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] Fix formatting errors #2786

Open
wants to merge 1 commit into
base: gh/vmoens/90/base
Choose a base branch
from
Open

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Feb 12, 2025

Stack from ghstack (oldest at bottom):

[ghstack-poisoned]
vmoens added a commit that referenced this pull request Feb 12, 2025
ghstack-source-id: 0b4f78aae6aa6d4276a5a76f9bf2d64607c5a5bd
Pull Request resolved: #2786
Copy link

pytorch-bot bot commented Feb 12, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2786

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

❌ 2 New Failures, 2 Unrelated Failures

As of commit 43d558c with merge base f1c42e0 (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 12, 2025
Copy link

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}14$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.5948s 0.4988s 2.0048 Ops/s 1.9532 Ops/s $\color{#35bf28}+2.64\%$
test_transformed 1.0615s 0.9756s 1.0250 Ops/s 1.0158 Ops/s $\color{#35bf28}+0.90\%$
test_serial 1.4982s 1.4838s 0.6740 Ops/s 0.6509 Ops/s $\color{#35bf28}+3.54\%$
test_parallel 1.4076s 1.2972s 0.7709 Ops/s 0.7709 Ops/s $-0.00\%$
test_step_mdp_speed[True-True-True-True-True] 0.2191ms 30.3654μs 32.9322 KOps/s 33.4090 KOps/s $\color{#d91a1a}-1.43\%$
test_step_mdp_speed[True-True-True-True-False] 50.9750μs 17.8583μs 55.9964 KOps/s 55.3685 KOps/s $\color{#35bf28}+1.13\%$
test_step_mdp_speed[True-True-True-False-True] 45.0240μs 16.9738μs 58.9144 KOps/s 58.4076 KOps/s $\color{#35bf28}+0.87\%$
test_step_mdp_speed[True-True-True-False-False] 32.4110μs 10.0525μs 99.4774 KOps/s 98.0012 KOps/s $\color{#35bf28}+1.51\%$
test_step_mdp_speed[True-True-False-True-True] 0.6226ms 32.4301μs 30.8355 KOps/s 30.9772 KOps/s $\color{#d91a1a}-0.46\%$
test_step_mdp_speed[True-True-False-True-False] 52.8390μs 19.8547μs 50.3659 KOps/s 50.5460 KOps/s $\color{#d91a1a}-0.36\%$
test_step_mdp_speed[True-True-False-False-True] 49.2920μs 18.9956μs 52.6438 KOps/s 52.4766 KOps/s $\color{#35bf28}+0.32\%$
test_step_mdp_speed[True-True-False-False-False] 36.3370μs 12.0328μs 83.1062 KOps/s 82.1329 KOps/s $\color{#35bf28}+1.19\%$
test_step_mdp_speed[True-False-True-True-True] 73.4370μs 34.1358μs 29.2948 KOps/s 29.3090 KOps/s $\color{#d91a1a}-0.05\%$
test_step_mdp_speed[True-False-True-True-False] 51.9770μs 21.6915μs 46.1010 KOps/s 45.9740 KOps/s $\color{#35bf28}+0.28\%$
test_step_mdp_speed[True-False-True-False-True] 42.0890μs 19.0202μs 52.5757 KOps/s 52.4849 KOps/s $\color{#35bf28}+0.17\%$
test_step_mdp_speed[True-False-True-False-False] 42.8400μs 11.9665μs 83.5668 KOps/s 83.9862 KOps/s $\color{#d91a1a}-0.50\%$
test_step_mdp_speed[True-False-False-True-True] 66.6950μs 36.0410μs 27.7462 KOps/s 27.9072 KOps/s $\color{#d91a1a}-0.58\%$
test_step_mdp_speed[True-False-False-True-False] 46.3070μs 23.5689μs 42.4288 KOps/s 42.8178 KOps/s $\color{#d91a1a}-0.91\%$
test_step_mdp_speed[True-False-False-False-True] 54.0300μs 20.8017μs 48.0730 KOps/s 48.3628 KOps/s $\color{#d91a1a}-0.60\%$
test_step_mdp_speed[True-False-False-False-False] 67.1330μs 13.6866μs 73.0642 KOps/s 72.8719 KOps/s $\color{#35bf28}+0.26\%$
test_step_mdp_speed[False-True-True-True-True] 66.6250μs 34.9560μs 28.6074 KOps/s 29.4504 KOps/s $\color{#d91a1a}-2.86\%$
test_step_mdp_speed[False-True-True-True-False] 67.3160μs 21.9754μs 45.5054 KOps/s 45.3152 KOps/s $\color{#35bf28}+0.42\%$
test_step_mdp_speed[False-True-True-False-True] 59.7110μs 21.8043μs 45.8624 KOps/s 46.5541 KOps/s $\color{#d91a1a}-1.49\%$
test_step_mdp_speed[False-True-True-False-False] 51.8170μs 13.4218μs 74.5056 KOps/s 75.0841 KOps/s $\color{#d91a1a}-0.77\%$
test_step_mdp_speed[False-True-False-True-True] 98.7070μs 35.9699μs 27.8010 KOps/s 28.3436 KOps/s $\color{#d91a1a}-1.91\%$
test_step_mdp_speed[False-True-False-True-False] 0.5842ms 23.3781μs 42.7751 KOps/s 42.5768 KOps/s $\color{#35bf28}+0.47\%$
test_step_mdp_speed[False-True-False-False-True] 2.6374ms 23.3463μs 42.8333 KOps/s 42.3160 KOps/s $\color{#35bf28}+1.22\%$
test_step_mdp_speed[False-True-False-False-False] 40.9670μs 15.0460μs 66.4629 KOps/s 66.6847 KOps/s $\color{#d91a1a}-0.33\%$
test_step_mdp_speed[False-False-True-True-True] 0.1013ms 38.3673μs 26.0639 KOps/s 26.3628 KOps/s $\color{#d91a1a}-1.13\%$
test_step_mdp_speed[False-False-True-True-False] 64.1200μs 25.1665μs 39.7354 KOps/s 39.4346 KOps/s $\color{#35bf28}+0.76\%$
test_step_mdp_speed[False-False-True-False-True] 53.1600μs 23.1297μs 43.2344 KOps/s 43.2553 KOps/s $\color{#d91a1a}-0.05\%$
test_step_mdp_speed[False-False-True-False-False] 51.5660μs 15.2023μs 65.7797 KOps/s 66.5243 KOps/s $\color{#d91a1a}-1.12\%$
test_step_mdp_speed[False-False-False-True-True] 79.0780μs 38.7876μs 25.7814 KOps/s 25.5721 KOps/s $\color{#35bf28}+0.82\%$
test_step_mdp_speed[False-False-False-True-False] 64.0900μs 26.7497μs 37.3836 KOps/s 37.1691 KOps/s $\color{#35bf28}+0.58\%$
test_step_mdp_speed[False-False-False-False-True] 49.6020μs 25.0535μs 39.9145 KOps/s 40.5052 KOps/s $\color{#d91a1a}-1.46\%$
test_step_mdp_speed[False-False-False-False-False] 65.5320μs 16.7475μs 59.7106 KOps/s 59.8334 KOps/s $\color{#d91a1a}-0.21\%$
test_values[generalized_advantage_estimate-True-True] 10.2558ms 9.8391ms 101.6348 Ops/s 103.1994 Ops/s $\color{#d91a1a}-1.52\%$
test_values[vec_generalized_advantage_estimate-True-True] 26.1617ms 24.1148ms 41.4683 Ops/s 38.3959 Ops/s $\textbf{\color{#35bf28}+8.00\%}$
test_values[td0_return_estimate-False-False] 0.2432ms 0.1794ms 5.5743 KOps/s 5.4855 KOps/s $\color{#35bf28}+1.62\%$
test_values[td1_return_estimate-False-False] 27.5610ms 24.6328ms 40.5962 Ops/s 41.6743 Ops/s $\color{#d91a1a}-2.59\%$
test_values[vec_td1_return_estimate-False-False] 26.0101ms 24.2366ms 41.2599 Ops/s 37.9530 Ops/s $\textbf{\color{#35bf28}+8.71\%}$
test_values[td_lambda_return_estimate-True-False] 36.6702ms 34.8822ms 28.6679 Ops/s 28.5317 Ops/s $\color{#35bf28}+0.48\%$
test_values[vec_td_lambda_return_estimate-True-False] 26.9827ms 24.4459ms 40.9067 Ops/s 37.6163 Ops/s $\textbf{\color{#35bf28}+8.75\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 10.9019ms 8.6526ms 115.5724 Ops/s 118.4805 Ops/s $\color{#d91a1a}-2.45\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.2447ms 1.8892ms 529.3228 Ops/s 504.5569 Ops/s $\color{#35bf28}+4.91\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5925ms 0.3672ms 2.7233 KOps/s 2.7176 KOps/s $\color{#35bf28}+0.21\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 45.5870ms 44.7670ms 22.3379 Ops/s 21.1560 Ops/s $\textbf{\color{#35bf28}+5.59\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8747ms 3.4296ms 291.5755 Ops/s 288.7992 Ops/s $\color{#35bf28}+0.96\%$
test_dqn_speed[False-None] 1.6454ms 1.3959ms 716.3623 Ops/s 708.4271 Ops/s $\color{#35bf28}+1.12\%$
test_dqn_speed[False-backward] 2.3928ms 1.9148ms 522.2476 Ops/s 528.9406 Ops/s $\color{#d91a1a}-1.27\%$
test_dqn_speed[True-None] 0.1627s 0.5711ms 1.7510 KOps/s 2.0878 KOps/s $\textbf{\color{#d91a1a}-16.13\%}$
test_dqn_speed[True-backward] 0.9608ms 0.9070ms 1.1025 KOps/s 1.1102 KOps/s $\color{#d91a1a}-0.69\%$
test_dqn_speed[reduce-overhead-None] 0.6614ms 0.4932ms 2.0276 KOps/s 2.0493 KOps/s $\color{#d91a1a}-1.06\%$
test_dqn_speed[reduce-overhead-backward] 0.9583ms 0.9089ms 1.1003 KOps/s 1.0995 KOps/s $\color{#35bf28}+0.06\%$
test_ddpg_speed[False-None] 3.5264ms 2.9117ms 343.4451 Ops/s 345.3578 Ops/s $\color{#d91a1a}-0.55\%$
test_ddpg_speed[False-backward] 5.0497ms 4.1308ms 242.0826 Ops/s 249.3566 Ops/s $\color{#d91a1a}-2.92\%$
test_ddpg_speed[True-None] 1.6677ms 1.2352ms 809.6113 Ops/s 814.4428 Ops/s $\color{#d91a1a}-0.59\%$
test_ddpg_speed[True-backward] 2.3600ms 2.1468ms 465.8151 Ops/s 429.5677 Ops/s $\textbf{\color{#35bf28}+8.44\%}$
test_ddpg_speed[reduce-overhead-None] 1.9607ms 1.2392ms 806.9845 Ops/s 810.3315 Ops/s $\color{#d91a1a}-0.41\%$
test_ddpg_speed[reduce-overhead-backward] 2.2168ms 2.1476ms 465.6420 Ops/s 469.9098 Ops/s $\color{#d91a1a}-0.91\%$
test_sac_speed[False-None] 8.8691ms 8.1439ms 122.7915 Ops/s 124.2235 Ops/s $\color{#d91a1a}-1.15\%$
test_sac_speed[False-backward] 12.5430ms 10.9465ms 91.3532 Ops/s 91.7471 Ops/s $\color{#d91a1a}-0.43\%$
test_sac_speed[True-None] 2.6361ms 2.1097ms 473.9925 Ops/s 471.5122 Ops/s $\color{#35bf28}+0.53\%$
test_sac_speed[True-backward] 4.3337ms 3.8073ms 262.6527 Ops/s 261.5603 Ops/s $\color{#35bf28}+0.42\%$
test_sac_speed[reduce-overhead-None] 2.6550ms 2.1174ms 472.2729 Ops/s 469.6309 Ops/s $\color{#35bf28}+0.56\%$
test_sac_speed[reduce-overhead-backward] 4.6481ms 3.8375ms 260.5837 Ops/s 250.8920 Ops/s $\color{#35bf28}+3.86\%$
test_redq_speed[False-None] 14.2388ms 12.9453ms 77.2481 Ops/s 74.3701 Ops/s $\color{#35bf28}+3.87\%$
test_redq_speed[False-backward] 23.4437ms 22.2779ms 44.8875 Ops/s 43.0179 Ops/s $\color{#35bf28}+4.35\%$
test_redq_speed[True-None] 7.1541ms 5.1571ms 193.9064 Ops/s 180.0644 Ops/s $\textbf{\color{#35bf28}+7.69\%}$
test_redq_speed[True-backward] 14.8180ms 13.0656ms 76.5366 Ops/s 77.0130 Ops/s $\color{#d91a1a}-0.62\%$
test_redq_speed[reduce-overhead-None] 5.7430ms 4.9396ms 202.4446 Ops/s 187.0224 Ops/s $\textbf{\color{#35bf28}+8.25\%}$
test_redq_speed[reduce-overhead-backward] 14.0085ms 12.7096ms 78.6805 Ops/s 79.6078 Ops/s $\color{#d91a1a}-1.16\%$
test_redq_deprec_speed[False-None] 13.8104ms 12.9956ms 76.9491 Ops/s 77.6032 Ops/s $\color{#d91a1a}-0.84\%$
test_redq_deprec_speed[False-backward] 22.1164ms 19.1083ms 52.3332 Ops/s 52.6412 Ops/s $\color{#d91a1a}-0.59\%$
test_redq_deprec_speed[True-None] 4.2640ms 3.8362ms 260.6780 Ops/s 243.1229 Ops/s $\textbf{\color{#35bf28}+7.22\%}$
test_redq_deprec_speed[True-backward] 8.9860ms 8.3016ms 120.4591 Ops/s 116.5647 Ops/s $\color{#35bf28}+3.34\%$
test_redq_deprec_speed[reduce-overhead-None] 4.5929ms 3.8702ms 258.3826 Ops/s 250.0775 Ops/s $\color{#35bf28}+3.32\%$
test_redq_deprec_speed[reduce-overhead-backward] 10.6631ms 8.7662ms 114.0740 Ops/s 117.3124 Ops/s $\color{#d91a1a}-2.76\%$
test_td3_speed[False-None] 8.3183ms 8.0763ms 123.8193 Ops/s 118.6625 Ops/s $\color{#35bf28}+4.35\%$
test_td3_speed[False-backward] 11.0526ms 10.5402ms 94.8749 Ops/s 92.3488 Ops/s $\color{#35bf28}+2.74\%$
test_td3_speed[True-None] 1.9274ms 1.7846ms 560.3464 Ops/s 535.4964 Ops/s $\color{#35bf28}+4.64\%$
test_td3_speed[True-backward] 3.5591ms 3.4110ms 293.1718 Ops/s 291.3352 Ops/s $\color{#35bf28}+0.63\%$
test_td3_speed[reduce-overhead-None] 2.0489ms 1.7832ms 560.7978 Ops/s 534.1023 Ops/s $\color{#35bf28}+5.00\%$
test_td3_speed[reduce-overhead-backward] 3.8606ms 3.4621ms 288.8445 Ops/s 286.4320 Ops/s $\color{#35bf28}+0.84\%$
test_cql_speed[False-None] 38.9457ms 36.5084ms 27.3909 Ops/s 27.0347 Ops/s $\color{#35bf28}+1.32\%$
test_cql_speed[False-backward] 51.2205ms 47.1254ms 21.2200 Ops/s 20.5493 Ops/s $\color{#35bf28}+3.26\%$
test_cql_speed[True-None] 17.8564ms 16.1178ms 62.0434 Ops/s 60.9825 Ops/s $\color{#35bf28}+1.74\%$
test_cql_speed[True-backward] 24.1033ms 22.9442ms 43.5840 Ops/s 43.5660 Ops/s $\color{#35bf28}+0.04\%$
test_cql_speed[reduce-overhead-None] 18.7157ms 16.1393ms 61.9606 Ops/s 59.9113 Ops/s $\color{#35bf28}+3.42\%$
test_cql_speed[reduce-overhead-backward] 24.2299ms 23.0830ms 43.3220 Ops/s 42.7391 Ops/s $\color{#35bf28}+1.36\%$
test_a2c_speed[False-None] 8.9209ms 7.2993ms 136.9995 Ops/s 135.5732 Ops/s $\color{#35bf28}+1.05\%$
test_a2c_speed[False-backward] 16.0305ms 14.5076ms 68.9292 Ops/s 67.1437 Ops/s $\color{#35bf28}+2.66\%$
test_a2c_speed[True-None] 5.2403ms 3.7642ms 265.6604 Ops/s 259.1191 Ops/s $\color{#35bf28}+2.52\%$
test_a2c_speed[True-backward] 11.3163ms 10.3181ms 96.9170 Ops/s 97.1815 Ops/s $\color{#d91a1a}-0.27\%$
test_a2c_speed[reduce-overhead-None] 4.0805ms 3.6901ms 270.9962 Ops/s 265.6585 Ops/s $\color{#35bf28}+2.01\%$
test_a2c_speed[reduce-overhead-backward] 10.6005ms 10.1406ms 98.6139 Ops/s 97.7713 Ops/s $\color{#35bf28}+0.86\%$
test_ppo_speed[False-None] 8.2037ms 7.4896ms 133.5177 Ops/s 129.9994 Ops/s $\color{#35bf28}+2.71\%$
test_ppo_speed[False-backward] 16.0748ms 15.0782ms 66.3211 Ops/s 65.9663 Ops/s $\color{#35bf28}+0.54\%$
test_ppo_speed[True-None] 5.0272ms 4.1674ms 239.9580 Ops/s 238.5602 Ops/s $\color{#35bf28}+0.59\%$
test_ppo_speed[True-backward] 11.4368ms 10.3485ms 96.6321 Ops/s 98.0776 Ops/s $\color{#d91a1a}-1.47\%$
test_ppo_speed[reduce-overhead-None] 5.6822ms 4.2163ms 237.1753 Ops/s 240.1814 Ops/s $\color{#d91a1a}-1.25\%$
test_ppo_speed[reduce-overhead-backward] 10.9657ms 10.1693ms 98.3349 Ops/s 94.5887 Ops/s $\color{#35bf28}+3.96\%$
test_reinforce_speed[False-None] 7.1532ms 6.5407ms 152.8884 Ops/s 150.3113 Ops/s $\color{#35bf28}+1.71\%$
test_reinforce_speed[False-backward] 10.2863ms 9.8882ms 101.1305 Ops/s 99.9667 Ops/s $\color{#35bf28}+1.16\%$
test_reinforce_speed[True-None] 4.0963ms 3.0943ms 323.1781 Ops/s 317.8368 Ops/s $\color{#35bf28}+1.68\%$
test_reinforce_speed[True-backward] 9.3628ms 8.9287ms 111.9982 Ops/s 105.8964 Ops/s $\textbf{\color{#35bf28}+5.76\%}$
test_reinforce_speed[reduce-overhead-None] 3.7868ms 3.0550ms 327.3355 Ops/s 321.2276 Ops/s $\color{#35bf28}+1.90\%$
test_reinforce_speed[reduce-overhead-backward] 10.2815ms 9.0965ms 109.9321 Ops/s 109.8869 Ops/s $\color{#35bf28}+0.04\%$
test_iql_speed[False-None] 33.7947ms 32.3392ms 30.9222 Ops/s 30.1334 Ops/s $\color{#35bf28}+2.62\%$
test_iql_speed[False-backward] 46.8006ms 45.1314ms 22.1575 Ops/s 21.5536 Ops/s $\color{#35bf28}+2.80\%$
test_iql_speed[True-None] 11.8094ms 11.3734ms 87.9242 Ops/s 87.9131 Ops/s $\color{#35bf28}+0.01\%$
test_iql_speed[True-backward] 23.5206ms 22.4557ms 44.5322 Ops/s 44.0643 Ops/s $\color{#35bf28}+1.06\%$
test_iql_speed[reduce-overhead-None] 12.3624ms 11.2478ms 88.9064 Ops/s 85.7327 Ops/s $\color{#35bf28}+3.70\%$
test_iql_speed[reduce-overhead-backward] 25.0769ms 22.8325ms 43.7971 Ops/s 43.5421 Ops/s $\color{#35bf28}+0.59\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 8.0406ms 5.0277ms 198.8984 Ops/s 202.2591 Ops/s $\color{#d91a1a}-1.66\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8152ms 0.5144ms 1.9441 KOps/s 1.9011 KOps/s $\color{#35bf28}+2.26\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8430ms 0.4932ms 2.0277 KOps/s 1.9690 KOps/s $\color{#35bf28}+2.98\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.2483ms 4.7041ms 212.5819 Ops/s 204.8197 Ops/s $\color{#35bf28}+3.79\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.4718ms 0.5099ms 1.9611 KOps/s 1.9503 KOps/s $\color{#35bf28}+0.55\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 1.0434ms 0.4889ms 2.0455 KOps/s 2.0159 KOps/s $\color{#35bf28}+1.47\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.3096ms 1.6694ms 599.0155 Ops/s 575.2467 Ops/s $\color{#35bf28}+4.13\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.0328ms 1.5665ms 638.3488 Ops/s 622.4702 Ops/s $\color{#35bf28}+2.55\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.4069ms 4.8016ms 208.2652 Ops/s 200.3804 Ops/s $\color{#35bf28}+3.93\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9576ms 0.6452ms 1.5498 KOps/s 1.4673 KOps/s $\textbf{\color{#35bf28}+5.63\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9060ms 0.6186ms 1.6166 KOps/s 1.5468 KOps/s $\color{#35bf28}+4.51\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.1963ms 4.6968ms 212.9089 Ops/s 210.8337 Ops/s $\color{#35bf28}+0.98\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6026s 1.2965ms 771.3185 Ops/s 1.8773 KOps/s $\textbf{\color{#d91a1a}-58.91\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8282ms 0.5074ms 1.9709 KOps/s 1.8323 KOps/s $\textbf{\color{#35bf28}+7.57\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.7092ms 4.7898ms 208.7762 Ops/s 215.3630 Ops/s $\color{#d91a1a}-3.06\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.7774ms 0.5121ms 1.9526 KOps/s 415.2872 Ops/s $\textbf{\color{#35bf28}+370.18\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.9053ms 0.5050ms 1.9801 KOps/s 2.0323 KOps/s $\color{#d91a1a}-2.57\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.0449ms 4.8515ms 206.1200 Ops/s 199.5724 Ops/s $\color{#35bf28}+3.28\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 3.1381ms 0.6583ms 1.5190 KOps/s 1.4943 KOps/s $\color{#35bf28}+1.66\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8166ms 0.6301ms 1.5869 KOps/s 1.5407 KOps/s $\color{#35bf28}+3.00\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.4757ms 4.2806ms 233.6113 Ops/s 227.9590 Ops/s $\color{#35bf28}+2.48\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 7.9706ms 2.2912ms 436.4558 Ops/s 421.1135 Ops/s $\color{#35bf28}+3.64\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.0251ms 1.4022ms 713.1502 Ops/s 780.4515 Ops/s $\textbf{\color{#d91a1a}-8.62\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4249s 12.7355ms 78.5207 Ops/s 223.1861 Ops/s $\textbf{\color{#d91a1a}-64.82\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 7.8247ms 2.4095ms 415.0181 Ops/s 438.3252 Ops/s $\textbf{\color{#d91a1a}-5.32\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.1395ms 1.3286ms 752.6679 Ops/s 703.0642 Ops/s $\textbf{\color{#35bf28}+7.06\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 6.0896ms 4.4373ms 225.3622 Ops/s 218.1003 Ops/s $\color{#35bf28}+3.33\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.5224ms 2.5136ms 397.8338 Ops/s 396.9008 Ops/s $\color{#35bf28}+0.24\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.6637ms 1.4080ms 710.2198 Ops/s 662.5699 Ops/s $\textbf{\color{#35bf28}+7.19\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.6647ms 12.3817ms 80.7644 Ops/s 78.7099 Ops/s $\color{#35bf28}+2.61\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 15.9094ms 14.6307ms 68.3497 Ops/s 68.4011 Ops/s $\color{#d91a1a}-0.08\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 22.2201ms 21.0199ms 47.5741 Ops/s 46.2107 Ops/s $\color{#35bf28}+2.95\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 17.8233ms 14.8494ms 67.3429 Ops/s 67.8576 Ops/s $\color{#d91a1a}-0.76\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 22.5680ms 21.0385ms 47.5320 Ops/s 46.6704 Ops/s $\color{#35bf28}+1.85\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 20.1570ms 16.2506ms 61.5362 Ops/s 62.0327 Ops/s $\color{#d91a1a}-0.80\%$

Copy link

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

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

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.8957s 0.8115s 1.2322 Ops/s 1.2811 Ops/s $\color{#d91a1a}-3.82\%$
test_transformed 1.5225s 1.4360s 0.6964 Ops/s 0.7483 Ops/s $\textbf{\color{#d91a1a}-6.94\%}$
test_serial 2.4404s 2.3568s 0.4243 Ops/s 0.4422 Ops/s $\color{#d91a1a}-4.04\%$
test_parallel 2.0669s 1.8786s 0.5323 Ops/s 0.5427 Ops/s $\color{#d91a1a}-1.92\%$
test_step_mdp_speed[True-True-True-True-True] 0.2501ms 40.0758μs 24.9527 KOps/s 24.9537 KOps/s $-0.00\%$
test_step_mdp_speed[True-True-True-True-False] 78.6910μs 23.2750μs 42.9646 KOps/s 43.9022 KOps/s $\color{#d91a1a}-2.14\%$
test_step_mdp_speed[True-True-True-False-True] 63.7610μs 22.3211μs 44.8007 KOps/s 44.9428 KOps/s $\color{#d91a1a}-0.32\%$
test_step_mdp_speed[True-True-True-False-False] 62.8110μs 12.9743μs 77.0752 KOps/s 77.4787 KOps/s $\color{#d91a1a}-0.52\%$
test_step_mdp_speed[True-True-False-True-True] 0.1073ms 42.8070μs 23.3607 KOps/s 24.0860 KOps/s $\color{#d91a1a}-3.01\%$
test_step_mdp_speed[True-True-False-True-False] 63.2310μs 25.4167μs 39.3442 KOps/s 39.4776 KOps/s $\color{#d91a1a}-0.34\%$
test_step_mdp_speed[True-True-False-False-True] 76.8510μs 24.3967μs 40.9891 KOps/s 40.9486 KOps/s $\color{#35bf28}+0.10\%$
test_step_mdp_speed[True-True-False-False-False] 57.5810μs 15.4432μs 64.7535 KOps/s 67.4704 KOps/s $\color{#d91a1a}-4.03\%$
test_step_mdp_speed[True-False-True-True-True] 90.6810μs 44.7189μs 22.3619 KOps/s 22.5994 KOps/s $\color{#d91a1a}-1.05\%$
test_step_mdp_speed[True-False-True-True-False] 70.3210μs 28.0012μs 35.7128 KOps/s 35.6082 KOps/s $\color{#35bf28}+0.29\%$
test_step_mdp_speed[True-False-True-False-True] 55.5010μs 24.3955μs 40.9912 KOps/s 40.9079 KOps/s $\color{#35bf28}+0.20\%$
test_step_mdp_speed[True-False-True-False-False] 45.4910μs 15.1786μs 65.8821 KOps/s 64.9387 KOps/s $\color{#35bf28}+1.45\%$
test_step_mdp_speed[True-False-False-True-True] 91.9710μs 46.9160μs 21.3147 KOps/s 21.3212 KOps/s $\color{#d91a1a}-0.03\%$
test_step_mdp_speed[True-False-False-True-False] 63.8910μs 30.1466μs 33.1712 KOps/s 33.1496 KOps/s $\color{#35bf28}+0.07\%$
test_step_mdp_speed[True-False-False-False-True] 66.8210μs 26.4621μs 37.7899 KOps/s 37.8901 KOps/s $\color{#d91a1a}-0.26\%$
test_step_mdp_speed[True-False-False-False-False] 72.7010μs 17.2058μs 58.1201 KOps/s 58.2834 KOps/s $\color{#d91a1a}-0.28\%$
test_step_mdp_speed[False-True-True-True-True] 0.4224ms 44.4082μs 22.5183 KOps/s 22.6057 KOps/s $\color{#d91a1a}-0.39\%$
test_step_mdp_speed[False-True-True-True-False] 63.8510μs 27.6650μs 36.1468 KOps/s 36.0543 KOps/s $\color{#35bf28}+0.26\%$
test_step_mdp_speed[False-True-True-False-True] 66.9610μs 28.4020μs 35.2088 KOps/s 34.5655 KOps/s $\color{#35bf28}+1.86\%$
test_step_mdp_speed[False-True-True-False-False] 69.6110μs 16.9792μs 58.8957 KOps/s 59.0367 KOps/s $\color{#d91a1a}-0.24\%$
test_step_mdp_speed[False-True-False-True-True] 0.1085ms 47.1790μs 21.1959 KOps/s 21.4002 KOps/s $\color{#d91a1a}-0.95\%$
test_step_mdp_speed[False-True-False-True-False] 64.4710μs 30.3361μs 32.9640 KOps/s 33.1536 KOps/s $\color{#d91a1a}-0.57\%$
test_step_mdp_speed[False-True-False-False-True] 3.1701ms 31.4341μs 31.8126 KOps/s 31.5957 KOps/s $\color{#35bf28}+0.69\%$
test_step_mdp_speed[False-True-False-False-False] 47.0410μs 19.1878μs 52.1165 KOps/s 51.3341 KOps/s $\color{#35bf28}+1.52\%$
test_step_mdp_speed[False-False-True-True-True] 0.1021ms 49.6213μs 20.1526 KOps/s 20.1689 KOps/s $\color{#d91a1a}-0.08\%$
test_step_mdp_speed[False-False-True-True-False] 63.6010μs 32.7377μs 30.5458 KOps/s 30.4657 KOps/s $\color{#35bf28}+0.26\%$
test_step_mdp_speed[False-False-True-False-True] 66.6210μs 30.8006μs 32.4669 KOps/s 32.3758 KOps/s $\color{#35bf28}+0.28\%$
test_step_mdp_speed[False-False-True-False-False] 54.3210μs 18.9570μs 52.7511 KOps/s 51.4650 KOps/s $\color{#35bf28}+2.50\%$
test_step_mdp_speed[False-False-False-True-True] 84.6710μs 51.1231μs 19.5606 KOps/s 19.6497 KOps/s $\color{#d91a1a}-0.45\%$
test_step_mdp_speed[False-False-False-True-False] 86.2220μs 34.7886μs 28.7451 KOps/s 28.8633 KOps/s $\color{#d91a1a}-0.41\%$
test_step_mdp_speed[False-False-False-False-True] 74.4110μs 32.3759μs 30.8872 KOps/s 31.6349 KOps/s $\color{#d91a1a}-2.36\%$
test_step_mdp_speed[False-False-False-False-False] 52.8910μs 21.4195μs 46.6863 KOps/s 47.6580 KOps/s $\color{#d91a1a}-2.04\%$
test_values[generalized_advantage_estimate-True-True] 25.4511ms 25.0849ms 39.8647 Ops/s 39.8364 Ops/s $\color{#35bf28}+0.07\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1040s 2.9814ms 335.4160 Ops/s 335.1185 Ops/s $\color{#35bf28}+0.09\%$
test_values[td0_return_estimate-False-False] 0.1060ms 80.0197μs 12.4969 KOps/s 12.1104 KOps/s $\color{#35bf28}+3.19\%$
test_values[td1_return_estimate-False-False] 56.4730ms 55.8288ms 17.9119 Ops/s 17.9084 Ops/s $\color{#35bf28}+0.02\%$
test_values[vec_td1_return_estimate-False-False] 1.3513ms 1.0917ms 915.9874 Ops/s 911.5434 Ops/s $\color{#35bf28}+0.49\%$
test_values[td_lambda_return_estimate-True-False] 89.2727ms 88.9249ms 11.2454 Ops/s 11.1703 Ops/s $\color{#35bf28}+0.67\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.3918ms 1.0895ms 917.8503 Ops/s 912.5527 Ops/s $\color{#35bf28}+0.58\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.3148ms 24.9010ms 40.1591 Ops/s 39.9334 Ops/s $\color{#35bf28}+0.57\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0377ms 0.7577ms 1.3198 KOps/s 1.3103 KOps/s $\color{#35bf28}+0.73\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7538ms 0.6740ms 1.4837 KOps/s 1.4711 KOps/s $\color{#35bf28}+0.86\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5907ms 1.4887ms 671.7243 Ops/s 669.7349 Ops/s $\color{#35bf28}+0.30\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7341ms 0.6901ms 1.4491 KOps/s 1.4397 KOps/s $\color{#35bf28}+0.65\%$
test_dqn_speed[False-None] 6.9941ms 1.5737ms 635.4565 Ops/s 656.7424 Ops/s $\color{#d91a1a}-3.24\%$
test_dqn_speed[False-backward] 2.3236ms 2.1915ms 456.3013 Ops/s 466.0633 Ops/s $\color{#d91a1a}-2.09\%$
test_dqn_speed[True-None] 0.9768ms 0.5599ms 1.7860 KOps/s 1.7601 KOps/s $\color{#35bf28}+1.47\%$
test_dqn_speed[True-backward] 1.2828ms 1.2423ms 804.9877 Ops/s 877.1846 Ops/s $\textbf{\color{#d91a1a}-8.23\%}$
test_dqn_speed[reduce-overhead-None] 0.7537ms 0.6079ms 1.6450 KOps/s 1.7268 KOps/s $\color{#d91a1a}-4.73\%$
test_dqn_speed[reduce-overhead-backward] 1.1611ms 1.1026ms 906.9478 Ops/s 980.7935 Ops/s $\textbf{\color{#d91a1a}-7.53\%}$
test_ddpg_speed[False-None] 3.2059ms 2.9901ms 334.4421 Ops/s 344.3895 Ops/s $\color{#d91a1a}-2.89\%$
test_ddpg_speed[False-backward] 4.7314ms 4.3685ms 228.9121 Ops/s 242.2268 Ops/s $\textbf{\color{#d91a1a}-5.50\%}$
test_ddpg_speed[True-None] 5.8884ms 1.3567ms 737.0813 Ops/s 735.4445 Ops/s $\color{#35bf28}+0.22\%$
test_ddpg_speed[True-backward] 2.5074ms 2.4659ms 405.5322 Ops/s 403.8041 Ops/s $\color{#35bf28}+0.43\%$
test_ddpg_speed[reduce-overhead-None] 1.4674ms 1.3707ms 729.5677 Ops/s 722.8386 Ops/s $\color{#35bf28}+0.93\%$
test_ddpg_speed[reduce-overhead-backward] 1.9803ms 1.9130ms 522.7331 Ops/s 516.0974 Ops/s $\color{#35bf28}+1.29\%$
test_sac_speed[False-None] 9.5773ms 8.2335ms 121.4555 Ops/s 123.7728 Ops/s $\color{#d91a1a}-1.87\%$
test_sac_speed[False-backward] 11.5904ms 11.1436ms 89.7374 Ops/s 91.0022 Ops/s $\color{#d91a1a}-1.39\%$
test_sac_speed[True-None] 1.9452ms 1.8591ms 537.8908 Ops/s 532.3837 Ops/s $\color{#35bf28}+1.03\%$
test_sac_speed[True-backward] 4.0631ms 3.6271ms 275.7025 Ops/s 271.8702 Ops/s $\color{#35bf28}+1.41\%$
test_sac_speed[reduce-overhead-None] 18.0564ms 11.0376ms 90.5997 Ops/s 89.9479 Ops/s $\color{#35bf28}+0.72\%$
test_sac_speed[reduce-overhead-backward] 1.6753ms 1.6242ms 615.6785 Ops/s 594.2698 Ops/s $\color{#35bf28}+3.60\%$
test_redq_speed[False-None] 8.0606ms 7.6476ms 130.7604 Ops/s 131.8548 Ops/s $\color{#d91a1a}-0.83\%$
test_redq_speed[False-backward] 11.9161ms 11.4681ms 87.1981 Ops/s 86.8428 Ops/s $\color{#35bf28}+0.41\%$
test_redq_speed[True-None] 2.5424ms 2.3669ms 422.4850 Ops/s 419.8292 Ops/s $\color{#35bf28}+0.63\%$
test_redq_speed[True-backward] 4.3334ms 4.2536ms 235.0932 Ops/s 231.5144 Ops/s $\color{#35bf28}+1.55\%$
test_redq_speed[reduce-overhead-None] 2.6110ms 2.4078ms 415.3244 Ops/s 415.0139 Ops/s $\color{#35bf28}+0.07\%$
test_redq_speed[reduce-overhead-backward] 4.4443ms 4.2937ms 232.8985 Ops/s 231.6849 Ops/s $\color{#35bf28}+0.52\%$
test_redq_deprec_speed[False-None] 9.9884ms 9.3809ms 106.5992 Ops/s 110.8909 Ops/s $\color{#d91a1a}-3.87\%$
test_redq_deprec_speed[False-backward] 13.2993ms 12.5361ms 79.7699 Ops/s 81.4816 Ops/s $\color{#d91a1a}-2.10\%$
test_redq_deprec_speed[True-None] 2.7622ms 2.6676ms 374.8698 Ops/s 371.7975 Ops/s $\color{#35bf28}+0.83\%$
test_redq_deprec_speed[True-backward] 4.6102ms 4.5515ms 219.7065 Ops/s 218.0513 Ops/s $\color{#35bf28}+0.76\%$
test_redq_deprec_speed[reduce-overhead-None] 2.7417ms 2.6741ms 373.9552 Ops/s 371.4519 Ops/s $\color{#35bf28}+0.67\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.5914ms 4.5364ms 220.4412 Ops/s 215.5581 Ops/s $\color{#35bf28}+2.27\%$
test_td3_speed[False-None] 8.3705ms 8.1427ms 122.8094 Ops/s 124.9099 Ops/s $\color{#d91a1a}-1.68\%$
test_td3_speed[False-backward] 11.2324ms 10.7034ms 93.4281 Ops/s 94.8952 Ops/s $\color{#d91a1a}-1.55\%$
test_td3_speed[True-None] 1.7408ms 1.6772ms 596.2393 Ops/s 559.9207 Ops/s $\textbf{\color{#35bf28}+6.49\%}$
test_td3_speed[True-backward] 3.5016ms 3.3812ms 295.7529 Ops/s 307.7190 Ops/s $\color{#d91a1a}-3.89\%$
test_td3_speed[reduce-overhead-None] 69.7641ms 27.5987ms 36.2335 Ops/s 36.2409 Ops/s $\color{#d91a1a}-0.02\%$
test_td3_speed[reduce-overhead-backward] 1.5755ms 1.4986ms 667.2751 Ops/s 718.9938 Ops/s $\textbf{\color{#d91a1a}-7.19\%}$
test_cql_speed[False-None] 17.9880ms 17.1749ms 58.2244 Ops/s 59.1563 Ops/s $\color{#d91a1a}-1.58\%$
test_cql_speed[False-backward] 23.1342ms 22.6698ms 44.1115 Ops/s 45.3561 Ops/s $\color{#d91a1a}-2.74\%$
test_cql_speed[True-None] 3.6520ms 3.3777ms 296.0629 Ops/s 298.3873 Ops/s $\color{#d91a1a}-0.78\%$
test_cql_speed[True-backward] 5.9047ms 5.5956ms 178.7105 Ops/s 172.8701 Ops/s $\color{#35bf28}+3.38\%$
test_cql_speed[reduce-overhead-None] 19.4423ms 13.2379ms 75.5404 Ops/s 74.9969 Ops/s $\color{#35bf28}+0.72\%$
test_cql_speed[reduce-overhead-backward] 2.1626ms 2.0165ms 495.9145 Ops/s 488.0936 Ops/s $\color{#35bf28}+1.60\%$
test_a2c_speed[False-None] 3.3825ms 3.2752ms 305.3241 Ops/s 305.9197 Ops/s $\color{#d91a1a}-0.19\%$
test_a2c_speed[False-backward] 7.3385ms 6.5009ms 153.8238 Ops/s 155.0008 Ops/s $\color{#d91a1a}-0.76\%$
test_a2c_speed[True-None] 1.7532ms 1.3711ms 729.3654 Ops/s 727.8100 Ops/s $\color{#35bf28}+0.21\%$
test_a2c_speed[True-backward] 3.1670ms 3.1040ms 322.1664 Ops/s 320.0632 Ops/s $\color{#35bf28}+0.66\%$
test_a2c_speed[reduce-overhead-None] 14.5812ms 8.5250ms 117.3017 Ops/s 117.8082 Ops/s $\color{#d91a1a}-0.43\%$
test_a2c_speed[reduce-overhead-backward] 2.0745ms 1.6470ms 607.1528 Ops/s 608.2914 Ops/s $\color{#d91a1a}-0.19\%$
test_ppo_speed[False-None] 3.9420ms 3.8020ms 263.0167 Ops/s 268.7566 Ops/s $\color{#d91a1a}-2.14\%$
test_ppo_speed[False-backward] 7.5751ms 7.1546ms 139.7703 Ops/s 141.3672 Ops/s $\color{#d91a1a}-1.13\%$
test_ppo_speed[True-None] 1.6703ms 1.4422ms 693.3850 Ops/s 693.0646 Ops/s $\color{#35bf28}+0.05\%$
test_ppo_speed[True-backward] 3.1451ms 3.1005ms 322.5270 Ops/s 301.9483 Ops/s $\textbf{\color{#35bf28}+6.82\%}$
test_ppo_speed[reduce-overhead-None] 1.0470ms 0.9744ms 1.0263 KOps/s 1.0252 KOps/s $\color{#35bf28}+0.10\%$
test_ppo_speed[reduce-overhead-backward] 1.5187ms 1.4231ms 702.7124 Ops/s 609.7117 Ops/s $\textbf{\color{#35bf28}+15.25\%}$
test_reinforce_speed[False-None] 2.4428ms 2.3287ms 429.4159 Ops/s 435.9824 Ops/s $\color{#d91a1a}-1.51\%$
test_reinforce_speed[False-backward] 3.7901ms 3.3573ms 297.8578 Ops/s 291.6234 Ops/s $\color{#35bf28}+2.14\%$
test_reinforce_speed[True-None] 1.3922ms 1.3105ms 763.0690 Ops/s 750.8565 Ops/s $\color{#35bf28}+1.63\%$
test_reinforce_speed[True-backward] 3.0315ms 2.9794ms 335.6399 Ops/s 321.4706 Ops/s $\color{#35bf28}+4.41\%$
test_reinforce_speed[reduce-overhead-None] 16.4874ms 9.4736ms 105.5569 Ops/s 106.9110 Ops/s $\color{#d91a1a}-1.27\%$
test_reinforce_speed[reduce-overhead-backward] 1.5631ms 1.5085ms 662.9181 Ops/s 591.6058 Ops/s $\textbf{\color{#35bf28}+12.05\%}$
test_iql_speed[False-None] 9.8002ms 9.3870ms 106.5299 Ops/s 106.8198 Ops/s $\color{#d91a1a}-0.27\%$
test_iql_speed[False-backward] 13.5117ms 13.0187ms 76.8125 Ops/s 76.0953 Ops/s $\color{#35bf28}+0.94\%$
test_iql_speed[True-None] 2.3393ms 2.2492ms 444.5980 Ops/s 420.0493 Ops/s $\textbf{\color{#35bf28}+5.84\%}$
test_iql_speed[True-backward] 5.3048ms 4.8441ms 206.4367 Ops/s 200.4050 Ops/s $\color{#35bf28}+3.01\%$
test_iql_speed[reduce-overhead-None] 0.4702s 12.8748ms 77.6708 Ops/s 94.7112 Ops/s $\textbf{\color{#d91a1a}-17.99\%}$
test_iql_speed[reduce-overhead-backward] 1.9741ms 1.9147ms 522.2624 Ops/s 498.0880 Ops/s $\color{#35bf28}+4.85\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.9711ms 6.2941ms 158.8792 Ops/s 155.3025 Ops/s $\color{#35bf28}+2.30\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6294ms 0.3813ms 2.6227 KOps/s 2.7625 KOps/s $\textbf{\color{#d91a1a}-5.06\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5842ms 0.3626ms 2.7579 KOps/s 2.9417 KOps/s $\textbf{\color{#d91a1a}-6.25\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3219ms 6.1096ms 163.6780 Ops/s 164.8633 Ops/s $\color{#d91a1a}-0.72\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.0187ms 0.3052ms 3.2770 KOps/s 3.8088 KOps/s $\textbf{\color{#d91a1a}-13.96\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5505ms 0.3122ms 3.2035 KOps/s 3.6148 KOps/s $\textbf{\color{#d91a1a}-11.38\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6035ms 1.3111ms 762.7072 Ops/s 781.2827 Ops/s $\color{#d91a1a}-2.38\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4719ms 1.2131ms 824.3363 Ops/s 842.2940 Ops/s $\color{#d91a1a}-2.13\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.3705ms 6.2331ms 160.4344 Ops/s 158.1682 Ops/s $\color{#35bf28}+1.43\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1795ms 0.4990ms 2.0040 KOps/s 2.0187 KOps/s $\color{#d91a1a}-0.73\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7918ms 0.3953ms 2.5298 KOps/s 2.5708 KOps/s $\color{#d91a1a}-1.60\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.2436ms 6.0746ms 164.6207 Ops/s 162.6386 Ops/s $\color{#35bf28}+1.22\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.1171ms 0.3386ms 2.9536 KOps/s 2.8858 KOps/s $\color{#35bf28}+2.35\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5413ms 0.3134ms 3.1907 KOps/s 4.0653 KOps/s $\textbf{\color{#d91a1a}-21.51\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.2541ms 6.0214ms 166.0743 Ops/s 163.6232 Ops/s $\color{#35bf28}+1.50\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.0698ms 0.3041ms 3.2880 KOps/s 3.0520 KOps/s $\textbf{\color{#35bf28}+7.73\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5444ms 0.2969ms 3.3678 KOps/s 3.2163 KOps/s $\color{#35bf28}+4.71\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4316ms 6.2591ms 159.7680 Ops/s 158.9046 Ops/s $\color{#35bf28}+0.54\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.7556ms 0.4344ms 2.3020 KOps/s 2.4150 KOps/s $\color{#d91a1a}-4.68\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6302ms 0.4149ms 2.4103 KOps/s 2.5573 KOps/s $\textbf{\color{#d91a1a}-5.75\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 7.0843ms 5.5386ms 180.5509 Ops/s 178.3612 Ops/s $\color{#35bf28}+1.23\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 9.2211ms 2.0814ms 480.4453 Ops/s 431.0051 Ops/s $\textbf{\color{#35bf28}+11.47\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.0204ms 1.2155ms 822.7314 Ops/s 782.6606 Ops/s $\textbf{\color{#35bf28}+5.12\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4519s 14.5677ms 68.6452 Ops/s 177.8629 Ops/s $\textbf{\color{#d91a1a}-61.41\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 10.2243ms 2.0873ms 479.0985 Ops/s 445.3595 Ops/s $\textbf{\color{#35bf28}+7.58\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 3.3869ms 1.1610ms 861.3395 Ops/s 824.6852 Ops/s $\color{#35bf28}+4.44\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 10.0644ms 5.7963ms 172.5244 Ops/s 31.4731 Ops/s $\textbf{\color{#35bf28}+448.16\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 6.5640ms 2.2144ms 451.5988 Ops/s 449.7282 Ops/s $\color{#35bf28}+0.42\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 9.0633ms 1.4237ms 702.4131 Ops/s 714.9391 Ops/s $\color{#d91a1a}-1.75\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 13.3690ms 13.1766ms 75.8919 Ops/s 71.4014 Ops/s $\textbf{\color{#35bf28}+6.29\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 18.4577ms 16.5683ms 60.3562 Ops/s 56.9360 Ops/s $\textbf{\color{#35bf28}+6.01\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.0183ms 17.8569ms 56.0008 Ops/s 53.4957 Ops/s $\color{#35bf28}+4.68\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 18.8226ms 16.9889ms 58.8620 Ops/s 56.5897 Ops/s $\color{#35bf28}+4.02\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 18.2236ms 17.8830ms 55.9191 Ops/s 53.3614 Ops/s $\color{#35bf28}+4.79\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 19.6152ms 18.4420ms 54.2240 Ops/s 51.5860 Ops/s $\textbf{\color{#35bf28}+5.11\%}$

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.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants