KOps/s | 2.9067 KOps/s | |
| test_unlock_nested | 0.5011ms | 0.2989ms | 3.3452 KOps/s | 3.4489 KOps/s | |
| test_unlock_stack_nested | 0.3191ms | 0.2828ms | 3.5364 KOps/s | 3.5647 KOps/s | |
| test_flatten_speed | 0.1126ms | 77.2772μs | 12.9404 KOps/s | 12.7643 KOps/s | |
| test_unflatten_speed | 0.7804ms | 0.4035ms | 2.4783 KOps/s | 2.4997 KOps/s | |
| test_common_ops | 1.0054ms | 0.6289ms | 1.5902 KOps/s | 1.5945 KOps/s | |
| test_creation | 0.1329ms | 1.7595μs | 568.3329 KOps/s | 569.9571 KOps/s | |
| test_creation_empty | 0.5453ms | 7.3317μs | 136.3943 KOps/s | 139.1530 KOps/s | |
| test_creation_nested_1 | 99.6110μs | 10.2008μs | 98.0318 KOps/s | 99.6897 KOps/s | |
| test_creation_nested_2 | 0.4037ms | 13.0738μs | 76.4887 KOps/s | 76.6725 KOps/s | |
| test_clone | 97.2920μs | 10.3921μs | 96.2265 KOps/s | 99.6344 KOps/s | |
| test_getitem[int] | 0.1784ms | 10.7554μs | 92.9764 KOps/s | 64.0398 KOps/s | |
| test_getitem[slice_int] | 0.1143ms | 20.4492μs | 48.9016 KOps/s | 48.8877 KOps/s | |
| test_getitem[range] | 0.4436ms | 40.6750μs | 24.5851 KOps/s | 26.4554 KOps/s | |
| test_getitem[tuple] | 0.1109ms | 18.2691μs | 54.7371 KOps/s | 55.4791 KOps/s | |
| test_getitem[list] | 0.1326ms | 32.4884μs | 30.7802 KOps/s | 30.5367 KOps/s | |
| test_setitem_dim[int] | 41.0600μs | 20.2770μs | 49.3170 KOps/s | 53.0512 KOps/s | |
| test_setitem_dim[slice_int] | 62.6210μs | 39.2092μs | 25.5042 KOps/s | 26.6466 KOps/s | |
| test_setitem_dim[range] | 80.6210μs | 55.8509μs | 17.9048 KOps/s | 19.5174 KOps/s | |
| test_setitem_dim[tuple] | 53.5110μs | 32.0970μs | 31.1556 KOps/s | 31.5702 KOps/s | |
| test_setitem | 0.2147ms | 15.0249μs | 66.5560 KOps/s | 66.1879 KOps/s | |
| test_set | 0.4133ms | 14.4936μs | 68.9958 KOps/s | 70.0589 KOps/s | |
| test_set_shared | 0.5329ms | 0.1654ms | 6.0453 KOps/s | 6.3116 KOps/s | |
| test_update | 0.4092ms | 18.2306μs | 54.8529 KOps/s | 55.7038 KOps/s | |
| test_update_nested | 0.4282ms | 30.0238μs | 33.3069 KOps/s | 34.9584 KOps/s | |
| test_update__nested | 67.9610μs | 24.3491μs | 41.0693 KOps/s | 42.6222 KOps/s | |
| test_set_nested | 0.1342ms | 15.9347μs | 62.7562 KOps/s | 64.4414 KOps/s | |
| test_set_nested_new | 0.4203ms | 18.9133μs | 52.8727 KOps/s | 52.9856 KOps/s | |
| test_select | 0.1166ms | 30.2301μs | 33.0797 KOps/s | 33.3268 KOps/s | |
| test_select_nested | 0.4308ms | 43.3735μs | 23.0555 KOps/s | 22.7858 KOps/s | |
| test_exclude_nested | 0.4618ms | 63.4549μs | 15.7592 KOps/s | 15.6954 KOps/s | |
| test_empty[True] | 0.3303ms | 0.2968ms | 3.3692 KOps/s | 3.3709 KOps/s | |
| test_empty[False] | 39.2847μs | 0.8243μs | 1.2131 MOps/s | 1.2073 MOps/s | |
| test_to | 89.3720μs | 58.3387μs | 17.1413 KOps/s | 17.4112 KOps/s | |
| test_to_nonblocking | 0.4520ms | 49.6750μs | 20.1308 KOps/s | 19.9454 KOps/s | |
| test_unbind_speed | 0.8423ms | 0.2410ms | 4.1494 KOps/s | 4.1320 KOps/s | |
| test_unbind_speed_stack0 | 0.2850ms | 0.2354ms | 4.2488 KOps/s | 4.1366 KOps/s | |
| test_unbind_speed_stack1 | 93.4563ms | 0.7347ms | 1.3610 KOps/s | 1.4888 KOps/s | |
| test_split | 94.0070ms | 1.5885ms | 629.5416 Ops/s | 574.3775 Ops/s | |
| test_chunk | 94.7254ms | 1.5990ms | 625.4101 Ops/s | 686.8355 Ops/s | |
| test_consolidate[False-None] | 96.9260ms | 3.1003ms | 322.5536 Ops/s | 325.5700 Ops/s | |
| test_consolidate[default-None] | 1.8065ms | 1.7379ms | 575.4175 Ops/s | 576.1416 Ops/s | |
| test_consolidate[reduce-overhead-None] | 1.8234ms | 1.7602ms | 568.1196 Ops/s | 569.4821 Ops/s | |
| test_consolidate_njt[False-None] | 7.2790ms | 6.8173ms | 146.6847 Ops/s | 112.8152 Ops/s | |
| test_to[False-False-None] | 1.8940ms | 1.8001ms | 555.5294 Ops/s | 565.0895 Ops/s | |
| test_to[True-False-None] | 1.9577ms | 1.4243ms | 702.0892 Ops/s | 696.3913 Ops/s | |
| test_to[within-False-None] | 4.7220ms | 4.3384ms | 230.4975 Ops/s | 226.6597 Ops/s | |
| test_to[True-default-None] | 5.4819ms | 5.1586ms | 193.8509 Ops/s | 185.6798 Ops/s | |
| test_to_njt[False-False-None] | 7.4044ms | 6.9663ms | 143.5479 Ops/s | 142.7365 Ops/s | |
| test_to_njt[True-False-None] | 6.1158ms | 5.5511ms | 180.1439 Ops/s | 176.9641 Ops/s | |
| test_to_njt[within-False-None] | 13.5401ms | 12.8326ms | 77.9263 Ops/s | 81.0409 Ops/s | |
| test_creation[device0] | 0.3001ms | 79.5750μs | 12.5668 KOps/s | 12.5616 KOps/s | |
| test_creation_from_tensor | 0.5474ms | 88.5773μs | 11.2896 KOps/s | 11.7600 KOps/s | |
| test_add_one[memmap_tensor0] | 0.4335ms | 6.4807μs | 154.3046 KOps/s | 158.8140 KOps/s | |
| test_contiguous[memmap_tensor0] | 3.4940μs | 0.4277μs | 2.3382 MOps/s | 2.3961 MOps/s | |
| test_stack[memmap_tensor0] | 35.5800μs | 4.6875μs | 213.3314 KOps/s | 228.9571 KOps/s | |
| test_memmaptd_index | 1.6602ms | 0.2424ms | 4.1258 KOps/s | 4.2036 KOps/s | |
| test_memmaptd_index_astensor | 0.4364ms | 0.3032ms | 3.2987 KOps/s | 3.3022 KOps/s | |
| test_memmaptd_index_op | 0.9380ms | 0.5418ms | 1.8456 KOps/s | 1.8306 KOps/s | |
| test_serialize_model | 0.1350s | 0.1326s | 7.5439 Ops/s | 7.5421 Ops/s | |
| test_serialize_model_pickle | 1.3470s | 1.2145s | 0.8234 Ops/s | 0.8254 Ops/s | |
| test_serialize_weights | 0.2861s | 0.1535s | 6.5140 Ops/s | 7.5781 Ops/s | |
| test_serialize_weights_returnearly | 0.3343s | 53.3288ms | 18.7516 Ops/s | 12.9389 Ops/s | |
| test_serialize_weights_pickle | 1.3760s | 1.2158s | 0.8225 Ops/s | 0.8138 Ops/s | |
| test_reshape_pytree | 50.6410μs | 22.0732μs | 45.3039 KOps/s | 44.7185 KOps/s | |
| test_reshape_td | 49.5710μs | 27.2394μs | 36.7116 KOps/s | 36.7874 KOps/s | |
| test_view_pytree | 51.6710μs | 21.6160μs | 46.2620 KOps/s | 45.4449 KOps/s | |
| test_view_td | 77.3820μs | 33.4129μs | 29.9286 KOps/s | 30.6693 KOps/s | |
| test_unbind_pytree | 83.8510μs | 28.1633μs | 35.5072 KOps/s | 35.5664 KOps/s | |
| test_unbind_td | 0.6087ms | 38.4347μs | 26.0182 KOps/s | 27.0597 KOps/s | |
| test_split_pytree | 61.2410μs | 30.2643μs | 33.0422 KOps/s | 33.2739 KOps/s | |
| test_split_td | 0.7371ms | 40.4795μs | 24.7039 KOps/s | 24.8689 KOps/s | |
| test_add_pytree | 73.0820μs | 32.9384μs | 30.3597 KOps/s | 30.5818 KOps/s | |
| test_add_td | 0.2785ms | 47.2912μs | 21.1456 KOps/s | 20.9945 KOps/s | |
| test_compile_add_one_nested[tensordict-compile] | 0.1778ms | 0.1241ms | 8.0556 KOps/s | 7.7412 KOps/s | |
| test_compile_add_one_nested[tensordict-eager] | 0.2336ms | 0.1411ms | 7.0874 KOps/s | 6.9513 KOps/s | |
| test_compile_add_one_nested[pytree-compile] | 0.1436ms | 96.5759μs | 10.3545 KOps/s | 10.1791 KOps/s | |
| test_compile_add_one_nested[pytree-eager] | 1.0096ms | 0.1501ms | 6.6608 KOps/s | 6.5381 KOps/s | |
| test_compile_copy_nested[tensordict-compile] | 65.7110μs | 23.9714μs | 41.7163 KOps/s | 43.9636 KOps/s | |
| test_compile_copy_nested[tensordict-eager] | 0.1061ms | 36.2615μs | 27.5774 KOps/s | 28.6101 KOps/s | |
| test_compile_copy_nested[pytree-compile] | 0.4457ms | 64.6528μs | 15.4672 KOps/s | 15.3272 KOps/s | |
| test_compile_copy_nested[pytree-eager] | 78.4010μs | 48.6425μs | 20.5582 KOps/s | 20.1086 KOps/s | |
| test_compile_add_one_flat[tensordict-compile] | 0.1985ms | 0.1501ms | 6.6608 KOps/s | 7.0345 KOps/s | |
| test_compile_add_one_flat[tensordict-eager] | 0.3277ms | 0.2215ms | 4.5148 KOps/s | 4.4722 KOps/s | |
| test_compile_add_one_flat[tensorclass-compile] | 0.1496ms | 0.1009ms | 9.9067 KOps/s | 10.3362 KOps/s | |
| test_compile_add_one_flat[tensorclass-eager] | 0.1291ms | 59.3846μs | 16.8394 KOps/s | 16.1446 KOps/s | |
| test_compile_add_one_flat[pytree-compile] | 0.2106ms | 0.1381ms | 7.2432 KOps/s | 7.3519 KOps/s | |
| test_compile_add_one_flat[pytree-eager] | 0.5660ms | 0.4861ms | 2.0572 KOps/s | 2.0212 KOps/s | |
| test_compile_add_self_flat[tensordict-eager] | 0.4315ms | 0.2690ms | 3.7170 KOps/s | 3.7106 KOps/s | |
| test_compile_add_self_flat[tensordict-compile] | 0.1849ms | 0.1467ms | 6.8184 KOps/s | 6.9554 KOps/s | |
| test_compile_add_self_flat[tensorclass-eager] | 0.1663ms | 72.2010μs | 13.8502 KOps/s | 13.5710 KOps/s | |
| test_compile_add_self_flat[tensorclass-compile] | 0.1382ms | 0.1007ms | 9.9264 KOps/s | 10.1578 KOps/s | |
| test_compile_add_self_flat[pytree-eager] | 0.4746ms | 0.4187ms | 2.3885 KOps/s | 2.4154 KOps/s | |
| test_compile_add_self_flat[pytree-compile] | 0.1935ms | 0.1393ms | 7.1801 KOps/s | 7.4245 KOps/s | |
| test_compile_copy_flat[tensordict-compile] | 94.2210μs | 20.2219μs | 49.4514 KOps/s | 54.6818 KOps/s | |
| test_compile_copy_flat[tensordict-eager] | 64.7010μs | 32.0017μs | 31.2483 KOps/s | 30.9516 KOps/s | |
| test_compile_copy_flat[pytree-compile] | 0.1042ms | 69.1073μs | 14.4703 KOps/s | 14.3602 KOps/s | |
| test_compile_copy_flat[pytree-eager] | 86.0910μs | 51.9341μs | 19.2552 KOps/s | 19.3714 KOps/s | |
| test_compile_assign_and_add[tensordict-compile] | 1.6588ms | 0.3983ms | 2.5110 KOps/s | 2.2157 KOps/s | |
| test_compile_assign_and_add[tensordict-eager] | 3.0078ms | 2.8005ms | 357.0814 Ops/s | 362.4276 Ops/s | |
| test_compile_assign_and_add[pytree-compile] | 1.5917ms | 0.4327ms | 2.3109 KOps/s | 2.2753 KOps/s | |
| test_compile_assign_and_add[pytree-eager] | 2.8000ms | 2.6893ms | 371.8416 Ops/s | 379.1233 Ops/s | |
| test_compile_indexing[tensor-tensordict-compile] | 0.1644ms | 0.1150ms | 8.6950 KOps/s | 9.0320 KOps/s | |
| test_compile_indexing[tensor-tensordict-eager] | 0.5534ms | 82.9029μs | 12.0623 KOps/s | 12.0560 KOps/s | |
| test_compile_indexing[tensor-tensorclass-compile] | 0.2304ms | 0.1096ms | 9.1244 KOps/s | 9.4553 KOps/s | |
| test_compile_indexing[tensor-tensorclass-eager] | 0.1139ms | 68.1058μs | 14.6830 KOps/s | 14.5688 KOps/s | |
| test_compile_indexing[tensor-pytree-compile] | 0.1561ms | 0.1121ms | 8.9239 KOps/s | 9.4490 KOps/s | |
| test_compile_indexing[tensor-pytree-eager] | 0.1170ms | 71.4899μs | 13.9880 KOps/s | 14.6908 KOps/s | |
| test_compile_indexing[slice-tensordict-compile] | 0.1419ms | 99.2252μs | 10.0781 KOps/s | 9.9965 KOps/s | |
| test_compile_indexing[slice-tensordict-eager] | 0.1486ms | 19.3848μs | 51.5868 KOps/s | 53.0194 KOps/s | |
| test_compile_indexing[slice-tensorclass-compile] | 0.1475ms | 96.2101μs | 10.3939 KOps/s | 9.9302 KOps/s | |
| test_compile_indexing[slice-tensorclass-eager] | 46.4110μs | 15.7557μs | 63.4691 KOps/s | 64.1581 KOps/s | |
| test_compile_indexing[slice-pytree-compile] | 0.1485ms | 0.1003ms | 9.9720 KOps/s | 10.1925 KOps/s | |
| test_compile_indexing[slice-pytree-eager] | 53.3310μs | 15.9765μs | 62.5921 KOps/s | 64.0749 KOps/s | |
| test_compile_indexing[int-tensordict-compile] | 0.1492ms | 0.1049ms | 9.5343 KOps/s | 9.7120 KOps/s | |
| test_compile_indexing[int-tensordict-eager] | 0.6465ms | 19.4544μs | 51.4024 KOps/s | 53.4599 KOps/s | |
| test_compile_indexing[int-tensorclass-compile] | 0.1574ms | 0.1006ms | 9.9355 KOps/s | 10.1418 KOps/s | |
| test_compile_indexing[int-tensorclass-eager] | 80.9510μs | 15.7413μs | 63.5270 KOps/s | 64.4231 KOps/s | |
| test_compile_indexing[int-pytree-compile] | 0.1239ms | 96.6006μs | 10.3519 KOps/s | 10.2359 KOps/s | |
| test_compile_indexing[int-pytree-eager] | 62.0610μs | 15.7655μs | 63.4296 KOps/s | 64.8981 KOps/s | |
| test_mod_add[eager] | 81.8910μs | 38.4468μs | 26.0100 KOps/s | 26.1044 KOps/s | |
| test_mod_add[compile] | 0.1251ms | 83.7849μs | 11.9353 KOps/s | 12.1770 KOps/s | |
| test_mod_add[compile-overhead] | 0.3307ms | 0.1702ms | 5.8755 KOps/s | 5.5977 KOps/s | |
| test_mod_wrap[eager] | 0.3325ms | 0.2515ms | 3.9767 KOps/s | 3.7696 KOps/s | |
| test_mod_wrap[compile] | 0.3513ms | 0.3024ms | 3.3063 KOps/s | 3.4430 KOps/s | |
| test_mod_wrap[compile-overhead] | 7.5182ms | 3.9370ms | 253.9999 Ops/s | 266.7229 Ops/s | |
| test_mod_wrap_and_backward[eager] | 1.4844ms | 1.3581ms | 736.3406 Ops/s | 698.9184 Ops/s | |
| test_mod_wrap_and_backward[compile] | 1.4049ms | 1.2920ms | 773.9865 Ops/s | 714.4871 Ops/s | |
| test_mod_wrap_and_backward[compile-overhead] | 1.3870ms | 0.9250ms | 1.0811 KOps/s | 967.2420 Ops/s | |
| test_seq_add[eager] | 0.3264ms | 0.1358ms | 7.3636 KOps/s | 7.7509 KOps/s | |
| test_seq_add[compile] | 0.1926ms | 95.1267μs | 10.5123 KOps/s | 10.6248 KOps/s | |
| test_seq_add[compile-overhead] | 0.1814ms | 0.1354ms | 7.3832 KOps/s | 7.5256 KOps/s | |
| test_seq_wrap[eager] | 1.0425ms | 0.4466ms | 2.2391 KOps/s | 2.2435 KOps/s | |
| test_seq_wrap[compile] | 1.2368ms | 0.3317ms | 3.0151 KOps/s | 3.1033 KOps/s | |
| test_seq_wrap[compile-overhead] | 0.2780ms | 0.2344ms | 4.2661 KOps/s | 4.3821 KOps/s | |
| test_func_call_runtime[False-eager] | 0.8585ms | 0.7848ms | 1.2742 KOps/s | 1.3025 KOps/s | |
| test_func_call_runtime[False-compile] | 1.0919ms | 0.7886ms | 1.2680 KOps/s | 1.3157 KOps/s | |
| test_func_call_runtime[False-compile-overhead] | 0.4128ms | 0.3681ms | 2.7165 KOps/s | 2.7195 KOps/s | |
| test_func_call_runtime[True-eager] | 1.0773ms | 0.9376ms | 1.0666 KOps/s | 1.1184 KOps/s | |
| test_func_call_runtime[True-compile] | 0.8911ms | 0.8306ms | 1.2039 KOps/s | 1.2905 KOps/s | |
| test_func_call_runtime[True-compile-overhead] | 0.4413ms | 0.3923ms | 2.5489 KOps/s | 2.5702 KOps/s | |
| test_func_call_cm_runtime[False-eager] | 0.7884ms | 0.7225ms | 1.3841 KOps/s | 1.3961 KOps/s | |
| test_func_call_cm_runtime[False-compile] | 0.8757ms | 0.7626ms | 1.3113 KOps/s | 1.2622 KOps/s | |
| test_func_call_cm_runtime[False-compile-overhead] | 0.4207ms | 0.3707ms | 2.6977 KOps/s | 2.7160 KOps/s | |
| test_func_call_cm_runtime[True-eager] | 1.0934ms | 1.0020ms | 997.9672 Ops/s | 1.0013 KOps/s | |
| test_func_call_cm_runtime[True-compile] | 1.0387ms | 0.9799ms | 1.0205 KOps/s | 998.9312 Ops/s | |
| test_func_call_cm_runtime[True-compile-overhead] | 1.0620ms | 0.9880ms | 1.0122 KOps/s | 1.0134 KOps/s | |
| test_vmap_func_call_cm_runtime[eager] | 2.5235ms | 2.0528ms | 487.1333 Ops/s | 482.8268 Ops/s | |
| test_vmap_func_call_cm_runtime[compile] | 0.8881ms | 0.8232ms | 1.2147 KOps/s | 1.2012 KOps/s | |
| test_vmap_func_call_cm_runtime[compile-overhead] | 0.4785ms | 0.4276ms | 2.3389 KOps/s | 2.3756 KOps/s | |
| test_distributed | 2.8613ms | 0.2832ms | 3.5307 KOps/s | 8.5829 KOps/s | |
| test_tdmodule | 57.3710μs | 21.4393μs | 46.6434 KOps/s | 47.3013 KOps/s | |
| test_tdmodule_dispatch | 63.9410μs | 39.8472μs | 25.0959 KOps/s | 25.8330 KOps/s | |
| test_tdseq | 33.1410μs | 20.8928μs | 47.8635 KOps/s | 48.1893 KOps/s | |
| test_tdseq_dispatch | 62.0120μs | 42.3797μs | 23.5962 KOps/s | 24.9057 KOps/s | |
| test_instantiation_functorch | 1.7129ms | 1.5447ms | 647.3754 Ops/s | 653.4166 Ops/s | |
| test_exec_functorch | 0.1711ms | 0.1379ms | 7.2517 KOps/s | 7.1747 KOps/s | |
| test_exec_functional_call | 0.1856ms | 0.1286ms | 7.7735 KOps/s | 7.6009 KOps/s | |
| test_exec_td_decorator | 0.3810ms | 0.1809ms | 5.5270 KOps/s | 5.5011 KOps/s | |
| test_vmap_mlp_speed_decorator[True-True] | 0.8923ms | 0.6818ms | 1.4668 KOps/s | 1.4685 KOps/s | |
| test_vmap_mlp_speed_decorator[True-False] | 1.0533ms | 0.6773ms | 1.4764 KOps/s | 1.4776 KOps/s | |
| test_vmap_mlp_speed_decorator[False-True] | 0.9688ms | 0.5863ms | 1.7057 KOps/s | 1.7072 KOps/s | |
| test_vmap_mlp_speed_decorator[False-False] | 0.9931ms | 0.5892ms | 1.6971 KOps/s | 1.7046 KOps/s | |
| test_vmap_transformer_speed_decorator[True-True] | 19.3876ms | 19.0154ms | 52.5889 Ops/s | 53.0085 Ops/s | |
| test_vmap_transformer_speed_decorator[True-False] | 19.3833ms | 19.0063ms | 52.6142 Ops/s | 53.1396 Ops/s | |
| test_vmap_transformer_speed_decorator[False-True] | 19.2050ms | 18.9335ms | 52.8164 Ops/s | 53.5632 Ops/s | |
| test_vmap_transformer_speed_decorator[False-False] | 19.6056ms | 18.9687ms | 52.7183 Ops/s | 53.3088 Ops/s | |
| test_to_module_speed[True] | 1.4958ms | 0.9781ms | 1.0224 KOps/s | 1.0171 KOps/s | |
| test_to_module_speed[False] | 1.4224ms | 0.9789ms | 1.0216 KOps/s | 1.0272 KOps/s | |
| test_tc_init | 0.4349ms | 34.8168μs | 28.7218 KOps/s | 28.6653 KOps/s | |
| test_tc_init_tensor_only | 0.1017ms | 10.9352μs | 91.4479 KOps/s | 92.8246 KOps/s | |
| test_tc_init_nested | 0.4573ms | 68.8419μs | 14.5260 KOps/s | 14.6132 KOps/s | |
| test_tc_first_layer_tensor | 23.2800μs | 0.8990μs | 1.1124 MOps/s | 1.2218 MOps/s | |
| test_tc_first_layer_tensor_only | 39.2007μs | 0.4235μs | 2.3615 MOps/s | 2.3660 MOps/s | |
| test_tc_first_layer_tensor_set | 22.5400μs | 2.9252μs | 341.8533 KOps/s | 335.3999 KOps/s | |
| test_tc_first_layer_tensor_only_set | 0.1321ms | 1.7951μs | 557.0614 KOps/s | 550.4090 KOps/s | |
| test_tc_first_layer_nontensor | 22.6610μs | 2.3475μs | 425.9809 KOps/s | 428.9554 KOps/s | |
| test_tc_second_layer_tensor | 0.4005ms | 1.7277μs | 578.8184 KOps/s | 568.3438 KOps/s | |
| test_tc_second_layer_nontensor | 69.9310μs | 3.1748μs | 314.9839 KOps/s | 315.6774 KOps/s | |
| test_unbind | 0.2459s | 9.9631ms | 100.3708 Ops/s | 144.4284 Ops/s | |
| test_full_like | 9.3148ms | 7.4574ms | 134.0943 Ops/s | 135.1390 Ops/s | |
| test_zeros_like | 5.9907ms | 4.3669ms | 228.9938 Ops/s | 230.4555 Ops/s | |
| test_ones_like | 11.9161ms | 8.7076ms | 114.8417 Ops/s | 230.1480 Ops/s | |
| test_clone | 6.9736ms | 6.5971ms | 151.5809 Ops/s | 151.8811 Ops/s | |
| test_squeeze | 62.4610μs | 10.2029μs | 98.0114 KOps/s | 102.4090 KOps/s | |
| test_unsqueeze | 0.5079ms | 78.7398μs | 12.7000 KOps/s | 13.5776 KOps/s | |
| test_split | 0.2726ms | 0.1634ms | 6.1213 KOps/s | 6.0335 KOps/s | |
| test_permute | 0.5995ms | 0.1868ms | 5.3523 KOps/s | 5.3889 KOps/s | |
| test_stack | 51.8193ms | 51.1232ms | 19.5606 Ops/s | 20.0443 Ops/s | |
| test_cat | 51.6585ms | 51.0157ms | 19.6018 Ops/s | 19.1026 Ops/s |
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):