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

[BugFix] Fix typing for python 3.9 #2631

Merged
merged 1 commit into from
Dec 4, 2024
Merged

[BugFix] Fix typing for python 3.9 #2631

merged 1 commit into from
Dec 4, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Dec 4, 2024 •
edited
Loading

Stack from ghstack (oldest at bottom):

@vmoens
Update
84e9fa7 
[ghstack-poisoned]
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Dec 4, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2631

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

✅ You can merge normally! (11 Unrelated Failures)

As of commit 84e9fa7 with merge base 594462d (image):

FLAKY - The following job failed but was likely due to flakiness present on trunk:

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

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

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

vmoens added a commit that referenced this pull request Dec 4, 2024
@vmoens
[BugFix] Fix typing for python 3.9
64d6ce6 
ghstack-source-id: 663da84096214611804a726e2d38d27a6f21c958
Pull Request resolved: #2631
@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 Dec 4, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Dec 4, 2024

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}12$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4459s 0.4430s 2.2574 Ops/s 2.1442 Ops/s $\textbf{\color{#35bf28}+5.28\%}$
test_transformed 0.6333s 0.6278s 1.5928 Ops/s 1.5844 Ops/s $\color{#35bf28}+0.53\%$
test_serial 1.3813s 1.3778s 0.7258 Ops/s 0.7252 Ops/s $\color{#35bf28}+0.08\%$
test_parallel 1.4146s 1.3184s 0.7585 Ops/s 0.7505 Ops/s $\color{#35bf28}+1.06\%$
test_step_mdp_speed[True-True-True-True-True] 0.2108ms 30.0747μs 33.2506 KOps/s 33.6537 KOps/s $\color{#d91a1a}-1.20\%$
test_step_mdp_speed[True-True-True-True-False] 42.6500μs 17.5770μs 56.8925 KOps/s 56.9211 KOps/s $\color{#d91a1a}-0.05\%$
test_step_mdp_speed[True-True-True-False-True] 91.9720μs 16.9802μs 58.8920 KOps/s 58.8936 KOps/s $-0.00\%$
test_step_mdp_speed[True-True-True-False-False] 33.1620μs 9.9356μs 100.6484 KOps/s 100.6305 KOps/s $\color{#35bf28}+0.02\%$
test_step_mdp_speed[True-True-False-True-True] 77.1440μs 31.6860μs 31.5597 KOps/s 30.9921 KOps/s $\color{#35bf28}+1.83\%$
test_step_mdp_speed[True-True-False-True-False] 46.5370μs 19.4479μs 51.4196 KOps/s 51.2416 KOps/s $\color{#35bf28}+0.35\%$
test_step_mdp_speed[True-True-False-False-True] 63.1480μs 18.7060μs 53.4587 KOps/s 53.3225 KOps/s $\color{#35bf28}+0.26\%$
test_step_mdp_speed[True-True-False-False-False] 40.9560μs 11.8115μs 84.6631 KOps/s 84.9026 KOps/s $\color{#d91a1a}-0.28\%$
test_step_mdp_speed[True-False-True-True-True] 80.3590μs 34.1978μs 29.2416 KOps/s 29.6233 KOps/s $\color{#d91a1a}-1.29\%$
test_step_mdp_speed[True-False-True-True-False] 0.6342ms 21.4867μs 46.5404 KOps/s 47.0355 KOps/s $\color{#d91a1a}-1.05\%$
test_step_mdp_speed[True-False-True-False-True] 54.7730μs 18.5216μs 53.9910 KOps/s 53.1701 KOps/s $\color{#35bf28}+1.54\%$
test_step_mdp_speed[True-False-True-False-False] 61.2050μs 11.7358μs 85.2090 KOps/s 83.8918 KOps/s $\color{#35bf28}+1.57\%$
test_step_mdp_speed[True-False-False-True-True] 67.9070μs 34.6909μs 28.8260 KOps/s 27.9864 KOps/s $\color{#35bf28}+3.00\%$
test_step_mdp_speed[True-False-False-True-False] 50.2840μs 22.9111μs 43.6469 KOps/s 43.3438 KOps/s $\color{#35bf28}+0.70\%$
test_step_mdp_speed[True-False-False-False-True] 54.9030μs 20.2749μs 49.3220 KOps/s 48.6794 KOps/s $\color{#35bf28}+1.32\%$
test_step_mdp_speed[True-False-False-False-False] 44.8640μs 13.4630μs 74.2775 KOps/s 73.4108 KOps/s $\color{#35bf28}+1.18\%$
test_step_mdp_speed[False-True-True-True-True] 77.7250μs 33.4739μs 29.8740 KOps/s 29.4068 KOps/s $\color{#35bf28}+1.59\%$
test_step_mdp_speed[False-True-True-True-False] 52.6380μs 21.1173μs 47.3546 KOps/s 47.1428 KOps/s $\color{#35bf28}+0.45\%$
test_step_mdp_speed[False-True-True-False-True] 49.3020μs 21.0195μs 47.5748 KOps/s 46.2609 KOps/s $\color{#35bf28}+2.84\%$
test_step_mdp_speed[False-True-True-False-False] 41.8880μs 13.0510μs 76.6227 KOps/s 75.6632 KOps/s $\color{#35bf28}+1.27\%$
test_step_mdp_speed[False-True-False-True-True] 75.5510μs 35.5717μs 28.1122 KOps/s 28.2086 KOps/s $\color{#d91a1a}-0.34\%$
test_step_mdp_speed[False-True-False-True-False] 62.7070μs 22.9491μs 43.5746 KOps/s 43.6619 KOps/s $\color{#d91a1a}-0.20\%$
test_step_mdp_speed[False-True-False-False-True] 2.5518ms 22.5228μs 44.3995 KOps/s 43.5854 KOps/s $\color{#35bf28}+1.87\%$
test_step_mdp_speed[False-True-False-False-False] 45.9850μs 14.5751μs 68.6102 KOps/s 67.5384 KOps/s $\color{#35bf28}+1.59\%$
test_step_mdp_speed[False-False-True-True-True] 91.1890μs 36.9371μs 27.0731 KOps/s 26.7554 KOps/s $\color{#35bf28}+1.19\%$
test_step_mdp_speed[False-False-True-True-False] 59.2000μs 24.7313μs 40.4346 KOps/s 40.2845 KOps/s $\color{#35bf28}+0.37\%$
test_step_mdp_speed[False-False-True-False-True] 60.8830μs 22.6676μs 44.1157 KOps/s 43.2847 KOps/s $\color{#35bf28}+1.92\%$
test_step_mdp_speed[False-False-True-False-False] 45.5540μs 14.7104μs 67.9793 KOps/s 67.3057 KOps/s $\color{#35bf28}+1.00\%$
test_step_mdp_speed[False-False-False-True-True] 0.6300ms 38.5209μs 25.9599 KOps/s 25.8236 KOps/s $\color{#35bf28}+0.53\%$
test_step_mdp_speed[False-False-False-True-False] 54.2310μs 26.4752μs 37.7712 KOps/s 37.9231 KOps/s $\color{#d91a1a}-0.40\%$
test_step_mdp_speed[False-False-False-False-True] 55.8340μs 23.9696μs 41.7194 KOps/s 41.2502 KOps/s $\color{#35bf28}+1.14\%$
test_step_mdp_speed[False-False-False-False-False] 51.0550μs 16.1342μs 61.9802 KOps/s 60.4510 KOps/s $\color{#35bf28}+2.53\%$
test_values[generalized_advantage_estimate-True-True] 10.4621ms 9.7137ms 102.9472 Ops/s 83.1700 Ops/s $\textbf{\color{#35bf28}+23.78\%}$
test_values[vec_generalized_advantage_estimate-True-True] 38.5031ms 33.5895ms 29.7712 Ops/s 29.2683 Ops/s $\color{#35bf28}+1.72\%$
test_values[td0_return_estimate-False-False] 0.2563ms 0.2040ms 4.9013 KOps/s 5.2265 KOps/s $\textbf{\color{#d91a1a}-6.22\%}$
test_values[td1_return_estimate-False-False] 27.4310ms 24.4591ms 40.8845 Ops/s 41.2769 Ops/s $\color{#d91a1a}-0.95\%$
test_values[vec_td1_return_estimate-False-False] 36.2383ms 33.6365ms 29.7296 Ops/s 29.7388 Ops/s $\color{#d91a1a}-0.03\%$
test_values[td_lambda_return_estimate-True-False] 35.3335ms 34.7306ms 28.7931 Ops/s 28.5723 Ops/s $\color{#35bf28}+0.77\%$
test_values[vec_td_lambda_return_estimate-True-False] 35.3524ms 33.6051ms 29.7574 Ops/s 29.7637 Ops/s $\color{#d91a1a}-0.02\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 11.6907ms 8.3934ms 119.1415 Ops/s 119.9393 Ops/s $\color{#d91a1a}-0.67\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.1396ms 1.8285ms 546.9094 Ops/s 521.7760 Ops/s $\color{#35bf28}+4.82\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4937ms 0.3649ms 2.7408 KOps/s 2.7037 KOps/s $\color{#35bf28}+1.37\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 41.2309ms 40.1613ms 24.8996 Ops/s 21.8095 Ops/s $\textbf{\color{#35bf28}+14.17\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.0096ms 3.0563ms 327.1944 Ops/s 322.5982 Ops/s $\color{#35bf28}+1.42\%$
test_dqn_speed[False-None] 1.9563ms 1.3899ms 719.4845 Ops/s 694.5764 Ops/s $\color{#35bf28}+3.59\%$
test_dqn_speed[False-backward] 2.1851ms 1.8792ms 532.1540 Ops/s 434.1287 Ops/s $\textbf{\color{#35bf28}+22.58\%}$
test_dqn_speed[True-None] 0.7130ms 0.4667ms 2.1427 KOps/s 2.1113 KOps/s $\color{#35bf28}+1.49\%$
test_dqn_speed[True-backward] 1.2337ms 0.9564ms 1.0456 KOps/s 877.2959 Ops/s $\textbf{\color{#35bf28}+19.18\%}$
test_dqn_speed[reduce-overhead-None] 1.8018ms 0.4723ms 2.1175 KOps/s 2.1487 KOps/s $\color{#d91a1a}-1.45\%$
test_dqn_speed[reduce-overhead-backward] 0.9953ms 0.8918ms 1.1213 KOps/s 1.1107 KOps/s $\color{#35bf28}+0.96\%$
test_ddpg_speed[False-None] 3.6950ms 2.8883ms 346.2255 Ops/s 341.7323 Ops/s $\color{#35bf28}+1.31\%$
test_ddpg_speed[False-backward] 4.3907ms 4.0809ms 245.0436 Ops/s 243.7819 Ops/s $\color{#35bf28}+0.52\%$
test_ddpg_speed[True-None] 1.5914ms 1.0056ms 994.4000 Ops/s 992.0276 Ops/s $\color{#35bf28}+0.24\%$
test_ddpg_speed[True-backward] 2.3401ms 1.9527ms 512.1050 Ops/s 521.7272 Ops/s $\color{#d91a1a}-1.84\%$
test_ddpg_speed[reduce-overhead-None] 1.2381ms 1.0088ms 991.2750 Ops/s 980.1838 Ops/s $\color{#35bf28}+1.13\%$
test_ddpg_speed[reduce-overhead-backward] 2.0005ms 1.9087ms 523.9186 Ops/s 509.8984 Ops/s $\color{#35bf28}+2.75\%$
test_sac_speed[False-None] 9.2010ms 8.1244ms 123.0861 Ops/s 114.4433 Ops/s $\textbf{\color{#35bf28}+7.55\%}$
test_sac_speed[False-backward] 12.3592ms 11.2783ms 88.6659 Ops/s 85.5619 Ops/s $\color{#35bf28}+3.63\%$
test_sac_speed[True-None] 2.3910ms 1.8342ms 545.1849 Ops/s 542.0845 Ops/s $\color{#35bf28}+0.57\%$
test_sac_speed[True-backward] 3.6505ms 3.5365ms 282.7618 Ops/s 285.0123 Ops/s $\color{#d91a1a}-0.79\%$
test_sac_speed[reduce-overhead-None] 2.1409ms 1.8415ms 543.0295 Ops/s 540.6669 Ops/s $\color{#35bf28}+0.44\%$
test_sac_speed[reduce-overhead-backward] 4.2842ms 3.6083ms 277.1413 Ops/s 280.5075 Ops/s $\color{#d91a1a}-1.20\%$
test_redq_speed[False-None] 14.8587ms 12.9545ms 77.1935 Ops/s 74.0805 Ops/s $\color{#35bf28}+4.20\%$
test_redq_speed[False-backward] 24.0128ms 22.1893ms 45.0667 Ops/s 43.6918 Ops/s $\color{#35bf28}+3.15\%$
test_redq_speed[True-None] 5.4188ms 4.6965ms 212.9243 Ops/s 207.4529 Ops/s $\color{#35bf28}+2.64\%$
test_redq_speed[True-backward] 13.7915ms 12.6425ms 79.0985 Ops/s 80.5239 Ops/s $\color{#d91a1a}-1.77\%$
test_redq_speed[reduce-overhead-None] 5.7268ms 4.8929ms 204.3795 Ops/s 208.9711 Ops/s $\color{#d91a1a}-2.20\%$
test_redq_speed[reduce-overhead-backward] 12.9585ms 12.3090ms 81.2411 Ops/s 80.0010 Ops/s $\color{#35bf28}+1.55\%$
test_redq_deprec_speed[False-None] 14.8746ms 13.2925ms 75.2303 Ops/s 72.6901 Ops/s $\color{#35bf28}+3.49\%$
test_redq_deprec_speed[False-backward] 20.7574ms 19.1160ms 52.3121 Ops/s 50.0715 Ops/s $\color{#35bf28}+4.47\%$
test_redq_deprec_speed[True-None] 4.2051ms 3.6310ms 275.4070 Ops/s 268.1575 Ops/s $\color{#35bf28}+2.70\%$
test_redq_deprec_speed[True-backward] 10.0048ms 8.2421ms 121.3280 Ops/s 119.2078 Ops/s $\color{#35bf28}+1.78\%$
test_redq_deprec_speed[reduce-overhead-None] 4.3258ms 3.6243ms 275.9120 Ops/s 275.5309 Ops/s $\color{#35bf28}+0.14\%$
test_redq_deprec_speed[reduce-overhead-backward] 8.8332ms 8.1752ms 122.3215 Ops/s 120.9462 Ops/s $\color{#35bf28}+1.14\%$
test_td3_speed[False-None] 9.6871ms 8.1941ms 122.0385 Ops/s 118.5630 Ops/s $\color{#35bf28}+2.93\%$
test_td3_speed[False-backward] 11.5889ms 10.8740ms 91.9624 Ops/s 92.5457 Ops/s $\color{#d91a1a}-0.63\%$
test_td3_speed[True-None] 1.8883ms 1.7089ms 585.1746 Ops/s 577.7195 Ops/s $\color{#35bf28}+1.29\%$
test_td3_speed[True-backward] 3.8146ms 3.5220ms 283.9306 Ops/s 294.4631 Ops/s $\color{#d91a1a}-3.58\%$
test_td3_speed[reduce-overhead-None] 1.8892ms 1.7091ms 585.0901 Ops/s 567.7847 Ops/s $\color{#35bf28}+3.05\%$
test_td3_speed[reduce-overhead-backward] 4.3830ms 3.3897ms 295.0077 Ops/s 283.7792 Ops/s $\color{#35bf28}+3.96\%$
test_cql_speed[False-None] 36.7149ms 35.5917ms 28.0965 Ops/s 26.5894 Ops/s $\textbf{\color{#35bf28}+5.67\%}$
test_cql_speed[False-backward] 54.7869ms 46.3088ms 21.5942 Ops/s 20.9239 Ops/s $\color{#35bf28}+3.20\%$
test_cql_speed[True-None] 16.9475ms 15.9951ms 62.5193 Ops/s 63.3322 Ops/s $\color{#d91a1a}-1.28\%$
test_cql_speed[True-backward] 24.1756ms 22.8063ms 43.8476 Ops/s 43.8790 Ops/s $\color{#d91a1a}-0.07\%$
test_cql_speed[reduce-overhead-None] 16.5688ms 15.6672ms 63.8275 Ops/s 63.0615 Ops/s $\color{#35bf28}+1.21\%$
test_cql_speed[reduce-overhead-backward] 23.3510ms 22.5903ms 44.2668 Ops/s 44.1116 Ops/s $\color{#35bf28}+0.35\%$
test_a2c_speed[False-None] 7.8790ms 7.2724ms 137.5059 Ops/s 133.1535 Ops/s $\color{#35bf28}+3.27\%$
test_a2c_speed[False-backward] 15.4727ms 14.6082ms 68.4545 Ops/s 65.1553 Ops/s $\textbf{\color{#35bf28}+5.06\%}$
test_a2c_speed[True-None] 5.0531ms 4.3508ms 229.8427 Ops/s 234.3170 Ops/s $\color{#d91a1a}-1.91\%$
test_a2c_speed[True-backward] 11.4616ms 11.0927ms 90.1497 Ops/s 91.7548 Ops/s $\color{#d91a1a}-1.75\%$
test_a2c_speed[reduce-overhead-None] 4.9591ms 4.2933ms 232.9205 Ops/s 234.1601 Ops/s $\color{#d91a1a}-0.53\%$
test_a2c_speed[reduce-overhead-backward] 11.9922ms 10.9473ms 91.3469 Ops/s 88.4181 Ops/s $\color{#35bf28}+3.31\%$
test_ppo_speed[False-None] 8.8232ms 7.5621ms 132.2385 Ops/s 128.5860 Ops/s $\color{#35bf28}+2.84\%$
test_ppo_speed[False-backward] 15.5616ms 14.9177ms 67.0343 Ops/s 64.0915 Ops/s $\color{#35bf28}+4.59\%$
test_ppo_speed[True-None] 4.3455ms 3.7647ms 265.6239 Ops/s 268.0409 Ops/s $\color{#d91a1a}-0.90\%$
test_ppo_speed[True-backward] 10.3635ms 9.8632ms 101.3874 Ops/s 101.6899 Ops/s $\color{#d91a1a}-0.30\%$
test_ppo_speed[reduce-overhead-None] 4.7623ms 3.7562ms 266.2242 Ops/s 267.7488 Ops/s $\color{#d91a1a}-0.57\%$
test_ppo_speed[reduce-overhead-backward] 10.1362ms 9.7466ms 102.6000 Ops/s 103.2483 Ops/s $\color{#d91a1a}-0.63\%$
test_reinforce_speed[False-None] 7.0894ms 6.5161ms 153.4670 Ops/s 149.1968 Ops/s $\color{#35bf28}+2.86\%$
test_reinforce_speed[False-backward] 10.6522ms 9.8946ms 101.0648 Ops/s 98.1086 Ops/s $\color{#35bf28}+3.01\%$
test_reinforce_speed[True-None] 3.2089ms 2.6872ms 372.1299 Ops/s 368.0094 Ops/s $\color{#35bf28}+1.12\%$
test_reinforce_speed[True-backward] 9.3358ms 8.8699ms 112.7405 Ops/s 113.5100 Ops/s $\color{#d91a1a}-0.68\%$
test_reinforce_speed[reduce-overhead-None] 3.1359ms 2.6582ms 376.1992 Ops/s 364.8470 Ops/s $\color{#35bf28}+3.11\%$
test_reinforce_speed[reduce-overhead-backward] 9.4056ms 8.8076ms 113.5378 Ops/s 113.6884 Ops/s $\color{#d91a1a}-0.13\%$
test_iql_speed[False-None] 0.3056s 41.1634ms 24.2934 Ops/s 29.9120 Ops/s $\textbf{\color{#d91a1a}-18.78\%}$
test_iql_speed[False-backward] 46.5754ms 45.5595ms 21.9493 Ops/s 21.7070 Ops/s $\color{#35bf28}+1.12\%$
test_iql_speed[True-None] 11.1193ms 10.7767ms 92.7929 Ops/s 91.7155 Ops/s $\color{#35bf28}+1.17\%$
test_iql_speed[True-backward] 22.8439ms 21.8835ms 45.6966 Ops/s 44.1228 Ops/s $\color{#35bf28}+3.57\%$
test_iql_speed[reduce-overhead-None] 12.0832ms 10.8097ms 92.5094 Ops/s 92.0803 Ops/s $\color{#35bf28}+0.47\%$
test_iql_speed[reduce-overhead-backward] 29.3466ms 22.5945ms 44.2585 Ops/s 45.0019 Ops/s $\color{#d91a1a}-1.65\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.7713ms 5.0938ms 196.3187 Ops/s 188.5307 Ops/s $\color{#35bf28}+4.13\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1674ms 0.5304ms 1.8852 KOps/s 1.8932 KOps/s $\color{#d91a1a}-0.43\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.9276ms 0.4967ms 2.0134 KOps/s 2.0041 KOps/s $\color{#35bf28}+0.46\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.4518ms 4.9641ms 201.4465 Ops/s 198.1955 Ops/s $\color{#35bf28}+1.64\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8052ms 0.5012ms 1.9954 KOps/s 1.9011 KOps/s $\color{#35bf28}+4.96\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7656ms 0.4835ms 2.0683 KOps/s 2.0641 KOps/s $\color{#35bf28}+0.20\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.4726ms 1.6526ms 605.1077 Ops/s 596.5236 Ops/s $\color{#35bf28}+1.44\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.2157ms 1.5912ms 628.4405 Ops/s 620.7229 Ops/s $\color{#35bf28}+1.24\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.0886ms 5.0645ms 197.4546 Ops/s 192.2236 Ops/s $\color{#35bf28}+2.72\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.5062ms 0.6523ms 1.5331 KOps/s 1.5108 KOps/s $\color{#35bf28}+1.48\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.0081ms 0.6263ms 1.5967 KOps/s 1.5741 KOps/s $\color{#35bf28}+1.43\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.0912ms 4.9049ms 203.8772 Ops/s 197.3598 Ops/s $\color{#35bf28}+3.30\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.5628ms 0.5203ms 1.9219 KOps/s 1.8609 KOps/s $\color{#35bf28}+3.27\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.9063ms 0.5002ms 1.9992 KOps/s 1.9754 KOps/s $\color{#35bf28}+1.20\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.6310ms 4.9721ms 201.1237 Ops/s 201.2072 Ops/s $\color{#d91a1a}-0.04\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7891ms 0.5079ms 1.9691 KOps/s 1.9290 KOps/s $\color{#35bf28}+2.08\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 7.8831ms 0.4907ms 2.0377 KOps/s 2.0714 KOps/s $\color{#d91a1a}-1.63\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.2779ms 5.0352ms 198.6003 Ops/s 195.3349 Ops/s $\color{#35bf28}+1.67\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1993ms 0.6548ms 1.5273 KOps/s 1.4977 KOps/s $\color{#35bf28}+1.98\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8346ms 0.6275ms 1.5936 KOps/s 1.5805 KOps/s $\color{#35bf28}+0.83\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.4256s 12.6287ms 79.1846 Ops/s 247.7948 Ops/s $\textbf{\color{#d91a1a}-68.04\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 7.6875ms 2.3073ms 433.4006 Ops/s 437.8813 Ops/s $\color{#d91a1a}-1.02\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.6415ms 1.3759ms 726.8161 Ops/s 741.3224 Ops/s $\color{#d91a1a}-1.96\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 5.6953ms 4.2427ms 235.7014 Ops/s 34.6684 Ops/s $\textbf{\color{#35bf28}+579.87\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 6.6423ms 2.2751ms 439.5483 Ops/s 419.2708 Ops/s $\color{#35bf28}+4.84\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 4.6221ms 1.3038ms 767.0140 Ops/s 706.5901 Ops/s $\textbf{\color{#35bf28}+8.55\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.4051s 12.4119ms 80.5679 Ops/s 223.1484 Ops/s $\textbf{\color{#d91a1a}-63.89\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 10.6057ms 2.4504ms 408.0980 Ops/s 387.3460 Ops/s $\textbf{\color{#35bf28}+5.36\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 3.9900ms 1.4013ms 713.6193 Ops/s 658.9744 Ops/s $\textbf{\color{#35bf28}+8.29\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 11.7730ms 11.2529ms 88.8660 Ops/s 87.9330 Ops/s $\color{#35bf28}+1.06\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 16.4347ms 14.5244ms 68.8495 Ops/s 68.2222 Ops/s $\color{#35bf28}+0.92\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 21.5934ms 20.0093ms 49.9767 Ops/s 49.4365 Ops/s $\color{#35bf28}+1.09\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 15.6872ms 14.7394ms 67.8452 Ops/s 67.0998 Ops/s $\color{#35bf28}+1.11\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 20.4934ms 19.9070ms 50.2336 Ops/s 49.2075 Ops/s $\color{#35bf28}+2.09\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 20.1094ms 15.9600ms 62.6565 Ops/s 62.4205 Ops/s $\color{#35bf28}+0.38\%$

@github-actions GitHub Actions
Copy link

github-actions bot commented Dec 4, 2024

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}8$. Worsened: $\large\color{#d91a1a}12$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7634s 0.7627s 1.3111 Ops/s 1.2861 Ops/s $\color{#35bf28}+1.95\%$
test_transformed 1.1223s 1.0449s 0.9570 Ops/s 0.9888 Ops/s $\color{#d91a1a}-3.22\%$
test_serial 2.2863s 2.2111s 0.4523 Ops/s 0.4624 Ops/s $\color{#d91a1a}-2.18\%$
test_parallel 2.0513s 1.9760s 0.5061 Ops/s 0.4956 Ops/s $\color{#35bf28}+2.12\%$
test_step_mdp_speed[True-True-True-True-True] 0.1503ms 39.1130μs 25.5670 KOps/s 25.4340 KOps/s $\color{#35bf28}+0.52\%$
test_step_mdp_speed[True-True-True-True-False] 49.9300μs 23.1720μs 43.1555 KOps/s 43.8062 KOps/s $\color{#d91a1a}-1.49\%$
test_step_mdp_speed[True-True-True-False-True] 51.3000μs 22.4925μs 44.4593 KOps/s 46.8989 KOps/s $\textbf{\color{#d91a1a}-5.20\%}$
test_step_mdp_speed[True-True-True-False-False] 38.8810μs 12.5855μs 79.4566 KOps/s 78.1210 KOps/s $\color{#35bf28}+1.71\%$
test_step_mdp_speed[True-True-False-True-True] 72.1510μs 42.8846μs 23.3184 KOps/s 23.6095 KOps/s $\color{#d91a1a}-1.23\%$
test_step_mdp_speed[True-True-False-True-False] 54.0300μs 24.6854μs 40.5098 KOps/s 40.7123 KOps/s $\color{#d91a1a}-0.50\%$
test_step_mdp_speed[True-True-False-False-True] 85.2310μs 23.8416μs 41.9435 KOps/s 41.3375 KOps/s $\color{#35bf28}+1.47\%$
test_step_mdp_speed[True-True-False-False-False] 51.2310μs 14.6479μs 68.2693 KOps/s 67.4296 KOps/s $\color{#35bf28}+1.25\%$
test_step_mdp_speed[True-False-True-True-True] 76.5220μs 44.6213μs 22.4108 KOps/s 22.5958 KOps/s $\color{#d91a1a}-0.82\%$
test_step_mdp_speed[True-False-True-True-False] 55.7410μs 27.3096μs 36.6172 KOps/s 37.4897 KOps/s $\color{#d91a1a}-2.33\%$
test_step_mdp_speed[True-False-True-False-True] 50.8610μs 25.1387μs 39.7793 KOps/s 41.9438 KOps/s $\textbf{\color{#d91a1a}-5.16\%}$
test_step_mdp_speed[True-False-True-False-False] 40.0710μs 14.8501μs 67.3398 KOps/s 68.2468 KOps/s $\color{#d91a1a}-1.33\%$
test_step_mdp_speed[True-False-False-True-True] 77.4510μs 46.7215μs 21.4034 KOps/s 22.1316 KOps/s $\color{#d91a1a}-3.29\%$
test_step_mdp_speed[True-False-False-True-False] 64.0110μs 29.3340μs 34.0902 KOps/s 34.9179 KOps/s $\color{#d91a1a}-2.37\%$
test_step_mdp_speed[True-False-False-False-True] 61.5710μs 26.8051μs 37.3063 KOps/s 38.9338 KOps/s $\color{#d91a1a}-4.18\%$
test_step_mdp_speed[True-False-False-False-False] 46.1410μs 16.9556μs 58.9776 KOps/s 60.5038 KOps/s $\color{#d91a1a}-2.52\%$
test_step_mdp_speed[False-True-True-True-True] 78.8210μs 45.0621μs 22.1916 KOps/s 22.5542 KOps/s $\color{#d91a1a}-1.61\%$
test_step_mdp_speed[False-True-True-True-False] 54.8410μs 27.1473μs 36.8360 KOps/s 37.1433 KOps/s $\color{#d91a1a}-0.83\%$
test_step_mdp_speed[False-True-True-False-True] 54.2810μs 27.5529μs 36.2938 KOps/s 35.9905 KOps/s $\color{#35bf28}+0.84\%$
test_step_mdp_speed[False-True-True-False-False] 59.1310μs 16.9907μs 58.8556 KOps/s 61.4729 KOps/s $\color{#d91a1a}-4.26\%$
test_step_mdp_speed[False-True-False-True-True] 77.3110μs 47.5801μs 21.0172 KOps/s 21.7194 KOps/s $\color{#d91a1a}-3.23\%$
test_step_mdp_speed[False-True-False-True-False] 62.4710μs 29.4695μs 33.9334 KOps/s 34.7973 KOps/s $\color{#d91a1a}-2.48\%$
test_step_mdp_speed[False-True-False-False-True] 3.2196ms 30.8677μs 32.3964 KOps/s 34.1141 KOps/s $\textbf{\color{#d91a1a}-5.04\%}$
test_step_mdp_speed[False-True-False-False-False] 48.3510μs 19.2293μs 52.0041 KOps/s 54.2398 KOps/s $\color{#d91a1a}-4.12\%$
test_step_mdp_speed[False-False-True-True-True] 78.9610μs 50.2984μs 19.8814 KOps/s 20.6713 KOps/s $\color{#d91a1a}-3.82\%$
test_step_mdp_speed[False-False-True-True-False] 56.4300μs 31.6013μs 31.6443 KOps/s 32.2542 KOps/s $\color{#d91a1a}-1.89\%$
test_step_mdp_speed[False-False-True-False-True] 61.3500μs 30.3924μs 32.9030 KOps/s 35.4610 KOps/s $\textbf{\color{#d91a1a}-7.21\%}$
test_step_mdp_speed[False-False-True-False-False] 45.6410μs 18.8534μs 53.0409 KOps/s 55.0626 KOps/s $\color{#d91a1a}-3.67\%$
test_step_mdp_speed[False-False-False-True-True] 81.2210μs 50.8665μs 19.6593 KOps/s 19.9579 KOps/s $\color{#d91a1a}-1.50\%$
test_step_mdp_speed[False-False-False-True-False] 66.6510μs 33.8209μs 29.5675 KOps/s 30.8320 KOps/s $\color{#d91a1a}-4.10\%$
test_step_mdp_speed[False-False-False-False-True] 76.4910μs 31.8889μs 31.3589 KOps/s 32.8849 KOps/s $\color{#d91a1a}-4.64\%$
test_step_mdp_speed[False-False-False-False-False] 46.4110μs 20.7914μs 48.0967 KOps/s 49.4599 KOps/s $\color{#d91a1a}-2.76\%$
test_values[generalized_advantage_estimate-True-True] 25.8721ms 25.5181ms 39.1879 Ops/s 38.6149 Ops/s $\color{#35bf28}+1.48\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1056s 3.0173ms 331.4175 Ops/s 328.5359 Ops/s $\color{#35bf28}+0.88\%$
test_values[td0_return_estimate-False-False] 0.1071ms 82.3663μs 12.1409 KOps/s 12.0996 KOps/s $\color{#35bf28}+0.34\%$
test_values[td1_return_estimate-False-False] 58.2575ms 56.9127ms 17.5708 Ops/s 17.1232 Ops/s $\color{#35bf28}+2.61\%$
test_values[vec_td1_return_estimate-False-False] 1.3038ms 1.0952ms 913.0626 Ops/s 909.2530 Ops/s $\color{#35bf28}+0.42\%$
test_values[td_lambda_return_estimate-True-False] 90.3339ms 89.9123ms 11.1219 Ops/s 11.1173 Ops/s $\color{#35bf28}+0.04\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.2227ms 1.0891ms 918.2015 Ops/s 902.4727 Ops/s $\color{#35bf28}+1.74\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.7146ms 25.4001ms 39.3699 Ops/s 37.4732 Ops/s $\textbf{\color{#35bf28}+5.06\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0426ms 0.7720ms 1.2954 KOps/s 1.2954 KOps/s $-0.01\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7832ms 0.6828ms 1.4646 KOps/s 1.4634 KOps/s $\color{#35bf28}+0.08\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5306ms 1.4960ms 668.4438 Ops/s 667.3824 Ops/s $\color{#35bf28}+0.16\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7478ms 0.6982ms 1.4322 KOps/s 1.4173 KOps/s $\color{#35bf28}+1.05\%$
test_dqn_speed[False-None] 7.0733ms 1.5303ms 653.4728 Ops/s 657.4083 Ops/s $\color{#d91a1a}-0.60\%$
test_dqn_speed[False-backward] 2.2181ms 2.1408ms 467.1220 Ops/s 471.8956 Ops/s $\color{#d91a1a}-1.01\%$
test_dqn_speed[True-None] 0.6605ms 0.5449ms 1.8354 KOps/s 1.8239 KOps/s $\color{#35bf28}+0.63\%$
test_dqn_speed[True-backward] 1.2933ms 1.2253ms 816.1027 Ops/s 817.7681 Ops/s $\color{#d91a1a}-0.20\%$
test_dqn_speed[reduce-overhead-None] 0.6031ms 0.5586ms 1.7901 KOps/s 1.7896 KOps/s $\color{#35bf28}+0.03\%$
test_dqn_speed[reduce-overhead-backward] 1.2311ms 1.0854ms 921.2863 Ops/s 919.0982 Ops/s $\color{#35bf28}+0.24\%$
test_ddpg_speed[False-None] 3.1807ms 2.8537ms 350.4178 Ops/s 349.9300 Ops/s $\color{#35bf28}+0.14\%$
test_ddpg_speed[False-backward] 4.8482ms 4.3149ms 231.7551 Ops/s 237.2594 Ops/s $\color{#d91a1a}-2.32\%$
test_ddpg_speed[True-None] 1.1806ms 1.0942ms 913.8908 Ops/s 920.4818 Ops/s $\color{#d91a1a}-0.72\%$
test_ddpg_speed[True-backward] 2.4427ms 2.3457ms 426.3047 Ops/s 426.5892 Ops/s $\color{#d91a1a}-0.07\%$
test_ddpg_speed[reduce-overhead-None] 1.1843ms 1.1067ms 903.6036 Ops/s 859.1968 Ops/s $\textbf{\color{#35bf28}+5.17\%}$
test_ddpg_speed[reduce-overhead-backward] 1.8642ms 1.8022ms 554.8896 Ops/s 554.5761 Ops/s $\color{#35bf28}+0.06\%$
test_sac_speed[False-None] 8.6714ms 8.1274ms 123.0410 Ops/s 123.0341 Ops/s $+0.01\%$
test_sac_speed[False-backward] 12.1451ms 11.4889ms 87.0403 Ops/s 87.3258 Ops/s $\color{#d91a1a}-0.33\%$
test_sac_speed[True-None] 1.6842ms 1.5595ms 641.2450 Ops/s 644.4655 Ops/s $\color{#d91a1a}-0.50\%$
test_sac_speed[True-backward] 3.5181ms 3.4529ms 289.6139 Ops/s 289.8039 Ops/s $\color{#d91a1a}-0.07\%$
test_sac_speed[reduce-overhead-None] 23.1871ms 12.7240ms 78.5913 Ops/s 78.9650 Ops/s $\color{#d91a1a}-0.47\%$
test_sac_speed[reduce-overhead-backward] 1.6172ms 1.5238ms 656.2755 Ops/s 655.4005 Ops/s $\color{#35bf28}+0.13\%$
test_redq_speed[False-None] 8.5326ms 7.6341ms 130.9915 Ops/s 130.0724 Ops/s $\color{#35bf28}+0.71\%$
test_redq_speed[False-backward] 13.1312ms 11.9600ms 83.6118 Ops/s 83.6529 Ops/s $\color{#d91a1a}-0.05\%$
test_redq_speed[True-None] 2.0890ms 2.0051ms 498.7286 Ops/s 494.4675 Ops/s $\color{#35bf28}+0.86\%$
test_redq_speed[True-backward] 4.3499ms 3.9019ms 256.2883 Ops/s 255.2992 Ops/s $\color{#35bf28}+0.39\%$
test_redq_speed[reduce-overhead-None] 2.0978ms 2.0068ms 498.2987 Ops/s 496.9676 Ops/s $\color{#35bf28}+0.27\%$
test_redq_speed[reduce-overhead-backward] 3.9365ms 3.8523ms 259.5836 Ops/s 265.0092 Ops/s $\color{#d91a1a}-2.05\%$
test_redq_deprec_speed[False-None] 9.8218ms 9.1657ms 109.1025 Ops/s 108.9390 Ops/s $\color{#35bf28}+0.15\%$
test_redq_deprec_speed[False-backward] 13.2610ms 12.6143ms 79.2750 Ops/s 80.6511 Ops/s $\color{#d91a1a}-1.71\%$
test_redq_deprec_speed[True-None] 2.4433ms 2.3507ms 425.4129 Ops/s 427.0111 Ops/s $\color{#d91a1a}-0.37\%$
test_redq_deprec_speed[True-backward] 4.5980ms 4.2274ms 236.5502 Ops/s 239.1174 Ops/s $\color{#d91a1a}-1.07\%$
test_redq_deprec_speed[reduce-overhead-None] 2.4520ms 2.3398ms 427.3841 Ops/s 429.0032 Ops/s $\color{#d91a1a}-0.38\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.6405ms 4.2418ms 235.7487 Ops/s 238.1929 Ops/s $\color{#d91a1a}-1.03\%$
test_td3_speed[False-None] 8.0434ms 8.0078ms 124.8787 Ops/s 117.7291 Ops/s $\textbf{\color{#35bf28}+6.07\%}$
test_td3_speed[False-backward] 11.1184ms 10.6495ms 93.9009 Ops/s 93.6058 Ops/s $\color{#35bf28}+0.32\%$
test_td3_speed[True-None] 1.6235ms 1.5961ms 626.5456 Ops/s 632.4923 Ops/s $\color{#d91a1a}-0.94\%$
test_td3_speed[True-backward] 3.3942ms 3.3162ms 301.5538 Ops/s 300.7076 Ops/s $\color{#35bf28}+0.28\%$
test_td3_speed[reduce-overhead-None] 50.6853ms 25.8362ms 38.7054 Ops/s 36.8674 Ops/s $\color{#35bf28}+4.99\%$
test_td3_speed[reduce-overhead-backward] 1.4914ms 1.4552ms 687.1686 Ops/s 675.0541 Ops/s $\color{#35bf28}+1.79\%$
test_cql_speed[False-None] 17.0628ms 16.4422ms 60.8192 Ops/s 60.4972 Ops/s $\color{#35bf28}+0.53\%$
test_cql_speed[False-backward] 22.4531ms 22.0862ms 45.2772 Ops/s 44.8792 Ops/s $\color{#35bf28}+0.89\%$
test_cql_speed[True-None] 3.1670ms 2.9983ms 333.5210 Ops/s 340.4174 Ops/s $\color{#d91a1a}-2.03\%$
test_cql_speed[True-backward] 5.5810ms 5.1181ms 195.3831 Ops/s 188.4513 Ops/s $\color{#35bf28}+3.68\%$
test_cql_speed[reduce-overhead-None] 21.8417ms 13.2502ms 75.4707 Ops/s 75.4883 Ops/s $\color{#d91a1a}-0.02\%$
test_cql_speed[reduce-overhead-backward] 1.5588ms 1.5169ms 659.2404 Ops/s 649.8779 Ops/s $\color{#35bf28}+1.44\%$
test_a2c_speed[False-None] 3.3710ms 3.2213ms 310.4334 Ops/s 309.2041 Ops/s $\color{#35bf28}+0.40\%$
test_a2c_speed[False-backward] 6.9368ms 6.2870ms 159.0582 Ops/s 160.0853 Ops/s $\color{#d91a1a}-0.64\%$
test_a2c_speed[True-None] 1.0825ms 1.0037ms 996.3062 Ops/s 984.2558 Ops/s $\color{#35bf28}+1.22\%$
test_a2c_speed[True-backward] 2.7215ms 2.6633ms 375.4807 Ops/s 378.6575 Ops/s $\color{#d91a1a}-0.84\%$
test_a2c_speed[reduce-overhead-None] 0.3890s 12.3908ms 80.7053 Ops/s 85.4144 Ops/s $\textbf{\color{#d91a1a}-5.51\%}$
test_a2c_speed[reduce-overhead-backward] 1.0823ms 1.0137ms 986.5063 Ops/s 990.6452 Ops/s $\color{#d91a1a}-0.42\%$
test_ppo_speed[False-None] 3.9111ms 3.7049ms 269.9125 Ops/s 268.3887 Ops/s $\color{#35bf28}+0.57\%$
test_ppo_speed[False-backward] 7.3822ms 6.9688ms 143.4961 Ops/s 142.9111 Ops/s $\color{#35bf28}+0.41\%$
test_ppo_speed[True-None] 1.0318ms 0.9530ms 1.0493 KOps/s 1.0507 KOps/s $\color{#d91a1a}-0.14\%$
test_ppo_speed[True-backward] 2.7009ms 2.6085ms 383.3592 Ops/s 386.1179 Ops/s $\color{#d91a1a}-0.71\%$
test_ppo_speed[reduce-overhead-None] 0.5858ms 0.4977ms 2.0091 KOps/s 1.8538 KOps/s $\textbf{\color{#35bf28}+8.38\%}$
test_ppo_speed[reduce-overhead-backward] 1.0503ms 0.9900ms 1.0101 KOps/s 993.0008 Ops/s $\color{#35bf28}+1.72\%$
test_reinforce_speed[False-None] 2.3870ms 2.2627ms 441.9443 Ops/s 437.2200 Ops/s $\color{#35bf28}+1.08\%$
test_reinforce_speed[False-backward] 3.8519ms 3.3138ms 301.7666 Ops/s 302.5084 Ops/s $\color{#d91a1a}-0.25\%$
test_reinforce_speed[True-None] 0.9410ms 0.8605ms 1.1620 KOps/s 1.1883 KOps/s $\color{#d91a1a}-2.21\%$
test_reinforce_speed[True-backward] 2.5302ms 2.4591ms 406.6541 Ops/s 379.2452 Ops/s $\textbf{\color{#35bf28}+7.23\%}$
test_reinforce_speed[reduce-overhead-None] 22.7727ms 12.0215ms 83.1840 Ops/s 86.4121 Ops/s $\color{#d91a1a}-3.74\%$
test_reinforce_speed[reduce-overhead-backward] 1.1310ms 1.0760ms 929.3497 Ops/s 932.4125 Ops/s $\color{#d91a1a}-0.33\%$
test_iql_speed[False-None] 9.7180ms 9.3009ms 107.5160 Ops/s 107.3707 Ops/s $\color{#35bf28}+0.14\%$
test_iql_speed[False-backward] 13.8085ms 13.1970ms 75.7748 Ops/s 75.9621 Ops/s $\color{#d91a1a}-0.25\%$
test_iql_speed[True-None] 1.8916ms 1.7763ms 562.9623 Ops/s 570.7877 Ops/s $\color{#d91a1a}-1.37\%$
test_iql_speed[True-backward] 4.7966ms 4.4619ms 224.1218 Ops/s 223.6949 Ops/s $\color{#35bf28}+0.19\%$
test_iql_speed[reduce-overhead-None] 20.7227ms 11.6907ms 85.5378 Ops/s 108.1379 Ops/s $\textbf{\color{#d91a1a}-20.90\%}$
test_iql_speed[reduce-overhead-backward] 1.7048ms 1.6266ms 614.7916 Ops/s 694.4646 Ops/s $\textbf{\color{#d91a1a}-11.47\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.9385ms 6.4582ms 154.8425 Ops/s 152.6716 Ops/s $\color{#35bf28}+1.42\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5888ms 0.3342ms 2.9925 KOps/s 3.0105 KOps/s $\color{#d91a1a}-0.60\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6559ms 0.3459ms 2.8913 KOps/s 3.0021 KOps/s $\color{#d91a1a}-3.69\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.5999ms 6.2466ms 160.0871 Ops/s 158.3347 Ops/s $\color{#35bf28}+1.11\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.1735ms 0.3285ms 3.0438 KOps/s 3.1611 KOps/s $\color{#d91a1a}-3.71\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5815ms 0.3392ms 2.9483 KOps/s 3.3666 KOps/s $\textbf{\color{#d91a1a}-12.42\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.7814ms 1.5307ms 653.2932 Ops/s 672.1154 Ops/s $\color{#d91a1a}-2.80\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.6329ms 1.4819ms 674.8279 Ops/s 705.0280 Ops/s $\color{#d91a1a}-4.28\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5298ms 6.3943ms 156.3903 Ops/s 155.6841 Ops/s $\color{#35bf28}+0.45\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.8799ms 0.4645ms 2.1530 KOps/s 2.2375 KOps/s $\color{#d91a1a}-3.78\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7150ms 0.4986ms 2.0056 KOps/s 2.2285 KOps/s $\textbf{\color{#d91a1a}-10.00\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.3622ms 6.2286ms 160.5489 Ops/s 158.1957 Ops/s $\color{#35bf28}+1.49\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7211ms 0.3357ms 2.9784 KOps/s 3.4937 KOps/s $\textbf{\color{#d91a1a}-14.75\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5733ms 0.3040ms 3.2898 KOps/s 3.3755 KOps/s $\color{#d91a1a}-2.54\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.4415ms 6.1936ms 161.4583 Ops/s 159.9538 Ops/s $\color{#35bf28}+0.94\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8404ms 0.3367ms 2.9696 KOps/s 2.8711 KOps/s $\color{#35bf28}+3.43\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5008ms 0.2925ms 3.4188 KOps/s 3.4952 KOps/s $\color{#d91a1a}-2.19\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4978ms 6.3669ms 157.0633 Ops/s 155.6019 Ops/s $\color{#35bf28}+0.94\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.0076ms 0.4135ms 2.4182 KOps/s 2.3755 KOps/s $\color{#35bf28}+1.80\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7309ms 0.3912ms 2.5561 KOps/s 2.3144 KOps/s $\textbf{\color{#35bf28}+10.45\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 7.1109ms 5.3189ms 188.0096 Ops/s 189.6039 Ops/s $\color{#d91a1a}-0.84\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 9.8618ms 1.9407ms 515.2778 Ops/s 524.0225 Ops/s $\color{#d91a1a}-1.67\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.6332ms 1.2563ms 796.0101 Ops/s 847.7340 Ops/s $\textbf{\color{#d91a1a}-6.10\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4859s 14.9698ms 66.8012 Ops/s 190.5375 Ops/s $\textbf{\color{#d91a1a}-64.94\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 9.9495ms 2.0041ms 498.9749 Ops/s 437.8176 Ops/s $\textbf{\color{#35bf28}+13.97\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.1162ms 1.2290ms 813.6416 Ops/s 854.8390 Ops/s $\color{#d91a1a}-4.82\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 7.2672ms 5.5869ms 178.9914 Ops/s 33.3892 Ops/s $\textbf{\color{#35bf28}+436.08\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 10.1951ms 2.2180ms 450.8555 Ops/s 449.8908 Ops/s $\color{#35bf28}+0.21\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 3.6279ms 1.3233ms 755.6954 Ops/s 785.6749 Ops/s $\color{#d91a1a}-3.82\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 14.0934ms 13.5026ms 74.0597 Ops/s 74.2365 Ops/s $\color{#d91a1a}-0.24\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 18.7198ms 17.1301ms 58.3767 Ops/s 59.3830 Ops/s $\color{#d91a1a}-1.69\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.4191ms 17.8533ms 56.0122 Ops/s 53.8939 Ops/s $\color{#35bf28}+3.93\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 17.7880ms 17.2701ms 57.9036 Ops/s 58.5132 Ops/s $\color{#d91a1a}-1.04\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 18.3863ms 17.7900ms 56.2113 Ops/s 55.4489 Ops/s $\color{#35bf28}+1.37\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 20.3211ms 18.5460ms 53.9199 Ops/s 54.5218 Ops/s $\color{#d91a1a}-1.10\%$

@vmoens vmoens merged commit 84e9fa7 into gh/vmoens/48/base Dec 4, 2024
66 of 77 checks passed
vmoens added a commit that referenced this pull request Dec 4, 2024
@vmoens
[BugFix] Fix typing for python 3.9
e7062a1 
ghstack-source-id: 663da84096214611804a726e2d38d27a6f21c958
Pull Request resolved: #2631
@vmoens vmoens deleted the gh/vmoens/48/head branch December 4, 2024 12:58
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.
Projects
None yet
Milestone
No milestone
Development

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