rl
rl copied to clipboard
pytorch
[Feature] flexible batch_locked for jumanji
:link: Helpful Links
:test_tube: See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2382
- :page_facing_up: Preview Python docs built from this PR
Note: Links to docs will display an error until the docs builds have been completed.
:x: 9 New Failures, 9 Unrelated Failures
As of commit d9d02ef5409f5ba0d8b98e13b0721e943fe855d7 with merge base 14b63e4f07c826135897ea0812eb9e3ce9908794 (
NEW FAILURES - The following jobs have failed:
- Habitat Tests on Linux / tests (3.9, 12.1) / linux-job (gh)
RuntimeError: Command docker exec -t c100a3f1ea7403689a3a010269cd34d17c8d262c28de3e195e66b8d9905d878a /exec failed with exit code 1 - Libs Tests on Linux / unittests-smacv2 (3.9, 12.1) / linux-job (gh)
##[error]fatal: couldn't find remote ref refs/pull/2382/merge - Libs Tests on Linux / unittests-unity_mlagents (3.10.12, 12.1) / linux-job (gh)
##[error]fatal: couldn't find remote ref refs/pull/2382/merge - Libs Tests on Linux / unittests-vmas (3.9, 12.1) / linux-job (gh)
##[error]fatal: couldn't find remote ref refs/pull/2382/merge - Unit-tests on Linux / tests-gpu (3.11, 12.1) / linux-job (gh)
##[error]fatal: couldn't find remote ref refs/pull/2382/merge - Unit-tests on Linux / tests-olddeps (3.8, 11.6) / linux-job (gh)
##[error]fatal: couldn't find remote ref refs/pull/2382/merge - Unit-tests on Linux / tests-optdeps (3.11, 12.1) / linux-job (gh)
##[error]fatal: couldn't find remote ref refs/pull/2382/merge - Unit-tests on Linux / tests-stable-gpu (3.10, 11.8) / linux-job (gh)
##[error]fatal: couldn't find remote ref refs/pull/2382/merge - Unit-tests on Windows / unittests-cpu / windows-job (gh)
##[error]fatal: couldn't find remote ref refs/pull/2382/merge
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
- Unit-tests on Linux / tests-cpu (3.11) / linux-job (gh) (similar failure)
test/test_storage_map.py::TestMCTSForest::test_forest_build - Unit-tests on Linux / tests-cpu (3.12) / linux-job (gh) (similar failure)
test/test_storage_map.py::TestMCTSForest::test_forest_build - Unit-tests on Linux / tests-cpu-oldget (3.12) / linux-job (gh) (similar failure)
test/test_transforms.py::TestTrajCounter::test_collector_match
BROKEN TRUNK - The following jobs failed but were present on the merge base:
👉 Rebase onto the `viable/strict` branch to avoid these failures
- Build Windows Wheels / pytorch/rl / upload / wheel-py3_9-cpu (gh) (trunk failure)
##[error]Unable to find any artifacts for the associated workflow - Build Windows Wheels / pytorch/rl / upload / wheel-py3_9-cuda11_8 (gh) (trunk failure)
##[error]Unable to find any artifacts for the associated workflow - Build Windows Wheels / pytorch/rl / upload / wheel-py3_9-cuda12_1 (gh) (trunk failure)
##[error]Unable to find any artifacts for the associated workflow - Build Windows Wheels / pytorch/rl / upload / wheel-py3_9-cuda12_4 (gh) (trunk failure)
##[error]Unable to find any artifacts for the associated workflow - Unit-tests on Linux / tests-cpu (3.10) / linux-job (gh) (trunk failure)
test/test_transforms.py::TestTrajCounter::test_collector_match - Unit-tests on Linux / tests-cpu (3.9) / linux-job (gh) (trunk failure)
test/test_storage_map.py::TestMCTSForest::test_forest_build
This comment was automatically generated by Dr. CI and updates every 15 minutes.
![pytorch-bot[bot] avatar](https://avatars.githubusercontent.com/in/40112?v=4 "Published by a pub.dev verified publisher"){kind=small}
$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of CPU Benchmark Tests
Total Benchmarks: 149. Improved: $\large\color{#35bf28}44$. Worsened: $\large\color{#d91a1a}6$.
Expand to view detailed results
| Name | Max | Mean | Ops | Ops on Repo HEAD |
Change |
|---|---|---|---|---|---|
| test_simple | 0.4406s | 0.4381s | 2.2827 Ops/s | 2.1736 Ops/s | $\textbf{\color{#35bf28}+5.02\%}$ |
| test_transformed | 0.6209s | 0.6181s | 1.6178 Ops/s | 1.6496 Ops/s | $\color{#d91a1a}-1.93\%$ |
| test_serial | 1.3840s | 1.3716s | 0.7291 Ops/s | 0.7221 Ops/s | $\color{#35bf28}+0.97\%$ |
| test_parallel | 1.2970s | 1.2918s | 0.7741 Ops/s | 0.7541 Ops/s | $\color{#35bf28}+2.65\%$ |
| test_step_mdp_speed[True-True-True-True-True] | 0.1979ms | 26.5933μs | 37.6034 KOps/s | 37.2074 KOps/s | $\color{#35bf28}+1.06\%$ |
| test_step_mdp_speed[True-True-True-True-False] | 52.7890μs | 15.7581μs | 63.4595 KOps/s | 63.5744 KOps/s | $\color{#d91a1a}-0.18\%$ |
| test_step_mdp_speed[True-True-True-False-True] | 70.2310μs | 15.1324μs | 66.0836 KOps/s | 65.3059 KOps/s | $\color{#35bf28}+1.19\%$ |
| test_step_mdp_speed[True-True-True-False-False] | 45.0840μs | 8.9122μs | 112.2054 KOps/s | 112.4038 KOps/s | $\color{#d91a1a}-0.18\%$ |
| test_step_mdp_speed[True-True-False-True-True] | 85.6400μs | 28.4892μs | 35.1010 KOps/s | 34.8849 KOps/s | $\color{#35bf28}+0.62\%$ |
| test_step_mdp_speed[True-True-False-True-False] | 62.3360μs | 17.3978μs | 57.4786 KOps/s | 57.7006 KOps/s | $\color{#d91a1a}-0.38\%$ |
| test_step_mdp_speed[True-True-False-False-True] | 76.9940μs | 16.8885μs | 59.2119 KOps/s | 58.9111 KOps/s | $\color{#35bf28}+0.51\%$ |
| test_step_mdp_speed[True-True-False-False-False] | 66.0530μs | 10.5312μs | 94.9560 KOps/s | 94.2248 KOps/s | $\color{#35bf28}+0.78\%$ |
| test_step_mdp_speed[True-False-True-True-True] | 82.2230μs | 30.1079μs | 33.2139 KOps/s | 32.4022 KOps/s | $\color{#35bf28}+2.50\%$ |
| test_step_mdp_speed[True-False-True-True-False] | 77.8050μs | 19.1662μs | 52.1753 KOps/s | 52.2734 KOps/s | $\color{#d91a1a}-0.19\%$ |
| test_step_mdp_speed[True-False-True-False-True] | 61.7040μs | 16.5665μs | 60.3626 KOps/s | 57.8618 KOps/s | $\color{#35bf28}+4.32\%$ |
| test_step_mdp_speed[True-False-True-False-False] | 71.3630μs | 10.5825μs | 94.4953 KOps/s | 93.5379 KOps/s | $\color{#35bf28}+1.02\%$ |
| test_step_mdp_speed[True-False-False-True-True] | 0.1746ms | 31.0174μs | 32.2399 KOps/s | 31.0774 KOps/s | $\color{#35bf28}+3.74\%$ |
| test_step_mdp_speed[True-False-False-True-False] | 77.1740μs | 20.3264μs | 49.1971 KOps/s | 49.8546 KOps/s | $\color{#d91a1a}-1.32\%$ |
| test_step_mdp_speed[True-False-False-False-True] | 70.5720μs | 18.1356μs | 55.1401 KOps/s | 53.8352 KOps/s | $\color{#35bf28}+2.42\%$ |
| test_step_mdp_speed[True-False-False-False-False] | 51.4460μs | 12.1304μs | 82.4376 KOps/s | 83.2629 KOps/s | $\color{#d91a1a}-0.99\%$ |
| test_step_mdp_speed[False-True-True-True-True] | 71.4930μs | 30.2900μs | 33.0142 KOps/s | 32.6864 KOps/s | $\color{#35bf28}+1.00\%$ |
| test_step_mdp_speed[False-True-True-True-False] | 60.0620μs | 19.0942μs | 52.3720 KOps/s | 52.4760 KOps/s | $\color{#d91a1a}-0.20\%$ |
| test_step_mdp_speed[False-True-True-False-True] | 50.2130μs | 19.5838μs | 51.0627 KOps/s | 50.9269 KOps/s | $\color{#35bf28}+0.27\%$ |
| test_step_mdp_speed[False-True-True-False-False] | 46.9880μs | 11.8952μs | 84.0673 KOps/s | 83.4336 KOps/s | $\color{#35bf28}+0.76\%$ |
| test_step_mdp_speed[False-True-False-True-True] | 73.0060μs | 31.9307μs | 31.3178 KOps/s | 30.8775 KOps/s | $\color{#35bf28}+1.43\%$ |
| test_step_mdp_speed[False-True-False-True-False] | 65.3520μs | 20.8290μs | 48.0100 KOps/s | 47.6840 KOps/s | $\color{#35bf28}+0.68\%$ |
| test_step_mdp_speed[False-True-False-False-True] | 2.9663ms | 20.8182μs | 48.0349 KOps/s | 47.4728 KOps/s | $\color{#35bf28}+1.18\%$ |
| test_step_mdp_speed[False-True-False-False-False] | 77.9150μs | 13.3025μs | 75.1738 KOps/s | 74.1685 KOps/s | $\color{#35bf28}+1.36\%$ |
| test_step_mdp_speed[False-False-True-True-True] | 77.0840μs | 33.2828μs | 30.0456 KOps/s | 30.4730 KOps/s | $\color{#d91a1a}-1.40\%$ |
| test_step_mdp_speed[False-False-True-True-False] | 61.9160μs | 22.5887μs | 44.2699 KOps/s | 45.2606 KOps/s | $\color{#d91a1a}-2.19\%$ |
| test_step_mdp_speed[False-False-True-False-True] | 64.3700μs | 20.9427μs | 47.7493 KOps/s | 47.6325 KOps/s | $\color{#35bf28}+0.25\%$ |
| test_step_mdp_speed[False-False-True-False-False] | 66.3140μs | 13.4619μs | 74.2837 KOps/s | 73.7163 KOps/s | $\color{#35bf28}+0.77\%$ |
| test_step_mdp_speed[False-False-False-True-True] | 94.3330μs | 35.1119μs | 28.4804 KOps/s | 27.5807 KOps/s | $\color{#35bf28}+3.26\%$ |
| test_step_mdp_speed[False-False-False-True-False] | 63.3780μs | 23.8985μs | 41.8437 KOps/s | 41.9261 KOps/s | $\color{#d91a1a}-0.20\%$ |
| test_step_mdp_speed[False-False-False-False-True] | 58.3590μs | 22.4575μs | 44.5286 KOps/s | 44.4192 KOps/s | $\color{#35bf28}+0.25\%$ |
| test_step_mdp_speed[False-False-False-False-False] | 75.0290μs | 14.7257μs | 67.9086 KOps/s | 67.1997 KOps/s | $\color{#35bf28}+1.05\%$ |
| test_values[generalized_advantage_estimate-True-True] | 9.8849ms | 9.5736ms | 104.4542 Ops/s | 101.6170 Ops/s | $\color{#35bf28}+2.79\%$ |
| test_values[vec_generalized_advantage_estimate-True-True] | 37.1371ms | 33.8261ms | 29.5630 Ops/s | 27.4785 Ops/s | $\textbf{\color{#35bf28}+7.59\%}$ |
| test_values[td0_return_estimate-False-False] | 0.2683ms | 0.1905ms | 5.2489 KOps/s | 5.3849 KOps/s | $\color{#d91a1a}-2.53\%$ |
| test_values[td1_return_estimate-False-False] | 27.7899ms | 24.2426ms | 41.2497 Ops/s | 39.9964 Ops/s | $\color{#35bf28}+3.13\%$ |
| test_values[vec_td1_return_estimate-False-False] | 36.0974ms | 33.7072ms | 29.6673 Ops/s | 27.2243 Ops/s | $\textbf{\color{#35bf28}+8.97\%}$ |
| test_values[td_lambda_return_estimate-True-False] | 35.8739ms | 34.9997ms | 28.5717 Ops/s | 28.1074 Ops/s | $\color{#35bf28}+1.65\%$ |
| test_values[vec_td_lambda_return_estimate-True-False] | 52.1267ms | 34.3855ms | 29.0820 Ops/s | 27.3363 Ops/s | $\textbf{\color{#35bf28}+6.39\%}$ |
| test_gae_speed[generalized_advantage_estimate-False-1-512] | 11.5527ms | 8.2887ms | 120.6455 Ops/s | 117.5131 Ops/s | $\color{#35bf28}+2.67\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-True-1-512] | 2.4054ms | 1.8265ms | 547.4938 Ops/s | 491.7671 Ops/s | $\textbf{\color{#35bf28}+11.33\%}$ |
| test_gae_speed[vec_generalized_advantage_estimate-False-1-512] | 0.4606ms | 0.3585ms | 2.7893 KOps/s | 2.7778 KOps/s | $\color{#35bf28}+0.41\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-True-32-512] | 44.9133ms | 42.3466ms | 23.6146 Ops/s | 21.3531 Ops/s | $\textbf{\color{#35bf28}+10.59\%}$ |
| test_gae_speed[vec_generalized_advantage_estimate-False-32-512] | 4.0663ms | 3.1360ms | 318.8810 Ops/s | 315.8781 Ops/s | $\color{#35bf28}+0.95\%$ |
| test_dqn_speed[False-None] | 7.2108ms | 1.3702ms | 729.8349 Ops/s | 741.8367 Ops/s | $\color{#d91a1a}-1.62\%$ |
| test_dqn_speed[False-backward] | 2.0934ms | 1.8510ms | 540.2479 Ops/s | 553.8201 Ops/s | $\color{#d91a1a}-2.45\%$ |
| test_dqn_speed[True-None] | 1.2793ms | 0.4708ms | 2.1242 KOps/s | 2.0584 KOps/s | $\color{#35bf28}+3.19\%$ |
| test_dqn_speed[True-backward] | 1.0193ms | 0.9027ms | 1.1078 KOps/s | 1.0536 KOps/s | $\textbf{\color{#35bf28}+5.14\%}$ |
| test_dqn_speed[reduce-overhead-None] | 0.7164ms | 0.4747ms | 2.1065 KOps/s | 2.1389 KOps/s | $\color{#d91a1a}-1.52\%$ |
| test_dqn_speed[reduce-overhead-backward] | 1.0469ms | 0.9400ms | 1.0638 KOps/s | 1.1195 KOps/s | $\color{#d91a1a}-4.98\%$ |
| test_ddpg_speed[False-None] | 3.9823ms | 2.8257ms | 353.8896 Ops/s | 347.5797 Ops/s | $\color{#35bf28}+1.82\%$ |
| test_ddpg_speed[False-backward] | 4.8363ms | 4.1489ms | 241.0258 Ops/s | 246.4324 Ops/s | $\color{#d91a1a}-2.19\%$ |
| test_ddpg_speed[True-None] | 1.4637ms | 1.0240ms | 976.5656 Ops/s | 988.4279 Ops/s | $\color{#d91a1a}-1.20\%$ |
| test_ddpg_speed[True-backward] | 2.6252ms | 2.0618ms | 485.0105 Ops/s | 499.0647 Ops/s | $\color{#d91a1a}-2.82\%$ |
| test_ddpg_speed[reduce-overhead-None] | 1.5730ms | 1.0218ms | 978.6857 Ops/s | 981.1323 Ops/s | $\color{#d91a1a}-0.25\%$ |
| test_ddpg_speed[reduce-overhead-backward] | 2.5827ms | 2.1439ms | 466.4490 Ops/s | 492.2581 Ops/s | $\textbf{\color{#d91a1a}-5.24\%}$ |
| test_sac_speed[False-None] | 11.8106ms | 8.4207ms | 118.7549 Ops/s | 121.3359 Ops/s | $\color{#d91a1a}-2.13\%$ |
| test_sac_speed[False-backward] | 14.0164ms | 11.9037ms | 84.0076 Ops/s | 89.8439 Ops/s | $\textbf{\color{#d91a1a}-6.50\%}$ |
| test_sac_speed[True-None] | 2.6976ms | 1.9783ms | 505.4792 Ops/s | 508.6295 Ops/s | $\color{#d91a1a}-0.62\%$ |
| test_sac_speed[True-backward] | 4.7905ms | 4.1183ms | 242.8174 Ops/s | 259.2218 Ops/s | $\textbf{\color{#d91a1a}-6.33\%}$ |
| test_sac_speed[reduce-overhead-None] | 2.6486ms | 1.9327ms | 517.4223 Ops/s | 467.3388 Ops/s | $\textbf{\color{#35bf28}+10.72\%}$ |
| test_sac_speed[reduce-overhead-backward] | 4.5996ms | 3.9666ms | 252.1031 Ops/s | 242.6324 Ops/s | $\color{#35bf28}+3.90\%$ |
| test_redq_speed[False-None] | 15.2066ms | 13.3434ms | 74.9431 Ops/s | 66.6564 Ops/s | $\textbf{\color{#35bf28}+12.43\%}$ |
| test_redq_speed[False-backward] | 24.8493ms | 22.8872ms | 43.6925 Ops/s | 42.2266 Ops/s | $\color{#35bf28}+3.47\%$ |
| test_redq_speed[True-None] | 6.6725ms | 5.6050ms | 178.4122 Ops/s | 175.9522 Ops/s | $\color{#35bf28}+1.40\%$ |
| test_redq_speed[True-backward] | 14.1817ms | 13.1049ms | 76.3072 Ops/s | 73.5098 Ops/s | $\color{#35bf28}+3.81\%$ |
| test_redq_speed[reduce-overhead-None] | 6.6227ms | 5.1451ms | 194.3613 Ops/s | 170.6708 Ops/s | $\textbf{\color{#35bf28}+13.88\%}$ |
| test_redq_speed[reduce-overhead-backward] | 16.7376ms | 13.3383ms | 74.9719 Ops/s | 73.0542 Ops/s | $\color{#35bf28}+2.63\%$ |
| test_redq_deprec_speed[False-None] | 17.0063ms | 13.9662ms | 71.6013 Ops/s | 66.2710 Ops/s | $\textbf{\color{#35bf28}+8.04\%}$ |
| test_redq_deprec_speed[False-backward] | 24.0826ms | 19.9358ms | 50.1609 Ops/s | 46.8131 Ops/s | $\textbf{\color{#35bf28}+7.15\%}$ |
| test_redq_deprec_speed[True-None] | 5.6476ms | 4.2593ms | 234.7790 Ops/s | 217.8408 Ops/s | $\textbf{\color{#35bf28}+7.78\%}$ |
| test_redq_deprec_speed[True-backward] | 9.9921ms | 9.2390ms | 108.2368 Ops/s | 105.1918 Ops/s | $\color{#35bf28}+2.89\%$ |
| test_redq_deprec_speed[reduce-overhead-None] | 5.5559ms | 4.3302ms | 230.9381 Ops/s | 228.2560 Ops/s | $\color{#35bf28}+1.18\%$ |
| test_redq_deprec_speed[reduce-overhead-backward] | 10.4082ms | 9.3144ms | 107.3608 Ops/s | 103.4798 Ops/s | $\color{#35bf28}+3.75\%$ |
| test_td3_speed[False-None] | 9.2294ms | 8.3949ms | 119.1197 Ops/s | 113.5504 Ops/s | $\color{#35bf28}+4.90\%$ |
| test_td3_speed[False-backward] | 12.9850ms | 11.2393ms | 88.9737 Ops/s | 89.4515 Ops/s | $\color{#d91a1a}-0.53\%$ |
| test_td3_speed[True-None] | 2.2412ms | 1.7921ms | 558.0054 Ops/s | 513.8156 Ops/s | $\textbf{\color{#35bf28}+8.60\%}$ |
| test_td3_speed[True-backward] | 4.1981ms | 3.6117ms | 276.8752 Ops/s | 268.1461 Ops/s | $\color{#35bf28}+3.26\%$ |
| test_td3_speed[reduce-overhead-None] | 2.4589ms | 1.7927ms | 557.8195 Ops/s | 522.7137 Ops/s | $\textbf{\color{#35bf28}+6.72\%}$ |
| test_td3_speed[reduce-overhead-backward] | 4.5392ms | 3.7229ms | 268.6102 Ops/s | 264.1867 Ops/s | $\color{#35bf28}+1.67\%$ |
| test_cql_speed[False-None] | 38.8354ms | 36.5939ms | 27.3270 Ops/s | 26.6683 Ops/s | $\color{#35bf28}+2.47\%$ |
| test_cql_speed[False-backward] | 51.2081ms | 46.7147ms | 21.4066 Ops/s | 20.2997 Ops/s | $\textbf{\color{#35bf28}+5.45\%}$ |
| test_cql_speed[True-None] | 17.5906ms | 16.0829ms | 62.1779 Ops/s | 60.2554 Ops/s | $\color{#35bf28}+3.19\%$ |
| test_cql_speed[True-backward] | 24.5772ms | 22.9777ms | 43.5205 Ops/s | 41.4739 Ops/s | $\color{#35bf28}+4.93\%$ |
| test_cql_speed[reduce-overhead-None] | 17.4244ms | 16.2233ms | 61.6399 Ops/s | 60.7618 Ops/s | $\color{#35bf28}+1.45\%$ |
| test_cql_speed[reduce-overhead-backward] | 25.0876ms | 23.2610ms | 42.9904 Ops/s | 42.0090 Ops/s | $\color{#35bf28}+2.34\%$ |
| test_a2c_speed[False-None] | 9.6295ms | 7.8046ms | 128.1303 Ops/s | 123.5481 Ops/s | $\color{#35bf28}+3.71\%$ |
| test_a2c_speed[False-backward] | 17.0822ms | 15.5283ms | 64.3987 Ops/s | 62.0893 Ops/s | $\color{#35bf28}+3.72\%$ |
| test_a2c_speed[True-None] | 5.0903ms | 3.5393ms | 282.5432 Ops/s | 277.8581 Ops/s | $\color{#35bf28}+1.69\%$ |
| test_a2c_speed[True-backward] | 11.6051ms | 10.5083ms | 95.1627 Ops/s | 96.2484 Ops/s | $\color{#d91a1a}-1.13\%$ |
| test_a2c_speed[reduce-overhead-None] | 4.3272ms | 3.5261ms | 283.6010 Ops/s | 280.5099 Ops/s | $\color{#35bf28}+1.10\%$ |
| test_a2c_speed[reduce-overhead-backward] | 11.5530ms | 10.6284ms | 94.0879 Ops/s | 94.3311 Ops/s | $\color{#d91a1a}-0.26\%$ |
| test_ppo_speed[False-None] | 12.2106ms | 8.0571ms | 124.1142 Ops/s | 120.2480 Ops/s | $\color{#35bf28}+3.22\%$ |
| test_ppo_speed[False-backward] | 17.5141ms | 15.8313ms | 63.1658 Ops/s | 60.7827 Ops/s | $\color{#35bf28}+3.92\%$ |
| test_ppo_speed[True-None] | 4.9278ms | 4.0621ms | 246.1752 Ops/s | 241.6064 Ops/s | $\color{#35bf28}+1.89\%$ |
| test_ppo_speed[True-backward] | 13.1255ms | 10.3680ms | 96.4502 Ops/s | 94.7285 Ops/s | $\color{#35bf28}+1.82\%$ |
| test_ppo_speed[reduce-overhead-None] | 4.9222ms | 4.0014ms | 249.9103 Ops/s | 243.8376 Ops/s | $\color{#35bf28}+2.49\%$ |
| test_ppo_speed[reduce-overhead-backward] | 11.2006ms | 10.3180ms | 96.9185 Ops/s | 94.8230 Ops/s | $\color{#35bf28}+2.21\%$ |
| test_reinforce_speed[False-None] | 9.3071ms | 6.8641ms | 145.6858 Ops/s | 145.1098 Ops/s | $\color{#35bf28}+0.40\%$ |
| test_reinforce_speed[False-backward] | 11.5858ms | 10.4039ms | 96.1176 Ops/s | 92.5786 Ops/s | $\color{#35bf28}+3.82\%$ |
| test_reinforce_speed[True-None] | 3.5593ms | 2.8642ms | 349.1388 Ops/s | 345.3139 Ops/s | $\color{#35bf28}+1.11\%$ |
| test_reinforce_speed[True-backward] | 10.1060ms | 9.4347ms | 105.9915 Ops/s | 108.3100 Ops/s | $\color{#d91a1a}-2.14\%$ |
| test_reinforce_speed[reduce-overhead-None] | 3.9202ms | 2.8810ms | 347.1011 Ops/s | 326.4245 Ops/s | $\textbf{\color{#35bf28}+6.33\%}$ |
| test_reinforce_speed[reduce-overhead-backward] | 10.5116ms | 8.9639ms | 111.5586 Ops/s | 103.8653 Ops/s | $\textbf{\color{#35bf28}+7.41\%}$ |
| test_iql_speed[False-None] | 34.7606ms | 32.7634ms | 30.5219 Ops/s | 29.2011 Ops/s | $\color{#35bf28}+4.52\%$ |
| test_iql_speed[False-backward] | 60.9979ms | 46.8514ms | 21.3441 Ops/s | 21.0350 Ops/s | $\color{#35bf28}+1.47\%$ |
| test_iql_speed[True-None] | 12.3925ms | 11.0405ms | 90.5754 Ops/s | 85.7413 Ops/s | $\textbf{\color{#35bf28}+5.64\%}$ |
| test_iql_speed[True-backward] | 23.8164ms | 22.5809ms | 44.2852 Ops/s | 42.5676 Ops/s | $\color{#35bf28}+4.04\%$ |
| test_iql_speed[reduce-overhead-None] | 11.5823ms | 10.5777ms | 94.5383 Ops/s | 85.7446 Ops/s | $\textbf{\color{#35bf28}+10.26\%}$ |
| test_iql_speed[reduce-overhead-backward] | 22.9875ms | 22.0579ms | 45.3353 Ops/s | 42.3445 Ops/s | $\textbf{\color{#35bf28}+7.06\%}$ |
| test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] | 0.2942s | 6.3395ms | 157.7411 Ops/s | 185.8946 Ops/s | $\textbf{\color{#d91a1a}-15.14\%}$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] | 0.7772ms | 0.5108ms | 1.9577 KOps/s | 1.8216 KOps/s | $\textbf{\color{#35bf28}+7.47\%}$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] | 0.6791ms | 0.4808ms | 2.0799 KOps/s | 1.9472 KOps/s | $\textbf{\color{#35bf28}+6.82\%}$ |
| test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] | 5.6091ms | 4.5170ms | 221.3863 Ops/s | 191.3348 Ops/s | $\textbf{\color{#35bf28}+15.71\%}$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] | 2.7160ms | 0.5040ms | 1.9841 KOps/s | 1.9057 KOps/s | $\color{#35bf28}+4.11\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] | 0.7235ms | 0.4854ms | 2.0603 KOps/s | 1.9724 KOps/s | $\color{#35bf28}+4.45\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] | 2.2285ms | 1.6372ms | 610.8018 Ops/s | 568.9939 Ops/s | $\textbf{\color{#35bf28}+7.35\%}$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] | 1.7459ms | 1.5631ms | 639.7410 Ops/s | 611.6682 Ops/s | $\color{#35bf28}+4.59\%$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] | 4.8836ms | 4.6921ms | 213.1241 Ops/s | 185.0106 Ops/s | $\textbf{\color{#35bf28}+15.20\%}$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] | 2.7489ms | 0.6443ms | 1.5520 KOps/s | 1.4500 KOps/s | $\textbf{\color{#35bf28}+7.03\%}$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] | 0.8925ms | 0.6244ms | 1.6016 KOps/s | 1.5336 KOps/s | $\color{#35bf28}+4.43\%$ |
| test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] | 4.8246ms | 4.5635ms | 219.1317 Ops/s | 190.2232 Ops/s | $\textbf{\color{#35bf28}+15.20\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] | 0.7216ms | 0.5044ms | 1.9826 KOps/s | 1.8679 KOps/s | $\textbf{\color{#35bf28}+6.14\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] | 9.6832ms | 0.4981ms | 2.0078 KOps/s | 1.8844 KOps/s | $\textbf{\color{#35bf28}+6.55\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] | 6.0563ms | 4.5703ms | 218.8020 Ops/s | 194.2550 Ops/s | $\textbf{\color{#35bf28}+12.64\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] | 1.2686ms | 0.4990ms | 2.0040 KOps/s | 1.8783 KOps/s | $\textbf{\color{#35bf28}+6.69\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] | 0.7032ms | 0.4776ms | 2.0939 KOps/s | 1.9109 KOps/s | $\textbf{\color{#35bf28}+9.58\%}$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] | 5.8326ms | 4.9503ms | 202.0062 Ops/s | 181.3236 Ops/s | $\textbf{\color{#35bf28}+11.41\%}$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] | 2.2089ms | 0.6544ms | 1.5282 KOps/s | 1.4057 KOps/s | $\textbf{\color{#35bf28}+8.71\%}$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] | 0.8534ms | 0.6238ms | 1.6031 KOps/s | 1.4978 KOps/s | $\textbf{\color{#35bf28}+7.03\%}$ |
| test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] | 6.4531ms | 4.2508ms | 235.2476 Ops/s | 198.7269 Ops/s | $\textbf{\color{#35bf28}+18.38\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] | 8.7573ms | 2.3265ms | 429.8323 Ops/s | 376.0096 Ops/s | $\textbf{\color{#35bf28}+14.31\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] | 1.9020ms | 1.2132ms | 824.2326 Ops/s | 689.2266 Ops/s | $\textbf{\color{#35bf28}+19.59\%}$ |
| test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] | 0.4485s | 13.2490ms | 75.4775 Ops/s | 211.1761 Ops/s | $\textbf{\color{#d91a1a}-64.26\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] | 5.4141ms | 2.2931ms | 436.0994 Ops/s | 414.8709 Ops/s | $\textbf{\color{#35bf28}+5.12\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] | 9.9065ms | 1.4853ms | 673.2629 Ops/s | 766.6496 Ops/s | $\textbf{\color{#d91a1a}-12.18\%}$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] | 6.1586ms | 4.4167ms | 226.4116 Ops/s | 203.1433 Ops/s | $\textbf{\color{#35bf28}+11.45\%}$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] | 7.4490ms | 2.5195ms | 396.9068 Ops/s | 361.6854 Ops/s | $\textbf{\color{#35bf28}+9.74\%}$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] | 5.3527ms | 1.4525ms | 688.4911 Ops/s | 690.8159 Ops/s | $\color{#d91a1a}-0.34\%$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] | 12.2324ms | 10.7523ms | 93.0030 Ops/s | 82.9034 Ops/s | $\textbf{\color{#35bf28}+12.18\%}$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] | 16.0720ms | 14.2550ms | 70.1510 Ops/s | 66.6155 Ops/s | $\textbf{\color{#35bf28}+5.31\%}$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] | 22.9903ms | 20.0294ms | 49.9266 Ops/s | 48.5468 Ops/s | $\color{#35bf28}+2.84\%$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] | 16.0585ms | 14.3655ms | 69.6113 Ops/s | 67.0055 Ops/s | $\color{#35bf28}+3.89\%$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] | 20.3580ms | 19.8613ms | 50.3491 Ops/s | 48.7337 Ops/s | $\color{#35bf28}+3.31\%$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] | 16.7875ms | 15.5238ms | 64.4173 Ops/s | 63.2262 Ops/s | $\color{#35bf28}+1.88\%$ |
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
$\color{#D29922}\textsf{\Large⚠\kern{0.2cm}\normalsize Warning}$ Result of GPU Benchmark Tests
Total Benchmarks: 149. Improved: $\large\color{#35bf28}8$. Worsened: $\large\color{#d91a1a}9$.
Expand to view detailed results
| Name | Max | Mean | Ops | Ops on Repo HEAD |
Change |
|---|---|---|---|---|---|
| test_simple | 0.7286s | 0.7279s | 1.3737 Ops/s | 1.3721 Ops/s | $\color{#35bf28}+0.12\%$ |
| test_transformed | 1.0681s | 0.9896s | 1.0106 Ops/s | 1.0362 Ops/s | $\color{#d91a1a}-2.47\%$ |
| test_serial | 2.1792s | 2.1014s | 0.4759 Ops/s | 0.4810 Ops/s | $\color{#d91a1a}-1.06\%$ |
| test_parallel | 1.9972s | 1.9936s | 0.5016 Ops/s | 0.5257 Ops/s | $\color{#d91a1a}-4.59\%$ |
| test_step_mdp_speed[True-True-True-True-True] | 0.2049ms | 34.7258μs | 28.7970 KOps/s | 28.9136 KOps/s | $\color{#d91a1a}-0.40\%$ |
| test_step_mdp_speed[True-True-True-True-False] | 49.2410μs | 19.9635μs | 50.0913 KOps/s | 51.5501 KOps/s | $\color{#d91a1a}-2.83\%$ |
| test_step_mdp_speed[True-True-True-False-True] | 83.8010μs | 18.7479μs | 53.3392 KOps/s | 52.8384 KOps/s | $\color{#35bf28}+0.95\%$ |
| test_step_mdp_speed[True-True-True-False-False] | 43.9810μs | 11.0564μs | 90.4450 KOps/s | 90.6510 KOps/s | $\color{#d91a1a}-0.23\%$ |
| test_step_mdp_speed[True-True-False-True-True] | 69.3610μs | 37.0689μs | 26.9768 KOps/s | 27.2385 KOps/s | $\color{#d91a1a}-0.96\%$ |
| test_step_mdp_speed[True-True-False-True-False] | 47.5400μs | 21.2645μs | 47.0267 KOps/s | 47.1041 KOps/s | $\color{#d91a1a}-0.16\%$ |
| test_step_mdp_speed[True-True-False-False-True] | 51.7800μs | 21.4735μs | 46.5690 KOps/s | 48.5441 KOps/s | $\color{#d91a1a}-4.07\%$ |
| test_step_mdp_speed[True-True-False-False-False] | 40.6710μs | 12.9119μs | 77.4479 KOps/s | 77.4364 KOps/s | $\color{#35bf28}+0.01\%$ |
| test_step_mdp_speed[True-False-True-True-True] | 69.2610μs | 39.6029μs | 25.2506 KOps/s | 26.1920 KOps/s | $\color{#d91a1a}-3.59\%$ |
| test_step_mdp_speed[True-False-True-True-False] | 51.5710μs | 23.5794μs | 42.4099 KOps/s | 43.6213 KOps/s | $\color{#d91a1a}-2.78\%$ |
| test_step_mdp_speed[True-False-True-False-True] | 58.8110μs | 21.5213μs | 46.4656 KOps/s | 48.3577 KOps/s | $\color{#d91a1a}-3.91\%$ |
| test_step_mdp_speed[True-False-True-False-False] | 47.5010μs | 13.2035μs | 75.7377 KOps/s | 78.5781 KOps/s | $\color{#d91a1a}-3.61\%$ |
| test_step_mdp_speed[True-False-False-True-True] | 79.9610μs | 41.1522μs | 24.3001 KOps/s | 25.1802 KOps/s | $\color{#d91a1a}-3.50\%$ |
| test_step_mdp_speed[True-False-False-True-False] | 57.1100μs | 25.3187μs | 39.4966 KOps/s | 40.3076 KOps/s | $\color{#d91a1a}-2.01\%$ |
| test_step_mdp_speed[True-False-False-False-True] | 54.9800μs | 23.0066μs | 43.4657 KOps/s | 44.9615 KOps/s | $\color{#d91a1a}-3.33\%$ |
| test_step_mdp_speed[True-False-False-False-False] | 41.8100μs | 14.8846μs | 67.1837 KOps/s | 67.9270 KOps/s | $\color{#d91a1a}-1.09\%$ |
| test_step_mdp_speed[False-True-True-True-True] | 71.7400μs | 39.0630μs | 25.5996 KOps/s | 26.2077 KOps/s | $\color{#d91a1a}-2.32\%$ |
| test_step_mdp_speed[False-True-True-True-False] | 59.5410μs | 23.6476μs | 42.2876 KOps/s | 42.9214 KOps/s | $\color{#d91a1a}-1.48\%$ |
| test_step_mdp_speed[False-True-True-False-True] | 53.0510μs | 24.5029μs | 40.8115 KOps/s | 40.1501 KOps/s | $\color{#35bf28}+1.65\%$ |
| test_step_mdp_speed[False-True-True-False-False] | 39.2110μs | 14.6853μs | 68.0952 KOps/s | 68.9531 KOps/s | $\color{#d91a1a}-1.24\%$ |
| test_step_mdp_speed[False-True-False-True-True] | 69.6010μs | 40.5747μs | 24.6459 KOps/s | 24.9245 KOps/s | $\color{#d91a1a}-1.12\%$ |
| test_step_mdp_speed[False-True-False-True-False] | 52.1910μs | 25.4193μs | 39.3402 KOps/s | 40.5884 KOps/s | $\color{#d91a1a}-3.08\%$ |
| test_step_mdp_speed[False-True-False-False-True] | 3.4930ms | 27.2551μs | 36.6903 KOps/s | 37.7333 KOps/s | $\color{#d91a1a}-2.76\%$ |
| test_step_mdp_speed[False-True-False-False-False] | 43.8300μs | 16.9068μs | 59.1477 KOps/s | 61.7000 KOps/s | $\color{#d91a1a}-4.14\%$ |
| test_step_mdp_speed[False-False-True-True-True] | 73.5000μs | 42.3158μs | 23.6318 KOps/s | 24.0459 KOps/s | $\color{#d91a1a}-1.72\%$ |
| test_step_mdp_speed[False-False-True-True-False] | 53.6400μs | 27.3257μs | 36.5956 KOps/s | 36.7066 KOps/s | $\color{#d91a1a}-0.30\%$ |
| test_step_mdp_speed[False-False-True-False-True] | 56.2310μs | 26.7089μs | 37.4407 KOps/s | 38.1970 KOps/s | $\color{#d91a1a}-1.98\%$ |
| test_step_mdp_speed[False-False-True-False-False] | 46.1210μs | 16.5117μs | 60.5633 KOps/s | 61.5854 KOps/s | $\color{#d91a1a}-1.66\%$ |
| test_step_mdp_speed[False-False-False-True-True] | 76.2410μs | 44.2369μs | 22.6056 KOps/s | 23.3142 KOps/s | $\color{#d91a1a}-3.04\%$ |
| test_step_mdp_speed[False-False-False-True-False] | 57.2210μs | 29.3359μs | 34.0879 KOps/s | 34.9522 KOps/s | $\color{#d91a1a}-2.47\%$ |
| test_step_mdp_speed[False-False-False-False-True] | 54.4000μs | 28.6382μs | 34.9183 KOps/s | 36.6510 KOps/s | $\color{#d91a1a}-4.73\%$ |
| test_step_mdp_speed[False-False-False-False-False] | 47.1510μs | 18.0802μs | 55.3090 KOps/s | 55.7790 KOps/s | $\color{#d91a1a}-0.84\%$ |
| test_values[generalized_advantage_estimate-True-True] | 24.3748ms | 23.9335ms | 41.7824 Ops/s | 42.2228 Ops/s | $\color{#d91a1a}-1.04\%$ |
| test_values[vec_generalized_advantage_estimate-True-True] | 0.1115s | 3.1097ms | 321.5768 Ops/s | 365.1540 Ops/s | $\textbf{\color{#d91a1a}-11.93\%}$ |
| test_values[td0_return_estimate-False-False] | 87.1010μs | 64.6578μs | 15.4660 KOps/s | 15.5472 KOps/s | $\color{#d91a1a}-0.52\%$ |
| test_values[td1_return_estimate-False-False] | 53.9480ms | 53.6241ms | 18.6483 Ops/s | 18.9170 Ops/s | $\color{#d91a1a}-1.42\%$ |
| test_values[vec_td1_return_estimate-False-False] | 1.2190ms | 1.0553ms | 947.6228 Ops/s | 939.2463 Ops/s | $\color{#35bf28}+0.89\%$ |
| test_values[td_lambda_return_estimate-True-False] | 90.1223ms | 86.1942ms | 11.6017 Ops/s | 11.8834 Ops/s | $\color{#d91a1a}-2.37\%$ |
| test_values[vec_td_lambda_return_estimate-True-False] | 1.1658ms | 1.0535ms | 949.1778 Ops/s | 943.9986 Ops/s | $\color{#35bf28}+0.55\%$ |
| test_gae_speed[generalized_advantage_estimate-False-1-512] | 23.9723ms | 23.7435ms | 42.1169 Ops/s | 43.1787 Ops/s | $\color{#d91a1a}-2.46\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-True-1-512] | 1.0011ms | 0.7241ms | 1.3810 KOps/s | 1.3822 KOps/s | $\color{#d91a1a}-0.09\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-False-1-512] | 0.7475ms | 0.6432ms | 1.5546 KOps/s | 1.5579 KOps/s | $\color{#d91a1a}-0.21\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-True-32-512] | 1.4971ms | 1.4549ms | 687.3142 Ops/s | 687.2545 Ops/s | $+0.01\%$ |
| test_gae_speed[vec_generalized_advantage_estimate-False-32-512] | 0.8020ms | 0.6571ms | 1.5218 KOps/s | 1.5033 KOps/s | $\color{#35bf28}+1.23\%$ |
| test_dqn_speed[False-None] | 7.0179ms | 1.2661ms | 789.8298 Ops/s | 784.0219 Ops/s | $\color{#35bf28}+0.74\%$ |
| test_dqn_speed[False-backward] | 1.7903ms | 1.7463ms | 572.6533 Ops/s | 568.4858 Ops/s | $\color{#35bf28}+0.73\%$ |
| test_dqn_speed[True-None] | 0.9675ms | 0.5375ms | 1.8603 KOps/s | 1.7994 KOps/s | $\color{#35bf28}+3.38\%$ |
| test_dqn_speed[True-backward] | 1.0126ms | 0.9668ms | 1.0343 KOps/s | 946.7806 Ops/s | $\textbf{\color{#35bf28}+9.25\%}$ |
| test_dqn_speed[reduce-overhead-None] | 0.5867ms | 0.5311ms | 1.8828 KOps/s | 1.8553 KOps/s | $\color{#35bf28}+1.48\%$ |
| test_dqn_speed[reduce-overhead-backward] | 1.0251ms | 0.9743ms | 1.0264 KOps/s | 1.0326 KOps/s | $\color{#d91a1a}-0.60\%$ |
| test_ddpg_speed[False-None] | 3.1383ms | 2.6136ms | 382.6073 Ops/s | 385.6673 Ops/s | $\color{#d91a1a}-0.79\%$ |
| test_ddpg_speed[False-backward] | 3.9712ms | 3.8307ms | 261.0484 Ops/s | 264.9819 Ops/s | $\color{#d91a1a}-1.48\%$ |
| test_ddpg_speed[True-None] | 1.3695ms | 1.2172ms | 821.5798 Ops/s | 839.6793 Ops/s | $\color{#d91a1a}-2.16\%$ |
| test_ddpg_speed[True-backward] | 2.1841ms | 2.1171ms | 472.3480 Ops/s | 468.1631 Ops/s | $\color{#35bf28}+0.89\%$ |
| test_ddpg_speed[reduce-overhead-None] | 1.3489ms | 1.2138ms | 823.8304 Ops/s | 844.7377 Ops/s | $\color{#d91a1a}-2.47\%$ |
| test_ddpg_speed[reduce-overhead-backward] | 2.2601ms | 2.1603ms | 462.9046 Ops/s | 465.2752 Ops/s | $\color{#d91a1a}-0.51\%$ |
| test_sac_speed[False-None] | 8.6131ms | 7.3442ms | 136.1622 Ops/s | 135.6384 Ops/s | $\color{#35bf28}+0.39\%$ |
| test_sac_speed[False-backward] | 10.9993ms | 10.5470ms | 94.8141 Ops/s | 95.6655 Ops/s | $\color{#d91a1a}-0.89\%$ |
| test_sac_speed[True-None] | 2.0789ms | 1.9348ms | 516.8616 Ops/s | 509.8830 Ops/s | $\color{#35bf28}+1.37\%$ |
| test_sac_speed[True-backward] | 3.9143ms | 3.7870ms | 264.0610 Ops/s | 257.9257 Ops/s | $\color{#35bf28}+2.38\%$ |
| test_sac_speed[reduce-overhead-None] | 2.0108ms | 1.9473ms | 513.5232 Ops/s | 508.3856 Ops/s | $\color{#35bf28}+1.01\%$ |
| test_sac_speed[reduce-overhead-backward] | 3.8934ms | 3.7868ms | 264.0763 Ops/s | 264.4901 Ops/s | $\color{#d91a1a}-0.16\%$ |
| test_redq_speed[False-None] | 15.5756ms | 10.4191ms | 95.9779 Ops/s | 96.9931 Ops/s | $\color{#d91a1a}-1.05\%$ |
| test_redq_speed[False-backward] | 18.1935ms | 17.0474ms | 58.6601 Ops/s | 58.9964 Ops/s | $\color{#d91a1a}-0.57\%$ |
| test_redq_speed[True-None] | 4.6840ms | 3.5802ms | 279.3155 Ops/s | 281.1095 Ops/s | $\color{#d91a1a}-0.64\%$ |
| test_redq_speed[True-backward] | 8.7835ms | 8.3430ms | 119.8606 Ops/s | 119.2929 Ops/s | $\color{#35bf28}+0.48\%$ |
| test_redq_speed[reduce-overhead-None] | 3.7029ms | 3.4563ms | 289.3258 Ops/s | 283.6572 Ops/s | $\color{#35bf28}+2.00\%$ |
| test_redq_speed[reduce-overhead-backward] | 8.5833ms | 8.2799ms | 120.7741 Ops/s | 121.5435 Ops/s | $\color{#d91a1a}-0.63\%$ |
| test_redq_deprec_speed[False-None] | 10.6298ms | 10.2246ms | 97.8037 Ops/s | 97.7253 Ops/s | $\color{#35bf28}+0.08\%$ |
| test_redq_deprec_speed[False-backward] | 15.5105ms | 14.9869ms | 66.7248 Ops/s | 67.0983 Ops/s | $\color{#d91a1a}-0.56\%$ |
| test_redq_deprec_speed[True-None] | 3.4007ms | 3.1018ms | 322.3966 Ops/s | 314.9657 Ops/s | $\color{#35bf28}+2.36\%$ |
| test_redq_deprec_speed[True-backward] | 6.9968ms | 6.8093ms | 146.8585 Ops/s | 144.9326 Ops/s | $\color{#35bf28}+1.33\%$ |
| test_redq_deprec_speed[reduce-overhead-None] | 3.2459ms | 3.0607ms | 326.7215 Ops/s | 321.5817 Ops/s | $\color{#35bf28}+1.60\%$ |
| test_redq_deprec_speed[reduce-overhead-backward] | 6.9107ms | 6.7720ms | 147.6662 Ops/s | 145.3528 Ops/s | $\color{#35bf28}+1.59\%$ |
| test_td3_speed[False-None] | 7.4057ms | 7.2389ms | 138.1417 Ops/s | 136.7138 Ops/s | $\color{#35bf28}+1.04\%$ |
| test_td3_speed[False-backward] | 10.2857ms | 9.9673ms | 100.3278 Ops/s | 98.0766 Ops/s | $\color{#35bf28}+2.30\%$ |
| test_td3_speed[True-None] | 1.8734ms | 1.8244ms | 548.1227 Ops/s | 540.0253 Ops/s | $\color{#35bf28}+1.50\%$ |
| test_td3_speed[True-backward] | 3.6597ms | 3.5718ms | 279.9726 Ops/s | 284.3610 Ops/s | $\color{#d91a1a}-1.54\%$ |
| test_td3_speed[reduce-overhead-None] | 1.8354ms | 1.8172ms | 550.2822 Ops/s | 547.1646 Ops/s | $\color{#35bf28}+0.57\%$ |
| test_td3_speed[reduce-overhead-backward] | 3.6846ms | 3.5492ms | 281.7566 Ops/s | 283.7609 Ops/s | $\color{#d91a1a}-0.71\%$ |
| test_cql_speed[False-None] | 26.9162ms | 24.2272ms | 41.2759 Ops/s | 41.3083 Ops/s | $\color{#d91a1a}-0.08\%$ |
| test_cql_speed[False-backward] | 37.1559ms | 33.5715ms | 29.7871 Ops/s | 29.8601 Ops/s | $\color{#d91a1a}-0.24\%$ |
| test_cql_speed[True-None] | 11.0242ms | 10.5856ms | 94.4683 Ops/s | 94.0907 Ops/s | $\color{#35bf28}+0.40\%$ |
| test_cql_speed[True-backward] | 16.5679ms | 16.2257ms | 61.6306 Ops/s | 62.0915 Ops/s | $\color{#d91a1a}-0.74\%$ |
| test_cql_speed[reduce-overhead-None] | 11.1548ms | 10.6072ms | 94.2758 Ops/s | 94.9085 Ops/s | $\color{#d91a1a}-0.67\%$ |
| test_cql_speed[reduce-overhead-backward] | 16.5530ms | 16.2033ms | 61.7160 Ops/s | 61.8536 Ops/s | $\color{#d91a1a}-0.22\%$ |
| test_a2c_speed[False-None] | 5.4647ms | 5.1898ms | 192.6874 Ops/s | 184.1644 Ops/s | $\color{#35bf28}+4.63\%$ |
| test_a2c_speed[False-backward] | 11.8465ms | 11.4028ms | 87.6977 Ops/s | 84.9999 Ops/s | $\color{#35bf28}+3.17\%$ |
| test_a2c_speed[True-None] | 3.1841ms | 2.9949ms | 333.9027 Ops/s | 339.0857 Ops/s | $\color{#d91a1a}-1.53\%$ |
| test_a2c_speed[True-backward] | 8.5723ms | 8.2670ms | 120.9632 Ops/s | 122.5143 Ops/s | $\color{#d91a1a}-1.27\%$ |
| test_a2c_speed[reduce-overhead-None] | 3.3518ms | 2.9647ms | 337.2976 Ops/s | 337.3748 Ops/s | $\color{#d91a1a}-0.02\%$ |
| test_a2c_speed[reduce-overhead-backward] | 8.7969ms | 8.2288ms | 121.5242 Ops/s | 121.6607 Ops/s | $\color{#d91a1a}-0.11\%$ |
| test_ppo_speed[False-None] | 5.8325ms | 5.5693ms | 179.5542 Ops/s | 177.6159 Ops/s | $\color{#35bf28}+1.09\%$ |
| test_ppo_speed[False-backward] | 12.5600ms | 12.0218ms | 83.1823 Ops/s | 84.2190 Ops/s | $\color{#d91a1a}-1.23\%$ |
| test_ppo_speed[True-None] | 3.7066ms | 3.4053ms | 293.6572 Ops/s | 283.9612 Ops/s | $\color{#35bf28}+3.41\%$ |
| test_ppo_speed[True-backward] | 8.3804ms | 7.9904ms | 125.1505 Ops/s | 125.7627 Ops/s | $\color{#d91a1a}-0.49\%$ |
| test_ppo_speed[reduce-overhead-None] | 4.0139ms | 3.4064ms | 293.5685 Ops/s | 297.6568 Ops/s | $\color{#d91a1a}-1.37\%$ |
| test_ppo_speed[reduce-overhead-backward] | 8.4718ms | 8.0988ms | 123.4752 Ops/s | 124.6265 Ops/s | $\color{#d91a1a}-0.92\%$ |
| test_reinforce_speed[False-None] | 6.1327ms | 4.4199ms | 226.2498 Ops/s | 231.7829 Ops/s | $\color{#d91a1a}-2.39\%$ |
| test_reinforce_speed[False-backward] | 7.5598ms | 7.2681ms | 137.5885 Ops/s | 139.4466 Ops/s | $\color{#d91a1a}-1.33\%$ |
| test_reinforce_speed[True-None] | 2.3719ms | 2.1790ms | 458.9329 Ops/s | 456.6428 Ops/s | $\color{#35bf28}+0.50\%$ |
| test_reinforce_speed[True-backward] | 7.1758ms | 6.9475ms | 143.9367 Ops/s | 136.6472 Ops/s | $\textbf{\color{#35bf28}+5.33\%}$ |
| test_reinforce_speed[reduce-overhead-None] | 2.4598ms | 2.2000ms | 454.5547 Ops/s | 462.7889 Ops/s | $\color{#d91a1a}-1.78\%$ |
| test_reinforce_speed[reduce-overhead-backward] | 7.1495ms | 6.9505ms | 143.8737 Ops/s | 145.0498 Ops/s | $\color{#d91a1a}-0.81\%$ |
| test_iql_speed[False-None] | 0.2814s | 24.2606ms | 41.2190 Ops/s | 52.0009 Ops/s | $\textbf{\color{#d91a1a}-20.73\%}$ |
| test_iql_speed[False-backward] | 30.5241ms | 29.7801ms | 33.5795 Ops/s | 33.7658 Ops/s | $\color{#d91a1a}-0.55\%$ |
| test_iql_speed[True-None] | 6.9160ms | 6.5845ms | 151.8709 Ops/s | 151.3946 Ops/s | $\color{#35bf28}+0.31\%$ |
| test_iql_speed[True-backward] | 15.4468ms | 15.1085ms | 66.1879 Ops/s | 67.9051 Ops/s | $\color{#d91a1a}-2.53\%$ |
| test_iql_speed[reduce-overhead-None] | 6.9316ms | 6.6132ms | 151.2136 Ops/s | 153.5599 Ops/s | $\color{#d91a1a}-1.53\%$ |
| test_iql_speed[reduce-overhead-backward] | 15.4245ms | 15.1013ms | 66.2197 Ops/s | 68.1863 Ops/s | $\color{#d91a1a}-2.88\%$ |
| test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] | 6.1648ms | 6.0529ms | 165.2088 Ops/s | 161.7159 Ops/s | $\color{#35bf28}+2.16\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] | 1.5957ms | 0.3501ms | 2.8563 KOps/s | 3.0552 KOps/s | $\textbf{\color{#d91a1a}-6.51\%}$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] | 0.5044ms | 0.3316ms | 3.0154 KOps/s | 3.2605 KOps/s | $\textbf{\color{#d91a1a}-7.52\%}$ |
| test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] | 5.9810ms | 5.6972ms | 175.5237 Ops/s | 170.3430 Ops/s | $\color{#35bf28}+3.04\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] | 1.2438ms | 0.2753ms | 3.6323 KOps/s | 3.2523 KOps/s | $\textbf{\color{#35bf28}+11.69\%}$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] | 0.4734ms | 0.2573ms | 3.8861 KOps/s | 3.7746 KOps/s | $\color{#35bf28}+2.95\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] | 1.5916ms | 1.3193ms | 757.9730 Ops/s | 787.1631 Ops/s | $\color{#d91a1a}-3.71\%$ |
| test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] | 1.4631ms | 1.2302ms | 812.8656 Ops/s | 824.4037 Ops/s | $\color{#d91a1a}-1.40\%$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] | 6.2536ms | 5.9974ms | 166.7384 Ops/s | 164.6836 Ops/s | $\color{#35bf28}+1.25\%$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] | 1.3603ms | 0.4659ms | 2.1464 KOps/s | 2.2513 KOps/s | $\color{#d91a1a}-4.66\%$ |
| test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] | 0.6708ms | 0.4418ms | 2.2637 KOps/s | 2.2581 KOps/s | $\color{#35bf28}+0.25\%$ |
| test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] | 6.0188ms | 5.9081ms | 169.2596 Ops/s | 168.0786 Ops/s | $\color{#35bf28}+0.70\%$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] | 0.8354ms | 0.2666ms | 3.7506 KOps/s | 2.7277 KOps/s | $\textbf{\color{#35bf28}+37.50\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] | 0.4689ms | 0.2443ms | 4.0926 KOps/s | 2.8869 KOps/s | $\textbf{\color{#35bf28}+41.76\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] | 6.1858ms | 5.8649ms | 170.5067 Ops/s | 170.0106 Ops/s | $\color{#35bf28}+0.29\%$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] | 0.8637ms | 0.3174ms | 3.1505 KOps/s | 3.8432 KOps/s | $\textbf{\color{#d91a1a}-18.03\%}$ |
| test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] | 0.4955ms | 0.2904ms | 3.4435 KOps/s | 4.2953 KOps/s | $\textbf{\color{#d91a1a}-19.83\%}$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] | 6.1138ms | 5.9889ms | 166.9742 Ops/s | 164.4917 Ops/s | $\color{#35bf28}+1.51\%$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] | 0.7324ms | 0.5114ms | 1.9553 KOps/s | 1.9994 KOps/s | $\color{#d91a1a}-2.20\%$ |
| test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] | 7.0500ms | 0.4755ms | 2.1031 KOps/s | 2.1113 KOps/s | $\color{#d91a1a}-0.39\%$ |
| test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] | 0.4026s | 13.1482ms | 76.0558 Ops/s | 194.9902 Ops/s | $\textbf{\color{#d91a1a}-61.00\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] | 8.2258ms | 1.9406ms | 515.3131 Ops/s | 445.7439 Ops/s | $\textbf{\color{#35bf28}+15.61\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] | 1.9959ms | 1.0069ms | 993.1840 Ops/s | 875.9073 Ops/s | $\textbf{\color{#35bf28}+13.39\%}$ |
| test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] | 7.3363ms | 5.1924ms | 192.5880 Ops/s | 34.1774 Ops/s | $\textbf{\color{#35bf28}+463.50\%}$ |
| test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] | 8.5838ms | 1.9986ms | 500.3416 Ops/s | 481.5828 Ops/s | $\color{#35bf28}+3.90\%$ |
| test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] | 7.1024ms | 1.2262ms | 815.5073 Ops/s | 904.4948 Ops/s | $\textbf{\color{#d91a1a}-9.84\%}$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] | 0.3930s | 13.1948ms | 75.7872 Ops/s | 178.9121 Ops/s | $\textbf{\color{#d91a1a}-57.64\%}$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] | 11.7607ms | 2.0670ms | 483.7847 Ops/s | 470.2621 Ops/s | $\color{#35bf28}+2.88\%$ |
| test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] | 7.1873ms | 1.3824ms | 723.3943 Ops/s | 696.9961 Ops/s | $\color{#35bf28}+3.79\%$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] | 13.2937ms | 12.3563ms | 80.9307 Ops/s | 79.1722 Ops/s | $\color{#35bf28}+2.22\%$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] | 17.0788ms | 16.0077ms | 62.4701 Ops/s | 62.6509 Ops/s | $\color{#d91a1a}-0.29\%$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] | 17.0114ms | 16.8332ms | 59.4063 Ops/s | 57.7063 Ops/s | $\color{#35bf28}+2.95\%$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] | 18.0166ms | 16.3712ms | 61.0827 Ops/s | 61.0057 Ops/s | $\color{#35bf28}+0.13\%$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] | 17.1325ms | 16.6525ms | 60.0510 Ops/s | 58.1581 Ops/s | $\color{#35bf28}+3.25\%$ |
| test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] | 18.5467ms | 17.4681ms | 57.2473 Ops/s | 57.2478 Ops/s | $-0.00\%$ |