Skip to content
New issue

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

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

Already on GitHub? Sign in to your account

[CI] Fix gymnasium version in minari #2512

Merged
merged 3 commits into from
Oct 22, 2024
Merged

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Oct 22, 2024

Stack from ghstack (oldest at bottom):

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Oct 22, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2512

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

❌ 1 New Failure, 4 Unrelated Failures

As of commit 1b9f86b with merge base 9332809 (image):

NEW FAILURE - The following job has 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.

vmoens added a commit that referenced this pull request Oct 22, 2024
ghstack-source-id: ad7bf38df149649a0b78d845dc8d361de2bd3413
Pull Request resolved: #2512
@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 22, 2024
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Oct 22, 2024
ghstack-source-id: a25e28ee447d02de655d1658fbb42736bc07ef08
Pull Request resolved: #2512
@vmoens vmoens added Environments Adds or modifies an environment wrapper Data Data-related PR, will launch data-related jobs labels Oct 22, 2024
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Oct 22, 2024
ghstack-source-id: 06c5f1ece3bb5cc222d7b3accfee799af98816ae
Pull Request resolved: #2512
Copy link

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

Total Benchmarks: 143. Improved: $\large\color{#35bf28}13$. Worsened: $\large\color{#d91a1a}15$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4296s 0.4214s 2.3728 Ops/s 2.2794 Ops/s $\color{#35bf28}+4.10\%$
test_transformed 0.7239s 0.6249s 1.6003 Ops/s 1.6979 Ops/s $\textbf{\color{#d91a1a}-5.74\%}$
test_serial 1.4811s 1.3775s 0.7259 Ops/s 0.7408 Ops/s $\color{#d91a1a}-2.01\%$
test_parallel 1.4563s 1.3549s 0.7381 Ops/s 0.7249 Ops/s $\color{#35bf28}+1.82\%$
test_step_mdp_speed[True-True-True-True-True] 0.2071ms 28.4957μs 35.0930 KOps/s 35.3078 KOps/s $\color{#d91a1a}-0.61\%$
test_step_mdp_speed[True-True-True-True-False] 54.5510μs 17.2700μs 57.9039 KOps/s 58.9083 KOps/s $\color{#d91a1a}-1.71\%$
test_step_mdp_speed[True-True-True-False-True] 54.3210μs 15.9787μs 62.5831 KOps/s 62.6823 KOps/s $\color{#d91a1a}-0.16\%$
test_step_mdp_speed[True-True-True-False-False] 0.5980ms 10.2578μs 97.4869 KOps/s 107.7675 KOps/s $\textbf{\color{#d91a1a}-9.54\%}$
test_step_mdp_speed[True-True-False-True-True] 78.8460μs 31.2891μs 31.9600 KOps/s 32.8475 KOps/s $\color{#d91a1a}-2.70\%$
test_step_mdp_speed[True-True-False-True-False] 62.8760μs 19.8005μs 50.5038 KOps/s 52.3738 KOps/s $\color{#d91a1a}-3.57\%$
test_step_mdp_speed[True-True-False-False-True] 61.0730μs 18.2779μs 54.7110 KOps/s 56.3076 KOps/s $\color{#d91a1a}-2.84\%$
test_step_mdp_speed[True-True-False-False-False] 56.1140μs 11.7290μs 85.2584 KOps/s 88.0453 KOps/s $\color{#d91a1a}-3.17\%$
test_step_mdp_speed[True-False-True-True-True] 74.5690μs 33.3350μs 29.9985 KOps/s 30.7180 KOps/s $\color{#d91a1a}-2.34\%$
test_step_mdp_speed[True-False-True-True-False] 61.5540μs 21.9206μs 45.6191 KOps/s 47.2538 KOps/s $\color{#d91a1a}-3.46\%$
test_step_mdp_speed[True-False-True-False-True] 50.2230μs 18.0229μs 55.4848 KOps/s 55.9486 KOps/s $\color{#d91a1a}-0.83\%$
test_step_mdp_speed[True-False-True-False-False] 90.2570μs 11.6041μs 86.1763 KOps/s 87.5762 KOps/s $\color{#d91a1a}-1.60\%$
test_step_mdp_speed[True-False-False-True-True] 88.1830μs 35.1141μs 28.4786 KOps/s 28.7878 KOps/s $\color{#d91a1a}-1.07\%$
test_step_mdp_speed[True-False-False-True-False] 70.8510μs 23.6238μs 42.3302 KOps/s 42.8620 KOps/s $\color{#d91a1a}-1.24\%$
test_step_mdp_speed[True-False-False-False-True] 82.2620μs 19.9975μs 50.0062 KOps/s 50.1774 KOps/s $\color{#d91a1a}-0.34\%$
test_step_mdp_speed[True-False-False-False-False] 51.3650μs 13.5299μs 73.9104 KOps/s 74.0238 KOps/s $\color{#d91a1a}-0.15\%$
test_step_mdp_speed[False-True-True-True-True] 71.0720μs 33.0721μs 30.2370 KOps/s 30.4660 KOps/s $\color{#d91a1a}-0.75\%$
test_step_mdp_speed[False-True-True-True-False] 56.9560μs 21.7172μs 46.0464 KOps/s 46.3037 KOps/s $\color{#d91a1a}-0.56\%$
test_step_mdp_speed[False-True-True-False-True] 55.6830μs 21.1867μs 47.1994 KOps/s 48.0947 KOps/s $\color{#d91a1a}-1.86\%$
test_step_mdp_speed[False-True-True-False-False] 48.6400μs 13.4110μs 74.5658 KOps/s 75.1908 KOps/s $\color{#d91a1a}-0.83\%$
test_step_mdp_speed[False-True-False-True-True] 78.8770μs 35.4379μs 28.2184 KOps/s 28.9548 KOps/s $\color{#d91a1a}-2.54\%$
test_step_mdp_speed[False-True-False-True-False] 68.8080μs 23.7580μs 42.0911 KOps/s 42.7229 KOps/s $\color{#d91a1a}-1.48\%$
test_step_mdp_speed[False-True-False-False-True] 2.7649ms 23.6818μs 42.2265 KOps/s 44.0268 KOps/s $\color{#d91a1a}-4.09\%$
test_step_mdp_speed[False-True-False-False-False] 53.8200μs 15.4020μs 64.9265 KOps/s 65.4484 KOps/s $\color{#d91a1a}-0.80\%$
test_step_mdp_speed[False-False-True-True-True] 0.1082ms 37.4038μs 26.7352 KOps/s 26.9378 KOps/s $\color{#d91a1a}-0.75\%$
test_step_mdp_speed[False-False-True-True-False] 58.6990μs 25.8835μs 38.6346 KOps/s 39.1582 KOps/s $\color{#d91a1a}-1.34\%$
test_step_mdp_speed[False-False-True-False-True] 58.6090μs 23.0977μs 43.2944 KOps/s 43.0974 KOps/s $\color{#35bf28}+0.46\%$
test_step_mdp_speed[False-False-True-False-False] 42.5790μs 15.4654μs 64.6606 KOps/s 65.5774 KOps/s $\color{#d91a1a}-1.40\%$
test_step_mdp_speed[False-False-False-True-True] 92.9730μs 38.9589μs 25.6681 KOps/s 25.6770 KOps/s $\color{#d91a1a}-0.03\%$
test_step_mdp_speed[False-False-False-True-False] 66.6230μs 27.6231μs 36.2016 KOps/s 36.4689 KOps/s $\color{#d91a1a}-0.73\%$
test_step_mdp_speed[False-False-False-False-True] 64.6700μs 25.3404μs 39.4626 KOps/s 39.7748 KOps/s $\color{#d91a1a}-0.78\%$
test_step_mdp_speed[False-False-False-False-False] 48.0790μs 17.5414μs 57.0079 KOps/s 58.1703 KOps/s $\color{#d91a1a}-2.00\%$
test_values[generalized_advantage_estimate-True-True] 10.0892ms 9.5111ms 105.1398 Ops/s 103.4198 Ops/s $\color{#35bf28}+1.66\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.9247ms 36.0528ms 27.7371 Ops/s 29.4984 Ops/s $\textbf{\color{#d91a1a}-5.97\%}$
test_values[td0_return_estimate-False-False] 0.2273ms 0.1958ms 5.1069 KOps/s 5.0016 KOps/s $\color{#35bf28}+2.10\%$
test_values[td1_return_estimate-False-False] 28.0483ms 24.5746ms 40.6925 Ops/s 39.3365 Ops/s $\color{#35bf28}+3.45\%$
test_values[vec_td1_return_estimate-False-False] 39.2251ms 36.0495ms 27.7396 Ops/s 29.5268 Ops/s $\textbf{\color{#d91a1a}-6.05\%}$
test_values[td_lambda_return_estimate-True-False] 43.5756ms 35.5622ms 28.1198 Ops/s 29.0259 Ops/s $\color{#d91a1a}-3.12\%$
test_values[vec_td_lambda_return_estimate-True-False] 37.5304ms 36.0241ms 27.7592 Ops/s 29.5759 Ops/s $\textbf{\color{#d91a1a}-6.14\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 11.5757ms 8.3792ms 119.3438 Ops/s 120.7824 Ops/s $\color{#d91a1a}-1.19\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.2753ms 1.8157ms 550.7456 Ops/s 492.4202 Ops/s $\textbf{\color{#35bf28}+11.84\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5201ms 0.3565ms 2.8052 KOps/s 2.7991 KOps/s $\color{#35bf28}+0.22\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 48.6204ms 46.4576ms 21.5250 Ops/s 23.2433 Ops/s $\textbf{\color{#d91a1a}-7.39\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8630ms 3.0638ms 326.3920 Ops/s 329.6569 Ops/s $\color{#d91a1a}-0.99\%$
test_dqn_speed[False-None] 5.9202ms 1.3602ms 735.1860 Ops/s 746.4724 Ops/s $\color{#d91a1a}-1.51\%$
test_dqn_speed[False-backward] 3.4025ms 1.8806ms 531.7332 Ops/s 550.0931 Ops/s $\color{#d91a1a}-3.34\%$
test_dqn_speed[True-None] 0.7484ms 0.4613ms 2.1677 KOps/s 2.1517 KOps/s $\color{#35bf28}+0.74\%$
test_dqn_speed[True-backward] 0.9789ms 0.8857ms 1.1291 KOps/s 888.3990 Ops/s $\textbf{\color{#35bf28}+27.09\%}$
test_dqn_speed[reduce-overhead-None] 0.6029ms 0.4668ms 2.1421 KOps/s 2.1217 KOps/s $\color{#35bf28}+0.96\%$
test_dqn_speed[reduce-overhead-backward] 0.9247ms 0.8709ms 1.1482 KOps/s 1.1168 KOps/s $\color{#35bf28}+2.81\%$
test_ddpg_speed[False-None] 4.3201ms 2.8022ms 356.8578 Ops/s 343.7987 Ops/s $\color{#35bf28}+3.80\%$
test_ddpg_speed[False-backward] 4.9022ms 3.9784ms 251.3582 Ops/s 250.3766 Ops/s $\color{#35bf28}+0.39\%$
test_ddpg_speed[True-None] 1.4375ms 1.0020ms 997.9904 Ops/s 992.4425 Ops/s $\color{#35bf28}+0.56\%$
test_ddpg_speed[True-backward] 2.2911ms 2.0154ms 496.1875 Ops/s 512.1670 Ops/s $\color{#d91a1a}-3.12\%$
test_ddpg_speed[reduce-overhead-None] 1.2683ms 1.0061ms 993.9534 Ops/s 956.2736 Ops/s $\color{#35bf28}+3.94\%$
test_ddpg_speed[reduce-overhead-backward] 1.9753ms 1.9224ms 520.1964 Ops/s 526.7776 Ops/s $\color{#d91a1a}-1.25\%$
test_sac_speed[False-None] 10.6116ms 8.2981ms 120.5101 Ops/s 127.5547 Ops/s $\textbf{\color{#d91a1a}-5.52\%}$
test_sac_speed[False-backward] 12.1001ms 11.1374ms 89.7877 Ops/s 94.7900 Ops/s $\textbf{\color{#d91a1a}-5.28\%}$
test_sac_speed[True-None] 3.2634ms 1.8695ms 534.8973 Ops/s 529.5087 Ops/s $\color{#35bf28}+1.02\%$
test_sac_speed[True-backward] 3.7037ms 3.5769ms 279.5722 Ops/s 271.1175 Ops/s $\color{#35bf28}+3.12\%$
test_sac_speed[reduce-overhead-None] 2.2123ms 1.8680ms 535.3259 Ops/s 529.7742 Ops/s $\color{#35bf28}+1.05\%$
test_sac_speed[reduce-overhead-backward] 3.7771ms 3.5725ms 279.9136 Ops/s 269.3767 Ops/s $\color{#35bf28}+3.91\%$
test_redq_speed[False-None] 14.8648ms 13.0990ms 76.3418 Ops/s 74.9143 Ops/s $\color{#35bf28}+1.91\%$
test_redq_speed[False-backward] 24.1650ms 22.6612ms 44.1284 Ops/s 42.6439 Ops/s $\color{#35bf28}+3.48\%$
test_redq_speed[True-None] 6.2334ms 5.5014ms 181.7711 Ops/s 222.6488 Ops/s $\textbf{\color{#d91a1a}-18.36\%}$
test_redq_speed[True-backward] 14.1336ms 12.9174ms 77.4148 Ops/s 75.4169 Ops/s $\color{#35bf28}+2.65\%$
test_redq_speed[reduce-overhead-None] 6.8280ms 5.7614ms 173.5678 Ops/s 192.1608 Ops/s $\textbf{\color{#d91a1a}-9.68\%}$
test_redq_speed[reduce-overhead-backward] 13.4014ms 12.8080ms 78.0761 Ops/s 76.6205 Ops/s $\color{#35bf28}+1.90\%$
test_redq_deprec_speed[False-None] 14.0692ms 13.3211ms 75.0690 Ops/s 73.2701 Ops/s $\color{#35bf28}+2.46\%$
test_redq_deprec_speed[False-backward] 20.7815ms 18.7735ms 53.2666 Ops/s 50.4351 Ops/s $\textbf{\color{#35bf28}+5.61\%}$
test_redq_deprec_speed[True-None] 5.0596ms 3.9681ms 252.0087 Ops/s 226.5272 Ops/s $\textbf{\color{#35bf28}+11.25\%}$
test_redq_deprec_speed[True-backward] 9.7628ms 8.8445ms 113.0648 Ops/s 113.3885 Ops/s $\color{#d91a1a}-0.29\%$
test_redq_deprec_speed[reduce-overhead-None] 4.6210ms 3.8325ms 260.9275 Ops/s 258.6021 Ops/s $\color{#35bf28}+0.90\%$
test_redq_deprec_speed[reduce-overhead-backward] 9.0308ms 8.6730ms 115.3001 Ops/s 125.3221 Ops/s $\textbf{\color{#d91a1a}-8.00\%}$
test_td3_speed[False-None] 8.3974ms 8.0924ms 123.5731 Ops/s 125.1282 Ops/s $\color{#d91a1a}-1.24\%$
test_td3_speed[False-backward] 11.4249ms 10.6865ms 93.5764 Ops/s 96.2348 Ops/s $\color{#d91a1a}-2.76\%$
test_td3_speed[True-None] 1.9763ms 1.7658ms 566.3272 Ops/s 565.7979 Ops/s $\color{#35bf28}+0.09\%$
test_td3_speed[True-backward] 4.4850ms 3.7145ms 269.2172 Ops/s 286.2075 Ops/s $\textbf{\color{#d91a1a}-5.94\%}$
test_td3_speed[reduce-overhead-None] 1.8730ms 1.7332ms 576.9804 Ops/s 559.5591 Ops/s $\color{#35bf28}+3.11\%$
test_td3_speed[reduce-overhead-backward] 3.7941ms 3.6654ms 272.8180 Ops/s 283.3105 Ops/s $\color{#d91a1a}-3.70\%$
test_cql_speed[False-None] 41.2267ms 37.9683ms 26.3377 Ops/s 27.4095 Ops/s $\color{#d91a1a}-3.91\%$
test_cql_speed[False-backward] 52.3910ms 48.0343ms 20.8184 Ops/s 21.4252 Ops/s $\color{#d91a1a}-2.83\%$
test_cql_speed[True-None] 17.5747ms 16.1797ms 61.8057 Ops/s 59.8633 Ops/s $\color{#35bf28}+3.24\%$
test_cql_speed[True-backward] 24.3643ms 23.2941ms 42.9293 Ops/s 43.7435 Ops/s $\color{#d91a1a}-1.86\%$
test_cql_speed[reduce-overhead-None] 17.5116ms 16.5242ms 60.5172 Ops/s 61.1487 Ops/s $\color{#d91a1a}-1.03\%$
test_cql_speed[reduce-overhead-backward] 24.8026ms 23.3285ms 42.8660 Ops/s 42.5871 Ops/s $\color{#35bf28}+0.65\%$
test_a2c_speed[False-None] 10.0069ms 7.6997ms 129.8757 Ops/s 125.8417 Ops/s $\color{#35bf28}+3.21\%$
test_a2c_speed[False-backward] 15.5396ms 15.1678ms 65.9290 Ops/s 63.1470 Ops/s $\color{#35bf28}+4.41\%$
test_a2c_speed[True-None] 4.5536ms 3.6907ms 270.9478 Ops/s 299.1685 Ops/s $\textbf{\color{#d91a1a}-9.43\%}$
test_a2c_speed[True-backward] 11.4754ms 10.8158ms 92.4570 Ops/s 93.7322 Ops/s $\color{#d91a1a}-1.36\%$
test_a2c_speed[reduce-overhead-None] 4.7142ms 3.7625ms 265.7811 Ops/s 264.7791 Ops/s $\color{#35bf28}+0.38\%$
test_a2c_speed[reduce-overhead-backward] 11.2818ms 10.8954ms 91.7818 Ops/s 95.8886 Ops/s $\color{#d91a1a}-4.28\%$
test_ppo_speed[False-None] 9.1266ms 8.2458ms 121.2735 Ops/s 129.9410 Ops/s $\textbf{\color{#d91a1a}-6.67\%}$
test_ppo_speed[False-backward] 17.0096ms 16.1760ms 61.8199 Ops/s 64.1697 Ops/s $\color{#d91a1a}-3.66\%$
test_ppo_speed[True-None] 4.6677ms 3.9355ms 254.0991 Ops/s 255.6039 Ops/s $\color{#d91a1a}-0.59\%$
test_ppo_speed[True-backward] 11.1185ms 10.5305ms 94.9625 Ops/s 93.6488 Ops/s $\color{#35bf28}+1.40\%$
test_ppo_speed[reduce-overhead-None] 4.6234ms 3.9581ms 252.6466 Ops/s 238.9160 Ops/s $\textbf{\color{#35bf28}+5.75\%}$
test_ppo_speed[reduce-overhead-backward] 12.2697ms 10.6131ms 94.2230 Ops/s 93.4211 Ops/s $\color{#35bf28}+0.86\%$
test_reinforce_speed[False-None] 7.6015ms 6.8801ms 145.3472 Ops/s 145.2724 Ops/s $\color{#35bf28}+0.05\%$
test_reinforce_speed[False-backward] 11.7505ms 10.3926ms 96.2226 Ops/s 94.6014 Ops/s $\color{#35bf28}+1.71\%$
test_reinforce_speed[True-None] 3.2675ms 2.8562ms 350.1215 Ops/s 333.4713 Ops/s $\color{#35bf28}+4.99\%$
test_reinforce_speed[True-backward] 9.4648ms 9.0242ms 110.8128 Ops/s 103.4313 Ops/s $\textbf{\color{#35bf28}+7.14\%}$
test_reinforce_speed[reduce-overhead-None] 3.1541ms 2.7268ms 366.7254 Ops/s 346.8478 Ops/s $\textbf{\color{#35bf28}+5.73\%}$
test_reinforce_speed[reduce-overhead-backward] 9.6513ms 9.3678ms 106.7490 Ops/s 102.7132 Ops/s $\color{#35bf28}+3.93\%$
test_iql_speed[False-None] 34.4951ms 33.4998ms 29.8510 Ops/s 29.6498 Ops/s $\color{#35bf28}+0.68\%$
test_iql_speed[False-backward] 47.5114ms 46.5769ms 21.4699 Ops/s 21.4261 Ops/s $\color{#35bf28}+0.20\%$
test_iql_speed[True-None] 12.1673ms 11.3043ms 88.4617 Ops/s 87.9276 Ops/s $\color{#35bf28}+0.61\%$
test_iql_speed[True-backward] 24.3368ms 23.4513ms 42.6415 Ops/s 42.9341 Ops/s $\color{#d91a1a}-0.68\%$
test_iql_speed[reduce-overhead-None] 12.1852ms 11.3508ms 88.0993 Ops/s 88.0472 Ops/s $\color{#35bf28}+0.06\%$
test_iql_speed[reduce-overhead-backward] 23.4130ms 22.4484ms 44.5467 Ops/s 42.9106 Ops/s $\color{#35bf28}+3.81\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.0279ms 5.1342ms 194.7707 Ops/s 178.0219 Ops/s $\textbf{\color{#35bf28}+9.41\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1631ms 0.4880ms 2.0494 KOps/s 1.9813 KOps/s $\color{#35bf28}+3.43\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 1.0325ms 0.4891ms 2.0448 KOps/s 2.1041 KOps/s $\color{#d91a1a}-2.82\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.8672ms 5.1558ms 193.9574 Ops/s 182.5603 Ops/s $\textbf{\color{#35bf28}+6.24\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.2109ms 0.4953ms 2.0192 KOps/s 2.0037 KOps/s $\color{#35bf28}+0.77\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7127ms 0.4698ms 2.1284 KOps/s 2.1211 KOps/s $\color{#35bf28}+0.34\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.1801ms 1.6006ms 624.7716 Ops/s 625.8073 Ops/s $\color{#d91a1a}-0.17\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.1456ms 1.5577ms 641.9838 Ops/s 644.1794 Ops/s $\color{#d91a1a}-0.34\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.7066ms 5.3735ms 186.0993 Ops/s 180.0426 Ops/s $\color{#35bf28}+3.36\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 3.6089ms 0.6449ms 1.5507 KOps/s 1.5854 KOps/s $\color{#d91a1a}-2.19\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.1479ms 0.6191ms 1.6154 KOps/s 1.6311 KOps/s $\color{#d91a1a}-0.97\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.6975ms 5.2932ms 188.9233 Ops/s 189.5965 Ops/s $\color{#d91a1a}-0.36\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.4989ms 0.5224ms 1.9141 KOps/s 1.9792 KOps/s $\color{#d91a1a}-3.29\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7462ms 0.4786ms 2.0894 KOps/s 2.0557 KOps/s $\color{#35bf28}+1.64\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.4820ms 5.1466ms 194.3028 Ops/s 195.0293 Ops/s $\color{#d91a1a}-0.37\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.7524ms 0.5055ms 1.9783 KOps/s 1.9872 KOps/s $\color{#d91a1a}-0.45\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7315ms 0.4785ms 2.0898 KOps/s 2.0973 KOps/s $\color{#d91a1a}-0.36\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.7641ms 5.3706ms 186.2004 Ops/s 190.5038 Ops/s $\color{#d91a1a}-2.26\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2135ms 0.6460ms 1.5481 KOps/s 1.5872 KOps/s $\color{#d91a1a}-2.46\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 8.4444ms 0.6133ms 1.6304 KOps/s 1.6286 KOps/s $\color{#35bf28}+0.11\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 5.6462ms 4.2509ms 235.2423 Ops/s 250.4220 Ops/s $\textbf{\color{#d91a1a}-6.06\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 7.8954ms 2.3021ms 434.3922 Ops/s 392.7074 Ops/s $\textbf{\color{#35bf28}+10.61\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 5.0862ms 1.2737ms 785.1104 Ops/s 734.9479 Ops/s $\textbf{\color{#35bf28}+6.83\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4472s 13.2489ms 75.4780 Ops/s 30.7282 Ops/s $\textbf{\color{#35bf28}+145.63\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 7.9242ms 2.3442ms 426.5872 Ops/s 422.2040 Ops/s $\color{#35bf28}+1.04\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 3.8386ms 1.2568ms 795.7027 Ops/s 773.2344 Ops/s $\color{#35bf28}+2.91\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 6.2868ms 4.4023ms 227.1557 Ops/s 205.5497 Ops/s $\textbf{\color{#35bf28}+10.51\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.0958ms 2.5263ms 395.8431 Ops/s 393.0610 Ops/s $\color{#35bf28}+0.71\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 1.8652ms 1.3434ms 744.3539 Ops/s 714.0888 Ops/s $\color{#35bf28}+4.24\%$

Copy link

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

Total Benchmarks: 143. Improved: $\large\color{#35bf28}12$. Worsened: $\large\color{#d91a1a}12$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7545s 0.7464s 1.3398 Ops/s 1.3412 Ops/s $\color{#d91a1a}-0.10\%$
test_transformed 1.0749s 0.9994s 1.0006 Ops/s 1.0121 Ops/s $\color{#d91a1a}-1.14\%$
test_serial 2.2430s 2.1622s 0.4625 Ops/s 0.4625 Ops/s $-0.01\%$
test_parallel 2.0481s 2.0148s 0.4963 Ops/s 0.4847 Ops/s $\color{#35bf28}+2.39\%$
test_step_mdp_speed[True-True-True-True-True] 0.2526ms 39.7128μs 25.1808 KOps/s 25.4887 KOps/s $\color{#d91a1a}-1.21\%$
test_step_mdp_speed[True-True-True-True-False] 49.7310μs 23.4153μs 42.7071 KOps/s 43.4344 KOps/s $\color{#d91a1a}-1.67\%$
test_step_mdp_speed[True-True-True-False-True] 49.9710μs 21.9244μs 45.6113 KOps/s 46.3868 KOps/s $\color{#d91a1a}-1.67\%$
test_step_mdp_speed[True-True-True-False-False] 38.8310μs 12.9163μs 77.4217 KOps/s 79.9489 KOps/s $\color{#d91a1a}-3.16\%$
test_step_mdp_speed[True-True-False-True-True] 82.4520μs 42.7106μs 23.4134 KOps/s 23.6079 KOps/s $\color{#d91a1a}-0.82\%$
test_step_mdp_speed[True-True-False-True-False] 57.6810μs 25.8836μs 38.6345 KOps/s 39.1690 KOps/s $\color{#d91a1a}-1.36\%$
test_step_mdp_speed[True-True-False-False-True] 52.8210μs 24.9284μs 40.1150 KOps/s 41.4397 KOps/s $\color{#d91a1a}-3.20\%$
test_step_mdp_speed[True-True-False-False-False] 48.3210μs 15.6137μs 64.0463 KOps/s 66.9518 KOps/s $\color{#d91a1a}-4.34\%$
test_step_mdp_speed[True-False-True-True-True] 77.9620μs 45.7966μs 21.8357 KOps/s 22.5658 KOps/s $\color{#d91a1a}-3.24\%$
test_step_mdp_speed[True-False-True-True-False] 97.2430μs 28.4800μs 35.1123 KOps/s 35.5460 KOps/s $\color{#d91a1a}-1.22\%$
test_step_mdp_speed[True-False-True-False-True] 52.1510μs 25.0346μs 39.9447 KOps/s 42.1101 KOps/s $\textbf{\color{#d91a1a}-5.14\%}$
test_step_mdp_speed[True-False-True-False-False] 38.7700μs 15.5462μs 64.3245 KOps/s 65.9421 KOps/s $\color{#d91a1a}-2.45\%$
test_step_mdp_speed[True-False-False-True-True] 78.9820μs 48.1526μs 20.7673 KOps/s 21.3935 KOps/s $\color{#d91a1a}-2.93\%$
test_step_mdp_speed[True-False-False-True-False] 71.6520μs 31.5345μs 31.7113 KOps/s 32.2879 KOps/s $\color{#d91a1a}-1.79\%$
test_step_mdp_speed[True-False-False-False-True] 57.1620μs 27.3513μs 36.5614 KOps/s 37.2069 KOps/s $\color{#d91a1a}-1.73\%$
test_step_mdp_speed[True-False-False-False-False] 45.6110μs 18.3142μs 54.6025 KOps/s 56.0275 KOps/s $\color{#d91a1a}-2.54\%$
test_step_mdp_speed[False-True-True-True-True] 81.5210μs 45.7380μs 21.8636 KOps/s 22.7265 KOps/s $\color{#d91a1a}-3.80\%$
test_step_mdp_speed[False-True-True-True-False] 56.2110μs 28.9800μs 34.5066 KOps/s 35.7459 KOps/s $\color{#d91a1a}-3.47\%$
test_step_mdp_speed[False-True-True-False-True] 57.8010μs 29.5444μs 33.8474 KOps/s 35.5022 KOps/s $\color{#d91a1a}-4.66\%$
test_step_mdp_speed[False-True-True-False-False] 45.1310μs 18.0477μs 55.4088 KOps/s 56.6732 KOps/s $\color{#d91a1a}-2.23\%$
test_step_mdp_speed[False-True-False-True-True] 76.5420μs 48.3706μs 20.6737 KOps/s 21.5548 KOps/s $\color{#d91a1a}-4.09\%$
test_step_mdp_speed[False-True-False-True-False] 58.8910μs 31.3682μs 31.8794 KOps/s 32.3434 KOps/s $\color{#d91a1a}-1.43\%$
test_step_mdp_speed[False-True-False-False-True] 3.1137ms 32.8488μs 30.4425 KOps/s 32.9434 KOps/s $\textbf{\color{#d91a1a}-7.59\%}$
test_step_mdp_speed[False-True-False-False-False] 46.1310μs 20.9160μs 47.8104 KOps/s 49.6391 KOps/s $\color{#d91a1a}-3.68\%$
test_step_mdp_speed[False-False-True-True-True] 79.9920μs 51.5073μs 19.4147 KOps/s 19.8865 KOps/s $\color{#d91a1a}-2.37\%$
test_step_mdp_speed[False-False-True-True-False] 65.1720μs 34.2810μs 29.1707 KOps/s 29.6964 KOps/s $\color{#d91a1a}-1.77\%$
test_step_mdp_speed[False-False-True-False-True] 71.9510μs 32.6145μs 30.6612 KOps/s 31.6072 KOps/s $\color{#d91a1a}-2.99\%$
test_step_mdp_speed[False-False-True-False-False] 49.9810μs 20.9173μs 47.8072 KOps/s 49.8073 KOps/s $\color{#d91a1a}-4.02\%$
test_step_mdp_speed[False-False-False-True-True] 82.1610μs 52.7204μs 18.9680 KOps/s 19.1703 KOps/s $\color{#d91a1a}-1.06\%$
test_step_mdp_speed[False-False-False-True-False] 62.3020μs 37.3048μs 26.8062 KOps/s 27.7373 KOps/s $\color{#d91a1a}-3.36\%$
test_step_mdp_speed[False-False-False-False-True] 62.3910μs 34.1637μs 29.2708 KOps/s 30.5802 KOps/s $\color{#d91a1a}-4.28\%$
test_step_mdp_speed[False-False-False-False-False] 49.6610μs 23.3204μs 42.8808 KOps/s 44.8322 KOps/s $\color{#d91a1a}-4.35\%$
test_values[generalized_advantage_estimate-True-True] 25.1473ms 24.6990ms 40.4874 Ops/s 41.3892 Ops/s $\color{#d91a1a}-2.18\%$
test_values[vec_generalized_advantage_estimate-True-True] 99.6525ms 2.8832ms 346.8354 Ops/s 320.5818 Ops/s $\textbf{\color{#35bf28}+8.19\%}$
test_values[td0_return_estimate-False-False] 0.1090ms 66.1497μs 15.1172 KOps/s 15.3069 KOps/s $\color{#d91a1a}-1.24\%$
test_values[td1_return_estimate-False-False] 55.0595ms 54.7369ms 18.2692 Ops/s 18.5082 Ops/s $\color{#d91a1a}-1.29\%$
test_values[vec_td1_return_estimate-False-False] 1.3320ms 1.0749ms 930.2824 Ops/s 932.1143 Ops/s $\color{#d91a1a}-0.20\%$
test_values[td_lambda_return_estimate-True-False] 93.2931ms 86.9674ms 11.4986 Ops/s 11.6868 Ops/s $\color{#d91a1a}-1.61\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.3952ms 1.0751ms 930.1705 Ops/s 937.0191 Ops/s $\color{#d91a1a}-0.73\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.7958ms 24.5612ms 40.7147 Ops/s 41.8577 Ops/s $\color{#d91a1a}-2.73\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0271ms 0.7436ms 1.3448 KOps/s 1.3218 KOps/s $\color{#35bf28}+1.73\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7635ms 0.6615ms 1.5116 KOps/s 1.4692 KOps/s $\color{#35bf28}+2.88\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5053ms 1.4708ms 679.9158 Ops/s 679.4014 Ops/s $\color{#35bf28}+0.08\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7134ms 0.6775ms 1.4761 KOps/s 1.4745 KOps/s $\color{#35bf28}+0.11\%$
test_dqn_speed[False-None] 6.8323ms 1.4258ms 701.3820 Ops/s 732.7824 Ops/s $\color{#d91a1a}-4.29\%$
test_dqn_speed[False-backward] 2.0774ms 1.9190ms 521.1157 Ops/s 537.5584 Ops/s $\color{#d91a1a}-3.06\%$
test_dqn_speed[True-None] 0.8138ms 0.5675ms 1.7622 KOps/s 1.7135 KOps/s $\color{#35bf28}+2.84\%$
test_dqn_speed[True-backward] 1.0923ms 1.0228ms 977.6848 Ops/s 879.9064 Ops/s $\textbf{\color{#35bf28}+11.11\%}$
test_dqn_speed[reduce-overhead-None] 0.9261ms 0.5733ms 1.7442 KOps/s 1.7174 KOps/s $\color{#35bf28}+1.56\%$
test_dqn_speed[reduce-overhead-backward] 1.0521ms 1.0220ms 978.4355 Ops/s 981.6565 Ops/s $\color{#d91a1a}-0.33\%$
test_ddpg_speed[False-None] 3.0102ms 2.7949ms 357.7884 Ops/s 359.6805 Ops/s $\color{#d91a1a}-0.53\%$
test_ddpg_speed[False-backward] 4.1043ms 4.0032ms 249.8006 Ops/s 249.9926 Ops/s $\color{#d91a1a}-0.08\%$
test_ddpg_speed[True-None] 1.6209ms 1.2650ms 790.4866 Ops/s 796.5742 Ops/s $\color{#d91a1a}-0.76\%$
test_ddpg_speed[True-backward] 2.2909ms 2.2433ms 445.7676 Ops/s 345.8710 Ops/s $\textbf{\color{#35bf28}+28.88\%}$
test_ddpg_speed[reduce-overhead-None] 1.4938ms 1.2707ms 786.9950 Ops/s 793.0117 Ops/s $\color{#d91a1a}-0.76\%$
test_ddpg_speed[reduce-overhead-backward] 2.2918ms 2.2462ms 445.2047 Ops/s 449.2882 Ops/s $\color{#d91a1a}-0.91\%$
test_sac_speed[False-None] 8.6059ms 7.8035ms 128.1481 Ops/s 127.7589 Ops/s $\color{#35bf28}+0.30\%$
test_sac_speed[False-backward] 11.4473ms 11.0185ms 90.7567 Ops/s 90.9733 Ops/s $\color{#d91a1a}-0.24\%$
test_sac_speed[True-None] 2.4011ms 2.0509ms 487.5870 Ops/s 483.0109 Ops/s $\color{#35bf28}+0.95\%$
test_sac_speed[True-backward] 4.0844ms 3.9672ms 252.0693 Ops/s 208.1584 Ops/s $\textbf{\color{#35bf28}+21.09\%}$
test_sac_speed[reduce-overhead-None] 2.5195ms 2.0808ms 480.5737 Ops/s 481.9923 Ops/s $\color{#d91a1a}-0.29\%$
test_sac_speed[reduce-overhead-backward] 4.1841ms 3.9993ms 250.0425 Ops/s 253.1531 Ops/s $\color{#d91a1a}-1.23\%$
test_redq_speed[False-None] 16.1082ms 11.0635ms 90.3873 Ops/s 97.9342 Ops/s $\textbf{\color{#d91a1a}-7.71\%}$
test_redq_speed[False-backward] 18.4399ms 17.4373ms 57.3482 Ops/s 57.0258 Ops/s $\color{#35bf28}+0.57\%$
test_redq_speed[True-None] 3.8822ms 3.5782ms 279.4709 Ops/s 284.8652 Ops/s $\color{#d91a1a}-1.89\%$
test_redq_speed[True-backward] 8.8538ms 8.5649ms 116.7550 Ops/s 118.7442 Ops/s $\color{#d91a1a}-1.68\%$
test_redq_speed[reduce-overhead-None] 3.8691ms 3.5461ms 282.0026 Ops/s 286.0817 Ops/s $\color{#d91a1a}-1.43\%$
test_redq_speed[reduce-overhead-backward] 8.9631ms 8.5821ms 116.5211 Ops/s 117.9561 Ops/s $\color{#d91a1a}-1.22\%$
test_redq_deprec_speed[False-None] 11.2176ms 10.7420ms 93.0922 Ops/s 94.5159 Ops/s $\color{#d91a1a}-1.51\%$
test_redq_deprec_speed[False-backward] 15.9131ms 15.4671ms 64.6532 Ops/s 65.7936 Ops/s $\color{#d91a1a}-1.73\%$
test_redq_deprec_speed[True-None] 3.6721ms 3.3123ms 301.9044 Ops/s 310.3335 Ops/s $\color{#d91a1a}-2.72\%$
test_redq_deprec_speed[True-backward] 7.4822ms 7.1541ms 139.7808 Ops/s 125.5691 Ops/s $\textbf{\color{#35bf28}+11.32\%}$
test_redq_deprec_speed[reduce-overhead-None] 3.5747ms 3.2559ms 307.1325 Ops/s 296.8422 Ops/s $\color{#35bf28}+3.47\%$
test_redq_deprec_speed[reduce-overhead-backward] 7.3076ms 7.1717ms 139.4363 Ops/s 134.6448 Ops/s $\color{#35bf28}+3.56\%$
test_td3_speed[False-None] 7.9713ms 7.7175ms 129.5750 Ops/s 130.2094 Ops/s $\color{#d91a1a}-0.49\%$
test_td3_speed[False-backward] 10.8263ms 10.5490ms 94.7955 Ops/s 95.6558 Ops/s $\color{#d91a1a}-0.90\%$
test_td3_speed[True-None] 1.9871ms 1.9294ms 518.2840 Ops/s 513.2429 Ops/s $\color{#35bf28}+0.98\%$
test_td3_speed[True-backward] 3.8434ms 3.7279ms 268.2451 Ops/s 266.9826 Ops/s $\color{#35bf28}+0.47\%$
test_td3_speed[reduce-overhead-None] 1.9530ms 1.9158ms 521.9711 Ops/s 512.4906 Ops/s $\color{#35bf28}+1.85\%$
test_td3_speed[reduce-overhead-backward] 3.8604ms 3.7249ms 268.4667 Ops/s 259.5301 Ops/s $\color{#35bf28}+3.44\%$
test_cql_speed[False-None] 28.1889ms 25.0771ms 39.8770 Ops/s 40.7543 Ops/s $\color{#d91a1a}-2.15\%$
test_cql_speed[False-backward] 37.8016ms 34.2650ms 29.1843 Ops/s 29.1213 Ops/s $\color{#35bf28}+0.22\%$
test_cql_speed[True-None] 11.2093ms 10.9036ms 91.7128 Ops/s 93.2535 Ops/s $\color{#d91a1a}-1.65\%$
test_cql_speed[True-backward] 16.9802ms 16.6395ms 60.0981 Ops/s 58.7035 Ops/s $\color{#35bf28}+2.38\%$
test_cql_speed[reduce-overhead-None] 11.2414ms 10.9318ms 91.4759 Ops/s 91.6640 Ops/s $\color{#d91a1a}-0.21\%$
test_cql_speed[reduce-overhead-backward] 17.0842ms 16.6219ms 60.1617 Ops/s 60.6753 Ops/s $\color{#d91a1a}-0.85\%$
test_a2c_speed[False-None] 5.7262ms 5.3683ms 186.2772 Ops/s 179.3654 Ops/s $\color{#35bf28}+3.85\%$
test_a2c_speed[False-backward] 13.1684ms 11.7980ms 84.7600 Ops/s 83.2401 Ops/s $\color{#35bf28}+1.83\%$
test_a2c_speed[True-None] 3.4616ms 3.0549ms 327.3472 Ops/s 317.7767 Ops/s $\color{#35bf28}+3.01\%$
test_a2c_speed[True-backward] 8.9464ms 8.5750ms 116.6185 Ops/s 101.6491 Ops/s $\textbf{\color{#35bf28}+14.73\%}$
test_a2c_speed[reduce-overhead-None] 3.2113ms 3.0680ms 325.9490 Ops/s 326.4326 Ops/s $\color{#d91a1a}-0.15\%$
test_a2c_speed[reduce-overhead-backward] 8.9378ms 8.5805ms 116.5432 Ops/s 118.6328 Ops/s $\color{#d91a1a}-1.76\%$
test_ppo_speed[False-None] 7.6775ms 5.8124ms 172.0450 Ops/s 171.6340 Ops/s $\color{#35bf28}+0.24\%$
test_ppo_speed[False-backward] 12.6547ms 12.3424ms 81.0214 Ops/s 81.1621 Ops/s $\color{#d91a1a}-0.17\%$
test_ppo_speed[True-None] 3.5938ms 3.4650ms 288.5977 Ops/s 288.0967 Ops/s $\color{#35bf28}+0.17\%$
test_ppo_speed[True-backward] 8.5822ms 8.3280ms 120.0775 Ops/s 108.2618 Ops/s $\textbf{\color{#35bf28}+10.91\%}$
test_ppo_speed[reduce-overhead-None] 3.5730ms 3.4410ms 290.6113 Ops/s 287.6069 Ops/s $\color{#35bf28}+1.04\%$
test_ppo_speed[reduce-overhead-backward] 8.4186ms 8.2233ms 121.6053 Ops/s 120.4578 Ops/s $\color{#35bf28}+0.95\%$
test_reinforce_speed[False-None] 4.8160ms 4.4895ms 222.7434 Ops/s 218.9224 Ops/s $\color{#35bf28}+1.75\%$
test_reinforce_speed[False-backward] 7.5158ms 7.3165ms 136.6777 Ops/s 135.5850 Ops/s $\color{#35bf28}+0.81\%$
test_reinforce_speed[True-None] 2.4043ms 2.2242ms 449.5963 Ops/s 444.2252 Ops/s $\color{#35bf28}+1.21\%$
test_reinforce_speed[True-backward] 7.2361ms 7.0984ms 140.8763 Ops/s 144.1004 Ops/s $\color{#d91a1a}-2.24\%$
test_reinforce_speed[reduce-overhead-None] 2.6869ms 2.2274ms 448.9630 Ops/s 447.3951 Ops/s $\color{#35bf28}+0.35\%$
test_reinforce_speed[reduce-overhead-backward] 7.2404ms 7.0607ms 141.6286 Ops/s 142.6949 Ops/s $\color{#d91a1a}-0.75\%$
test_iql_speed[False-None] 19.8124ms 19.3096ms 51.7878 Ops/s 51.6525 Ops/s $\color{#35bf28}+0.26\%$
test_iql_speed[False-backward] 38.2979ms 30.4138ms 32.8799 Ops/s 33.6569 Ops/s $\color{#d91a1a}-2.31\%$
test_iql_speed[True-None] 7.0074ms 6.7332ms 148.5169 Ops/s 162.5087 Ops/s $\textbf{\color{#d91a1a}-8.61\%}$
test_iql_speed[True-backward] 15.8778ms 15.4161ms 64.8672 Ops/s 64.1764 Ops/s $\color{#35bf28}+1.08\%$
test_iql_speed[reduce-overhead-None] 7.1085ms 6.7371ms 148.4313 Ops/s 149.2963 Ops/s $\color{#d91a1a}-0.58\%$
test_iql_speed[reduce-overhead-backward] 15.9739ms 15.4137ms 64.8775 Ops/s 63.2073 Ops/s $\color{#35bf28}+2.64\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.4701ms 6.3690ms 157.0109 Ops/s 156.7082 Ops/s $\color{#35bf28}+0.19\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8881ms 0.2510ms 3.9845 KOps/s 2.4140 KOps/s $\textbf{\color{#35bf28}+65.05\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5357ms 0.2646ms 3.7799 KOps/s 2.7895 KOps/s $\textbf{\color{#35bf28}+35.51\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.4226ms 6.1533ms 162.5150 Ops/s 164.5291 Ops/s $\color{#d91a1a}-1.22\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.7251ms 0.2410ms 4.1487 KOps/s 3.9793 KOps/s $\color{#35bf28}+4.26\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6131ms 0.3372ms 2.9657 KOps/s 4.2577 KOps/s $\textbf{\color{#d91a1a}-30.35\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6743ms 1.4548ms 687.3845 Ops/s 780.5858 Ops/s $\textbf{\color{#d91a1a}-11.94\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.7024ms 1.4071ms 710.6877 Ops/s 819.1501 Ops/s $\textbf{\color{#d91a1a}-13.24\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4271ms 6.2985ms 158.7668 Ops/s 159.7609 Ops/s $\color{#d91a1a}-0.62\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1359ms 0.4977ms 2.0094 KOps/s 2.2446 KOps/s $\textbf{\color{#d91a1a}-10.48\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7094ms 0.4891ms 2.0446 KOps/s 2.3823 KOps/s $\textbf{\color{#d91a1a}-14.17\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.2377ms 6.1253ms 163.2566 Ops/s 164.4341 Ops/s $\color{#d91a1a}-0.72\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.2514ms 0.3749ms 2.6677 KOps/s 4.0676 KOps/s $\textbf{\color{#d91a1a}-34.41\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5483ms 0.2881ms 3.4711 KOps/s 4.5062 KOps/s $\textbf{\color{#d91a1a}-22.97\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.0458ms 6.1219ms 163.3491 Ops/s 165.5554 Ops/s $\color{#d91a1a}-1.33\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.6305ms 0.2470ms 4.0481 KOps/s 3.3755 KOps/s $\textbf{\color{#35bf28}+19.92\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.4313ms 0.2178ms 4.5906 KOps/s 3.5476 KOps/s $\textbf{\color{#35bf28}+29.40\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5335ms 6.2990ms 158.7548 Ops/s 156.2255 Ops/s $\color{#35bf28}+1.62\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0518ms 0.4700ms 2.1276 KOps/s 2.1656 KOps/s $\color{#d91a1a}-1.75\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6765ms 0.4496ms 2.2244 KOps/s 2.2368 KOps/s $\color{#d91a1a}-0.56\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 7.1199ms 5.5328ms 180.7399 Ops/s 185.7093 Ops/s $\color{#d91a1a}-2.68\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 9.9199ms 2.0612ms 485.1614 Ops/s 496.5848 Ops/s $\color{#d91a1a}-2.30\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 3.4444ms 1.1699ms 854.7830 Ops/s 801.8704 Ops/s $\textbf{\color{#35bf28}+6.60\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4298s 14.1267ms 70.7878 Ops/s 183.3106 Ops/s $\textbf{\color{#d91a1a}-61.38\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 7.1752ms 2.0307ms 492.4406 Ops/s 496.0060 Ops/s $\color{#d91a1a}-0.72\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 8.8135ms 1.2465ms 802.2660 Ops/s 795.2469 Ops/s $\color{#35bf28}+0.88\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 8.1495ms 5.7745ms 173.1737 Ops/s 179.4427 Ops/s $\color{#d91a1a}-3.49\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.4839ms 2.1721ms 460.3874 Ops/s 455.1078 Ops/s $\color{#35bf28}+1.16\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.8726ms 1.4037ms 712.3796 Ops/s 724.5719 Ops/s $\color{#d91a1a}-1.68\%$

@vmoens vmoens merged commit 1b9f86b into gh/vmoens/35/base Oct 22, 2024
73 of 74 checks passed
vmoens added a commit that referenced this pull request Oct 22, 2024
ghstack-source-id: 06c5f1ece3bb5cc222d7b3accfee799af98816ae
Pull Request resolved: #2512
@vmoens vmoens deleted the gh/vmoens/35/head branch October 22, 2024 07:45
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. Data Data-related PR, will launch data-related jobs Environments Adds or modifies an environment wrapper
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants