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 unwanted lazy stacks #2102

Merged
merged 10 commits into from
Apr 23, 2024
Merged

[BugFix] Fix unwanted lazy stacks #2102

merged 10 commits into from
Apr 23, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Apr 23, 2024

No description provided.

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Apr 23, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2102

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

❌ 3 New Failures, 16 Unrelated Failures

As of commit 6427212 with merge base 6c2e141 (image):

NEW FAILURES - The following jobs have failed:

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

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 Apr 23, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Apr 23, 2024 •
edited
Loading

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

Total Benchmarks: 94. Improved: $\large\color{#35bf28}2$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1009s 0.1004s 9.9635 Ops/s 9.5797 Ops/s $\color{#35bf28}+4.01\%$
test_sync 89.5296ms 87.5423ms 11.4231 Ops/s 11.2960 Ops/s $\color{#35bf28}+1.12\%$
test_async 0.1675s 82.3134ms 12.1487 Ops/s 11.7553 Ops/s $\color{#35bf28}+3.35\%$
test_single_pixels 0.1119s 0.1114s 8.9760 Ops/s 9.0210 Ops/s $\color{#d91a1a}-0.50\%$
test_sync_pixels 68.5402ms 66.7802ms 14.9745 Ops/s 14.8990 Ops/s $\color{#35bf28}+0.51\%$
test_async_pixels 62.4342ms 61.8272ms 16.1741 Ops/s 16.0327 Ops/s $\color{#35bf28}+0.88\%$
test_simple 0.7016s 0.6928s 1.4435 Ops/s 1.4685 Ops/s $\color{#d91a1a}-1.71\%$
test_transformed 0.9220s 0.9188s 1.0883 Ops/s 1.1034 Ops/s $\color{#d91a1a}-1.36\%$
test_serial 2.2316s 2.1718s 0.4604 Ops/s 0.4818 Ops/s $\color{#d91a1a}-4.43\%$
test_parallel 1.8854s 1.8185s 0.5499 Ops/s 0.5677 Ops/s $\color{#d91a1a}-3.13\%$
test_step_mdp_speed[True-True-True-True-True] 81.9050μs 33.4274μs 29.9156 KOps/s 30.7331 KOps/s $\color{#d91a1a}-2.66\%$
test_step_mdp_speed[True-True-True-True-False] 0.1563ms 20.0862μs 49.7855 KOps/s 52.1317 KOps/s $\color{#d91a1a}-4.50\%$
test_step_mdp_speed[True-True-True-False-True] 38.3220μs 19.0120μs 52.5982 KOps/s 52.9947 KOps/s $\color{#d91a1a}-0.75\%$
test_step_mdp_speed[True-True-True-False-False] 30.4520μs 11.5622μs 86.4885 KOps/s 90.4994 KOps/s $\color{#d91a1a}-4.43\%$
test_step_mdp_speed[True-True-False-True-True] 62.4940μs 35.5208μs 28.1525 KOps/s 29.4869 KOps/s $\color{#d91a1a}-4.53\%$
test_step_mdp_speed[True-True-False-True-False] 42.2630μs 21.9315μs 45.5964 KOps/s 47.4477 KOps/s $\color{#d91a1a}-3.90\%$
test_step_mdp_speed[True-True-False-False-True] 40.9030μs 20.9484μs 47.7364 KOps/s 48.6847 KOps/s $\color{#d91a1a}-1.95\%$
test_step_mdp_speed[True-True-False-False-False] 33.5920μs 13.4734μs 74.2205 KOps/s 77.8685 KOps/s $\color{#d91a1a}-4.68\%$
test_step_mdp_speed[True-False-True-True-True] 0.2153ms 37.3319μs 26.7867 KOps/s 27.2287 KOps/s $\color{#d91a1a}-1.62\%$
test_step_mdp_speed[True-False-True-True-False] 49.4730μs 23.9034μs 41.8350 KOps/s 43.6900 KOps/s $\color{#d91a1a}-4.25\%$
test_step_mdp_speed[True-False-True-False-True] 97.2660μs 20.9620μs 47.7053 KOps/s 49.0933 KOps/s $\color{#d91a1a}-2.83\%$
test_step_mdp_speed[True-False-True-False-False] 37.9530μs 13.4128μs 74.5556 KOps/s 78.3541 KOps/s $\color{#d91a1a}-4.85\%$
test_step_mdp_speed[True-False-False-True-True] 87.5850μs 39.4565μs 25.3443 KOps/s 26.0649 KOps/s $\color{#d91a1a}-2.76\%$
test_step_mdp_speed[True-False-False-True-False] 49.1730μs 26.1401μs 38.2554 KOps/s 40.1125 KOps/s $\color{#d91a1a}-4.63\%$
test_step_mdp_speed[True-False-False-False-True] 40.1720μs 22.7426μs 43.9704 KOps/s 45.1659 KOps/s $\color{#d91a1a}-2.65\%$
test_step_mdp_speed[True-False-False-False-False] 88.1460μs 15.2767μs 65.4591 KOps/s 68.6391 KOps/s $\color{#d91a1a}-4.63\%$
test_step_mdp_speed[False-True-True-True-True] 56.5730μs 37.6048μs 26.5923 KOps/s 27.6395 KOps/s $\color{#d91a1a}-3.79\%$
test_step_mdp_speed[False-True-True-True-False] 47.2730μs 24.2779μs 41.1898 KOps/s 43.0862 KOps/s $\color{#d91a1a}-4.40\%$
test_step_mdp_speed[False-True-True-False-True] 61.3640μs 24.8713μs 40.2069 KOps/s 41.8997 KOps/s $\color{#d91a1a}-4.04\%$
test_step_mdp_speed[False-True-True-False-False] 39.9020μs 15.4004μs 64.9333 KOps/s 68.6972 KOps/s $\textbf{\color{#d91a1a}-5.48\%}$
test_step_mdp_speed[False-True-False-True-True] 58.8930μs 39.6215μs 25.2388 KOps/s 26.2495 KOps/s $\color{#d91a1a}-3.85\%$
test_step_mdp_speed[False-True-False-True-False] 56.7430μs 26.2127μs 38.1494 KOps/s 40.0479 KOps/s $\color{#d91a1a}-4.74\%$
test_step_mdp_speed[False-True-False-False-True] 97.3650μs 26.4913μs 37.7483 KOps/s 38.5774 KOps/s $\color{#d91a1a}-2.15\%$
test_step_mdp_speed[False-True-False-False-False] 51.8130μs 17.3091μs 57.7730 KOps/s 60.7368 KOps/s $\color{#d91a1a}-4.88\%$
test_step_mdp_speed[False-False-True-True-True] 58.4640μs 40.7570μs 24.5357 KOps/s 25.1187 KOps/s $\color{#d91a1a}-2.32\%$
test_step_mdp_speed[False-False-True-True-False] 43.9130μs 27.9018μs 35.8400 KOps/s 37.4965 KOps/s $\color{#d91a1a}-4.42\%$
test_step_mdp_speed[False-False-True-False-True] 0.2247ms 26.8882μs 37.1911 KOps/s 39.4585 KOps/s $\textbf{\color{#d91a1a}-5.75\%}$
test_step_mdp_speed[False-False-True-False-False] 43.1530μs 17.1312μs 58.3730 KOps/s 60.5909 KOps/s $\color{#d91a1a}-3.66\%$
test_step_mdp_speed[False-False-False-True-True] 70.2940μs 42.8121μs 23.3579 KOps/s 24.3017 KOps/s $\color{#d91a1a}-3.88\%$
test_step_mdp_speed[False-False-False-True-False] 46.9030μs 29.8560μs 33.4941 KOps/s 35.3172 KOps/s $\textbf{\color{#d91a1a}-5.16\%}$
test_step_mdp_speed[False-False-False-False-True] 45.5530μs 28.0059μs 35.7067 KOps/s 36.0711 KOps/s $\color{#d91a1a}-1.01\%$
test_step_mdp_speed[False-False-False-False-False] 42.2920μs 18.7006μs 53.4743 KOps/s 55.9361 KOps/s $\color{#d91a1a}-4.40\%$
test_values[generalized_advantage_estimate-True-True] 24.6506ms 24.0829ms 41.5233 Ops/s 42.2464 Ops/s $\color{#d91a1a}-1.71\%$
test_values[vec_generalized_advantage_estimate-True-True] 83.6359ms 3.2404ms 308.6069 Ops/s 299.5618 Ops/s $\color{#35bf28}+3.02\%$
test_values[td0_return_estimate-False-False] 92.4660μs 62.9734μs 15.8797 KOps/s 15.7435 KOps/s $\color{#35bf28}+0.87\%$
test_values[td1_return_estimate-False-False] 51.8738ms 51.1923ms 19.5342 Ops/s 19.6065 Ops/s $\color{#d91a1a}-0.37\%$
test_values[vec_td1_return_estimate-False-False] 2.1124ms 1.7623ms 567.4294 Ops/s 569.9457 Ops/s $\color{#d91a1a}-0.44\%$
test_values[td_lambda_return_estimate-True-False] 83.5835ms 82.1672ms 12.1703 Ops/s 11.5493 Ops/s $\textbf{\color{#35bf28}+5.38\%}$
test_values[vec_td_lambda_return_estimate-True-False] 2.1092ms 1.7589ms 568.5266 Ops/s 572.0713 Ops/s $\color{#d91a1a}-0.62\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 23.1914ms 22.7874ms 43.8839 Ops/s 43.2900 Ops/s $\color{#35bf28}+1.37\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.9068ms 0.7053ms 1.4178 KOps/s 1.3860 KOps/s $\color{#35bf28}+2.29\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.8191ms 0.6409ms 1.5602 KOps/s 1.4774 KOps/s $\textbf{\color{#35bf28}+5.61\%}$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.6245ms 1.4495ms 689.8951 Ops/s 687.2626 Ops/s $\color{#35bf28}+0.38\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9412ms 0.6637ms 1.5068 KOps/s 1.4935 KOps/s $\color{#35bf28}+0.89\%$
test_dqn_speed 1.7285ms 1.4639ms 683.0872 Ops/s 683.4364 Ops/s $\color{#d91a1a}-0.05\%$
test_ddpg_speed 3.0493ms 2.7694ms 361.0851 Ops/s 364.3863 Ops/s $\color{#d91a1a}-0.91\%$
test_sac_speed 8.9629ms 8.1478ms 122.7329 Ops/s 123.0834 Ops/s $\color{#d91a1a}-0.28\%$
test_redq_speed 11.3287ms 10.4062ms 96.0963 Ops/s 95.3936 Ops/s $\color{#35bf28}+0.74\%$
test_redq_deprec_speed 12.1701ms 11.7022ms 85.4540 Ops/s 88.9602 Ops/s $\color{#d91a1a}-3.94\%$
test_td3_speed 17.4840ms 8.1254ms 123.0712 Ops/s 121.0120 Ops/s $\color{#35bf28}+1.70\%$
test_cql_speed 26.8868ms 25.8582ms 38.6724 Ops/s 38.5055 Ops/s $\color{#35bf28}+0.43\%$
test_a2c_speed 6.3979ms 5.7245ms 174.6874 Ops/s 174.7399 Ops/s $\color{#d91a1a}-0.03\%$
test_ppo_speed 6.2686ms 5.9982ms 166.7171 Ops/s 165.3051 Ops/s $\color{#35bf28}+0.85\%$
test_reinforce_speed 5.1087ms 4.7200ms 211.8645 Ops/s 213.4979 Ops/s $\color{#d91a1a}-0.77\%$
test_iql_speed 20.9501ms 20.1814ms 49.5507 Ops/s 49.9483 Ops/s $\color{#d91a1a}-0.80\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.9862ms 2.8203ms 354.5742 Ops/s 361.4487 Ops/s $\color{#d91a1a}-1.90\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.4495ms 0.5485ms 1.8233 KOps/s 1.7984 KOps/s $\color{#35bf28}+1.39\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7535ms 0.5304ms 1.8853 KOps/s 1.8504 KOps/s $\color{#35bf28}+1.89\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.1335ms 2.8606ms 349.5803 Ops/s 357.7828 Ops/s $\color{#d91a1a}-2.29\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.3160ms 0.5405ms 1.8502 KOps/s 1.8377 KOps/s $\color{#35bf28}+0.68\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7074ms 0.5254ms 1.9032 KOps/s 1.8823 KOps/s $\color{#35bf28}+1.11\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 3.9259ms 1.4595ms 685.1695 Ops/s 679.3921 Ops/s $\color{#35bf28}+0.85\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5826ms 1.3787ms 725.3265 Ops/s 717.2108 Ops/s $\color{#35bf28}+1.13\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.1603ms 2.9854ms 334.9653 Ops/s 347.4654 Ops/s $\color{#d91a1a}-3.60\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8807ms 0.6797ms 1.4713 KOps/s 1.4730 KOps/s $\color{#d91a1a}-0.12\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.1228s 0.8142ms 1.2282 KOps/s 1.2243 KOps/s $\color{#35bf28}+0.32\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.0643ms 2.8484ms 351.0734 Ops/s 359.1928 Ops/s $\color{#d91a1a}-2.26\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7425ms 0.5490ms 1.8216 KOps/s 1.8043 KOps/s $\color{#35bf28}+0.96\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 4.2329ms 0.5318ms 1.8803 KOps/s 1.8572 KOps/s $\color{#35bf28}+1.24\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.1324ms 2.8776ms 347.5151 Ops/s 354.9144 Ops/s $\color{#d91a1a}-2.08\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.1207s 0.7015ms 1.4254 KOps/s 1.8336 KOps/s $\textbf{\color{#d91a1a}-22.26\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6681ms 0.5210ms 1.9194 KOps/s 1.9136 KOps/s $\color{#35bf28}+0.31\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.1511ms 2.9777ms 335.8348 Ops/s 342.1706 Ops/s $\color{#d91a1a}-1.85\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8719ms 0.6740ms 1.4837 KOps/s 1.4789 KOps/s $\color{#35bf28}+0.32\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 4.5437ms 0.6603ms 1.5145 KOps/s 1.5040 KOps/s $\color{#35bf28}+0.70\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1203s 7.2412ms 138.0989 Ops/s 137.3408 Ops/s $\color{#35bf28}+0.55\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 0.1285s 16.6547ms 60.0432 Ops/s 60.4355 Ops/s $\color{#d91a1a}-0.65\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.3333ms 1.1605ms 861.6956 Ops/s 860.1480 Ops/s $\color{#35bf28}+0.18\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1220s 7.3188ms 136.6348 Ops/s 138.4530 Ops/s $\color{#d91a1a}-1.31\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 16.9771ms 14.3548ms 69.6631 Ops/s 70.2817 Ops/s $\color{#d91a1a}-0.88\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.3973ms 1.1491ms 870.2454 Ops/s 887.9730 Ops/s $\color{#d91a1a}-2.00\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1242s 7.6920ms 130.0050 Ops/s 132.7437 Ops/s $\color{#d91a1a}-2.06\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 17.2978ms 14.6072ms 68.4595 Ops/s 69.4076 Ops/s $\color{#d91a1a}-1.37\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 1.6191ms 1.4970ms 668.0040 Ops/s 680.9436 Ops/s $\color{#d91a1a}-1.90\%$

@github-actions GitHub Actions
Copy link

github-actions bot commented Apr 23, 2024 •
edited
Loading

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}5$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 55.3133ms 53.6141ms 18.6518 Ops/s 17.9480 Ops/s $\color{#35bf28}+3.92\%$
test_sync 47.5179ms 30.6206ms 32.6578 Ops/s 33.6851 Ops/s $\color{#d91a1a}-3.05\%$
test_async 52.6274ms 28.2546ms 35.3925 Ops/s 38.2867 Ops/s $\textbf{\color{#d91a1a}-7.56\%}$
test_simple 0.3386s 0.3372s 2.9652 Ops/s 2.9872 Ops/s $\color{#d91a1a}-0.74\%$
test_transformed 0.4794s 0.4754s 2.1033 Ops/s 2.0459 Ops/s $\color{#35bf28}+2.80\%$
test_serial 1.2639s 1.2083s 0.8276 Ops/s 0.8393 Ops/s $\color{#d91a1a}-1.39\%$
test_parallel 1.0504s 1.0034s 0.9966 Ops/s 0.9903 Ops/s $\color{#35bf28}+0.63\%$
test_step_mdp_speed[True-True-True-True-True] 0.1760ms 21.5401μs 46.4251 KOps/s 46.8020 KOps/s $\color{#d91a1a}-0.81\%$
test_step_mdp_speed[True-True-True-True-False] 38.8030μs 12.9007μs 77.5150 KOps/s 77.0127 KOps/s $\color{#35bf28}+0.65\%$
test_step_mdp_speed[True-True-True-False-True] 46.8580μs 12.5831μs 79.4715 KOps/s 80.1435 KOps/s $\color{#d91a1a}-0.84\%$
test_step_mdp_speed[True-True-True-False-False] 29.5550μs 7.5885μs 131.7791 KOps/s 132.8620 KOps/s $\color{#d91a1a}-0.82\%$
test_step_mdp_speed[True-True-False-True-True] 50.2540μs 22.8674μs 43.7304 KOps/s 44.7064 KOps/s $\color{#d91a1a}-2.18\%$
test_step_mdp_speed[True-True-False-True-False] 38.9530μs 14.2681μs 70.0866 KOps/s 70.2916 KOps/s $\color{#d91a1a}-0.29\%$
test_step_mdp_speed[True-True-False-False-True] 39.4840μs 13.7836μs 72.5502 KOps/s 72.7113 KOps/s $\color{#d91a1a}-0.22\%$
test_step_mdp_speed[True-True-False-False-False] 28.8440μs 8.7455μs 114.3447 KOps/s 113.9908 KOps/s $\color{#35bf28}+0.31\%$
test_step_mdp_speed[True-False-True-True-True] 50.3850μs 24.2167μs 41.2938 KOps/s 41.8858 KOps/s $\color{#d91a1a}-1.41\%$
test_step_mdp_speed[True-False-True-True-False] 41.4570μs 15.6570μs 63.8691 KOps/s 64.2905 KOps/s $\color{#d91a1a}-0.66\%$
test_step_mdp_speed[True-False-True-False-True] 39.9050μs 13.7590μs 72.6795 KOps/s 73.7070 KOps/s $\color{#d91a1a}-1.39\%$
test_step_mdp_speed[True-False-True-False-False] 43.1100μs 9.0163μs 110.9108 KOps/s 114.7197 KOps/s $\color{#d91a1a}-3.32\%$
test_step_mdp_speed[True-False-False-True-True] 65.2420μs 25.8670μs 38.6593 KOps/s 40.1879 KOps/s $\color{#d91a1a}-3.80\%$
test_step_mdp_speed[True-False-False-True-False] 41.4780μs 17.0997μs 58.4806 KOps/s 60.4341 KOps/s $\color{#d91a1a}-3.23\%$
test_step_mdp_speed[True-False-False-False-True] 40.1650μs 15.1294μs 66.0963 KOps/s 68.5585 KOps/s $\color{#d91a1a}-3.59\%$
test_step_mdp_speed[True-False-False-False-False] 58.8170μs 10.0047μs 99.9531 KOps/s 102.0454 KOps/s $\color{#d91a1a}-2.05\%$
test_step_mdp_speed[False-True-True-True-True] 50.8950μs 24.0759μs 41.5352 KOps/s 41.6784 KOps/s $\color{#d91a1a}-0.34\%$
test_step_mdp_speed[False-True-True-True-False] 57.5980μs 15.8205μs 63.2092 KOps/s 63.8401 KOps/s $\color{#d91a1a}-0.99\%$
test_step_mdp_speed[False-True-True-False-True] 43.2910μs 16.1697μs 61.8441 KOps/s 62.7540 KOps/s $\color{#d91a1a}-1.45\%$
test_step_mdp_speed[False-True-True-False-False] 38.0510μs 10.0852μs 99.1551 KOps/s 99.5444 KOps/s $\color{#d91a1a}-0.39\%$
test_step_mdp_speed[False-True-False-True-True] 53.9210μs 26.1805μs 38.1964 KOps/s 39.7298 KOps/s $\color{#d91a1a}-3.86\%$
test_step_mdp_speed[False-True-False-True-False] 45.9260μs 16.8487μs 59.3517 KOps/s 60.1187 KOps/s $\color{#d91a1a}-1.28\%$
test_step_mdp_speed[False-True-False-False-True] 51.6970μs 17.2397μs 58.0056 KOps/s 59.2367 KOps/s $\color{#d91a1a}-2.08\%$
test_step_mdp_speed[False-True-False-False-False] 48.7710μs 11.2262μs 89.0776 KOps/s 90.2350 KOps/s $\color{#d91a1a}-1.28\%$
test_step_mdp_speed[False-False-True-True-True] 52.5890μs 26.6580μs 37.5122 KOps/s 38.2983 KOps/s $\color{#d91a1a}-2.05\%$
test_step_mdp_speed[False-False-True-True-False] 40.2050μs 18.2074μs 54.9226 KOps/s 56.0308 KOps/s $\color{#d91a1a}-1.98\%$
test_step_mdp_speed[False-False-True-False-True] 44.6640μs 17.5016μs 57.1375 KOps/s 59.0967 KOps/s $\color{#d91a1a}-3.32\%$
test_step_mdp_speed[False-False-True-False-False] 47.5890μs 11.3463μs 88.1341 KOps/s 90.3542 KOps/s $\color{#d91a1a}-2.46\%$
test_step_mdp_speed[False-False-False-True-True] 0.3094ms 28.6395μs 34.9168 KOps/s 36.5308 KOps/s $\color{#d91a1a}-4.42\%$
test_step_mdp_speed[False-False-False-True-False] 0.2054ms 20.1898μs 49.5298 KOps/s 52.0539 KOps/s $\color{#d91a1a}-4.85\%$
test_step_mdp_speed[False-False-False-False-True] 58.1190μs 18.9769μs 52.6957 KOps/s 56.1307 KOps/s $\textbf{\color{#d91a1a}-6.12\%}$
test_step_mdp_speed[False-False-False-False-False] 34.7650μs 12.6939μs 78.7778 KOps/s 82.0841 KOps/s $\color{#d91a1a}-4.03\%$
test_values[generalized_advantage_estimate-True-True] 11.5614ms 9.3691ms 106.7342 Ops/s 107.9143 Ops/s $\color{#d91a1a}-1.09\%$
test_values[vec_generalized_advantage_estimate-True-True] 36.3127ms 34.9633ms 28.6014 Ops/s 29.3909 Ops/s $\color{#d91a1a}-2.69\%$
test_values[td0_return_estimate-False-False] 0.4404ms 0.1703ms 5.8713 KOps/s 5.9454 KOps/s $\color{#d91a1a}-1.25\%$
test_values[td1_return_estimate-False-False] 37.4018ms 24.0279ms 41.6183 Ops/s 42.7561 Ops/s $\color{#d91a1a}-2.66\%$
test_values[vec_td1_return_estimate-False-False] 38.8767ms 35.2886ms 28.3378 Ops/s 30.1582 Ops/s $\textbf{\color{#d91a1a}-6.04\%}$
test_values[td_lambda_return_estimate-True-False] 36.6411ms 33.5702ms 29.7883 Ops/s 29.7068 Ops/s $\color{#35bf28}+0.27\%$
test_values[vec_td_lambda_return_estimate-True-False] 37.3193ms 35.2410ms 28.3760 Ops/s 30.0671 Ops/s $\textbf{\color{#d91a1a}-5.62\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 10.3827ms 8.1922ms 122.0678 Ops/s 121.3815 Ops/s $\color{#35bf28}+0.57\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.3828ms 2.0221ms 494.5317 Ops/s 511.6849 Ops/s $\color{#d91a1a}-3.35\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5539ms 0.3524ms 2.8380 KOps/s 2.8319 KOps/s $\color{#35bf28}+0.21\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 48.1688ms 47.1848ms 21.1933 Ops/s 24.3542 Ops/s $\textbf{\color{#d91a1a}-12.98\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.6565ms 3.0442ms 328.4973 Ops/s 328.2233 Ops/s $\color{#35bf28}+0.08\%$
test_dqn_speed 1.6171ms 1.3458ms 743.0732 Ops/s 736.6819 Ops/s $\color{#35bf28}+0.87\%$
test_ddpg_speed 3.4917ms 2.6832ms 372.6840 Ops/s 370.9166 Ops/s $\color{#35bf28}+0.48\%$
test_sac_speed 8.6941ms 8.2481ms 121.2394 Ops/s 111.3200 Ops/s $\textbf{\color{#35bf28}+8.91\%}$
test_redq_speed 14.5256ms 13.2433ms 75.5097 Ops/s 75.5341 Ops/s $\color{#d91a1a}-0.03\%$
test_redq_deprec_speed 13.9893ms 13.0633ms 76.5502 Ops/s 75.2377 Ops/s $\color{#35bf28}+1.74\%$
test_td3_speed 8.4881ms 8.1336ms 122.9469 Ops/s 122.3760 Ops/s $\color{#35bf28}+0.47\%$
test_cql_speed 37.8636ms 36.6397ms 27.2928 Ops/s 27.3902 Ops/s $\color{#d91a1a}-0.36\%$
test_a2c_speed 8.3123ms 7.3263ms 136.4945 Ops/s 132.5175 Ops/s $\color{#35bf28}+3.00\%$
test_ppo_speed 8.5047ms 7.5980ms 131.6129 Ops/s 130.3704 Ops/s $\color{#35bf28}+0.95\%$
test_reinforce_speed 7.5851ms 6.5597ms 152.4469 Ops/s 151.9969 Ops/s $\color{#35bf28}+0.30\%$
test_iql_speed 33.7914ms 32.5289ms 30.7419 Ops/s 29.9436 Ops/s $\color{#35bf28}+2.67\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.3763ms 2.1153ms 472.7489 Ops/s 430.2281 Ops/s $\textbf{\color{#35bf28}+9.88\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.2857ms 0.5027ms 1.9891 KOps/s 1.9423 KOps/s $\color{#35bf28}+2.41\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7271ms 0.4871ms 2.0530 KOps/s 1.9413 KOps/s $\textbf{\color{#35bf28}+5.75\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.4608ms 2.1693ms 460.9812 Ops/s 418.6241 Ops/s $\textbf{\color{#35bf28}+10.12\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7644ms 0.4933ms 2.0272 KOps/s 1.9640 KOps/s $\color{#35bf28}+3.21\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 3.5166ms 0.4781ms 2.0918 KOps/s 2.0509 KOps/s $\color{#35bf28}+1.99\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.8477ms 1.2291ms 813.5971 Ops/s 814.6368 Ops/s $\color{#d91a1a}-0.13\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 4.0398ms 1.1542ms 866.4085 Ops/s 855.7183 Ops/s $\color{#35bf28}+1.25\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.5242ms 2.3234ms 430.4077 Ops/s 415.2098 Ops/s $\color{#35bf28}+3.66\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9417ms 0.6257ms 1.5983 KOps/s 1.5884 KOps/s $\color{#35bf28}+0.63\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8453ms 0.5962ms 1.6774 KOps/s 1.6738 KOps/s $\color{#35bf28}+0.21\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.3699ms 2.1696ms 460.9169 Ops/s 453.3658 Ops/s $\color{#35bf28}+1.67\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8964ms 0.5578ms 1.7927 KOps/s 1.9774 KOps/s $\textbf{\color{#d91a1a}-9.34\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.9690ms 0.4948ms 2.0208 KOps/s 2.0691 KOps/s $\color{#d91a1a}-2.33\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 2.6753ms 2.2440ms 445.6369 Ops/s 461.3751 Ops/s $\color{#d91a1a}-3.41\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8275ms 0.5065ms 1.9742 KOps/s 2.0087 KOps/s $\color{#d91a1a}-1.72\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5641ms 0.4775ms 2.0945 KOps/s 2.1160 KOps/s $\color{#d91a1a}-1.02\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.9089ms 2.3755ms 420.9711 Ops/s 430.1674 Ops/s $\color{#d91a1a}-2.14\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7420ms 0.6215ms 1.6091 KOps/s 1.5736 KOps/s $\color{#35bf28}+2.25\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9049ms 0.5964ms 1.6768 KOps/s 1.6679 KOps/s $\color{#35bf28}+0.53\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1106s 7.8399ms 127.5530 Ops/s 123.7282 Ops/s $\color{#35bf28}+3.09\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 14.0037ms 11.9283ms 83.8341 Ops/s 81.9599 Ops/s $\color{#35bf28}+2.29\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.2075ms 1.0127ms 987.4141 Ops/s 970.8842 Ops/s $\color{#35bf28}+1.70\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1022s 5.5685ms 179.5822 Ops/s 173.2087 Ops/s $\color{#35bf28}+3.68\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.2332ms 12.0464ms 83.0126 Ops/s 82.2088 Ops/s $\color{#35bf28}+0.98\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.7897ms 1.0740ms 931.0741 Ops/s 971.6242 Ops/s $\color{#d91a1a}-4.17\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1096s 8.1281ms 123.0295 Ops/s 119.8640 Ops/s $\color{#35bf28}+2.64\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 15.1446ms 12.3459ms 80.9988 Ops/s 79.0195 Ops/s $\color{#35bf28}+2.50\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 2.2125ms 1.3879ms 720.5289 Ops/s 684.7269 Ops/s $\textbf{\color{#35bf28}+5.23\%}$

@vmoens vmoens added the bug Something isn't working label Apr 23, 2024
@vmoens vmoens merged commit 09c934d into main Apr 23, 2024
25 of 29 checks passed
@vmoens vmoens deleted the fix-stack-deprec branch April 23, 2024 20:22
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
bug Something isn't working 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