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

[Doc] Solve ref issues in docstrings #2776

Open
wants to merge 24 commits into
base: gh/vmoens/86/base
Choose a base branch
from

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Feb 10, 2025

Stack from ghstack (oldest at bottom):

[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: 4b0de4f1db5985befd7cbb1d9cae4b55b92eb189
Pull Request resolved: #2776
Copy link

pytorch-bot bot commented Feb 10, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2776

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

❌ 2 New Failures, 3 Pending, 2 Unrelated Failures

As of commit c93b9d2 with merge base c2a149d (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 Feb 10, 2025
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: 367be18eb407e8d5b56c571f820b356e4e92444a
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: a39dacba3ce04534fdb0c2f2753caa9a67eeee23
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: 1f79445c5c337cfc31326f70b58cbf5e1e7c74a3
Pull Request resolved: #2776
Copy link

github-actions bot commented Feb 10, 2025

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}4$. Worsened: $\large\color{#d91a1a}13$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.5863s 0.4932s 2.0276 Ops/s 1.9619 Ops/s $\color{#35bf28}+3.34\%$
test_transformed 1.0362s 0.9453s 1.0579 Ops/s 1.0192 Ops/s $\color{#35bf28}+3.79\%$
test_serial 1.5524s 1.4659s 0.6822 Ops/s 0.6596 Ops/s $\color{#35bf28}+3.43\%$
test_parallel 1.3692s 1.2817s 0.7802 Ops/s 0.7779 Ops/s $\color{#35bf28}+0.30\%$
test_step_mdp_speed[True-True-True-True-True] 0.4558ms 30.7780μs 32.4908 KOps/s 33.4827 KOps/s $\color{#d91a1a}-2.96\%$
test_step_mdp_speed[True-True-True-True-False] 57.1470μs 18.3430μs 54.5166 KOps/s 56.5368 KOps/s $\color{#d91a1a}-3.57\%$
test_step_mdp_speed[True-True-True-False-True] 61.2150μs 17.3558μs 57.6176 KOps/s 59.1124 KOps/s $\color{#d91a1a}-2.53\%$
test_step_mdp_speed[True-True-True-False-False] 43.7520μs 10.3010μs 97.0782 KOps/s 98.6639 KOps/s $\color{#d91a1a}-1.61\%$
test_step_mdp_speed[True-True-False-True-True] 86.9030μs 32.8136μs 30.4752 KOps/s 31.4326 KOps/s $\color{#d91a1a}-3.05\%$
test_step_mdp_speed[True-True-False-True-False] 66.8150μs 20.1784μs 49.5580 KOps/s 50.7052 KOps/s $\color{#d91a1a}-2.26\%$
test_step_mdp_speed[True-True-False-False-True] 65.1820μs 19.2518μs 51.9433 KOps/s 53.3434 KOps/s $\color{#d91a1a}-2.62\%$
test_step_mdp_speed[True-True-False-False-False] 67.4870μs 12.1209μs 82.5019 KOps/s 85.1494 KOps/s $\color{#d91a1a}-3.11\%$
test_step_mdp_speed[True-False-True-True-True] 73.4670μs 34.7300μs 28.7936 KOps/s 29.6231 KOps/s $\color{#d91a1a}-2.80\%$
test_step_mdp_speed[True-False-True-True-False] 72.3350μs 22.1365μs 45.1742 KOps/s 46.4840 KOps/s $\color{#d91a1a}-2.82\%$
test_step_mdp_speed[True-False-True-False-True] 58.2390μs 19.3444μs 51.6946 KOps/s 53.4730 KOps/s $\color{#d91a1a}-3.33\%$
test_step_mdp_speed[True-False-True-False-False] 62.9470μs 12.4702μs 80.1914 KOps/s 85.0801 KOps/s $\textbf{\color{#d91a1a}-5.75\%}$
test_step_mdp_speed[True-False-False-True-True] 0.5539ms 36.3715μs 27.4941 KOps/s 28.4073 KOps/s $\color{#d91a1a}-3.21\%$
test_step_mdp_speed[True-False-False-True-False] 57.2380μs 24.0135μs 41.6432 KOps/s 43.0734 KOps/s $\color{#d91a1a}-3.32\%$
test_step_mdp_speed[True-False-False-False-True] 81.9740μs 21.0344μs 47.5411 KOps/s 49.1062 KOps/s $\color{#d91a1a}-3.19\%$
test_step_mdp_speed[True-False-False-False-False] 46.2770μs 14.0579μs 71.1342 KOps/s 73.7078 KOps/s $\color{#d91a1a}-3.49\%$
test_step_mdp_speed[False-True-True-True-True] 79.7190μs 34.7417μs 28.7838 KOps/s 29.4256 KOps/s $\color{#d91a1a}-2.18\%$
test_step_mdp_speed[False-True-True-True-False] 79.0980μs 22.0941μs 45.2609 KOps/s 46.8827 KOps/s $\color{#d91a1a}-3.46\%$
test_step_mdp_speed[False-True-True-False-True] 56.1050μs 22.4230μs 44.5970 KOps/s 46.6261 KOps/s $\color{#d91a1a}-4.35\%$
test_step_mdp_speed[False-True-True-False-False] 45.8660μs 13.6009μs 73.5243 KOps/s 75.2759 KOps/s $\color{#d91a1a}-2.33\%$
test_step_mdp_speed[False-True-False-True-True] 90.9700μs 36.5393μs 27.3678 KOps/s 27.6791 KOps/s $\color{#d91a1a}-1.12\%$
test_step_mdp_speed[False-True-False-True-False] 51.5470μs 23.8268μs 41.9696 KOps/s 42.7956 KOps/s $\color{#d91a1a}-1.93\%$
test_step_mdp_speed[False-True-False-False-True] 2.5560ms 24.1332μs 41.4367 KOps/s 42.2962 KOps/s $\color{#d91a1a}-2.03\%$
test_step_mdp_speed[False-True-False-False-False] 46.2570μs 15.5534μs 64.2944 KOps/s 66.9401 KOps/s $\color{#d91a1a}-3.95\%$
test_step_mdp_speed[False-False-True-True-True] 0.1042ms 38.3976μs 26.0433 KOps/s 26.9263 KOps/s $\color{#d91a1a}-3.28\%$
test_step_mdp_speed[False-False-True-True-False] 63.5920μs 25.5619μs 39.1207 KOps/s 40.2495 KOps/s $\color{#d91a1a}-2.80\%$
test_step_mdp_speed[False-False-True-False-True] 66.3140μs 23.8239μs 41.9746 KOps/s 43.1324 KOps/s $\color{#d91a1a}-2.68\%$
test_step_mdp_speed[False-False-True-False-False] 64.2700μs 15.4572μs 64.6947 KOps/s 66.5895 KOps/s $\color{#d91a1a}-2.85\%$
test_step_mdp_speed[False-False-False-True-True] 0.5842ms 39.8048μs 25.1226 KOps/s 25.5932 KOps/s $\color{#d91a1a}-1.84\%$
test_step_mdp_speed[False-False-False-True-False] 65.2420μs 27.2954μs 36.6362 KOps/s 37.5469 KOps/s $\color{#d91a1a}-2.43\%$
test_step_mdp_speed[False-False-False-False-True] 66.0740μs 25.1211μs 39.8072 KOps/s 40.3863 KOps/s $\color{#d91a1a}-1.43\%$
test_step_mdp_speed[False-False-False-False-False] 61.9870μs 17.0698μs 58.5828 KOps/s 60.5700 KOps/s $\color{#d91a1a}-3.28\%$
test_values[generalized_advantage_estimate-True-True] 9.8916ms 9.6705ms 103.4068 Ops/s 100.6733 Ops/s $\color{#35bf28}+2.72\%$
test_values[vec_generalized_advantage_estimate-True-True] 28.2796ms 26.2160ms 38.1447 Ops/s 40.9910 Ops/s $\textbf{\color{#d91a1a}-6.94\%}$
test_values[td0_return_estimate-False-False] 0.2510ms 0.1769ms 5.6538 KOps/s 5.6701 KOps/s $\color{#d91a1a}-0.29\%$
test_values[td1_return_estimate-False-False] 24.3431ms 23.9477ms 41.7577 Ops/s 40.7811 Ops/s $\color{#35bf28}+2.39\%$
test_values[vec_td1_return_estimate-False-False] 28.1338ms 26.4065ms 37.8695 Ops/s 41.4960 Ops/s $\textbf{\color{#d91a1a}-8.74\%}$
test_values[td_lambda_return_estimate-True-False] 37.4211ms 34.2109ms 29.2305 Ops/s 28.6779 Ops/s $\color{#35bf28}+1.93\%$
test_values[vec_td_lambda_return_estimate-True-False] 29.5151ms 26.4796ms 37.7649 Ops/s 41.4070 Ops/s $\textbf{\color{#d91a1a}-8.80\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 10.2477ms 8.4934ms 117.7382 Ops/s 117.3939 Ops/s $\color{#35bf28}+0.29\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.3282ms 2.0291ms 492.8194 Ops/s 502.3635 Ops/s $\color{#d91a1a}-1.90\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5095ms 0.3652ms 2.7380 KOps/s 2.7293 KOps/s $\color{#35bf28}+0.32\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 48.7194ms 47.4152ms 21.0903 Ops/s 23.1817 Ops/s $\textbf{\color{#d91a1a}-9.02\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.7541ms 3.4256ms 291.9233 Ops/s 287.8249 Ops/s $\color{#35bf28}+1.42\%$
test_dqn_speed[False-None] 7.0483ms 1.4215ms 703.4942 Ops/s 697.3276 Ops/s $\color{#35bf28}+0.88\%$
test_dqn_speed[False-backward] 2.6995ms 1.9609ms 509.9777 Ops/s 513.2571 Ops/s $\color{#d91a1a}-0.64\%$
test_dqn_speed[True-None] 0.7309ms 0.4802ms 2.0824 KOps/s 2.0585 KOps/s $\color{#35bf28}+1.16\%$
test_dqn_speed[True-backward] 0.9705ms 0.9211ms 1.0857 KOps/s 1.0686 KOps/s $\color{#35bf28}+1.60\%$
test_dqn_speed[reduce-overhead-None] 0.6400ms 0.4813ms 2.0776 KOps/s 2.0625 KOps/s $\color{#35bf28}+0.73\%$
test_dqn_speed[reduce-overhead-backward] 0.9709ms 0.9117ms 1.0969 KOps/s 1.0773 KOps/s $\color{#35bf28}+1.82\%$
test_ddpg_speed[False-None] 3.9143ms 2.9183ms 342.6601 Ops/s 338.9996 Ops/s $\color{#35bf28}+1.08\%$
test_ddpg_speed[False-backward] 5.2587ms 4.1444ms 241.2919 Ops/s 244.6501 Ops/s $\color{#d91a1a}-1.37\%$
test_ddpg_speed[True-None] 1.5488ms 1.2337ms 810.5775 Ops/s 795.0452 Ops/s $\color{#35bf28}+1.95\%$
test_ddpg_speed[True-backward] 2.3531ms 2.1232ms 470.9950 Ops/s 463.9486 Ops/s $\color{#35bf28}+1.52\%$
test_ddpg_speed[reduce-overhead-None] 1.9816ms 1.2304ms 812.7291 Ops/s 796.8394 Ops/s $\color{#35bf28}+1.99\%$
test_ddpg_speed[reduce-overhead-backward] 2.1633ms 2.1167ms 472.4250 Ops/s 468.4890 Ops/s $\color{#35bf28}+0.84\%$
test_sac_speed[False-None] 8.3851ms 8.0335ms 124.4793 Ops/s 122.7130 Ops/s $\color{#35bf28}+1.44\%$
test_sac_speed[False-backward] 13.4405ms 10.8591ms 92.0886 Ops/s 91.6214 Ops/s $\color{#35bf28}+0.51\%$
test_sac_speed[True-None] 2.3424ms 2.0780ms 481.2250 Ops/s 475.2751 Ops/s $\color{#35bf28}+1.25\%$
test_sac_speed[True-backward] 4.3712ms 3.9058ms 256.0286 Ops/s 265.2817 Ops/s $\color{#d91a1a}-3.49\%$
test_sac_speed[reduce-overhead-None] 4.3767ms 2.1213ms 471.4109 Ops/s 466.8978 Ops/s $\color{#35bf28}+0.97\%$
test_sac_speed[reduce-overhead-backward] 4.3629ms 3.8210ms 261.7095 Ops/s 263.0750 Ops/s $\color{#d91a1a}-0.52\%$
test_redq_speed[False-None] 20.0027ms 14.3692ms 69.5934 Ops/s 54.5599 Ops/s $\textbf{\color{#35bf28}+27.55\%}$
test_redq_speed[False-backward] 25.5713ms 23.1814ms 43.1380 Ops/s 43.9108 Ops/s $\color{#d91a1a}-1.76\%$
test_redq_speed[True-None] 6.6851ms 5.4147ms 184.6841 Ops/s 206.8238 Ops/s $\textbf{\color{#d91a1a}-10.70\%}$
test_redq_speed[True-backward] 13.8676ms 12.5648ms 79.5875 Ops/s 79.5517 Ops/s $\color{#35bf28}+0.04\%$
test_redq_speed[reduce-overhead-None] 5.5296ms 4.9157ms 203.4303 Ops/s 204.5595 Ops/s $\color{#d91a1a}-0.55\%$
test_redq_speed[reduce-overhead-backward] 13.4958ms 12.8528ms 77.8042 Ops/s 81.0707 Ops/s $\color{#d91a1a}-4.03\%$
test_redq_deprec_speed[False-None] 23.0376ms 13.4714ms 74.2312 Ops/s 77.4225 Ops/s $\color{#d91a1a}-4.12\%$
test_redq_deprec_speed[False-backward] 21.8447ms 19.1198ms 52.3019 Ops/s 53.6939 Ops/s $\color{#d91a1a}-2.59\%$
test_redq_deprec_speed[True-None] 4.2415ms 3.8076ms 262.6300 Ops/s 258.9889 Ops/s $\color{#35bf28}+1.41\%$
test_redq_deprec_speed[True-backward] 9.7154ms 8.7489ms 114.3000 Ops/s 111.1888 Ops/s $\color{#35bf28}+2.80\%$
test_redq_deprec_speed[reduce-overhead-None] 4.4731ms 3.8436ms 260.1746 Ops/s 249.2878 Ops/s $\color{#35bf28}+4.37\%$
test_redq_deprec_speed[reduce-overhead-backward] 9.5184ms 8.6367ms 115.7854 Ops/s 116.2910 Ops/s $\color{#d91a1a}-0.43\%$
test_td3_speed[False-None] 8.4446ms 8.0631ms 124.0212 Ops/s 121.0640 Ops/s $\color{#35bf28}+2.44\%$
test_td3_speed[False-backward] 12.1246ms 10.8335ms 92.3062 Ops/s 94.5723 Ops/s $\color{#d91a1a}-2.40\%$
test_td3_speed[True-None] 2.0088ms 1.8243ms 548.1438 Ops/s 542.5028 Ops/s $\color{#35bf28}+1.04\%$
test_td3_speed[True-backward] 4.5067ms 3.4748ms 287.7825 Ops/s 287.3958 Ops/s $\color{#35bf28}+0.13\%$
test_td3_speed[reduce-overhead-None] 1.9671ms 1.8010ms 555.2369 Ops/s 549.4869 Ops/s $\color{#35bf28}+1.05\%$
test_td3_speed[reduce-overhead-backward] 3.5703ms 3.4627ms 288.7889 Ops/s 287.0774 Ops/s $\color{#35bf28}+0.60\%$
test_cql_speed[False-None] 38.5859ms 36.5184ms 27.3834 Ops/s 27.0554 Ops/s $\color{#35bf28}+1.21\%$
test_cql_speed[False-backward] 49.0186ms 46.8324ms 21.3527 Ops/s 20.9881 Ops/s $\color{#35bf28}+1.74\%$
test_cql_speed[True-None] 17.5099ms 16.5635ms 60.3737 Ops/s 62.1207 Ops/s $\color{#d91a1a}-2.81\%$
test_cql_speed[True-backward] 24.2308ms 23.2885ms 42.9397 Ops/s 42.7812 Ops/s $\color{#35bf28}+0.37\%$
test_cql_speed[reduce-overhead-None] 18.9089ms 16.4091ms 60.9416 Ops/s 62.4192 Ops/s $\color{#d91a1a}-2.37\%$
test_cql_speed[reduce-overhead-backward] 23.7380ms 22.3392ms 44.7644 Ops/s 43.7227 Ops/s $\color{#35bf28}+2.38\%$
test_a2c_speed[False-None] 8.1370ms 7.2166ms 138.5694 Ops/s 138.2606 Ops/s $\color{#35bf28}+0.22\%$
test_a2c_speed[False-backward] 15.7190ms 14.2522ms 70.1647 Ops/s 70.7370 Ops/s $\color{#d91a1a}-0.81\%$
test_a2c_speed[True-None] 4.3130ms 3.7688ms 265.3368 Ops/s 266.7516 Ops/s $\color{#d91a1a}-0.53\%$
test_a2c_speed[True-backward] 10.6111ms 10.1849ms 98.1849 Ops/s 96.2248 Ops/s $\color{#35bf28}+2.04\%$
test_a2c_speed[reduce-overhead-None] 4.0244ms 3.7290ms 268.1696 Ops/s 266.2462 Ops/s $\color{#35bf28}+0.72\%$
test_a2c_speed[reduce-overhead-backward] 10.3975ms 10.1409ms 98.6108 Ops/s 94.8005 Ops/s $\color{#35bf28}+4.02\%$
test_ppo_speed[False-None] 8.7334ms 7.5612ms 132.2542 Ops/s 130.0150 Ops/s $\color{#35bf28}+1.72\%$
test_ppo_speed[False-backward] 16.0335ms 15.2055ms 65.7658 Ops/s 66.2416 Ops/s $\color{#d91a1a}-0.72\%$
test_ppo_speed[True-None] 5.0319ms 4.1363ms 241.7641 Ops/s 243.7637 Ops/s $\color{#d91a1a}-0.82\%$
test_ppo_speed[True-backward] 10.6485ms 10.2781ms 97.2942 Ops/s 95.2180 Ops/s $\color{#35bf28}+2.18\%$
test_ppo_speed[reduce-overhead-None] 4.7456ms 4.1437ms 241.3297 Ops/s 242.0975 Ops/s $\color{#d91a1a}-0.32\%$
test_ppo_speed[reduce-overhead-backward] 12.7031ms 10.5029ms 95.2117 Ops/s 98.9340 Ops/s $\color{#d91a1a}-3.76\%$
test_reinforce_speed[False-None] 7.8971ms 6.6250ms 150.9430 Ops/s 146.9783 Ops/s $\color{#35bf28}+2.70\%$
test_reinforce_speed[False-backward] 11.8082ms 10.1635ms 98.3909 Ops/s 101.6724 Ops/s $\color{#d91a1a}-3.23\%$
test_reinforce_speed[True-None] 3.4480ms 3.1141ms 321.1213 Ops/s 318.6269 Ops/s $\color{#35bf28}+0.78\%$
test_reinforce_speed[True-backward] 9.8842ms 9.3351ms 107.1221 Ops/s 104.3376 Ops/s $\color{#35bf28}+2.67\%$
test_reinforce_speed[reduce-overhead-None] 4.1921ms 3.2030ms 312.2095 Ops/s 311.4156 Ops/s $\color{#35bf28}+0.25\%$
test_reinforce_speed[reduce-overhead-backward] 10.3184ms 9.2617ms 107.9716 Ops/s 106.4397 Ops/s $\color{#35bf28}+1.44\%$
test_iql_speed[False-None] 34.3418ms 33.1806ms 30.1381 Ops/s 30.2169 Ops/s $\color{#d91a1a}-0.26\%$
test_iql_speed[False-backward] 50.3316ms 46.4961ms 21.5072 Ops/s 21.1773 Ops/s $\color{#35bf28}+1.56\%$
test_iql_speed[True-None] 14.4309ms 12.1042ms 82.6158 Ops/s 87.7554 Ops/s $\textbf{\color{#d91a1a}-5.86\%}$
test_iql_speed[True-backward] 23.8594ms 23.0209ms 43.4388 Ops/s 44.8805 Ops/s $\color{#d91a1a}-3.21\%$
test_iql_speed[reduce-overhead-None] 13.1195ms 11.8428ms 84.4395 Ops/s 88.9651 Ops/s $\textbf{\color{#d91a1a}-5.09\%}$
test_iql_speed[reduce-overhead-backward] 25.1254ms 23.2984ms 42.9215 Ops/s 44.4192 Ops/s $\color{#d91a1a}-3.37\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 0.5340s 7.8531ms 127.3380 Ops/s 200.2893 Ops/s $\textbf{\color{#d91a1a}-36.42\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7421ms 0.5200ms 1.9232 KOps/s 1.8847 KOps/s $\color{#35bf28}+2.05\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7777ms 0.5027ms 1.9894 KOps/s 1.9565 KOps/s $\color{#35bf28}+1.68\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.1984ms 4.9004ms 204.0666 Ops/s 215.8624 Ops/s $\textbf{\color{#d91a1a}-5.46\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.7161ms 0.5153ms 1.9405 KOps/s 1.7894 KOps/s $\textbf{\color{#35bf28}+8.44\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7843ms 0.4873ms 2.0521 KOps/s 2.0153 KOps/s $\color{#35bf28}+1.82\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.1929ms 1.7219ms 580.7490 Ops/s 593.1538 Ops/s $\color{#d91a1a}-2.09\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.2473ms 1.5739ms 635.3805 Ops/s 631.1385 Ops/s $\color{#35bf28}+0.67\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.5729ms 5.0531ms 197.8993 Ops/s 204.7249 Ops/s $\color{#d91a1a}-3.33\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.7406ms 0.6746ms 1.4824 KOps/s 1.5230 KOps/s $\color{#d91a1a}-2.66\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.1193ms 0.6379ms 1.5677 KOps/s 1.5595 KOps/s $\color{#35bf28}+0.52\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.0757ms 4.8957ms 204.2613 Ops/s 204.6073 Ops/s $\color{#d91a1a}-0.17\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.2187ms 0.5242ms 1.9075 KOps/s 1.9044 KOps/s $\color{#35bf28}+0.16\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7987ms 0.4997ms 2.0012 KOps/s 1.9667 KOps/s $\color{#35bf28}+1.76\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.3148ms 4.8652ms 205.5400 Ops/s 204.9565 Ops/s $\color{#35bf28}+0.28\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.0799ms 0.5273ms 1.8965 KOps/s 1.9351 KOps/s $\color{#d91a1a}-1.99\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7139ms 0.4881ms 2.0489 KOps/s 1.9601 KOps/s $\color{#35bf28}+4.53\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.6180ms 5.0372ms 198.5217 Ops/s 195.8121 Ops/s $\color{#35bf28}+1.38\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3882ms 0.6673ms 1.4986 KOps/s 1.4820 KOps/s $\color{#35bf28}+1.12\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9765ms 0.6434ms 1.5542 KOps/s 1.5160 KOps/s $\color{#35bf28}+2.52\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.5421s 15.1278ms 66.1036 Ops/s 230.4317 Ops/s $\textbf{\color{#d91a1a}-71.31\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 9.8938ms 2.5013ms 399.7946 Ops/s 424.5187 Ops/s $\textbf{\color{#d91a1a}-5.82\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.0418ms 1.3542ms 738.4350 Ops/s 727.2329 Ops/s $\color{#35bf28}+1.54\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 5.9363ms 4.2833ms 233.4665 Ops/s 224.3650 Ops/s $\color{#35bf28}+4.06\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 5.3599ms 2.3375ms 427.8012 Ops/s 384.6552 Ops/s $\textbf{\color{#35bf28}+11.22\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.1147ms 1.4831ms 674.2660 Ops/s 699.5000 Ops/s $\color{#d91a1a}-3.61\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.4592s 13.6242ms 73.3988 Ops/s 207.1520 Ops/s $\textbf{\color{#d91a1a}-64.57\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.3326ms 2.5822ms 387.2617 Ops/s 388.5001 Ops/s $\color{#d91a1a}-0.32\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.6055ms 1.5611ms 640.5667 Ops/s 645.7767 Ops/s $\color{#d91a1a}-0.81\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.0306ms 11.9098ms 83.9643 Ops/s 76.5694 Ops/s $\textbf{\color{#35bf28}+9.66\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 15.8717ms 14.7357ms 67.8623 Ops/s 66.1992 Ops/s $\color{#35bf28}+2.51\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 21.6658ms 20.8934ms 47.8619 Ops/s 46.5272 Ops/s $\color{#35bf28}+2.87\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 16.8030ms 14.9041ms 67.0956 Ops/s 67.9615 Ops/s $\color{#d91a1a}-1.27\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 21.1139ms 20.5886ms 48.5706 Ops/s 47.6506 Ops/s $\color{#35bf28}+1.93\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 17.5411ms 16.1606ms 61.8789 Ops/s 62.3268 Ops/s $\color{#d91a1a}-0.72\%$

Copy link

github-actions bot commented Feb 10, 2025

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}17$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.8973s 0.8103s 1.2341 Ops/s 1.2725 Ops/s $\color{#d91a1a}-3.02\%$
test_transformed 1.4641s 1.3896s 0.7196 Ops/s 0.7303 Ops/s $\color{#d91a1a}-1.46\%$
test_serial 2.3889s 2.2922s 0.4363 Ops/s 0.4413 Ops/s $\color{#d91a1a}-1.13\%$
test_parallel 1.9568s 1.8578s 0.5383 Ops/s 0.5407 Ops/s $\color{#d91a1a}-0.45\%$
test_step_mdp_speed[True-True-True-True-True] 0.1926ms 40.5373μs 24.6686 KOps/s 24.8171 KOps/s $\color{#d91a1a}-0.60\%$
test_step_mdp_speed[True-True-True-True-False] 60.6910μs 24.0734μs 41.5396 KOps/s 42.3656 KOps/s $\color{#d91a1a}-1.95\%$
test_step_mdp_speed[True-True-True-False-True] 65.6110μs 23.1329μs 43.2284 KOps/s 44.4184 KOps/s $\color{#d91a1a}-2.68\%$
test_step_mdp_speed[True-True-True-False-False] 41.1210μs 13.3771μs 74.7547 KOps/s 76.5122 KOps/s $\color{#d91a1a}-2.30\%$
test_step_mdp_speed[True-True-False-True-True] 89.5310μs 44.6103μs 22.4164 KOps/s 23.5115 KOps/s $\color{#d91a1a}-4.66\%$
test_step_mdp_speed[True-True-False-True-False] 65.8410μs 26.7855μs 37.3336 KOps/s 38.3027 KOps/s $\color{#d91a1a}-2.53\%$
test_step_mdp_speed[True-True-False-False-True] 61.4710μs 25.5349μs 39.1621 KOps/s 40.1581 KOps/s $\color{#d91a1a}-2.48\%$
test_step_mdp_speed[True-True-False-False-False] 47.5710μs 15.8342μs 63.1545 KOps/s 64.5618 KOps/s $\color{#d91a1a}-2.18\%$
test_step_mdp_speed[True-False-True-True-True] 91.6920μs 46.4633μs 21.5224 KOps/s 22.3221 KOps/s $\color{#d91a1a}-3.58\%$
test_step_mdp_speed[True-False-True-True-False] 69.8810μs 29.2347μs 34.2059 KOps/s 35.0267 KOps/s $\color{#d91a1a}-2.34\%$
test_step_mdp_speed[True-False-True-False-True] 69.8710μs 25.5481μs 39.1419 KOps/s 39.4753 KOps/s $\color{#d91a1a}-0.84\%$
test_step_mdp_speed[True-False-True-False-False] 47.6810μs 15.8240μs 63.1950 KOps/s 63.9808 KOps/s $\color{#d91a1a}-1.23\%$
test_step_mdp_speed[True-False-False-True-True] 88.4820μs 48.6616μs 20.5501 KOps/s 20.9953 KOps/s $\color{#d91a1a}-2.12\%$
test_step_mdp_speed[True-False-False-True-False] 69.2110μs 31.5673μs 31.6783 KOps/s 32.1486 KOps/s $\color{#d91a1a}-1.46\%$
test_step_mdp_speed[True-False-False-False-True] 66.7910μs 27.6086μs 36.2206 KOps/s 36.5580 KOps/s $\color{#d91a1a}-0.92\%$
test_step_mdp_speed[True-False-False-False-False] 48.7510μs 18.3596μs 54.4673 KOps/s 55.8222 KOps/s $\color{#d91a1a}-2.43\%$
test_step_mdp_speed[False-True-True-True-True] 83.5520μs 46.8171μs 21.3597 KOps/s 22.2727 KOps/s $\color{#d91a1a}-4.10\%$
test_step_mdp_speed[False-True-True-True-False] 64.7310μs 29.3462μs 34.0760 KOps/s 35.2483 KOps/s $\color{#d91a1a}-3.33\%$
test_step_mdp_speed[False-True-True-False-True] 68.1910μs 29.6401μs 33.7381 KOps/s 34.3822 KOps/s $\color{#d91a1a}-1.87\%$
test_step_mdp_speed[False-True-True-False-False] 52.1510μs 17.7377μs 56.3772 KOps/s 57.2809 KOps/s $\color{#d91a1a}-1.58\%$
test_step_mdp_speed[False-True-False-True-True] 87.3420μs 49.5415μs 20.1851 KOps/s 21.3166 KOps/s $\textbf{\color{#d91a1a}-5.31\%}$
test_step_mdp_speed[False-True-False-True-False] 69.4810μs 31.7632μs 31.4829 KOps/s 32.3273 KOps/s $\color{#d91a1a}-2.61\%$
test_step_mdp_speed[False-True-False-False-True] 3.1404ms 32.7084μs 30.5731 KOps/s 31.9252 KOps/s $\color{#d91a1a}-4.24\%$
test_step_mdp_speed[False-True-False-False-False] 64.5310μs 20.0585μs 49.8542 KOps/s 50.7414 KOps/s $\color{#d91a1a}-1.75\%$
test_step_mdp_speed[False-False-True-True-True] 94.1020μs 51.0379μs 19.5933 KOps/s 19.9892 KOps/s $\color{#d91a1a}-1.98\%$
test_step_mdp_speed[False-False-True-True-False] 71.6310μs 34.1381μs 29.2928 KOps/s 30.1533 KOps/s $\color{#d91a1a}-2.85\%$
test_step_mdp_speed[False-False-True-False-True] 82.8520μs 32.2278μs 31.0291 KOps/s 32.0679 KOps/s $\color{#d91a1a}-3.24\%$
test_step_mdp_speed[False-False-True-False-False] 54.4510μs 20.1691μs 49.5809 KOps/s 50.9026 KOps/s $\color{#d91a1a}-2.60\%$
test_step_mdp_speed[False-False-False-True-True] 93.4210μs 52.9506μs 18.8855 KOps/s 19.3987 KOps/s $\color{#d91a1a}-2.65\%$
test_step_mdp_speed[False-False-False-True-False] 95.1620μs 36.5896μs 27.3301 KOps/s 28.0723 KOps/s $\color{#d91a1a}-2.64\%$
test_step_mdp_speed[False-False-False-False-True] 70.9910μs 33.8553μs 29.5374 KOps/s 30.4546 KOps/s $\color{#d91a1a}-3.01\%$
test_step_mdp_speed[False-False-False-False-False] 59.3510μs 22.3910μs 44.6608 KOps/s 45.7040 KOps/s $\color{#d91a1a}-2.28\%$
test_values[generalized_advantage_estimate-True-True] 23.9766ms 23.5379ms 42.4846 Ops/s 42.6098 Ops/s $\color{#d91a1a}-0.29\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1101s 3.0873ms 323.9095 Ops/s 320.6582 Ops/s $\color{#35bf28}+1.01\%$
test_values[td0_return_estimate-False-False] 0.1107ms 77.7867μs 12.8557 KOps/s 12.7313 KOps/s $\color{#35bf28}+0.98\%$
test_values[td1_return_estimate-False-False] 53.1776ms 52.7562ms 18.9551 Ops/s 19.0782 Ops/s $\color{#d91a1a}-0.64\%$
test_values[vec_td1_return_estimate-False-False] 1.3030ms 1.0659ms 938.1924 Ops/s 940.7705 Ops/s $\color{#d91a1a}-0.27\%$
test_values[td_lambda_return_estimate-True-False] 85.4487ms 83.9122ms 11.9172 Ops/s 11.9901 Ops/s $\color{#d91a1a}-0.61\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.2685ms 1.0606ms 942.8919 Ops/s 945.6273 Ops/s $\color{#d91a1a}-0.29\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 23.6588ms 23.5355ms 42.4891 Ops/s 42.6239 Ops/s $\color{#d91a1a}-0.32\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0208ms 0.7327ms 1.3648 KOps/s 1.3679 KOps/s $\color{#d91a1a}-0.23\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.8934ms 0.6514ms 1.5351 KOps/s 1.5377 KOps/s $\color{#d91a1a}-0.16\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5094ms 1.4659ms 682.1515 Ops/s 682.9935 Ops/s $\color{#d91a1a}-0.12\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7599ms 0.6645ms 1.5049 KOps/s 1.5044 KOps/s $\color{#35bf28}+0.03\%$
test_dqn_speed[False-None] 6.8414ms 1.5417ms 648.6339 Ops/s 662.0935 Ops/s $\color{#d91a1a}-2.03\%$
test_dqn_speed[False-backward] 2.2231ms 2.1170ms 472.3721 Ops/s 475.5233 Ops/s $\color{#d91a1a}-0.66\%$
test_dqn_speed[True-None] 0.9550ms 0.5519ms 1.8119 KOps/s 1.7937 KOps/s $\color{#35bf28}+1.01\%$
test_dqn_speed[True-backward] 1.2826ms 1.2153ms 822.8185 Ops/s 817.2425 Ops/s $\color{#35bf28}+0.68\%$
test_dqn_speed[reduce-overhead-None] 0.9956ms 0.5708ms 1.7518 KOps/s 1.7611 KOps/s $\color{#d91a1a}-0.53\%$
test_dqn_speed[reduce-overhead-backward] 1.1015ms 1.0575ms 945.6644 Ops/s 931.3340 Ops/s $\color{#35bf28}+1.54\%$
test_ddpg_speed[False-None] 3.2608ms 2.8677ms 348.7078 Ops/s 347.9010 Ops/s $\color{#35bf28}+0.23\%$
test_ddpg_speed[False-backward] 4.5602ms 4.2024ms 237.9619 Ops/s 237.7342 Ops/s $\color{#35bf28}+0.10\%$
test_ddpg_speed[True-None] 1.4398ms 1.3338ms 749.7435 Ops/s 746.5848 Ops/s $\color{#35bf28}+0.42\%$
test_ddpg_speed[True-backward] 2.6003ms 2.5567ms 391.1316 Ops/s 383.9803 Ops/s $\color{#35bf28}+1.86\%$
test_ddpg_speed[reduce-overhead-None] 1.4465ms 1.3448ms 743.5913 Ops/s 742.0986 Ops/s $\color{#35bf28}+0.20\%$
test_ddpg_speed[reduce-overhead-backward] 2.1377ms 2.0283ms 493.0233 Ops/s 491.0924 Ops/s $\color{#35bf28}+0.39\%$
test_sac_speed[False-None] 8.3408ms 7.9264ms 126.1604 Ops/s 125.3201 Ops/s $\color{#35bf28}+0.67\%$
test_sac_speed[False-backward] 11.3874ms 10.9625ms 91.2205 Ops/s 90.5124 Ops/s $\color{#35bf28}+0.78\%$
test_sac_speed[True-None] 1.9313ms 1.8263ms 547.5642 Ops/s 541.4221 Ops/s $\color{#35bf28}+1.13\%$
test_sac_speed[True-backward] 3.8041ms 3.7218ms 268.6901 Ops/s 267.0542 Ops/s $\color{#35bf28}+0.61\%$
test_sac_speed[reduce-overhead-None] 21.2201ms 11.8780ms 84.1890 Ops/s 82.6375 Ops/s $\color{#35bf28}+1.88\%$
test_sac_speed[reduce-overhead-backward] 1.8294ms 1.7771ms 562.7173 Ops/s 597.0008 Ops/s $\textbf{\color{#d91a1a}-5.74\%}$
test_redq_speed[False-None] 7.8459ms 7.4203ms 134.7662 Ops/s 130.8554 Ops/s $\color{#35bf28}+2.99\%$
test_redq_speed[False-backward] 11.9006ms 11.3751ms 87.9112 Ops/s 88.3482 Ops/s $\color{#d91a1a}-0.49\%$
test_redq_speed[True-None] 2.5075ms 2.3203ms 430.9790 Ops/s 433.1815 Ops/s $\color{#d91a1a}-0.51\%$
test_redq_speed[True-backward] 4.6893ms 4.1842ms 238.9925 Ops/s 239.9849 Ops/s $\color{#d91a1a}-0.41\%$
test_redq_speed[reduce-overhead-None] 2.7792ms 2.3391ms 427.5130 Ops/s 427.7772 Ops/s $\color{#d91a1a}-0.06\%$
test_redq_speed[reduce-overhead-backward] 4.6348ms 4.1921ms 238.5447 Ops/s 239.9257 Ops/s $\color{#d91a1a}-0.58\%$
test_redq_deprec_speed[False-None] 9.4364ms 8.9464ms 111.7769 Ops/s 111.8581 Ops/s $\color{#d91a1a}-0.07\%$
test_redq_deprec_speed[False-backward] 12.5536ms 12.0835ms 82.7577 Ops/s 82.9775 Ops/s $\color{#d91a1a}-0.26\%$
test_redq_deprec_speed[True-None] 2.7869ms 2.6206ms 381.5974 Ops/s 379.3950 Ops/s $\color{#35bf28}+0.58\%$
test_redq_deprec_speed[True-backward] 4.9072ms 4.4640ms 224.0144 Ops/s 229.1186 Ops/s $\color{#d91a1a}-2.23\%$
test_redq_deprec_speed[reduce-overhead-None] 2.7643ms 2.6283ms 380.4747 Ops/s 366.6656 Ops/s $\color{#35bf28}+3.77\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.5322ms 4.4419ms 225.1294 Ops/s 230.2218 Ops/s $\color{#d91a1a}-2.21\%$
test_td3_speed[False-None] 8.1369ms 7.8759ms 126.9698 Ops/s 125.8045 Ops/s $\color{#35bf28}+0.93\%$
test_td3_speed[False-backward] 10.8327ms 10.3518ms 96.6020 Ops/s 97.7415 Ops/s $\color{#d91a1a}-1.17\%$
test_td3_speed[True-None] 1.7129ms 1.6563ms 603.7595 Ops/s 604.9895 Ops/s $\color{#d91a1a}-0.20\%$
test_td3_speed[True-backward] 3.3763ms 3.3349ms 299.8597 Ops/s 312.7439 Ops/s $\color{#d91a1a}-4.12\%$
test_td3_speed[reduce-overhead-None] 50.0101ms 25.4928ms 39.2267 Ops/s 39.0650 Ops/s $\color{#35bf28}+0.41\%$
test_td3_speed[reduce-overhead-backward] 1.5462ms 1.4685ms 680.9561 Ops/s 732.9001 Ops/s $\textbf{\color{#d91a1a}-7.09\%}$
test_cql_speed[False-None] 16.8419ms 16.4659ms 60.7315 Ops/s 59.6046 Ops/s $\color{#35bf28}+1.89\%$
test_cql_speed[False-backward] 22.2702ms 21.8607ms 45.7441 Ops/s 46.3327 Ops/s $\color{#d91a1a}-1.27\%$
test_cql_speed[True-None] 3.3579ms 3.2548ms 307.2361 Ops/s 304.7161 Ops/s $\color{#35bf28}+0.83\%$
test_cql_speed[True-backward] 6.1932ms 5.5831ms 179.1104 Ops/s 180.9712 Ops/s $\color{#d91a1a}-1.03\%$
test_cql_speed[reduce-overhead-None] 20.5679ms 12.8928ms 77.5627 Ops/s 75.9416 Ops/s $\color{#35bf28}+2.13\%$
test_cql_speed[reduce-overhead-backward] 1.9841ms 1.8143ms 551.1886 Ops/s 534.7154 Ops/s $\color{#35bf28}+3.08\%$
test_a2c_speed[False-None] 3.5309ms 3.1677ms 315.6896 Ops/s 314.0224 Ops/s $\color{#35bf28}+0.53\%$
test_a2c_speed[False-backward] 6.6564ms 5.9948ms 166.8102 Ops/s 167.0387 Ops/s $\color{#d91a1a}-0.14\%$
test_a2c_speed[True-None] 1.4746ms 1.3643ms 732.9875 Ops/s 735.5268 Ops/s $\color{#d91a1a}-0.35\%$
test_a2c_speed[True-backward] 3.0553ms 2.9401ms 340.1277 Ops/s 339.5740 Ops/s $\color{#35bf28}+0.16\%$
test_a2c_speed[reduce-overhead-None] 15.7928ms 9.0042ms 111.0595 Ops/s 112.2080 Ops/s $\color{#d91a1a}-1.02\%$
test_a2c_speed[reduce-overhead-backward] 1.5279ms 1.4577ms 686.0177 Ops/s 679.4202 Ops/s $\color{#35bf28}+0.97\%$
test_ppo_speed[False-None] 3.7887ms 3.6424ms 274.5452 Ops/s 270.7115 Ops/s $\color{#35bf28}+1.42\%$
test_ppo_speed[False-backward] 7.2274ms 6.6624ms 150.0964 Ops/s 150.0896 Ops/s $+0.00\%$
test_ppo_speed[True-None] 1.5053ms 1.4173ms 705.5427 Ops/s 699.4246 Ops/s $\color{#35bf28}+0.87\%$
test_ppo_speed[True-backward] 3.1424ms 3.0432ms 328.5976 Ops/s 307.1922 Ops/s $\textbf{\color{#35bf28}+6.97\%}$
test_ppo_speed[reduce-overhead-None] 1.0390ms 0.9664ms 1.0348 KOps/s 1.0371 KOps/s $\color{#d91a1a}-0.23\%$
test_ppo_speed[reduce-overhead-backward] 1.5124ms 1.4058ms 711.3308 Ops/s 623.2776 Ops/s $\textbf{\color{#35bf28}+14.13\%}$
test_reinforce_speed[False-None] 2.3251ms 2.2479ms 444.8660 Ops/s 441.9268 Ops/s $\color{#35bf28}+0.67\%$
test_reinforce_speed[False-backward] 3.7125ms 3.2514ms 307.5641 Ops/s 295.4816 Ops/s $\color{#35bf28}+4.09\%$
test_reinforce_speed[True-None] 1.3801ms 1.2960ms 771.5867 Ops/s 757.5993 Ops/s $\color{#35bf28}+1.85\%$
test_reinforce_speed[True-backward] 3.0631ms 2.9265ms 341.7076 Ops/s 326.3830 Ops/s $\color{#35bf28}+4.70\%$
test_reinforce_speed[reduce-overhead-None] 17.7893ms 9.8610ms 101.4094 Ops/s 100.6996 Ops/s $\color{#35bf28}+0.70\%$
test_reinforce_speed[reduce-overhead-backward] 1.5691ms 1.4915ms 670.4786 Ops/s 603.8947 Ops/s $\textbf{\color{#35bf28}+11.03\%}$
test_iql_speed[False-None] 9.4970ms 9.0689ms 110.2674 Ops/s 108.1814 Ops/s $\color{#35bf28}+1.93\%$
test_iql_speed[False-backward] 12.9083ms 12.5214ms 79.8634 Ops/s 76.4487 Ops/s $\color{#35bf28}+4.47\%$
test_iql_speed[True-None] 2.3975ms 2.2364ms 447.1436 Ops/s 439.2292 Ops/s $\color{#35bf28}+1.80\%$
test_iql_speed[True-backward] 5.2058ms 4.7564ms 210.2409 Ops/s 200.3426 Ops/s $\color{#35bf28}+4.94\%$
test_iql_speed[reduce-overhead-None] 18.7069ms 11.1163ms 89.9581 Ops/s 90.5852 Ops/s $\color{#d91a1a}-0.69\%$
test_iql_speed[reduce-overhead-backward] 1.9713ms 1.8903ms 529.0037 Ops/s 470.4753 Ops/s $\textbf{\color{#35bf28}+12.44\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.8021ms 6.3467ms 157.5612 Ops/s 155.1451 Ops/s $\color{#35bf28}+1.56\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5057ms 0.2659ms 3.7611 KOps/s 3.3548 KOps/s $\textbf{\color{#35bf28}+12.11\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5223ms 0.2809ms 3.5596 KOps/s 3.3463 KOps/s $\textbf{\color{#35bf28}+6.37\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3272ms 6.0706ms 164.7273 Ops/s 163.3076 Ops/s $\color{#35bf28}+0.87\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.6859ms 0.3261ms 3.0665 KOps/s 2.8653 KOps/s $\textbf{\color{#35bf28}+7.02\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5277ms 0.3130ms 3.1949 KOps/s 3.1551 KOps/s $\color{#35bf28}+1.26\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.5631ms 1.3233ms 755.7029 Ops/s 797.1804 Ops/s $\textbf{\color{#d91a1a}-5.20\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4705ms 1.2102ms 826.3115 Ops/s 827.8549 Ops/s $\color{#d91a1a}-0.19\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4575ms 6.2218ms 160.7241 Ops/s 157.7494 Ops/s $\color{#35bf28}+1.89\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7750ms 0.4175ms 2.3954 KOps/s 1.9924 KOps/s $\textbf{\color{#35bf28}+20.23\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7711ms 0.4383ms 2.2815 KOps/s 2.2855 KOps/s $\color{#d91a1a}-0.17\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.2242ms 6.0863ms 164.3028 Ops/s 162.0072 Ops/s $\color{#35bf28}+1.42\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.7432ms 0.3061ms 3.2668 KOps/s 2.7483 KOps/s $\textbf{\color{#35bf28}+18.86\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5084ms 0.2500ms 3.9992 KOps/s 3.0375 KOps/s $\textbf{\color{#35bf28}+31.66\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.2945ms 6.0031ms 166.5793 Ops/s 163.5029 Ops/s $\color{#35bf28}+1.88\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.0802ms 0.3387ms 2.9525 KOps/s 3.2274 KOps/s $\textbf{\color{#d91a1a}-8.52\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5084ms 0.3131ms 3.1942 KOps/s 3.4723 KOps/s $\textbf{\color{#d91a1a}-8.01\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4376ms 6.1778ms 161.8699 Ops/s 158.9998 Ops/s $\color{#35bf28}+1.81\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.9727ms 0.4487ms 2.2285 KOps/s 2.0142 KOps/s $\textbf{\color{#35bf28}+10.64\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6095ms 0.4278ms 2.3377 KOps/s 2.1214 KOps/s $\textbf{\color{#35bf28}+10.19\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.9266ms 5.3976ms 185.2671 Ops/s 184.1886 Ops/s $\color{#35bf28}+0.59\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 10.1412ms 2.0744ms 482.0733 Ops/s 435.7642 Ops/s $\textbf{\color{#35bf28}+10.63\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.6980ms 1.2201ms 819.5919 Ops/s 787.2203 Ops/s $\color{#35bf28}+4.11\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 7.0310ms 5.5082ms 181.5471 Ops/s 184.4482 Ops/s $\color{#d91a1a}-1.57\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 10.5407ms 2.0815ms 480.4181 Ops/s 427.6454 Ops/s $\textbf{\color{#35bf28}+12.34\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 3.4867ms 1.1413ms 876.1962 Ops/s 837.8154 Ops/s $\color{#35bf28}+4.58\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.5228s 16.1787ms 61.8095 Ops/s 31.4972 Ops/s $\textbf{\color{#35bf28}+96.24\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.5624ms 2.1634ms 462.2271 Ops/s 441.8664 Ops/s $\color{#35bf28}+4.61\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 8.8900ms 1.3671ms 731.4841 Ops/s 739.7888 Ops/s $\color{#d91a1a}-1.12\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.2664ms 13.0738ms 76.4889 Ops/s 72.8385 Ops/s $\textbf{\color{#35bf28}+5.01\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 18.2692ms 16.2737ms 61.4487 Ops/s 59.0475 Ops/s $\color{#35bf28}+4.07\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 17.7938ms 17.5767ms 56.8935 Ops/s 53.2555 Ops/s $\textbf{\color{#35bf28}+6.83\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 18.1702ms 16.6824ms 59.9434 Ops/s 59.1445 Ops/s $\color{#35bf28}+1.35\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 17.8351ms 17.5686ms 56.9196 Ops/s 55.2462 Ops/s $\color{#35bf28}+3.03\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 19.1938ms 17.8025ms 56.1718 Ops/s 55.9563 Ops/s $\color{#35bf28}+0.39\%$

[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: 8121a3b4bf03c41866d72d23f7dfde5a2287bb5e
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: b85382662fd2610bc7a09d0023aaaae5fba1b73b
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: c0ca881bcf84c84e773bca18ee1c80a4d767e7db
Pull Request resolved: #2776
@vmoens vmoens added the documentation Improvements or additions to documentation label Feb 10, 2025
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: 438929bfc3bff494afbcf217baafa03cd5c78a3c
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: f37d83203a26f3b4f85fb95b7cbd3cc8838dd3ee
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: 2f81b7a0357bcd97659ba5a338f089cef1413589
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: f4f6b6c5b484292cf631258b2803069e42028780
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: bda4a18860612db78974df3c52078a81927d4a1c
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 10, 2025
ghstack-source-id: 9382af3d2d89382e434070d2d8b24eed63f40329
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: c24f82949ce3ad90fedaa506488ded975452bd3f
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: 3b10e7ffd4e3ed9f6958a198398a5c8faad2e029
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: 34b2a73b20e7ee91cb65a74cbdae9579933f9701
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: 9c2a3859b2da050a060fad0cec79dd6733219502
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: 0fb0987a3a663fb9620077bcc88db8a4962b2771
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: 1ff3097989167620e94d81a7c4669e0dee1f7423
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: 902b09d67dfeee457059400c20cf9737f727268d
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: 4f6fe4c1568e791817e10d9c4f3e3d0bb87e6dd6
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: e378df8fab9c5ccbb8f767ebe4259c4cfebf139f
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: 8d81baca1ce572055ff7ced565605a45b7054c47
Pull Request resolved: #2776
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 11, 2025
ghstack-source-id: 4c382f518b69d60158e63dd109db84f7a395d42a
Pull Request resolved: #2776
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.

2 participants