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.

Sign up for GitHub

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

Jump to bottom

[Doc] Fix tutorials #2560

Merged
merged 1 commit into from
Nov 13, 2024
Merged

[Doc] Fix tutorials #2560

merged 1 commit into from
Nov 13, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Nov 13, 2024 •
edited
Loading

Stack from ghstack (oldest at bottom):

@vmoens
Update
9f16e62 
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Nov 13, 2024
@vmoens
[Doc] Fix tutorials
074328b 
ghstack-source-id: 6c9114384015e76e96b3bbd0c8893cc42344537a
Pull Request resolved: #2560
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Nov 13, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2560

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

❌ 2 New Failures, 14 Unrelated Failures

As of commit 9f16e62 with merge base 165163a (image):

NEW FAILURES - The following jobs have failed:

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

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 Nov 13, 2024
@vmoens vmoens added the documentation Improvements or additions to documentation label Nov 13, 2024
@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}18$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4270s 0.4241s 2.3577 Ops/s 2.2544 Ops/s $\color{#35bf28}+4.58\%$
test_transformed 0.6045s 0.5984s 1.6712 Ops/s 1.6192 Ops/s $\color{#35bf28}+3.21\%$
test_serial 1.3291s 1.3237s 0.7554 Ops/s 0.7356 Ops/s $\color{#35bf28}+2.70\%$
test_parallel 1.2895s 1.2828s 0.7795 Ops/s 0.7512 Ops/s $\color{#35bf28}+3.78\%$
test_step_mdp_speed[True-True-True-True-True] 0.2252ms 26.1778μs 38.2003 KOps/s 36.1509 KOps/s $\textbf{\color{#35bf28}+5.67\%}$
test_step_mdp_speed[True-True-True-True-False] 52.3480μs 15.4525μs 64.7146 KOps/s 61.7461 KOps/s $\color{#35bf28}+4.81\%$
test_step_mdp_speed[True-True-True-False-True] 75.6820μs 15.0118μs 66.6145 KOps/s 64.3929 KOps/s $\color{#35bf28}+3.45\%$
test_step_mdp_speed[True-True-True-False-False] 52.4980μs 8.8180μs 113.4040 KOps/s 110.5224 KOps/s $\color{#35bf28}+2.61\%$
test_step_mdp_speed[True-True-False-True-True] 76.2520μs 28.3661μs 35.2533 KOps/s 34.0759 KOps/s $\color{#35bf28}+3.46\%$
test_step_mdp_speed[True-True-False-True-False] 50.1840μs 17.0614μs 58.6120 KOps/s 56.1278 KOps/s $\color{#35bf28}+4.43\%$
test_step_mdp_speed[True-True-False-False-True] 51.6160μs 16.5260μs 60.5105 KOps/s 58.2380 KOps/s $\color{#35bf28}+3.90\%$
test_step_mdp_speed[True-True-False-False-False] 0.5447ms 10.4658μs 95.5494 KOps/s 93.1284 KOps/s $\color{#35bf28}+2.60\%$
test_step_mdp_speed[True-False-True-True-True] 95.5620μs 29.7388μs 33.6261 KOps/s 32.5967 KOps/s $\color{#35bf28}+3.16\%$
test_step_mdp_speed[True-False-True-True-False] 71.0730μs 18.7010μs 53.4732 KOps/s 51.5495 KOps/s $\color{#35bf28}+3.73\%$
test_step_mdp_speed[True-False-True-False-True] 60.3020μs 16.7421μs 59.7298 KOps/s 58.7262 KOps/s $\color{#35bf28}+1.71\%$
test_step_mdp_speed[True-False-True-False-False] 68.0670μs 10.4597μs 95.6049 KOps/s 92.7809 KOps/s $\color{#35bf28}+3.04\%$
test_step_mdp_speed[True-False-False-True-True] 67.0250μs 31.7041μs 31.5416 KOps/s 31.2732 KOps/s $\color{#35bf28}+0.86\%$
test_step_mdp_speed[True-False-False-True-False] 78.7870μs 20.4610μs 48.8736 KOps/s 48.0306 KOps/s $\color{#35bf28}+1.76\%$
test_step_mdp_speed[True-False-False-False-True] 72.4450μs 18.2452μs 54.8090 KOps/s 53.9793 KOps/s $\color{#35bf28}+1.54\%$
test_step_mdp_speed[True-False-False-False-False] 76.7430μs 12.0341μs 83.0969 KOps/s 81.1944 KOps/s $\color{#35bf28}+2.34\%$
test_step_mdp_speed[False-True-True-True-True] 86.3820μs 30.0961μs 33.2269 KOps/s 32.1798 KOps/s $\color{#35bf28}+3.25\%$
test_step_mdp_speed[False-True-True-True-False] 95.9060μs 18.4521μs 54.1945 KOps/s 50.8598 KOps/s $\textbf{\color{#35bf28}+6.56\%}$
test_step_mdp_speed[False-True-True-False-True] 58.7700μs 18.7718μs 53.2715 KOps/s 50.9763 KOps/s $\color{#35bf28}+4.50\%$
test_step_mdp_speed[False-True-True-False-False] 60.3330μs 11.4705μs 87.1801 KOps/s 82.2242 KOps/s $\textbf{\color{#35bf28}+6.03\%}$
test_step_mdp_speed[False-True-False-True-True] 85.5400μs 30.7714μs 32.4977 KOps/s 30.9475 KOps/s $\textbf{\color{#35bf28}+5.01\%}$
test_step_mdp_speed[False-True-False-True-False] 49.8940μs 20.2148μs 49.4687 KOps/s 47.1411 KOps/s $\color{#35bf28}+4.94\%$
test_step_mdp_speed[False-True-False-False-True] 2.8737ms 20.5994μs 48.5451 KOps/s 46.8614 KOps/s $\color{#35bf28}+3.59\%$
test_step_mdp_speed[False-True-False-False-False] 84.0050μs 13.1622μs 75.9752 KOps/s 72.7930 KOps/s $\color{#35bf28}+4.37\%$
test_step_mdp_speed[False-False-True-True-True] 63.3380μs 32.4675μs 30.8000 KOps/s 29.4144 KOps/s $\color{#35bf28}+4.71\%$
test_step_mdp_speed[False-False-True-True-False] 54.0010μs 21.5792μs 46.3409 KOps/s 43.9635 KOps/s $\textbf{\color{#35bf28}+5.41\%}$
test_step_mdp_speed[False-False-True-False-True] 0.6071ms 20.2596μs 49.3592 KOps/s 47.3142 KOps/s $\color{#35bf28}+4.32\%$
test_step_mdp_speed[False-False-True-False-False] 58.3790μs 13.1300μs 76.1612 KOps/s 72.2536 KOps/s $\textbf{\color{#35bf28}+5.41\%}$
test_step_mdp_speed[False-False-False-True-True] 0.1027ms 33.7234μs 29.6530 KOps/s 28.2200 KOps/s $\textbf{\color{#35bf28}+5.08\%}$
test_step_mdp_speed[False-False-False-True-False] 76.6030μs 22.4755μs 44.4929 KOps/s 41.2296 KOps/s $\textbf{\color{#35bf28}+7.91\%}$
test_step_mdp_speed[False-False-False-False-True] 87.5630μs 21.7576μs 45.9609 KOps/s 44.1208 KOps/s $\color{#35bf28}+4.17\%$
test_step_mdp_speed[False-False-False-False-False] 50.1940μs 14.6208μs 68.3955 KOps/s 65.4543 KOps/s $\color{#35bf28}+4.49\%$
test_values[generalized_advantage_estimate-True-True] 10.7160ms 9.7814ms 102.2346 Ops/s 99.7924 Ops/s $\color{#35bf28}+2.45\%$
test_values[vec_generalized_advantage_estimate-True-True] 36.7363ms 33.7296ms 29.6475 Ops/s 29.5347 Ops/s $\color{#35bf28}+0.38\%$
test_values[td0_return_estimate-False-False] 0.2202ms 0.1717ms 5.8250 KOps/s 4.9698 KOps/s $\textbf{\color{#35bf28}+17.21\%}$
test_values[td1_return_estimate-False-False] 25.1748ms 24.5763ms 40.6896 Ops/s 39.6141 Ops/s $\color{#35bf28}+2.71\%$
test_values[vec_td1_return_estimate-False-False] 40.3183ms 34.1909ms 29.2476 Ops/s 29.4632 Ops/s $\color{#d91a1a}-0.73\%$
test_values[td_lambda_return_estimate-True-False] 38.4004ms 35.4864ms 28.1798 Ops/s 27.3339 Ops/s $\color{#35bf28}+3.09\%$
test_values[vec_td_lambda_return_estimate-True-False] 36.9281ms 33.9531ms 29.4524 Ops/s 29.5282 Ops/s $\color{#d91a1a}-0.26\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 9.8350ms 8.3958ms 119.1071 Ops/s 116.9653 Ops/s $\color{#35bf28}+1.83\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.3294ms 1.8791ms 532.1604 Ops/s 492.8174 Ops/s $\textbf{\color{#35bf28}+7.98\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4591ms 0.3545ms 2.8210 KOps/s 2.7835 KOps/s $\color{#35bf28}+1.35\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 45.2414ms 42.3904ms 23.5903 Ops/s 24.4665 Ops/s $\color{#d91a1a}-3.58\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8424ms 3.0611ms 326.6789 Ops/s 325.8594 Ops/s $\color{#35bf28}+0.25\%$
test_dqn_speed[False-None] 6.4743ms 1.3263ms 753.9723 Ops/s 751.7609 Ops/s $\color{#35bf28}+0.29\%$
test_dqn_speed[False-backward] 1.9114ms 1.8123ms 551.7987 Ops/s 550.9634 Ops/s $\color{#35bf28}+0.15\%$
test_dqn_speed[True-None] 0.6944ms 0.4600ms 2.1740 KOps/s 2.1478 KOps/s $\color{#35bf28}+1.22\%$
test_dqn_speed[True-backward] 0.9511ms 0.8868ms 1.1276 KOps/s 1.0865 KOps/s $\color{#35bf28}+3.78\%$
test_dqn_speed[reduce-overhead-None] 0.7039ms 0.4611ms 2.1685 KOps/s 2.0384 KOps/s $\textbf{\color{#35bf28}+6.39\%}$
test_dqn_speed[reduce-overhead-backward] 0.9350ms 0.8843ms 1.1309 KOps/s 1.1007 KOps/s $\color{#35bf28}+2.74\%$
test_ddpg_speed[False-None] 3.4667ms 2.7992ms 357.2420 Ops/s 362.2854 Ops/s $\color{#d91a1a}-1.39\%$
test_ddpg_speed[False-backward] 4.0843ms 3.9212ms 255.0243 Ops/s 251.2339 Ops/s $\color{#35bf28}+1.51\%$
test_ddpg_speed[True-None] 1.4415ms 0.9970ms 1.0030 KOps/s 991.9191 Ops/s $\color{#35bf28}+1.11\%$
test_ddpg_speed[True-backward] 2.0944ms 1.9124ms 522.9118 Ops/s 521.2928 Ops/s $\color{#35bf28}+0.31\%$
test_ddpg_speed[reduce-overhead-None] 1.1540ms 0.9985ms 1.0015 KOps/s 986.1312 Ops/s $\color{#35bf28}+1.56\%$
test_ddpg_speed[reduce-overhead-backward] 2.1049ms 1.9204ms 520.7172 Ops/s 512.3510 Ops/s $\color{#35bf28}+1.63\%$
test_sac_speed[False-None] 9.2203ms 8.2218ms 121.6276 Ops/s 123.2405 Ops/s $\color{#d91a1a}-1.31\%$
test_sac_speed[False-backward] 14.8324ms 11.2577ms 88.8283 Ops/s 90.4171 Ops/s $\color{#d91a1a}-1.76\%$
test_sac_speed[True-None] 2.1665ms 1.8211ms 549.1077 Ops/s 535.2061 Ops/s $\color{#35bf28}+2.60\%$
test_sac_speed[True-backward] 3.8604ms 3.6246ms 275.8892 Ops/s 274.6769 Ops/s $\color{#35bf28}+0.44\%$
test_sac_speed[reduce-overhead-None] 2.1051ms 1.8669ms 535.6554 Ops/s 536.6488 Ops/s $\color{#d91a1a}-0.19\%$
test_sac_speed[reduce-overhead-backward] 3.6305ms 3.5138ms 284.5960 Ops/s 278.2022 Ops/s $\color{#35bf28}+2.30\%$
test_redq_speed[False-None] 14.2570ms 13.2075ms 75.7144 Ops/s 74.8448 Ops/s $\color{#35bf28}+1.16\%$
test_redq_speed[False-backward] 24.1167ms 22.6708ms 44.1096 Ops/s 43.9037 Ops/s $\color{#35bf28}+0.47\%$
test_redq_speed[True-None] 6.2569ms 5.3785ms 185.9244 Ops/s 196.5119 Ops/s $\textbf{\color{#d91a1a}-5.39\%}$
test_redq_speed[True-backward] 13.1182ms 12.6959ms 78.7654 Ops/s 77.6619 Ops/s $\color{#35bf28}+1.42\%$
test_redq_speed[reduce-overhead-None] 6.1908ms 5.2322ms 191.1229 Ops/s 194.3244 Ops/s $\color{#d91a1a}-1.65\%$
test_redq_speed[reduce-overhead-backward] 13.3548ms 12.5603ms 79.6156 Ops/s 74.8519 Ops/s $\textbf{\color{#35bf28}+6.36\%}$
test_redq_deprec_speed[False-None] 14.9473ms 13.4608ms 74.2897 Ops/s 72.2261 Ops/s $\color{#35bf28}+2.86\%$
test_redq_deprec_speed[False-backward] 20.6546ms 19.5135ms 51.2465 Ops/s 51.3535 Ops/s $\color{#d91a1a}-0.21\%$
test_redq_deprec_speed[True-None] 5.0408ms 3.8173ms 261.9679 Ops/s 269.1873 Ops/s $\color{#d91a1a}-2.68\%$
test_redq_deprec_speed[True-backward] 9.4937ms 8.6534ms 115.5617 Ops/s 111.1369 Ops/s $\color{#35bf28}+3.98\%$
test_redq_deprec_speed[reduce-overhead-None] 4.5048ms 3.7826ms 264.3651 Ops/s 269.3732 Ops/s $\color{#d91a1a}-1.86\%$
test_redq_deprec_speed[reduce-overhead-backward] 9.1518ms 8.5325ms 117.1986 Ops/s 112.8000 Ops/s $\color{#35bf28}+3.90\%$
test_td3_speed[False-None] 8.7647ms 8.0113ms 124.8242 Ops/s 123.2086 Ops/s $\color{#35bf28}+1.31\%$
test_td3_speed[False-backward] 11.4085ms 10.5869ms 94.4565 Ops/s 93.5587 Ops/s $\color{#35bf28}+0.96\%$
test_td3_speed[True-None] 1.9035ms 1.7048ms 586.5820 Ops/s 562.3504 Ops/s $\color{#35bf28}+4.31\%$
test_td3_speed[True-backward] 3.6532ms 3.3569ms 297.8950 Ops/s 272.7592 Ops/s $\textbf{\color{#35bf28}+9.22\%}$
test_td3_speed[reduce-overhead-None] 1.8373ms 1.7137ms 583.5313 Ops/s 572.3039 Ops/s $\color{#35bf28}+1.96\%$
test_td3_speed[reduce-overhead-backward] 3.7393ms 3.3715ms 296.6064 Ops/s 283.1447 Ops/s $\color{#35bf28}+4.75\%$
test_cql_speed[False-None] 38.1053ms 36.0957ms 27.7041 Ops/s 27.1899 Ops/s $\color{#35bf28}+1.89\%$
test_cql_speed[False-backward] 49.8667ms 46.3410ms 21.5792 Ops/s 21.2281 Ops/s $\color{#35bf28}+1.65\%$
test_cql_speed[True-None] 19.1689ms 16.1482ms 61.9265 Ops/s 61.3684 Ops/s $\color{#35bf28}+0.91\%$
test_cql_speed[True-backward] 24.2133ms 23.1546ms 43.1880 Ops/s 43.3944 Ops/s $\color{#d91a1a}-0.48\%$
test_cql_speed[reduce-overhead-None] 16.6266ms 15.9841ms 62.5623 Ops/s 62.3024 Ops/s $\color{#35bf28}+0.42\%$
test_cql_speed[reduce-overhead-backward] 25.6174ms 23.0622ms 43.3610 Ops/s 42.9213 Ops/s $\color{#35bf28}+1.02\%$
test_a2c_speed[False-None] 8.7585ms 7.3506ms 136.0426 Ops/s 132.7088 Ops/s $\color{#35bf28}+2.51\%$
test_a2c_speed[False-backward] 16.2736ms 15.1944ms 65.8137 Ops/s 65.0162 Ops/s $\color{#35bf28}+1.23\%$
test_a2c_speed[True-None] 3.9720ms 3.3332ms 300.0132 Ops/s 272.6386 Ops/s $\textbf{\color{#35bf28}+10.04\%}$
test_a2c_speed[True-backward] 11.1687ms 10.2847ms 97.2318 Ops/s 96.2657 Ops/s $\color{#35bf28}+1.00\%$
test_a2c_speed[reduce-overhead-None] 3.9578ms 3.3733ms 296.4476 Ops/s 292.2258 Ops/s $\color{#35bf28}+1.44\%$
test_a2c_speed[reduce-overhead-backward] 10.5662ms 10.0624ms 99.3796 Ops/s 97.9012 Ops/s $\color{#35bf28}+1.51\%$
test_ppo_speed[False-None] 8.7476ms 7.5499ms 132.4513 Ops/s 126.3034 Ops/s $\color{#35bf28}+4.87\%$
test_ppo_speed[False-backward] 16.5700ms 15.4454ms 64.7444 Ops/s 63.5812 Ops/s $\color{#35bf28}+1.83\%$
test_ppo_speed[True-None] 4.3771ms 3.7305ms 268.0597 Ops/s 266.8215 Ops/s $\color{#35bf28}+0.46\%$
test_ppo_speed[True-backward] 10.5199ms 9.9866ms 100.1341 Ops/s 99.0112 Ops/s $\color{#35bf28}+1.13\%$
test_ppo_speed[reduce-overhead-None] 4.3252ms 3.8055ms 262.7772 Ops/s 251.9304 Ops/s $\color{#35bf28}+4.31\%$
test_ppo_speed[reduce-overhead-backward] 10.3072ms 9.9467ms 100.5354 Ops/s 101.7587 Ops/s $\color{#d91a1a}-1.20\%$
test_reinforce_speed[False-None] 8.4669ms 6.6654ms 150.0293 Ops/s 151.7014 Ops/s $\color{#d91a1a}-1.10\%$
test_reinforce_speed[False-backward] 11.0085ms 10.1011ms 98.9992 Ops/s 99.4519 Ops/s $\color{#d91a1a}-0.46\%$
test_reinforce_speed[True-None] 3.2038ms 2.7123ms 368.6954 Ops/s 369.4622 Ops/s $\color{#d91a1a}-0.21\%$
test_reinforce_speed[True-backward] 9.6444ms 8.8446ms 113.0628 Ops/s 108.6885 Ops/s $\color{#35bf28}+4.02\%$
test_reinforce_speed[reduce-overhead-None] 3.6093ms 2.7512ms 363.4801 Ops/s 359.2104 Ops/s $\color{#35bf28}+1.19\%$
test_reinforce_speed[reduce-overhead-backward] 9.7438ms 8.9637ms 111.5612 Ops/s 111.8145 Ops/s $\color{#d91a1a}-0.23\%$
test_iql_speed[False-None] 33.3448ms 32.2616ms 30.9966 Ops/s 30.3903 Ops/s $\color{#35bf28}+2.00\%$
test_iql_speed[False-backward] 47.4986ms 45.9446ms 21.7653 Ops/s 21.1054 Ops/s $\color{#35bf28}+3.13\%$
test_iql_speed[True-None] 13.3394ms 11.2004ms 89.2825 Ops/s 90.4280 Ops/s $\color{#d91a1a}-1.27\%$
test_iql_speed[True-backward] 23.2676ms 22.1866ms 45.0723 Ops/s 44.4342 Ops/s $\color{#35bf28}+1.44\%$
test_iql_speed[reduce-overhead-None] 11.6038ms 11.0424ms 90.5603 Ops/s 90.2651 Ops/s $\color{#35bf28}+0.33\%$
test_iql_speed[reduce-overhead-backward] 23.3537ms 22.4935ms 44.4573 Ops/s 43.4662 Ops/s $\color{#35bf28}+2.28\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.6428ms 5.0697ms 197.2514 Ops/s 191.9790 Ops/s $\color{#35bf28}+2.75\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7443ms 0.5216ms 1.9171 KOps/s 1.9014 KOps/s $\color{#35bf28}+0.82\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8210ms 0.4953ms 2.0192 KOps/s 1.9670 KOps/s $\color{#35bf28}+2.65\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 4.9604ms 4.6749ms 213.9074 Ops/s 204.2091 Ops/s $\color{#35bf28}+4.75\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.8370ms 0.5060ms 1.9765 KOps/s 1.9260 KOps/s $\color{#35bf28}+2.62\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7499ms 0.4851ms 2.0614 KOps/s 2.0617 KOps/s $\color{#d91a1a}-0.01\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.3986ms 1.6340ms 612.0024 Ops/s 605.5027 Ops/s $\color{#35bf28}+1.07\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.0517ms 1.5816ms 632.2655 Ops/s 629.1091 Ops/s $\color{#35bf28}+0.50\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.5807ms 4.8846ms 204.7269 Ops/s 202.2506 Ops/s $\color{#35bf28}+1.22\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0255ms 0.6519ms 1.5340 KOps/s 1.5194 KOps/s $\color{#35bf28}+0.96\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9657ms 0.6275ms 1.5935 KOps/s 1.5787 KOps/s $\color{#35bf28}+0.94\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.4206ms 4.7633ms 209.9393 Ops/s 208.1212 Ops/s $\color{#35bf28}+0.87\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7805ms 0.5190ms 1.9268 KOps/s 1.8818 KOps/s $\color{#35bf28}+2.39\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 8.0592ms 0.5083ms 1.9675 KOps/s 2.0156 KOps/s $\color{#d91a1a}-2.39\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.6771ms 4.7420ms 210.8814 Ops/s 204.1448 Ops/s $\color{#35bf28}+3.30\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.4173ms 0.5092ms 1.9639 KOps/s 1.9227 KOps/s $\color{#35bf28}+2.14\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7661ms 0.4884ms 2.0474 KOps/s 1.9934 KOps/s $\color{#35bf28}+2.71\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.8065ms 4.9241ms 203.0809 Ops/s 178.6017 Ops/s $\textbf{\color{#35bf28}+13.71\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 3.4370ms 0.6597ms 1.5158 KOps/s 1.5066 KOps/s $\color{#35bf28}+0.61\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8994ms 0.6304ms 1.5864 KOps/s 1.5150 KOps/s $\color{#35bf28}+4.72\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 5.7622ms 4.1967ms 238.2851 Ops/s 222.0783 Ops/s $\textbf{\color{#35bf28}+7.30\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 8.9461ms 2.3064ms 433.5806 Ops/s 455.0546 Ops/s $\color{#d91a1a}-4.72\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.7755ms 1.2069ms 828.5906 Ops/s 703.6012 Ops/s $\textbf{\color{#35bf28}+17.76\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 5.8688ms 4.2044ms 237.8481 Ops/s 234.6672 Ops/s $\color{#35bf28}+1.36\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 5.9688ms 2.2818ms 438.2551 Ops/s 421.7049 Ops/s $\color{#35bf28}+3.92\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.1342ms 1.3821ms 723.5531 Ops/s 722.9458 Ops/s $\color{#35bf28}+0.08\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.4013s 12.3898ms 80.7114 Ops/s 234.4611 Ops/s $\textbf{\color{#d91a1a}-65.58\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 3.5219ms 2.2752ms 439.5151 Ops/s 401.0712 Ops/s $\textbf{\color{#35bf28}+9.59\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.3591ms 1.5031ms 665.3028 Ops/s 701.8759 Ops/s $\textbf{\color{#d91a1a}-5.21\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 11.9010ms 10.9504ms 91.3211 Ops/s 87.8938 Ops/s $\color{#35bf28}+3.90\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 15.4327ms 14.3925ms 69.4806 Ops/s 69.3067 Ops/s $\color{#35bf28}+0.25\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 20.9275ms 20.1244ms 49.6910 Ops/s 49.8159 Ops/s $\color{#d91a1a}-0.25\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 16.3664ms 14.5885ms 68.5470 Ops/s 68.8631 Ops/s $\color{#d91a1a}-0.46\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 20.4239ms 19.9427ms 50.1436 Ops/s 50.0804 Ops/s $\color{#35bf28}+0.13\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 16.6775ms 15.6934ms 63.7211 Ops/s 63.0207 Ops/s $\color{#35bf28}+1.11\%$

@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}21$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7343s 0.7301s 1.3696 Ops/s 1.3347 Ops/s $\color{#35bf28}+2.61\%$
test_transformed 1.0697s 0.9934s 1.0066 Ops/s 1.0310 Ops/s $\color{#d91a1a}-2.37\%$
test_serial 2.1846s 2.1090s 0.4742 Ops/s 0.4769 Ops/s $\color{#d91a1a}-0.58\%$
test_parallel 2.1308s 2.0042s 0.4990 Ops/s 0.5169 Ops/s $\color{#d91a1a}-3.47\%$
test_step_mdp_speed[True-True-True-True-True] 0.2449ms 35.7984μs 27.9342 KOps/s 27.9451 KOps/s $\color{#d91a1a}-0.04\%$
test_step_mdp_speed[True-True-True-True-False] 0.1616ms 20.3003μs 49.2604 KOps/s 49.2970 KOps/s $\color{#d91a1a}-0.07\%$
test_step_mdp_speed[True-True-True-False-True] 87.4120μs 19.6112μs 50.9912 KOps/s 51.0155 KOps/s $\color{#d91a1a}-0.05\%$
test_step_mdp_speed[True-True-True-False-False] 75.3720μs 11.3482μs 88.1196 KOps/s 86.2451 KOps/s $\color{#35bf28}+2.17\%$
test_step_mdp_speed[True-True-False-True-True] 64.3110μs 38.6369μs 25.8820 KOps/s 25.9885 KOps/s $\color{#d91a1a}-0.41\%$
test_step_mdp_speed[True-True-False-True-False] 46.4010μs 22.6987μs 44.0554 KOps/s 44.6469 KOps/s $\color{#d91a1a}-1.32\%$
test_step_mdp_speed[True-True-False-False-True] 48.1710μs 22.2740μs 44.8953 KOps/s 44.2131 KOps/s $\color{#35bf28}+1.54\%$
test_step_mdp_speed[True-True-False-False-False] 39.1210μs 13.7367μs 72.7977 KOps/s 73.0160 KOps/s $\color{#d91a1a}-0.30\%$
test_step_mdp_speed[True-False-True-True-True] 65.8110μs 40.5189μs 24.6798 KOps/s 24.3737 KOps/s $\color{#35bf28}+1.26\%$
test_step_mdp_speed[True-False-True-True-False] 50.9110μs 24.8612μs 40.2234 KOps/s 40.1742 KOps/s $\color{#35bf28}+0.12\%$
test_step_mdp_speed[True-False-True-False-True] 48.0610μs 22.1804μs 45.0848 KOps/s 44.0537 KOps/s $\color{#35bf28}+2.34\%$
test_step_mdp_speed[True-False-True-False-False] 38.5510μs 13.7808μs 72.5646 KOps/s 73.9677 KOps/s $\color{#d91a1a}-1.90\%$
test_step_mdp_speed[True-False-False-True-True] 72.6710μs 41.9347μs 23.8466 KOps/s 23.3415 KOps/s $\color{#35bf28}+2.16\%$
test_step_mdp_speed[True-False-False-True-False] 66.7420μs 26.6544μs 37.5173 KOps/s 37.3662 KOps/s $\color{#35bf28}+0.40\%$
test_step_mdp_speed[True-False-False-False-True] 59.6120μs 23.6681μs 42.2509 KOps/s 40.9117 KOps/s $\color{#35bf28}+3.27\%$
test_step_mdp_speed[True-False-False-False-False] 42.0610μs 15.4976μs 64.5263 KOps/s 63.8314 KOps/s $\color{#35bf28}+1.09\%$
test_step_mdp_speed[False-True-True-True-True] 71.4620μs 40.0867μs 24.9459 KOps/s 24.5352 KOps/s $\color{#35bf28}+1.67\%$
test_step_mdp_speed[False-True-True-True-False] 52.2310μs 24.5534μs 40.7275 KOps/s 40.4467 KOps/s $\color{#35bf28}+0.69\%$
test_step_mdp_speed[False-True-True-False-True] 91.9330μs 25.3657μs 39.4234 KOps/s 38.0375 KOps/s $\color{#35bf28}+3.64\%$
test_step_mdp_speed[False-True-True-False-False] 39.3410μs 15.0408μs 66.4858 KOps/s 65.0835 KOps/s $\color{#35bf28}+2.15\%$
test_step_mdp_speed[False-True-False-True-True] 71.3120μs 42.2036μs 23.6947 KOps/s 23.5041 KOps/s $\color{#35bf28}+0.81\%$
test_step_mdp_speed[False-True-False-True-False] 91.2220μs 25.5041μs 39.2095 KOps/s 37.5740 KOps/s $\color{#35bf28}+4.35\%$
test_step_mdp_speed[False-True-False-False-True] 3.3364ms 27.9397μs 35.7914 KOps/s 35.6252 KOps/s $\color{#35bf28}+0.47\%$
test_step_mdp_speed[False-True-False-False-False] 44.7310μs 17.0459μs 58.6652 KOps/s 57.1211 KOps/s $\color{#35bf28}+2.70\%$
test_step_mdp_speed[False-False-True-True-True] 86.1520μs 44.5846μs 22.4293 KOps/s 22.2855 KOps/s $\color{#35bf28}+0.65\%$
test_step_mdp_speed[False-False-True-True-False] 53.5610μs 28.9688μs 34.5199 KOps/s 34.3257 KOps/s $\color{#35bf28}+0.57\%$
test_step_mdp_speed[False-False-True-False-True] 65.0120μs 27.7325μs 36.0587 KOps/s 35.6169 KOps/s $\color{#35bf28}+1.24\%$
test_step_mdp_speed[False-False-True-False-False] 47.4010μs 17.0535μs 58.6389 KOps/s 57.4155 KOps/s $\color{#35bf28}+2.13\%$
test_step_mdp_speed[False-False-False-True-True] 73.9220μs 45.7346μs 21.8653 KOps/s 21.8230 KOps/s $\color{#35bf28}+0.19\%$
test_step_mdp_speed[False-False-False-True-False] 95.6230μs 30.5032μs 32.7834 KOps/s 32.7834 KOps/s $+0.00\%$
test_step_mdp_speed[False-False-False-False-True] 54.7920μs 29.2743μs 34.1597 KOps/s 34.3030 KOps/s $\color{#d91a1a}-0.42\%$
test_step_mdp_speed[False-False-False-False-False] 47.4810μs 19.1108μs 52.3264 KOps/s 52.6104 KOps/s $\color{#d91a1a}-0.54\%$
test_values[generalized_advantage_estimate-True-True] 24.6676ms 24.1691ms 41.3752 Ops/s 41.5573 Ops/s $\color{#d91a1a}-0.44\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1057s 2.9917ms 334.2564 Ops/s 363.8088 Ops/s $\textbf{\color{#d91a1a}-8.12\%}$
test_values[td0_return_estimate-False-False] 83.8520μs 64.2832μs 15.5562 KOps/s 15.7208 KOps/s $\color{#d91a1a}-1.05\%$
test_values[td1_return_estimate-False-False] 54.1166ms 53.5583ms 18.6712 Ops/s 18.7189 Ops/s $\color{#d91a1a}-0.25\%$
test_values[vec_td1_return_estimate-False-False] 1.2694ms 1.0502ms 952.1920 Ops/s 950.4301 Ops/s $\color{#35bf28}+0.19\%$
test_values[td_lambda_return_estimate-True-False] 85.5207ms 84.9402ms 11.7730 Ops/s 11.7242 Ops/s $\color{#35bf28}+0.42\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.2673ms 1.0469ms 955.2289 Ops/s 947.4253 Ops/s $\color{#35bf28}+0.82\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.2850ms 24.1344ms 41.4346 Ops/s 41.8216 Ops/s $\color{#d91a1a}-0.93\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0131ms 0.7233ms 1.3826 KOps/s 1.3957 KOps/s $\color{#d91a1a}-0.94\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7980ms 0.6388ms 1.5654 KOps/s 1.5725 KOps/s $\color{#d91a1a}-0.45\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.6002ms 1.4519ms 688.7551 Ops/s 689.3692 Ops/s $\color{#d91a1a}-0.09\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7157ms 0.6508ms 1.5366 KOps/s 1.5355 KOps/s $\color{#35bf28}+0.07\%$
test_dqn_speed[False-None] 6.8211ms 1.2809ms 780.6962 Ops/s 789.3957 Ops/s $\color{#d91a1a}-1.10\%$
test_dqn_speed[False-backward] 1.8667ms 1.7539ms 570.1482 Ops/s 553.3476 Ops/s $\color{#35bf28}+3.04\%$
test_dqn_speed[True-None] 0.9653ms 0.5498ms 1.8188 KOps/s 1.7582 KOps/s $\color{#35bf28}+3.45\%$
test_dqn_speed[True-backward] 1.0614ms 1.0102ms 989.9144 Ops/s 876.9210 Ops/s $\textbf{\color{#35bf28}+12.89\%}$
test_dqn_speed[reduce-overhead-None] 0.7089ms 0.5582ms 1.7914 KOps/s 1.7695 KOps/s $\color{#35bf28}+1.24\%$
test_dqn_speed[reduce-overhead-backward] 1.0604ms 0.9955ms 1.0045 KOps/s 1.0025 KOps/s $\color{#35bf28}+0.20\%$
test_ddpg_speed[False-None] 3.3901ms 2.6126ms 382.7585 Ops/s 380.8855 Ops/s $\color{#35bf28}+0.49\%$
test_ddpg_speed[False-backward] 4.1972ms 3.8357ms 260.7099 Ops/s 261.3424 Ops/s $\color{#d91a1a}-0.24\%$
test_ddpg_speed[True-None] 1.3517ms 1.2231ms 817.5943 Ops/s 801.9711 Ops/s $\color{#35bf28}+1.95\%$
test_ddpg_speed[True-backward] 2.2337ms 2.1856ms 457.5460 Ops/s 450.3040 Ops/s $\color{#35bf28}+1.61\%$
test_ddpg_speed[reduce-overhead-None] 2.0774ms 1.2559ms 796.2696 Ops/s 814.4928 Ops/s $\color{#d91a1a}-2.24\%$
test_ddpg_speed[reduce-overhead-backward] 2.2125ms 2.1700ms 460.8241 Ops/s 452.4840 Ops/s $\color{#35bf28}+1.84\%$
test_sac_speed[False-None] 8.3237ms 7.2644ms 137.6570 Ops/s 137.1957 Ops/s $\color{#35bf28}+0.34\%$
test_sac_speed[False-backward] 11.0316ms 10.4761ms 95.4557 Ops/s 94.0163 Ops/s $\color{#35bf28}+1.53\%$
test_sac_speed[True-None] 2.3886ms 1.9959ms 501.0153 Ops/s 492.6101 Ops/s $\color{#35bf28}+1.71\%$
test_sac_speed[True-backward] 4.1029ms 3.9330ms 254.2617 Ops/s 229.2163 Ops/s $\textbf{\color{#35bf28}+10.93\%}$
test_sac_speed[reduce-overhead-None] 2.3802ms 2.0111ms 497.2403 Ops/s 494.7660 Ops/s $\color{#35bf28}+0.50\%$
test_sac_speed[reduce-overhead-backward] 4.0453ms 3.8877ms 257.2211 Ops/s 254.8786 Ops/s $\color{#35bf28}+0.92\%$
test_redq_speed[False-None] 15.3061ms 9.8753ms 101.2630 Ops/s 90.4735 Ops/s $\textbf{\color{#35bf28}+11.93\%}$
test_redq_speed[False-backward] 17.9498ms 17.2019ms 58.1333 Ops/s 57.7366 Ops/s $\color{#35bf28}+0.69\%$
test_redq_speed[True-None] 3.7718ms 3.5068ms 285.1582 Ops/s 286.2272 Ops/s $\color{#d91a1a}-0.37\%$
test_redq_speed[True-backward] 8.9166ms 8.6510ms 115.5932 Ops/s 117.7649 Ops/s $\color{#d91a1a}-1.84\%$
test_redq_speed[reduce-overhead-None] 3.7613ms 3.5086ms 285.0121 Ops/s 256.2904 Ops/s $\textbf{\color{#35bf28}+11.21\%}$
test_redq_speed[reduce-overhead-backward] 8.7880ms 8.4933ms 117.7402 Ops/s 114.6216 Ops/s $\color{#35bf28}+2.72\%$
test_redq_deprec_speed[False-None] 11.2377ms 10.2462ms 97.5973 Ops/s 96.0363 Ops/s $\color{#35bf28}+1.63\%$
test_redq_deprec_speed[False-backward] 15.5681ms 15.0555ms 66.4210 Ops/s 65.3991 Ops/s $\color{#35bf28}+1.56\%$
test_redq_deprec_speed[True-None] 3.3367ms 3.1977ms 312.7259 Ops/s 309.5778 Ops/s $\color{#35bf28}+1.02\%$
test_redq_deprec_speed[True-backward] 7.3755ms 7.0870ms 141.1044 Ops/s 143.0184 Ops/s $\color{#d91a1a}-1.34\%$
test_redq_deprec_speed[reduce-overhead-None] 3.4051ms 3.2216ms 310.4062 Ops/s 312.7365 Ops/s $\color{#d91a1a}-0.75\%$
test_redq_deprec_speed[reduce-overhead-backward] 7.4031ms 7.0902ms 141.0391 Ops/s 142.8078 Ops/s $\color{#d91a1a}-1.24\%$
test_td3_speed[False-None] 7.4518ms 7.2321ms 138.2729 Ops/s 128.7912 Ops/s $\textbf{\color{#35bf28}+7.36\%}$
test_td3_speed[False-backward] 10.3575ms 10.0501ms 99.5018 Ops/s 98.3243 Ops/s $\color{#35bf28}+1.20\%$
test_td3_speed[True-None] 1.9310ms 1.8949ms 527.7364 Ops/s 519.2925 Ops/s $\color{#35bf28}+1.63\%$
test_td3_speed[True-backward] 3.8313ms 3.7224ms 268.6438 Ops/s 268.0822 Ops/s $\color{#35bf28}+0.21\%$
test_td3_speed[reduce-overhead-None] 1.9276ms 1.8842ms 530.7407 Ops/s 523.1946 Ops/s $\color{#35bf28}+1.44\%$
test_td3_speed[reduce-overhead-backward] 3.7716ms 3.6712ms 272.3900 Ops/s 270.6313 Ops/s $\color{#35bf28}+0.65\%$
test_cql_speed[False-None] 27.0628ms 24.3912ms 40.9984 Ops/s 40.7979 Ops/s $\color{#35bf28}+0.49\%$
test_cql_speed[False-backward] 36.4616ms 33.4495ms 29.8959 Ops/s 29.6971 Ops/s $\color{#35bf28}+0.67\%$
test_cql_speed[True-None] 11.3192ms 10.7994ms 92.5980 Ops/s 87.7559 Ops/s $\textbf{\color{#35bf28}+5.52\%}$
test_cql_speed[True-backward] 17.1381ms 16.6889ms 59.9200 Ops/s 61.1927 Ops/s $\color{#d91a1a}-2.08\%$
test_cql_speed[reduce-overhead-None] 11.2068ms 10.8130ms 92.4816 Ops/s 93.6219 Ops/s $\color{#d91a1a}-1.22\%$
test_cql_speed[reduce-overhead-backward] 17.2490ms 16.6207ms 60.1660 Ops/s 61.5021 Ops/s $\color{#d91a1a}-2.17\%$
test_a2c_speed[False-None] 5.4306ms 5.1811ms 193.0085 Ops/s 189.6196 Ops/s $\color{#35bf28}+1.79\%$
test_a2c_speed[False-backward] 12.8249ms 11.4867ms 87.0571 Ops/s 85.3178 Ops/s $\color{#35bf28}+2.04\%$
test_a2c_speed[True-None] 3.2366ms 3.0185ms 331.2874 Ops/s 322.4408 Ops/s $\color{#35bf28}+2.74\%$
test_a2c_speed[True-backward] 8.6670ms 8.4424ms 118.4499 Ops/s 116.6843 Ops/s $\color{#35bf28}+1.51\%$
test_a2c_speed[reduce-overhead-None] 3.1616ms 2.9933ms 334.0833 Ops/s 321.4790 Ops/s $\color{#35bf28}+3.92\%$
test_a2c_speed[reduce-overhead-backward] 8.5854ms 8.3232ms 120.1466 Ops/s 119.5750 Ops/s $\color{#35bf28}+0.48\%$
test_ppo_speed[False-None] 7.2963ms 5.5478ms 180.2514 Ops/s 175.6535 Ops/s $\color{#35bf28}+2.62\%$
test_ppo_speed[False-backward] 12.6396ms 12.1110ms 82.5698 Ops/s 82.8539 Ops/s $\color{#d91a1a}-0.34\%$
test_ppo_speed[True-None] 3.6222ms 3.4249ms 291.9793 Ops/s 288.9608 Ops/s $\color{#35bf28}+1.04\%$
test_ppo_speed[True-backward] 8.3232ms 8.1307ms 122.9908 Ops/s 106.2286 Ops/s $\textbf{\color{#35bf28}+15.78\%}$
test_ppo_speed[reduce-overhead-None] 3.6077ms 3.4331ms 291.2815 Ops/s 287.8050 Ops/s $\color{#35bf28}+1.21\%$
test_ppo_speed[reduce-overhead-backward] 8.2952ms 8.0982ms 123.4849 Ops/s 121.4154 Ops/s $\color{#35bf28}+1.70\%$
test_reinforce_speed[False-None] 5.9341ms 4.3748ms 228.5803 Ops/s 226.1562 Ops/s $\color{#35bf28}+1.07\%$
test_reinforce_speed[False-backward] 7.5135ms 7.1597ms 139.6706 Ops/s 139.3770 Ops/s $\color{#35bf28}+0.21\%$
test_reinforce_speed[True-None] 2.4297ms 2.2055ms 453.4081 Ops/s 426.1069 Ops/s $\textbf{\color{#35bf28}+6.41\%}$
test_reinforce_speed[True-backward] 7.1506ms 6.9787ms 143.2941 Ops/s 141.8498 Ops/s $\color{#35bf28}+1.02\%$
test_reinforce_speed[reduce-overhead-None] 2.6275ms 2.2066ms 453.1855 Ops/s 438.9945 Ops/s $\color{#35bf28}+3.23\%$
test_reinforce_speed[reduce-overhead-backward] 7.2849ms 6.9715ms 143.4408 Ops/s 142.1880 Ops/s $\color{#35bf28}+0.88\%$
test_iql_speed[False-None] 20.2253ms 18.9273ms 52.8336 Ops/s 51.1527 Ops/s $\color{#35bf28}+3.29\%$
test_iql_speed[False-backward] 30.5891ms 29.6696ms 33.7046 Ops/s 33.4507 Ops/s $\color{#35bf28}+0.76\%$
test_iql_speed[True-None] 7.1486ms 6.7128ms 148.9682 Ops/s 148.6506 Ops/s $\color{#35bf28}+0.21\%$
test_iql_speed[True-backward] 15.9076ms 15.1866ms 65.8476 Ops/s 64.8253 Ops/s $\color{#35bf28}+1.58\%$
test_iql_speed[reduce-overhead-None] 6.9750ms 6.6922ms 149.4272 Ops/s 148.9422 Ops/s $\color{#35bf28}+0.33\%$
test_iql_speed[reduce-overhead-backward] 15.7877ms 15.2187ms 65.7087 Ops/s 64.9834 Ops/s $\color{#35bf28}+1.12\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.6478ms 6.2638ms 159.6465 Ops/s 159.0766 Ops/s $\color{#35bf28}+0.36\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.9141ms 0.3570ms 2.8008 KOps/s 3.3203 KOps/s $\textbf{\color{#d91a1a}-15.65\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7570ms 0.3268ms 3.0603 KOps/s 3.0617 KOps/s $\color{#d91a1a}-0.05\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.4800ms 5.9968ms 166.7543 Ops/s 166.5811 Ops/s $\color{#35bf28}+0.10\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8648ms 0.2885ms 3.4661 KOps/s 2.9973 KOps/s $\textbf{\color{#35bf28}+15.64\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5386ms 0.2579ms 3.8776 KOps/s 2.9416 KOps/s $\textbf{\color{#35bf28}+31.82\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.4468ms 1.2546ms 797.0875 Ops/s 737.4468 Ops/s $\textbf{\color{#35bf28}+8.09\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.6450ms 1.1670ms 856.9137 Ops/s 842.4971 Ops/s $\color{#35bf28}+1.71\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.6298ms 6.1630ms 162.2573 Ops/s 161.3101 Ops/s $\color{#35bf28}+0.59\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8516ms 0.4395ms 2.2755 KOps/s 2.1247 KOps/s $\textbf{\color{#35bf28}+7.09\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9102ms 0.3959ms 2.5256 KOps/s 1.9473 KOps/s $\textbf{\color{#35bf28}+29.70\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.4318ms 6.0348ms 165.7048 Ops/s 166.6275 Ops/s $\color{#d91a1a}-0.55\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9016ms 0.3412ms 2.9305 KOps/s 2.9261 KOps/s $\color{#35bf28}+0.15\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5365ms 0.3341ms 2.9933 KOps/s 2.6412 KOps/s $\textbf{\color{#35bf28}+13.33\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.5566ms 6.0160ms 166.2234 Ops/s 166.8364 Ops/s $\color{#d91a1a}-0.37\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9095ms 0.3113ms 3.2119 KOps/s 2.8693 KOps/s $\textbf{\color{#35bf28}+11.94\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6363ms 0.2983ms 3.3522 KOps/s 3.4196 KOps/s $\color{#d91a1a}-1.97\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4976ms 6.1202ms 163.3940 Ops/s 163.0803 Ops/s $\color{#35bf28}+0.19\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7548ms 0.4077ms 2.4526 KOps/s 2.3597 KOps/s $\color{#35bf28}+3.94\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8606ms 0.4235ms 2.3613 KOps/s 2.1150 KOps/s $\textbf{\color{#35bf28}+11.64\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.4246s 13.6463ms 73.2799 Ops/s 194.3790 Ops/s $\textbf{\color{#d91a1a}-62.30\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 5.5512ms 1.9805ms 504.9156 Ops/s 494.7770 Ops/s $\color{#35bf28}+2.05\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 10.0339ms 1.2744ms 784.6683 Ops/s 881.4840 Ops/s $\textbf{\color{#d91a1a}-10.98\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 8.7649ms 5.2947ms 188.8689 Ops/s 37.2948 Ops/s $\textbf{\color{#35bf28}+406.42\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 8.0551ms 2.0066ms 498.3474 Ops/s 473.1974 Ops/s $\textbf{\color{#35bf28}+5.31\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 8.3570ms 1.2325ms 811.3662 Ops/s 767.2776 Ops/s $\textbf{\color{#35bf28}+5.75\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.3671s 12.7251ms 78.5851 Ops/s 177.8957 Ops/s $\textbf{\color{#d91a1a}-55.83\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.5354ms 2.1455ms 466.1005 Ops/s 439.3846 Ops/s $\textbf{\color{#35bf28}+6.08\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.5681ms 1.3850ms 722.0124 Ops/s 666.1212 Ops/s $\textbf{\color{#35bf28}+8.39\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 14.4309ms 13.0686ms 76.5194 Ops/s 76.5363 Ops/s $\color{#d91a1a}-0.02\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 18.2651ms 16.8648ms 59.2950 Ops/s 59.7218 Ops/s $\color{#d91a1a}-0.71\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.5419ms 17.5826ms 56.8746 Ops/s 56.6855 Ops/s $\color{#35bf28}+0.33\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 18.0087ms 16.5815ms 60.3081 Ops/s 60.5200 Ops/s $\color{#d91a1a}-0.35\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 19.4473ms 17.4604ms 57.2724 Ops/s 57.5680 Ops/s $\color{#d91a1a}-0.51\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 19.0831ms 17.8557ms 56.0046 Ops/s 56.6001 Ops/s $\color{#d91a1a}-1.05\%$

@vmoens vmoens merged commit 9f16e62 into gh/vmoens/43/base Nov 13, 2024
52 of 70 checks passed
vmoens added a commit that referenced this pull request Nov 13, 2024
@vmoens
[Doc] Fix tutorials
2f3b4cd 
ghstack-source-id: 6c9114384015e76e96b3bbd0c8893cc42344537a
Pull Request resolved: #2560
@vmoens vmoens deleted the gh/vmoens/43/head branch November 13, 2024 19:08
vmoens added a commit that referenced this pull request Nov 14, 2024
@vmoens
[Doc] Fix tutorials
3b2dee2 
ghstack-source-id: 6c9114384015e76e96b3bbd0c8893cc42344537a
Pull Request resolved: #2560

(cherry picked from commit 2f3b4cd)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
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
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@vmoens @facebook-github-bot