Skip to content

Conversation

@vmoens
Copy link
Collaborator

@vmoens vmoens commented Oct 31, 2024

No description provided.

@pytorch-bot
Copy link

pytorch-bot bot commented Oct 31, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2531

Note: Links to docs will display an error until the docs builds have been completed.

❌ 2 New Failures, 4 Unrelated Failures

As of commit 62842f1 with merge base c851e16 (image):

NEW FAILURES - The following jobs have failed:

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@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 Oct 31, 2024
@vmoens vmoens added the documentation Improvements or additions to documentation label Oct 31, 2024
@vmoens vmoens linked an issue Oct 31, 2024 that may be closed by this pull request
2 tasks
@vmoens vmoens merged commit edbf3de into main Oct 31, 2024
59 of 61 checks passed
@vmoens vmoens deleted the fix-module-doc branch October 31, 2024 10:18
@github-actions
Copy link

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

Total Benchmarks: 145. Improved: $\large\color{#35bf28}7$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4175s 0.4157s 2.4058 Ops/s 2.2418 Ops/s $\textbf{\color{#35bf28}+7.32\%}$
test_transformed 0.5874s 0.5828s 1.7158 Ops/s 1.6799 Ops/s $\color{#35bf28}+2.14\%$
test_serial 1.3032s 1.2934s 0.7731 Ops/s 0.7471 Ops/s $\color{#35bf28}+3.48\%$
test_parallel 1.2635s 1.2532s 0.7979 Ops/s 0.7802 Ops/s $\color{#35bf28}+2.28\%$
test_step_mdp_speed[True-True-True-True-True] 0.2479ms 26.7496μs 37.3838 KOps/s 36.9418 KOps/s $\color{#35bf28}+1.20\%$
test_step_mdp_speed[True-True-True-True-False] 42.8900μs 15.6617μs 63.8501 KOps/s 61.7428 KOps/s $\color{#35bf28}+3.41\%$
test_step_mdp_speed[True-True-True-False-True] 66.2430μs 15.1643μs 65.9442 KOps/s 63.4265 KOps/s $\color{#35bf28}+3.97\%$
test_step_mdp_speed[True-True-True-False-False] 30.6270μs 8.8443μs 113.0670 KOps/s 108.3936 KOps/s $\color{#35bf28}+4.31\%$
test_step_mdp_speed[True-True-False-True-True] 81.6820μs 28.4731μs 35.1209 KOps/s 33.6576 KOps/s $\color{#35bf28}+4.35\%$
test_step_mdp_speed[True-True-False-True-False] 42.8900μs 17.2904μs 57.8356 KOps/s 55.3106 KOps/s $\color{#35bf28}+4.57\%$
test_step_mdp_speed[True-True-False-False-True] 68.9180μs 16.8061μs 59.5023 KOps/s 57.8331 KOps/s $\color{#35bf28}+2.89\%$
test_step_mdp_speed[True-True-False-False-False] 39.5130μs 10.5546μs 94.7452 KOps/s 91.7306 KOps/s $\color{#35bf28}+3.29\%$
test_step_mdp_speed[True-False-True-True-True] 85.6290μs 30.2695μs 33.0365 KOps/s 32.3365 KOps/s $\color{#35bf28}+2.16\%$
test_step_mdp_speed[True-False-True-True-False] 69.7790μs 19.2983μs 51.8179 KOps/s 51.3350 KOps/s $\color{#35bf28}+0.94\%$
test_step_mdp_speed[True-False-True-False-True] 54.4620μs 16.9201μs 59.1014 KOps/s 58.5211 KOps/s $\color{#35bf28}+0.99\%$
test_step_mdp_speed[True-False-True-False-False] 45.8250μs 10.4268μs 95.9064 KOps/s 91.6067 KOps/s $\color{#35bf28}+4.69\%$
test_step_mdp_speed[True-False-False-True-True] 83.3550μs 31.8407μs 31.4063 KOps/s 31.3864 KOps/s $\color{#35bf28}+0.06\%$
test_step_mdp_speed[True-False-False-True-False] 75.4100μs 20.6858μs 48.3423 KOps/s 47.3379 KOps/s $\color{#35bf28}+2.12\%$
test_step_mdp_speed[True-False-False-False-True] 65.9630μs 18.3936μs 54.3667 KOps/s 52.9620 KOps/s $\color{#35bf28}+2.65\%$
test_step_mdp_speed[True-False-False-False-False] 33.0010μs 12.0890μs 82.7197 KOps/s 81.4121 KOps/s $\color{#35bf28}+1.61\%$
test_step_mdp_speed[False-True-True-True-True] 59.8410μs 30.6161μs 32.6626 KOps/s 32.4476 KOps/s $\color{#35bf28}+0.66\%$
test_step_mdp_speed[False-True-True-True-False] 86.8290μs 18.8230μs 53.1266 KOps/s 50.9617 KOps/s $\color{#35bf28}+4.25\%$
test_step_mdp_speed[False-True-True-False-True] 64.5800μs 19.0132μs 52.5949 KOps/s 50.3682 KOps/s $\color{#35bf28}+4.42\%$
test_step_mdp_speed[False-True-True-False-False] 39.8340μs 11.8796μs 84.1782 KOps/s 82.4267 KOps/s $\color{#35bf28}+2.12\%$
test_step_mdp_speed[False-True-False-True-True] 81.6620μs 31.6668μs 31.5788 KOps/s 31.0347 KOps/s $\color{#35bf28}+1.75\%$
test_step_mdp_speed[False-True-False-True-False] 73.4670μs 20.4850μs 48.8161 KOps/s 48.0189 KOps/s $\color{#35bf28}+1.66\%$
test_step_mdp_speed[False-True-False-False-True] 2.9130ms 20.7024μs 48.3036 KOps/s 47.2985 KOps/s $\color{#35bf28}+2.13\%$
test_step_mdp_speed[False-True-False-False-False] 58.7190μs 13.3353μs 74.9890 KOps/s 73.1987 KOps/s $\color{#35bf28}+2.45\%$
test_step_mdp_speed[False-False-True-True-True] 0.1643ms 34.3567μs 29.1064 KOps/s 29.4615 KOps/s $\color{#d91a1a}-1.21\%$
test_step_mdp_speed[False-False-True-True-False] 70.8120μs 22.2981μs 44.8468 KOps/s 44.2693 KOps/s $\color{#35bf28}+1.30\%$
test_step_mdp_speed[False-False-True-False-True] 76.2510μs 20.7556μs 48.1797 KOps/s 47.9095 KOps/s $\color{#35bf28}+0.56\%$
test_step_mdp_speed[False-False-True-False-False] 50.8950μs 13.3530μs 74.8893 KOps/s 73.1576 KOps/s $\color{#35bf28}+2.37\%$
test_step_mdp_speed[False-False-False-True-True] 80.2290μs 34.7455μs 28.7807 KOps/s 28.2348 KOps/s $\color{#35bf28}+1.93\%$
test_step_mdp_speed[False-False-False-True-False] 53.2500μs 23.7399μs 42.1232 KOps/s 41.4036 KOps/s $\color{#35bf28}+1.74\%$
test_step_mdp_speed[False-False-False-False-True] 72.8730μs 22.1410μs 45.1650 KOps/s 43.8101 KOps/s $\color{#35bf28}+3.09\%$
test_step_mdp_speed[False-False-False-False-False] 65.0200μs 14.8266μs 67.4463 KOps/s 65.3272 KOps/s $\color{#35bf28}+3.24\%$
test_values[generalized_advantage_estimate-True-True] 9.8441ms 9.5699ms 104.4939 Ops/s 101.4467 Ops/s $\color{#35bf28}+3.00\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.6713ms 35.6069ms 28.0844 Ops/s 29.7202 Ops/s $\textbf{\color{#d91a1a}-5.50\%}$
test_values[td0_return_estimate-False-False] 0.2834ms 0.1742ms 5.7410 KOps/s 5.7700 KOps/s $\color{#d91a1a}-0.50\%$
test_values[td1_return_estimate-False-False] 28.5344ms 24.3790ms 41.0189 Ops/s 41.0999 Ops/s $\color{#d91a1a}-0.20\%$
test_values[vec_td1_return_estimate-False-False] 38.0894ms 35.7072ms 28.0056 Ops/s 29.7987 Ops/s $\textbf{\color{#d91a1a}-6.02\%}$
test_values[td_lambda_return_estimate-True-False] 37.2795ms 34.5491ms 28.9443 Ops/s 28.3998 Ops/s $\color{#35bf28}+1.92\%$
test_values[vec_td_lambda_return_estimate-True-False] 38.2468ms 35.7704ms 27.9561 Ops/s 29.6835 Ops/s $\textbf{\color{#d91a1a}-5.82\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.5743ms 8.2964ms 120.5337 Ops/s 117.8519 Ops/s $\color{#35bf28}+2.28\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.6794ms 2.0317ms 492.1988 Ops/s 510.5232 Ops/s $\color{#d91a1a}-3.59\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6497ms 0.3526ms 2.8359 KOps/s 2.6916 KOps/s $\textbf{\color{#35bf28}+5.36\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 51.0971ms 48.2300ms 20.7340 Ops/s 23.0777 Ops/s $\textbf{\color{#d91a1a}-10.16\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8641ms 3.0749ms 325.2124 Ops/s 324.9722 Ops/s $\color{#35bf28}+0.07\%$
test_dqn_speed[False-None] 1.8030ms 1.3282ms 752.9269 Ops/s 737.1836 Ops/s $\color{#35bf28}+2.14\%$
test_dqn_speed[False-backward] 1.8953ms 1.8182ms 550.0044 Ops/s 547.0558 Ops/s $\color{#35bf28}+0.54\%$
test_dqn_speed[True-None] 0.7277ms 0.4678ms 2.1377 KOps/s 2.1485 KOps/s $\color{#d91a1a}-0.50\%$
test_dqn_speed[True-backward] 0.9405ms 0.8847ms 1.1303 KOps/s 1.1174 KOps/s $\color{#35bf28}+1.16\%$
test_dqn_speed[reduce-overhead-None] 0.6323ms 0.4725ms 2.1163 KOps/s 2.1241 KOps/s $\color{#d91a1a}-0.37\%$
test_dqn_speed[reduce-overhead-backward] 1.0689ms 0.8875ms 1.1268 KOps/s 1.1262 KOps/s $\color{#35bf28}+0.06\%$
test_ddpg_speed[False-None] 3.4454ms 2.7308ms 366.1982 Ops/s 356.1875 Ops/s $\color{#35bf28}+2.81\%$
test_ddpg_speed[False-backward] 4.9002ms 3.9224ms 254.9474 Ops/s 252.2102 Ops/s $\color{#35bf28}+1.09\%$
test_ddpg_speed[True-None] 1.4343ms 1.0226ms 977.8690 Ops/s 983.3566 Ops/s $\color{#d91a1a}-0.56\%$
test_ddpg_speed[True-backward] 2.4455ms 1.9474ms 513.5060 Ops/s 519.2050 Ops/s $\color{#d91a1a}-1.10\%$
test_ddpg_speed[reduce-overhead-None] 1.1922ms 1.0152ms 985.0172 Ops/s 970.3569 Ops/s $\color{#35bf28}+1.51\%$
test_ddpg_speed[reduce-overhead-backward] 2.1403ms 1.9817ms 504.6099 Ops/s 517.5581 Ops/s $\color{#d91a1a}-2.50\%$
test_sac_speed[False-None] 9.0606ms 7.8175ms 127.9178 Ops/s 125.4441 Ops/s $\color{#35bf28}+1.97\%$
test_sac_speed[False-backward] 10.9480ms 10.4983ms 95.2533 Ops/s 93.4489 Ops/s $\color{#35bf28}+1.93\%$
test_sac_speed[True-None] 2.5769ms 1.8622ms 537.0069 Ops/s 534.8514 Ops/s $\color{#35bf28}+0.40\%$
test_sac_speed[True-backward] 4.5024ms 3.6294ms 275.5307 Ops/s 266.9490 Ops/s $\color{#35bf28}+3.21\%$
test_sac_speed[reduce-overhead-None] 2.4343ms 1.8588ms 537.9955 Ops/s 535.7166 Ops/s $\color{#35bf28}+0.43\%$
test_sac_speed[reduce-overhead-backward] 3.9007ms 3.6569ms 273.4551 Ops/s 274.2051 Ops/s $\color{#d91a1a}-0.27\%$
test_redq_speed[False-None] 15.4810ms 12.8792ms 77.6448 Ops/s 75.2510 Ops/s $\color{#35bf28}+3.18\%$
test_redq_speed[False-backward] 23.7177ms 22.3495ms 44.7438 Ops/s 44.2973 Ops/s $\color{#35bf28}+1.01\%$
test_redq_speed[True-None] 5.7657ms 4.9857ms 200.5737 Ops/s 186.6033 Ops/s $\textbf{\color{#35bf28}+7.49\%}$
test_redq_speed[True-backward] 13.9155ms 12.6393ms 79.1181 Ops/s 78.6204 Ops/s $\color{#35bf28}+0.63\%$
test_redq_speed[reduce-overhead-None] 6.0645ms 4.9603ms 201.6002 Ops/s 204.4885 Ops/s $\color{#d91a1a}-1.41\%$
test_redq_speed[reduce-overhead-backward] 15.6479ms 13.0812ms 76.4459 Ops/s 80.9169 Ops/s $\textbf{\color{#d91a1a}-5.53\%}$
test_redq_deprec_speed[False-None] 15.4245ms 13.1571ms 76.0045 Ops/s 74.4234 Ops/s $\color{#35bf28}+2.12\%$
test_redq_deprec_speed[False-backward] 20.7757ms 19.6307ms 50.9405 Ops/s 50.2623 Ops/s $\color{#35bf28}+1.35\%$
test_redq_deprec_speed[True-None] 4.7905ms 3.8956ms 256.6984 Ops/s 268.7096 Ops/s $\color{#d91a1a}-4.47\%$
test_redq_deprec_speed[True-backward] 9.1072ms 8.6168ms 116.0526 Ops/s 118.5108 Ops/s $\color{#d91a1a}-2.07\%$
test_redq_deprec_speed[reduce-overhead-None] 4.2839ms 3.6946ms 270.6652 Ops/s 274.2310 Ops/s $\color{#d91a1a}-1.30\%$
test_redq_deprec_speed[reduce-overhead-backward] 8.6014ms 8.2802ms 120.7697 Ops/s 117.6133 Ops/s $\color{#35bf28}+2.68\%$
test_td3_speed[False-None] 8.2011ms 7.6805ms 130.1997 Ops/s 124.7795 Ops/s $\color{#35bf28}+4.34\%$
test_td3_speed[False-backward] 10.6212ms 10.1266ms 98.7501 Ops/s 94.5892 Ops/s $\color{#35bf28}+4.40\%$
test_td3_speed[True-None] 1.8979ms 1.7480ms 572.0838 Ops/s 574.4087 Ops/s $\color{#d91a1a}-0.40\%$
test_td3_speed[True-backward] 3.5567ms 3.3596ms 297.6559 Ops/s 290.6863 Ops/s $\color{#35bf28}+2.40\%$
test_td3_speed[reduce-overhead-None] 1.9672ms 1.7276ms 578.8261 Ops/s 574.7525 Ops/s $\color{#35bf28}+0.71\%$
test_td3_speed[reduce-overhead-backward] 3.4277ms 3.3364ms 299.7277 Ops/s 300.3798 Ops/s $\color{#d91a1a}-0.22\%$
test_cql_speed[False-None] 38.3195ms 35.4012ms 28.2477 Ops/s 27.6606 Ops/s $\color{#35bf28}+2.12\%$
test_cql_speed[False-backward] 51.8018ms 45.8476ms 21.8114 Ops/s 21.2382 Ops/s $\color{#35bf28}+2.70\%$
test_cql_speed[True-None] 16.5056ms 15.7764ms 63.3856 Ops/s 62.5826 Ops/s $\color{#35bf28}+1.28\%$
test_cql_speed[True-backward] 24.6668ms 22.4294ms 44.5843 Ops/s 44.0667 Ops/s $\color{#35bf28}+1.17\%$
test_cql_speed[reduce-overhead-None] 16.9992ms 15.8928ms 62.9214 Ops/s 62.3720 Ops/s $\color{#35bf28}+0.88\%$
test_cql_speed[reduce-overhead-backward] 23.7181ms 22.4717ms 44.5003 Ops/s 43.7270 Ops/s $\color{#35bf28}+1.77\%$
test_a2c_speed[False-None] 7.8219ms 7.1652ms 139.5638 Ops/s 137.4431 Ops/s $\color{#35bf28}+1.54\%$
test_a2c_speed[False-backward] 16.0981ms 14.7907ms 67.6102 Ops/s 67.4774 Ops/s $\color{#35bf28}+0.20\%$
test_a2c_speed[True-None] 4.0606ms 3.3129ms 301.8525 Ops/s 297.1777 Ops/s $\color{#35bf28}+1.57\%$
test_a2c_speed[True-backward] 10.2250ms 9.7506ms 102.5573 Ops/s 99.9049 Ops/s $\color{#35bf28}+2.65\%$
test_a2c_speed[reduce-overhead-None] 4.1556ms 3.3436ms 299.0827 Ops/s 297.1849 Ops/s $\color{#35bf28}+0.64\%$
test_a2c_speed[reduce-overhead-backward] 10.5343ms 9.8461ms 101.5629 Ops/s 100.1491 Ops/s $\color{#35bf28}+1.41\%$
test_ppo_speed[False-None] 8.9646ms 7.4402ms 134.4055 Ops/s 129.8581 Ops/s $\color{#35bf28}+3.50\%$
test_ppo_speed[False-backward] 15.7487ms 15.0543ms 66.4264 Ops/s 64.2624 Ops/s $\color{#35bf28}+3.37\%$
test_ppo_speed[True-None] 4.2015ms 3.7215ms 268.7119 Ops/s 264.7358 Ops/s $\color{#35bf28}+1.50\%$
test_ppo_speed[True-backward] 10.3958ms 9.7871ms 102.1750 Ops/s 101.1257 Ops/s $\color{#35bf28}+1.04\%$
test_ppo_speed[reduce-overhead-None] 4.4486ms 3.7199ms 268.8270 Ops/s 261.6088 Ops/s $\color{#35bf28}+2.76\%$
test_ppo_speed[reduce-overhead-backward] 10.2340ms 9.7068ms 103.0203 Ops/s 102.4833 Ops/s $\color{#35bf28}+0.52\%$
test_reinforce_speed[False-None] 8.5652ms 6.4905ms 154.0703 Ops/s 152.1116 Ops/s $\color{#35bf28}+1.29\%$
test_reinforce_speed[False-backward] 11.5338ms 9.9712ms 100.2887 Ops/s 101.1198 Ops/s $\color{#d91a1a}-0.82\%$
test_reinforce_speed[True-None] 3.2371ms 2.6698ms 374.5577 Ops/s 375.0619 Ops/s $\color{#d91a1a}-0.13\%$
test_reinforce_speed[True-backward] 9.2632ms 8.5818ms 116.5263 Ops/s 110.5977 Ops/s $\textbf{\color{#35bf28}+5.36\%}$
test_reinforce_speed[reduce-overhead-None] 3.2629ms 2.6577ms 376.2708 Ops/s 366.0900 Ops/s $\color{#35bf28}+2.78\%$
test_reinforce_speed[reduce-overhead-backward] 9.2182ms 8.6476ms 115.6391 Ops/s 115.4728 Ops/s $\color{#35bf28}+0.14\%$
test_iql_speed[False-None] 33.8194ms 31.9534ms 31.2956 Ops/s 30.8045 Ops/s $\color{#35bf28}+1.59\%$
test_iql_speed[False-backward] 47.0224ms 45.1215ms 22.1624 Ops/s 21.9533 Ops/s $\color{#35bf28}+0.95\%$
test_iql_speed[True-None] 11.8286ms 10.8727ms 91.9738 Ops/s 91.0430 Ops/s $\color{#35bf28}+1.02\%$
test_iql_speed[True-backward] 23.1128ms 22.0812ms 45.2874 Ops/s 44.8582 Ops/s $\color{#35bf28}+0.96\%$
test_iql_speed[reduce-overhead-None] 11.6406ms 10.8999ms 91.7436 Ops/s 91.5984 Ops/s $\color{#35bf28}+0.16\%$
test_iql_speed[reduce-overhead-backward] 23.3745ms 22.1955ms 45.0541 Ops/s 44.9012 Ops/s $\color{#35bf28}+0.34\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.4148ms 5.0325ms 198.7088 Ops/s 198.4258 Ops/s $\color{#35bf28}+0.14\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8112ms 0.5062ms 1.9753 KOps/s 1.9389 KOps/s $\color{#35bf28}+1.88\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6594ms 0.4816ms 2.0765 KOps/s 2.0324 KOps/s $\color{#35bf28}+2.17\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.4461ms 4.7588ms 210.1353 Ops/s 204.3042 Ops/s $\color{#35bf28}+2.85\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 3.6085ms 0.5001ms 1.9995 KOps/s 1.9596 KOps/s $\color{#35bf28}+2.04\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6714ms 0.4749ms 2.1056 KOps/s 2.0880 KOps/s $\color{#35bf28}+0.85\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.3087ms 1.6230ms 616.1591 Ops/s 598.9813 Ops/s $\color{#35bf28}+2.87\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.2577ms 1.5714ms 636.3667 Ops/s 617.9715 Ops/s $\color{#35bf28}+2.98\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.5233ms 4.9613ms 201.5602 Ops/s 197.7682 Ops/s $\color{#35bf28}+1.92\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3798ms 0.6401ms 1.5622 KOps/s 1.5232 KOps/s $\color{#35bf28}+2.56\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8415ms 0.6154ms 1.6250 KOps/s 1.5758 KOps/s $\color{#35bf28}+3.13\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.2803ms 4.9010ms 204.0410 Ops/s 210.2856 Ops/s $\color{#d91a1a}-2.97\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.6633ms 0.5115ms 1.9551 KOps/s 1.9295 KOps/s $\color{#35bf28}+1.33\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7146ms 0.4792ms 2.0869 KOps/s 2.0007 KOps/s $\color{#35bf28}+4.31\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.7085ms 4.9328ms 202.7229 Ops/s 206.7109 Ops/s $\color{#d91a1a}-1.93\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.1102ms 0.4995ms 2.0021 KOps/s 1.8166 KOps/s $\textbf{\color{#35bf28}+10.21\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7073ms 0.4844ms 2.0644 KOps/s 2.0393 KOps/s $\color{#35bf28}+1.23\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.7982ms 4.9067ms 203.8024 Ops/s 195.1911 Ops/s $\color{#35bf28}+4.41\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 4.2755ms 0.6495ms 1.5395 KOps/s 1.5085 KOps/s $\color{#35bf28}+2.06\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8167ms 0.6296ms 1.5883 KOps/s 1.5344 KOps/s $\color{#35bf28}+3.51\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 5.9099ms 4.3214ms 231.4046 Ops/s 227.8557 Ops/s $\color{#35bf28}+1.56\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 6.8607ms 2.2949ms 435.7565 Ops/s 447.6662 Ops/s $\color{#d91a1a}-2.66\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 4.6199ms 1.2655ms 790.2029 Ops/s 764.2349 Ops/s $\color{#35bf28}+3.40\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4386s 13.1801ms 75.8718 Ops/s 220.8218 Ops/s $\textbf{\color{#d91a1a}-65.64\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 9.6937ms 2.3009ms 434.6161 Ops/s 442.3173 Ops/s $\color{#d91a1a}-1.74\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.7542ms 1.1692ms 855.3181 Ops/s 765.4970 Ops/s $\textbf{\color{#35bf28}+11.73\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 6.3047ms 4.5565ms 219.4673 Ops/s 217.6401 Ops/s $\color{#35bf28}+0.84\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 5.7889ms 2.4680ms 405.1938 Ops/s 396.2727 Ops/s $\color{#35bf28}+2.25\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.0999ms 1.4603ms 684.7683 Ops/s 690.5671 Ops/s $\color{#d91a1a}-0.84\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000-100-True] 47.3757ms 40.9877ms 24.3976 Ops/s 22.2642 Ops/s $\textbf{\color{#35bf28}+9.58\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000-100-False] 9.2142ms 8.6460ms 115.6600 Ops/s 110.3624 Ops/s $\color{#35bf28}+4.80\%$

@github-actions
Copy link

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

Total Benchmarks: 145. Improved: $\large\color{#35bf28}12$. Worsened: $\large\color{#d91a1a}8$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7342s 0.7338s 1.3627 Ops/s 1.3598 Ops/s $\color{#35bf28}+0.22\%$
test_transformed 1.0646s 0.9881s 1.0121 Ops/s 1.0235 Ops/s $\color{#d91a1a}-1.11\%$
test_serial 2.2014s 2.1182s 0.4721 Ops/s 0.4743 Ops/s $\color{#d91a1a}-0.47\%$
test_parallel 2.1782s 2.0353s 0.4913 Ops/s 0.5115 Ops/s $\color{#d91a1a}-3.94\%$
test_step_mdp_speed[True-True-True-True-True] 0.1391ms 36.7794μs 27.1891 KOps/s 27.7983 KOps/s $\color{#d91a1a}-2.19\%$
test_step_mdp_speed[True-True-True-True-False] 46.0810μs 20.8638μs 47.9299 KOps/s 48.0880 KOps/s $\color{#d91a1a}-0.33\%$
test_step_mdp_speed[True-True-True-False-True] 62.8610μs 19.7896μs 50.5316 KOps/s 50.6245 KOps/s $\color{#d91a1a}-0.18\%$
test_step_mdp_speed[True-True-True-False-False] 46.0410μs 11.7216μs 85.3127 KOps/s 87.1388 KOps/s $\color{#d91a1a}-2.10\%$
test_step_mdp_speed[True-True-False-True-True] 69.7320μs 38.2378μs 26.1522 KOps/s 26.5375 KOps/s $\color{#d91a1a}-1.45\%$
test_step_mdp_speed[True-True-False-True-False] 49.8310μs 22.6141μs 44.2202 KOps/s 45.0860 KOps/s $\color{#d91a1a}-1.92\%$
test_step_mdp_speed[True-True-False-False-True] 55.1510μs 21.7265μs 46.0267 KOps/s 44.3863 KOps/s $\color{#35bf28}+3.70\%$
test_step_mdp_speed[True-True-False-False-False] 48.5210μs 13.7615μs 72.6664 KOps/s 72.3048 KOps/s $\color{#35bf28}+0.50\%$
test_step_mdp_speed[True-False-True-True-True] 67.5610μs 41.5125μs 24.0891 KOps/s 24.6527 KOps/s $\color{#d91a1a}-2.29\%$
test_step_mdp_speed[True-False-True-True-False] 58.2810μs 25.0389μs 39.9378 KOps/s 40.2881 KOps/s $\color{#d91a1a}-0.87\%$
test_step_mdp_speed[True-False-True-False-True] 49.2410μs 22.2601μs 44.9235 KOps/s 45.0298 KOps/s $\color{#d91a1a}-0.24\%$
test_step_mdp_speed[True-False-True-False-False] 40.4810μs 13.6240μs 73.3999 KOps/s 73.1898 KOps/s $\color{#35bf28}+0.29\%$
test_step_mdp_speed[True-False-False-True-True] 75.0120μs 43.1270μs 23.1873 KOps/s 23.7425 KOps/s $\color{#d91a1a}-2.34\%$
test_step_mdp_speed[True-False-False-True-False] 58.0610μs 26.5550μs 37.6577 KOps/s 37.4092 KOps/s $\color{#35bf28}+0.66\%$
test_step_mdp_speed[True-False-False-False-True] 51.7110μs 24.2143μs 41.2979 KOps/s 41.8639 KOps/s $\color{#d91a1a}-1.35\%$
test_step_mdp_speed[True-False-False-False-False] 46.4310μs 15.7681μs 63.4190 KOps/s 65.1115 KOps/s $\color{#d91a1a}-2.60\%$
test_step_mdp_speed[False-True-True-True-True] 74.2620μs 41.0453μs 24.3633 KOps/s 24.9588 KOps/s $\color{#d91a1a}-2.39\%$
test_step_mdp_speed[False-True-True-True-False] 58.3610μs 25.0378μs 39.9396 KOps/s 40.2092 KOps/s $\color{#d91a1a}-0.67\%$
test_step_mdp_speed[False-True-True-False-True] 52.2610μs 25.7679μs 38.8080 KOps/s 38.7157 KOps/s $\color{#35bf28}+0.24\%$
test_step_mdp_speed[False-True-True-False-False] 44.9910μs 15.2486μs 65.5800 KOps/s 64.7373 KOps/s $\color{#35bf28}+1.30\%$
test_step_mdp_speed[False-True-False-True-True] 70.0610μs 42.5520μs 23.5007 KOps/s 23.9590 KOps/s $\color{#d91a1a}-1.91\%$
test_step_mdp_speed[False-True-False-True-False] 58.2110μs 27.0442μs 36.9765 KOps/s 37.5870 KOps/s $\color{#d91a1a}-1.62\%$
test_step_mdp_speed[False-True-False-False-True] 3.4862ms 27.9891μs 35.7281 KOps/s 31.5163 KOps/s $\textbf{\color{#35bf28}+13.36\%}$
test_step_mdp_speed[False-True-False-False-False] 44.9010μs 17.2318μs 58.0324 KOps/s 57.6795 KOps/s $\color{#35bf28}+0.61\%$
test_step_mdp_speed[False-False-True-True-True] 79.5410μs 44.9417μs 22.2510 KOps/s 22.3234 KOps/s $\color{#d91a1a}-0.32\%$
test_step_mdp_speed[False-False-True-True-False] 60.2410μs 29.1374μs 34.3201 KOps/s 34.6567 KOps/s $\color{#d91a1a}-0.97\%$
test_step_mdp_speed[False-False-True-False-True] 60.1310μs 27.5314μs 36.3222 KOps/s 35.6571 KOps/s $\color{#35bf28}+1.87\%$
test_step_mdp_speed[False-False-True-False-False] 43.5010μs 17.1289μs 58.3810 KOps/s 57.7834 KOps/s $\color{#35bf28}+1.03\%$
test_step_mdp_speed[False-False-False-True-True] 78.4710μs 46.6263μs 21.4471 KOps/s 21.8154 KOps/s $\color{#d91a1a}-1.69\%$
test_step_mdp_speed[False-False-False-True-False] 56.3910μs 31.3262μs 31.9221 KOps/s 32.5461 KOps/s $\color{#d91a1a}-1.92\%$
test_step_mdp_speed[False-False-False-False-True] 70.3820μs 29.3562μs 34.0644 KOps/s 33.7210 KOps/s $\color{#35bf28}+1.02\%$
test_step_mdp_speed[False-False-False-False-False] 47.8410μs 19.2928μs 51.8329 KOps/s 51.8704 KOps/s $\color{#d91a1a}-0.07\%$
test_values[generalized_advantage_estimate-True-True] 27.3929ms 26.9753ms 37.0710 Ops/s 39.2905 Ops/s $\textbf{\color{#d91a1a}-5.65\%}$
test_values[vec_generalized_advantage_estimate-True-True] 0.1013s 2.9250ms 341.8754 Ops/s 325.8774 Ops/s $\color{#35bf28}+4.91\%$
test_values[td0_return_estimate-False-False] 88.2010μs 67.9178μs 14.7237 KOps/s 14.8764 KOps/s $\color{#d91a1a}-1.03\%$
test_values[td1_return_estimate-False-False] 60.6095ms 59.5961ms 16.7796 Ops/s 17.4475 Ops/s $\color{#d91a1a}-3.83\%$
test_values[vec_td1_return_estimate-False-False] 1.3420ms 1.1022ms 907.2739 Ops/s 919.5939 Ops/s $\color{#d91a1a}-1.34\%$
test_values[td_lambda_return_estimate-True-False] 97.3209ms 95.7573ms 10.4431 Ops/s 10.8041 Ops/s $\color{#d91a1a}-3.34\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.3222ms 1.0854ms 921.2775 Ops/s 917.9043 Ops/s $\color{#35bf28}+0.37\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.4791ms 25.2634ms 39.5829 Ops/s 38.7291 Ops/s $\color{#35bf28}+2.20\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0367ms 0.7568ms 1.3214 KOps/s 1.3292 KOps/s $\color{#d91a1a}-0.59\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7691ms 0.6725ms 1.4869 KOps/s 1.4894 KOps/s $\color{#d91a1a}-0.17\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5178ms 1.4826ms 674.4714 Ops/s 672.7764 Ops/s $\color{#35bf28}+0.25\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7255ms 0.6884ms 1.4526 KOps/s 1.4546 KOps/s $\color{#d91a1a}-0.13\%$
test_dqn_speed[False-None] 7.3476ms 1.3193ms 757.9613 Ops/s 763.7781 Ops/s $\color{#d91a1a}-0.76\%$
test_dqn_speed[False-backward] 1.8819ms 1.8094ms 552.6622 Ops/s 549.7931 Ops/s $\color{#35bf28}+0.52\%$
test_dqn_speed[True-None] 0.8475ms 0.5515ms 1.8132 KOps/s 1.7525 KOps/s $\color{#35bf28}+3.46\%$
test_dqn_speed[True-backward] 1.0494ms 0.9977ms 1.0023 KOps/s 821.7015 Ops/s $\textbf{\color{#35bf28}+21.98\%}$
test_dqn_speed[reduce-overhead-None] 0.9077ms 0.5562ms 1.7980 KOps/s 1.7614 KOps/s $\color{#35bf28}+2.08\%$
test_dqn_speed[reduce-overhead-backward] 1.0467ms 1.0078ms 992.3066 Ops/s 993.3683 Ops/s $\color{#d91a1a}-0.11\%$
test_ddpg_speed[False-None] 3.2488ms 2.6546ms 376.7006 Ops/s 369.9043 Ops/s $\color{#35bf28}+1.84\%$
test_ddpg_speed[False-backward] 4.1795ms 3.8762ms 257.9829 Ops/s 254.1438 Ops/s $\color{#35bf28}+1.51\%$
test_ddpg_speed[True-None] 1.5996ms 1.2422ms 804.9932 Ops/s 798.8208 Ops/s $\color{#35bf28}+0.77\%$
test_ddpg_speed[True-backward] 2.2774ms 2.2047ms 453.5822 Ops/s 408.3184 Ops/s $\textbf{\color{#35bf28}+11.09\%}$
test_ddpg_speed[reduce-overhead-None] 1.3735ms 1.2428ms 804.6371 Ops/s 787.0225 Ops/s $\color{#35bf28}+2.24\%$
test_ddpg_speed[reduce-overhead-backward] 2.2675ms 2.1903ms 456.5485 Ops/s 450.4166 Ops/s $\color{#35bf28}+1.36\%$
test_sac_speed[False-None] 8.4209ms 7.4080ms 134.9887 Ops/s 132.6738 Ops/s $\color{#35bf28}+1.74\%$
test_sac_speed[False-backward] 11.0651ms 10.5443ms 94.8377 Ops/s 93.8446 Ops/s $\color{#35bf28}+1.06\%$
test_sac_speed[True-None] 2.1111ms 1.9815ms 504.6748 Ops/s 492.7876 Ops/s $\color{#35bf28}+2.41\%$
test_sac_speed[True-backward] 4.0263ms 3.9278ms 254.5983 Ops/s 230.5238 Ops/s $\textbf{\color{#35bf28}+10.44\%}$
test_sac_speed[reduce-overhead-None] 2.0985ms 1.9896ms 502.6097 Ops/s 502.5112 Ops/s $\color{#35bf28}+0.02\%$
test_sac_speed[reduce-overhead-backward] 4.0730ms 3.9192ms 255.1542 Ops/s 259.3970 Ops/s $\color{#d91a1a}-1.64\%$
test_redq_speed[False-None] 15.7444ms 11.2176ms 89.1453 Ops/s 99.9226 Ops/s $\textbf{\color{#d91a1a}-10.79\%}$
test_redq_speed[False-backward] 18.0816ms 17.0382ms 58.6917 Ops/s 60.4357 Ops/s $\color{#d91a1a}-2.89\%$
test_redq_speed[True-None] 3.7024ms 3.4704ms 288.1509 Ops/s 281.7171 Ops/s $\color{#35bf28}+2.28\%$
test_redq_speed[True-backward] 8.5686ms 8.3615ms 119.5953 Ops/s 118.8124 Ops/s $\color{#35bf28}+0.66\%$
test_redq_speed[reduce-overhead-None] 3.7740ms 3.4275ms 291.7557 Ops/s 287.9890 Ops/s $\color{#35bf28}+1.31\%$
test_redq_speed[reduce-overhead-backward] 8.4833ms 8.2488ms 121.2291 Ops/s 121.6662 Ops/s $\color{#d91a1a}-0.36\%$
test_redq_deprec_speed[False-None] 10.8409ms 10.3193ms 96.9062 Ops/s 93.2165 Ops/s $\color{#35bf28}+3.96\%$
test_redq_deprec_speed[False-backward] 15.4780ms 14.9049ms 67.0922 Ops/s 64.6103 Ops/s $\color{#35bf28}+3.84\%$
test_redq_deprec_speed[True-None] 3.2882ms 3.1400ms 318.4698 Ops/s 310.4778 Ops/s $\color{#35bf28}+2.57\%$
test_redq_deprec_speed[True-backward] 7.1327ms 6.9119ms 144.6782 Ops/s 132.6091 Ops/s $\textbf{\color{#35bf28}+9.10\%}$
test_redq_deprec_speed[reduce-overhead-None] 3.3389ms 3.1524ms 317.2210 Ops/s 314.6328 Ops/s $\color{#35bf28}+0.82\%$
test_redq_deprec_speed[reduce-overhead-backward] 7.2340ms 6.9186ms 144.5380 Ops/s 149.9748 Ops/s $\color{#d91a1a}-3.63\%$
test_td3_speed[False-None] 33.2448ms 7.5540ms 132.3804 Ops/s 125.7245 Ops/s $\textbf{\color{#35bf28}+5.29\%}$
test_td3_speed[False-backward] 10.3456ms 10.1611ms 98.4144 Ops/s 96.6475 Ops/s $\color{#35bf28}+1.83\%$
test_td3_speed[True-None] 1.8927ms 1.8749ms 533.3709 Ops/s 534.7324 Ops/s $\color{#d91a1a}-0.25\%$
test_td3_speed[True-backward] 3.7561ms 3.6409ms 274.6564 Ops/s 263.7596 Ops/s $\color{#35bf28}+4.13\%$
test_td3_speed[reduce-overhead-None] 1.9435ms 1.8689ms 535.0608 Ops/s 533.1643 Ops/s $\color{#35bf28}+0.36\%$
test_td3_speed[reduce-overhead-backward] 3.7625ms 3.6333ms 275.2303 Ops/s 275.8729 Ops/s $\color{#d91a1a}-0.23\%$
test_cql_speed[False-None] 28.3742ms 24.4751ms 40.8578 Ops/s 41.1428 Ops/s $\color{#d91a1a}-0.69\%$
test_cql_speed[False-backward] 37.3717ms 33.9218ms 29.4796 Ops/s 30.2299 Ops/s $\color{#d91a1a}-2.48\%$
test_cql_speed[True-None] 11.0151ms 10.7176ms 93.3047 Ops/s 95.6894 Ops/s $\color{#d91a1a}-2.49\%$
test_cql_speed[True-backward] 16.6019ms 16.2630ms 61.4894 Ops/s 63.0981 Ops/s $\color{#d91a1a}-2.55\%$
test_cql_speed[reduce-overhead-None] 10.8818ms 10.6661ms 93.7551 Ops/s 95.7531 Ops/s $\color{#d91a1a}-2.09\%$
test_cql_speed[reduce-overhead-backward] 16.4450ms 16.1936ms 61.7526 Ops/s 62.8416 Ops/s $\color{#d91a1a}-1.73\%$
test_a2c_speed[False-None] 5.4979ms 5.2240ms 191.4239 Ops/s 188.4483 Ops/s $\color{#35bf28}+1.58\%$
test_a2c_speed[False-backward] 12.3931ms 11.5349ms 86.6934 Ops/s 86.0777 Ops/s $\color{#35bf28}+0.72\%$
test_a2c_speed[True-None] 3.1330ms 2.9899ms 334.4540 Ops/s 333.5354 Ops/s $\color{#35bf28}+0.28\%$
test_a2c_speed[True-backward] 8.5163ms 8.2467ms 121.2610 Ops/s 124.1429 Ops/s $\color{#d91a1a}-2.32\%$
test_a2c_speed[reduce-overhead-None] 3.1420ms 2.9787ms 335.7170 Ops/s 334.0425 Ops/s $\color{#35bf28}+0.50\%$
test_a2c_speed[reduce-overhead-backward] 8.4802ms 8.1978ms 121.9833 Ops/s 122.4968 Ops/s $\color{#d91a1a}-0.42\%$
test_ppo_speed[False-None] 7.4319ms 5.6271ms 177.7104 Ops/s 180.3593 Ops/s $\color{#d91a1a}-1.47\%$
test_ppo_speed[False-backward] 12.4616ms 12.1023ms 82.6289 Ops/s 83.3804 Ops/s $\color{#d91a1a}-0.90\%$
test_ppo_speed[True-None] 3.5269ms 3.3989ms 294.2167 Ops/s 294.7555 Ops/s $\color{#d91a1a}-0.18\%$
test_ppo_speed[True-backward] 8.0662ms 7.9135ms 126.3655 Ops/s 122.4386 Ops/s $\color{#35bf28}+3.21\%$
test_ppo_speed[reduce-overhead-None] 3.5195ms 3.3738ms 296.3982 Ops/s 297.2154 Ops/s $\color{#d91a1a}-0.27\%$
test_ppo_speed[reduce-overhead-backward] 8.2350ms 8.0122ms 124.8092 Ops/s 123.8745 Ops/s $\color{#35bf28}+0.75\%$
test_reinforce_speed[False-None] 6.1121ms 4.3546ms 229.6416 Ops/s 225.7437 Ops/s $\color{#35bf28}+1.73\%$
test_reinforce_speed[False-backward] 7.3358ms 7.0650ms 141.5423 Ops/s 138.0002 Ops/s $\color{#35bf28}+2.57\%$
test_reinforce_speed[True-None] 2.3091ms 2.1698ms 460.8674 Ops/s 457.2131 Ops/s $\color{#35bf28}+0.80\%$
test_reinforce_speed[True-backward] 6.9831ms 6.8508ms 145.9690 Ops/s 147.6712 Ops/s $\color{#d91a1a}-1.15\%$
test_reinforce_speed[reduce-overhead-None] 2.3261ms 2.1685ms 461.1585 Ops/s 462.9397 Ops/s $\color{#d91a1a}-0.38\%$
test_reinforce_speed[reduce-overhead-backward] 7.0869ms 6.8531ms 145.9197 Ops/s 147.1379 Ops/s $\color{#d91a1a}-0.83\%$
test_iql_speed[False-None] 20.0315ms 18.6894ms 53.5063 Ops/s 51.9487 Ops/s $\color{#35bf28}+3.00\%$
test_iql_speed[False-backward] 29.5457ms 28.9691ms 34.5196 Ops/s 33.6418 Ops/s $\color{#35bf28}+2.61\%$
test_iql_speed[True-None] 6.9944ms 6.5627ms 152.3770 Ops/s 153.7312 Ops/s $\color{#d91a1a}-0.88\%$
test_iql_speed[True-backward] 15.2135ms 14.8912ms 67.1537 Ops/s 67.8926 Ops/s $\color{#d91a1a}-1.09\%$
test_iql_speed[reduce-overhead-None] 6.9051ms 6.5893ms 151.7614 Ops/s 168.0916 Ops/s $\textbf{\color{#d91a1a}-9.72\%}$
test_iql_speed[reduce-overhead-backward] 15.3624ms 14.9497ms 66.8910 Ops/s 69.1809 Ops/s $\color{#d91a1a}-3.31\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.5621ms 6.2853ms 159.1026 Ops/s 156.4885 Ops/s $\color{#35bf28}+1.67\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9765ms 0.2858ms 3.4985 KOps/s 3.6028 KOps/s $\color{#d91a1a}-2.90\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.4822ms 0.2718ms 3.6798 KOps/s 3.7331 KOps/s $\color{#d91a1a}-1.43\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.2973ms 6.0858ms 164.3160 Ops/s 163.5248 Ops/s $\color{#35bf28}+0.48\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7796ms 0.2530ms 3.9527 KOps/s 3.8837 KOps/s $\color{#35bf28}+1.78\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.4367ms 0.2304ms 4.3396 KOps/s 4.2738 KOps/s $\color{#35bf28}+1.54\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.5199ms 1.2445ms 803.5658 Ops/s 794.1357 Ops/s $\color{#35bf28}+1.19\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4331ms 1.1886ms 841.2927 Ops/s 824.9747 Ops/s $\color{#35bf28}+1.98\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4456ms 6.2759ms 159.3394 Ops/s 159.8073 Ops/s $\color{#d91a1a}-0.29\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9172ms 0.4414ms 2.2653 KOps/s 2.3621 KOps/s $\color{#d91a1a}-4.10\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.5766ms 0.3785ms 2.6423 KOps/s 2.4309 KOps/s $\textbf{\color{#35bf28}+8.69\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.2225ms 6.1302ms 163.1271 Ops/s 163.5051 Ops/s $\color{#d91a1a}-0.23\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0329ms 0.3755ms 2.6628 KOps/s 3.2888 KOps/s $\textbf{\color{#d91a1a}-19.04\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.4791ms 0.3017ms 3.3151 KOps/s 4.2130 KOps/s $\textbf{\color{#d91a1a}-21.31\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.4587ms 6.0643ms 164.8998 Ops/s 164.9775 Ops/s $\color{#d91a1a}-0.05\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9253ms 0.2529ms 3.9536 KOps/s 3.5121 KOps/s $\textbf{\color{#35bf28}+12.57\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.4234ms 0.2321ms 4.3088 KOps/s 3.6988 KOps/s $\textbf{\color{#35bf28}+16.49\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5254ms 6.2304ms 160.5032 Ops/s 159.9758 Ops/s $\color{#35bf28}+0.33\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8430ms 0.5416ms 1.8465 KOps/s 1.9688 KOps/s $\textbf{\color{#d91a1a}-6.21\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6345ms 0.4071ms 2.4566 KOps/s 2.2412 KOps/s $\textbf{\color{#35bf28}+9.61\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.4467s 14.1404ms 70.7191 Ops/s 192.3417 Ops/s $\textbf{\color{#d91a1a}-63.23\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 7.4357ms 1.9775ms 505.7014 Ops/s 466.9140 Ops/s $\textbf{\color{#35bf28}+8.31\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 8.3499ms 1.2354ms 809.4760 Ops/s 808.7593 Ops/s $\color{#35bf28}+0.09\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 8.3575ms 5.3405ms 187.2482 Ops/s 33.7576 Ops/s $\textbf{\color{#35bf28}+454.68\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 9.0460ms 2.0074ms 498.1596 Ops/s 498.4765 Ops/s $\color{#d91a1a}-0.06\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.4791ms 1.1697ms 854.9252 Ops/s 828.9275 Ops/s $\color{#35bf28}+3.14\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.3740s 12.9117ms 77.4493 Ops/s 174.5960 Ops/s $\textbf{\color{#d91a1a}-55.64\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.3364ms 2.1575ms 463.4889 Ops/s 458.6512 Ops/s $\color{#35bf28}+1.05\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.0063ms 1.3544ms 738.3383 Ops/s 728.5271 Ops/s $\color{#35bf28}+1.35\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000-100-True] 49.3994ms 46.9807ms 21.2853 Ops/s 21.4442 Ops/s $\color{#d91a1a}-0.74\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000-100-False] 10.8724ms 10.3124ms 96.9704 Ops/s 101.4741 Ops/s $\color{#d91a1a}-4.44\%$

vmoens pushed a commit that referenced this pull request Nov 4, 2024
(cherry picked from commit edbf3de)
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. documentation Improvements or additions to documentation

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[BUG] Typos and bugs in torchrl.modules package documentation

3 participants