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

[BugFix] Fix torch 2.3 compatibility of padding indices #2216

Merged
merged 1 commit into from
Jun 7, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Jun 7, 2024

No description provided.

Copy link

pytorch-bot bot commented Jun 7, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2216

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

❗ 1 Active SEVs

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

❌ 10 New Failures, 15 Unrelated Failures

As of commit 645fbba with merge base 332499a (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 Jun 7, 2024
@vmoens vmoens added the bug Something isn't working label Jun 7, 2024
@vmoens vmoens merged commit 2173b63 into main Jun 7, 2024
29 of 46 checks passed
@vmoens vmoens deleted the fix-padding-torch2.3 branch June 7, 2024 13:22
Copy link

github-actions bot commented Jun 7, 2024

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}7$. Worsened: $\large\color{#d91a1a}2$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1076s 58.2030ms 17.1813 Ops/s 17.8856 Ops/s $\color{#d91a1a}-3.94\%$
test_sync 35.7425ms 30.2096ms 33.1021 Ops/s 32.0326 Ops/s $\color{#35bf28}+3.34\%$
test_async 54.1413ms 28.9729ms 34.5150 Ops/s 35.6020 Ops/s $\color{#d91a1a}-3.05\%$
test_simple 0.4326s 0.3807s 2.6268 Ops/s 2.6715 Ops/s $\color{#d91a1a}-1.67\%$
test_transformed 0.5319s 0.5255s 1.9030 Ops/s 1.8848 Ops/s $\color{#35bf28}+0.97\%$
test_serial 1.2889s 1.2484s 0.8010 Ops/s 0.7937 Ops/s $\color{#35bf28}+0.92\%$
test_parallel 1.0963s 1.0466s 0.9554 Ops/s 0.9362 Ops/s $\color{#35bf28}+2.05\%$
test_step_mdp_speed[True-True-True-True-True] 0.1081ms 21.1710μs 47.2345 KOps/s 46.1423 KOps/s $\color{#35bf28}+2.37\%$
test_step_mdp_speed[True-True-True-True-False] 40.2250μs 13.0603μs 76.5680 KOps/s 76.5457 KOps/s $\color{#35bf28}+0.03\%$
test_step_mdp_speed[True-True-True-False-True] 41.0170μs 12.5034μs 79.9780 KOps/s 78.1437 KOps/s $\color{#35bf28}+2.35\%$
test_step_mdp_speed[True-True-True-False-False] 28.3420μs 7.5734μs 132.0413 KOps/s 129.3343 KOps/s $\color{#35bf28}+2.09\%$
test_step_mdp_speed[True-True-False-True-True] 59.1000μs 22.4043μs 44.6342 KOps/s 44.0922 KOps/s $\color{#35bf28}+1.23\%$
test_step_mdp_speed[True-True-False-True-False] 33.4420μs 14.1702μs 70.5705 KOps/s 69.0828 KOps/s $\color{#35bf28}+2.15\%$
test_step_mdp_speed[True-True-False-False-True] 52.7890μs 13.8166μs 72.3766 KOps/s 71.6366 KOps/s $\color{#35bf28}+1.03\%$
test_step_mdp_speed[True-True-False-False-False] 33.0610μs 8.8134μs 113.4632 KOps/s 111.8780 KOps/s $\color{#35bf28}+1.42\%$
test_step_mdp_speed[True-False-True-True-True] 64.7400μs 23.7563μs 42.0941 KOps/s 41.3510 KOps/s $\color{#35bf28}+1.80\%$
test_step_mdp_speed[True-False-True-True-False] 53.6600μs 15.5307μs 64.3887 KOps/s 62.1828 KOps/s $\color{#35bf28}+3.55\%$
test_step_mdp_speed[True-False-True-False-True] 34.9050μs 13.7186μs 72.8938 KOps/s 71.8113 KOps/s $\color{#35bf28}+1.51\%$
test_step_mdp_speed[True-False-True-False-False] 36.6890μs 8.7664μs 114.0718 KOps/s 111.5430 KOps/s $\color{#35bf28}+2.27\%$
test_step_mdp_speed[True-False-False-True-True] 69.2690μs 24.8900μs 40.1768 KOps/s 39.7090 KOps/s $\color{#35bf28}+1.18\%$
test_step_mdp_speed[True-False-False-True-False] 43.0700μs 16.6035μs 60.2284 KOps/s 59.7886 KOps/s $\color{#35bf28}+0.74\%$
test_step_mdp_speed[True-False-False-False-True] 38.8830μs 14.8467μs 67.3550 KOps/s 66.7598 KOps/s $\color{#35bf28}+0.89\%$
test_step_mdp_speed[True-False-False-False-False] 39.9540μs 9.9063μs 100.9454 KOps/s 97.5493 KOps/s $\color{#35bf28}+3.48\%$
test_step_mdp_speed[False-True-True-True-True] 58.8000μs 23.8279μs 41.9675 KOps/s 41.6465 KOps/s $\color{#35bf28}+0.77\%$
test_step_mdp_speed[False-True-True-True-False] 52.2370μs 15.4679μs 64.6499 KOps/s 63.6449 KOps/s $\color{#35bf28}+1.58\%$
test_step_mdp_speed[False-True-True-False-True] 45.9960μs 16.0676μs 62.2370 KOps/s 61.5973 KOps/s $\color{#35bf28}+1.04\%$
test_step_mdp_speed[False-True-True-False-False] 35.7970μs 9.9582μs 100.4196 KOps/s 97.9650 KOps/s $\color{#35bf28}+2.51\%$
test_step_mdp_speed[False-True-False-True-True] 53.7900μs 25.0108μs 39.9828 KOps/s 39.2594 KOps/s $\color{#35bf28}+1.84\%$
test_step_mdp_speed[False-True-False-True-False] 38.9020μs 16.6383μs 60.1022 KOps/s 58.7990 KOps/s $\color{#35bf28}+2.22\%$
test_step_mdp_speed[False-True-False-False-True] 71.8240μs 17.0932μs 58.5030 KOps/s 58.0030 KOps/s $\color{#35bf28}+0.86\%$
test_step_mdp_speed[False-True-False-False-False] 46.4060μs 11.1578μs 89.6231 KOps/s 87.4067 KOps/s $\color{#35bf28}+2.54\%$
test_step_mdp_speed[False-False-True-True-True] 64.8210μs 26.2169μs 38.1433 KOps/s 37.6826 KOps/s $\color{#35bf28}+1.22\%$
test_step_mdp_speed[False-False-True-True-False] 54.5220μs 17.9830μs 55.6081 KOps/s 54.7960 KOps/s $\color{#35bf28}+1.48\%$
test_step_mdp_speed[False-False-True-False-True] 55.6440μs 17.1383μs 58.3490 KOps/s 57.5104 KOps/s $\color{#35bf28}+1.46\%$
test_step_mdp_speed[False-False-True-False-False] 41.2570μs 11.1222μs 89.9105 KOps/s 88.1110 KOps/s $\color{#35bf28}+2.04\%$
test_step_mdp_speed[False-False-False-True-True] 38.4620μs 27.6571μs 36.1571 KOps/s 35.5513 KOps/s $\color{#35bf28}+1.70\%$
test_step_mdp_speed[False-False-False-True-False] 47.3690μs 19.0186μs 52.5800 KOps/s 52.0451 KOps/s $\color{#35bf28}+1.03\%$
test_step_mdp_speed[False-False-False-False-True] 51.0260μs 18.0631μs 55.3615 KOps/s 54.7183 KOps/s $\color{#35bf28}+1.18\%$
test_step_mdp_speed[False-False-False-False-False] 40.3350μs 12.1701μs 82.1688 KOps/s 80.2055 KOps/s $\color{#35bf28}+2.45\%$
test_values[generalized_advantage_estimate-True-True] 9.7469ms 9.4279ms 106.0680 Ops/s 106.3157 Ops/s $\color{#d91a1a}-0.23\%$
test_values[vec_generalized_advantage_estimate-True-True] 36.7673ms 33.2488ms 30.0763 Ops/s 28.4731 Ops/s $\textbf{\color{#35bf28}+5.63\%}$
test_values[td0_return_estimate-False-False] 0.2145ms 0.1621ms 6.1676 KOps/s 5.6769 KOps/s $\textbf{\color{#35bf28}+8.64\%}$
test_values[td1_return_estimate-False-False] 23.8475ms 23.6672ms 42.2525 Ops/s 42.7989 Ops/s $\color{#d91a1a}-1.28\%$
test_values[vec_td1_return_estimate-False-False] 36.7855ms 33.2849ms 30.0436 Ops/s 28.1109 Ops/s $\textbf{\color{#35bf28}+6.88\%}$
test_values[td_lambda_return_estimate-True-False] 37.8628ms 34.3651ms 29.0993 Ops/s 29.9000 Ops/s $\color{#d91a1a}-2.68\%$
test_values[vec_td_lambda_return_estimate-True-False] 34.5796ms 33.1187ms 30.1944 Ops/s 28.4827 Ops/s $\textbf{\color{#35bf28}+6.01\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 9.1830ms 8.3128ms 120.2966 Ops/s 120.0705 Ops/s $\color{#35bf28}+0.19\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 3.1933ms 2.2608ms 442.3163 Ops/s 510.6741 Ops/s $\textbf{\color{#d91a1a}-13.39\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4365ms 0.3494ms 2.8621 KOps/s 2.8301 KOps/s $\color{#35bf28}+1.13\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 40.3131ms 38.4584ms 26.0021 Ops/s 22.1582 Ops/s $\textbf{\color{#35bf28}+17.35\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8890ms 3.0231ms 330.7862 Ops/s 330.2192 Ops/s $\color{#35bf28}+0.17\%$
test_dqn_speed 1.8266ms 1.3316ms 750.9877 Ops/s 733.6688 Ops/s $\color{#35bf28}+2.36\%$
test_ddpg_speed 3.1977ms 2.8178ms 354.8818 Ops/s 350.1837 Ops/s $\color{#35bf28}+1.34\%$
test_sac_speed 10.0947ms 8.3081ms 120.3650 Ops/s 118.5059 Ops/s $\color{#35bf28}+1.57\%$
test_redq_speed 13.9983ms 12.9850ms 77.0122 Ops/s 75.7043 Ops/s $\color{#35bf28}+1.73\%$
test_redq_deprec_speed 14.8417ms 13.1900ms 75.8148 Ops/s 73.8557 Ops/s $\color{#35bf28}+2.65\%$
test_td3_speed 15.8846ms 8.3329ms 120.0063 Ops/s 118.1437 Ops/s $\color{#35bf28}+1.58\%$
test_cql_speed 37.7127ms 36.1263ms 27.6806 Ops/s 27.3238 Ops/s $\color{#35bf28}+1.31\%$
test_a2c_speed 7.9945ms 7.4499ms 134.2296 Ops/s 133.4383 Ops/s $\color{#35bf28}+0.59\%$
test_ppo_speed 8.9790ms 7.7599ms 128.8684 Ops/s 127.7391 Ops/s $\color{#35bf28}+0.88\%$
test_reinforce_speed 13.0029ms 6.8659ms 145.6480 Ops/s 147.4770 Ops/s $\color{#d91a1a}-1.24\%$
test_iql_speed 33.8942ms 32.8891ms 30.4052 Ops/s 29.7827 Ops/s $\color{#35bf28}+2.09\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.1036ms 3.4502ms 289.8411 Ops/s 273.8166 Ops/s $\textbf{\color{#35bf28}+5.85\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8917ms 0.4952ms 2.0195 KOps/s 1.9665 KOps/s $\color{#35bf28}+2.69\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6467ms 0.4784ms 2.0902 KOps/s 2.0408 KOps/s $\color{#35bf28}+2.42\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.3696ms 3.5153ms 284.4687 Ops/s 272.6073 Ops/s $\color{#35bf28}+4.35\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9497ms 0.4924ms 2.0310 KOps/s 2.0144 KOps/s $\color{#35bf28}+0.82\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7162ms 0.4698ms 2.1287 KOps/s 2.1000 KOps/s $\color{#35bf28}+1.37\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.2814ms 1.7064ms 586.0334 Ops/s 586.1606 Ops/s $\color{#d91a1a}-0.02\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 4.6233ms 1.6199ms 617.3062 Ops/s 614.6069 Ops/s $\color{#35bf28}+0.44\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.2190ms 3.6198ms 276.2563 Ops/s 272.2051 Ops/s $\color{#35bf28}+1.49\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1617ms 0.6196ms 1.6140 KOps/s 1.6109 KOps/s $\color{#35bf28}+0.19\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8692ms 0.5979ms 1.6725 KOps/s 1.6902 KOps/s $\color{#d91a1a}-1.04\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.7493ms 3.6122ms 276.8374 Ops/s 290.4515 Ops/s $\color{#d91a1a}-4.69\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0342ms 0.5047ms 1.9814 KOps/s 1.9999 KOps/s $\color{#d91a1a}-0.93\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7936ms 0.4861ms 2.0570 KOps/s 2.0883 KOps/s $\color{#d91a1a}-1.50\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.8021ms 3.5352ms 282.8658 Ops/s 293.9302 Ops/s $\color{#d91a1a}-3.76\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.5850ms 0.4883ms 2.0478 KOps/s 2.0223 KOps/s $\color{#35bf28}+1.26\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 3.5139ms 0.4742ms 2.1087 KOps/s 2.1425 KOps/s $\color{#d91a1a}-1.58\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 4.0088ms 3.5635ms 280.6214 Ops/s 285.4375 Ops/s $\color{#d91a1a}-1.69\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8438ms 0.6167ms 1.6214 KOps/s 1.6380 KOps/s $\color{#d91a1a}-1.01\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7135ms 0.5860ms 1.7065 KOps/s 1.6787 KOps/s $\color{#35bf28}+1.65\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 99.3628ms 7.4413ms 134.3843 Ops/s 129.7086 Ops/s $\color{#35bf28}+3.60\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 14.4434ms 12.3216ms 81.1583 Ops/s 80.4506 Ops/s $\color{#35bf28}+0.88\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.5292ms 1.0337ms 967.3679 Ops/s 942.3375 Ops/s $\color{#35bf28}+2.66\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 94.8460ms 5.5867ms 178.9968 Ops/s 181.4744 Ops/s $\color{#d91a1a}-1.37\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 14.3632ms 12.3399ms 81.0378 Ops/s 80.7980 Ops/s $\color{#35bf28}+0.30\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.5274ms 1.0345ms 966.6786 Ops/s 933.9146 Ops/s $\color{#35bf28}+3.51\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 93.4613ms 5.6265ms 177.7319 Ops/s 133.0130 Ops/s $\textbf{\color{#35bf28}+33.62\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 0.1060s 14.3818ms 69.5322 Ops/s 79.0266 Ops/s $\textbf{\color{#d91a1a}-12.01\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.2897ms 1.2282ms 814.2041 Ops/s 846.2337 Ops/s $\color{#d91a1a}-3.78\%$

Copy link

github-actions bot commented Jun 7, 2024

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

Total Benchmarks: 94. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1172s 0.1171s 8.5374 Ops/s 8.4202 Ops/s $\color{#35bf28}+1.39\%$
test_sync 0.1041s 0.1026s 9.7495 Ops/s 9.6876 Ops/s $\color{#35bf28}+0.64\%$
test_async 0.2061s 81.7523ms 12.2321 Ops/s 10.2610 Ops/s $\textbf{\color{#35bf28}+19.21\%}$
test_single_pixels 0.1299s 0.1288s 7.7634 Ops/s 7.8076 Ops/s $\color{#d91a1a}-0.57\%$
test_sync_pixels 83.1446ms 79.3338ms 12.6050 Ops/s 12.1286 Ops/s $\color{#35bf28}+3.93\%$
test_async_pixels 0.1597s 69.5276ms 14.3828 Ops/s 14.4008 Ops/s $\color{#d91a1a}-0.13\%$
test_simple 0.8908s 0.8281s 1.2076 Ops/s 1.2144 Ops/s $\color{#d91a1a}-0.56\%$
test_transformed 1.1460s 1.0868s 0.9201 Ops/s 0.9179 Ops/s $\color{#35bf28}+0.24\%$
test_serial 2.5774s 2.5194s 0.3969 Ops/s 0.4012 Ops/s $\color{#d91a1a}-1.08\%$
test_parallel 2.4124s 2.3495s 0.4256 Ops/s 0.4263 Ops/s $\color{#d91a1a}-0.15\%$
test_step_mdp_speed[True-True-True-True-True] 65.7310μs 34.0299μs 29.3859 KOps/s 30.4780 KOps/s $\color{#d91a1a}-3.58\%$
test_step_mdp_speed[True-True-True-True-False] 39.4210μs 20.1918μs 49.5250 KOps/s 50.6261 KOps/s $\color{#d91a1a}-2.17\%$
test_step_mdp_speed[True-True-True-False-True] 0.2821ms 19.2190μs 52.0317 KOps/s 52.5209 KOps/s $\color{#d91a1a}-0.93\%$
test_step_mdp_speed[True-True-True-False-False] 32.0800μs 11.6245μs 86.0253 KOps/s 87.2900 KOps/s $\color{#d91a1a}-1.45\%$
test_step_mdp_speed[True-True-False-True-True] 64.4310μs 35.3464μs 28.2914 KOps/s 27.9958 KOps/s $\color{#35bf28}+1.06\%$
test_step_mdp_speed[True-True-False-True-False] 41.9000μs 22.0119μs 45.4300 KOps/s 45.0247 KOps/s $\color{#35bf28}+0.90\%$
test_step_mdp_speed[True-True-False-False-True] 44.8310μs 21.1144μs 47.3611 KOps/s 47.5046 KOps/s $\color{#d91a1a}-0.30\%$
test_step_mdp_speed[True-True-False-False-False] 0.2455ms 13.4386μs 74.4123 KOps/s 75.0057 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[True-False-True-True-True] 68.8510μs 37.3171μs 26.7974 KOps/s 26.7029 KOps/s $\color{#35bf28}+0.35\%$
test_step_mdp_speed[True-False-True-True-False] 48.2510μs 24.0916μs 41.5082 KOps/s 41.3187 KOps/s $\color{#35bf28}+0.46\%$
test_step_mdp_speed[True-False-True-False-True] 0.3057ms 21.0895μs 47.4171 KOps/s 47.5707 KOps/s $\color{#d91a1a}-0.32\%$
test_step_mdp_speed[True-False-True-False-False] 0.3275ms 13.4961μs 74.0956 KOps/s 74.2233 KOps/s $\color{#d91a1a}-0.17\%$
test_step_mdp_speed[True-False-False-True-True] 62.9010μs 39.0083μs 25.6356 KOps/s 25.2977 KOps/s $\color{#35bf28}+1.34\%$
test_step_mdp_speed[True-False-False-True-False] 51.3610μs 26.0890μs 38.3304 KOps/s 39.1540 KOps/s $\color{#d91a1a}-2.10\%$
test_step_mdp_speed[True-False-False-False-True] 48.9310μs 22.8278μs 43.8062 KOps/s 43.6879 KOps/s $\color{#35bf28}+0.27\%$
test_step_mdp_speed[True-False-False-False-False] 32.1410μs 15.2560μs 65.5481 KOps/s 66.0688 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[False-True-True-True-True] 59.9920μs 37.4868μs 26.6760 KOps/s 26.7534 KOps/s $\color{#d91a1a}-0.29\%$
test_step_mdp_speed[False-True-True-True-False] 43.9110μs 24.1762μs 41.3630 KOps/s 41.9104 KOps/s $\color{#d91a1a}-1.31\%$
test_step_mdp_speed[False-True-True-False-True] 42.3510μs 25.3379μs 39.4666 KOps/s 39.8743 KOps/s $\color{#d91a1a}-1.02\%$
test_step_mdp_speed[False-True-True-False-False] 41.5310μs 15.4675μs 64.6516 KOps/s 64.4936 KOps/s $\color{#35bf28}+0.25\%$
test_step_mdp_speed[False-True-False-True-True] 61.4320μs 39.2199μs 25.4973 KOps/s 25.4457 KOps/s $\color{#35bf28}+0.20\%$
test_step_mdp_speed[False-True-False-True-False] 46.6510μs 25.9307μs 38.5644 KOps/s 39.3753 KOps/s $\color{#d91a1a}-2.06\%$
test_step_mdp_speed[False-True-False-False-True] 42.9510μs 27.1860μs 36.7836 KOps/s 38.0609 KOps/s $\color{#d91a1a}-3.36\%$
test_step_mdp_speed[False-True-False-False-False] 37.1800μs 17.1169μs 58.4218 KOps/s 58.7607 KOps/s $\color{#d91a1a}-0.58\%$
test_step_mdp_speed[False-False-True-True-True] 78.6020μs 41.1045μs 24.3283 KOps/s 24.3743 KOps/s $\color{#d91a1a}-0.19\%$
test_step_mdp_speed[False-False-True-True-False] 52.1010μs 27.9720μs 35.7501 KOps/s 35.9066 KOps/s $\color{#d91a1a}-0.44\%$
test_step_mdp_speed[False-False-True-False-True] 50.1610μs 27.3527μs 36.5594 KOps/s 37.3651 KOps/s $\color{#d91a1a}-2.16\%$
test_step_mdp_speed[False-False-True-False-False] 44.0310μs 17.2128μs 58.0963 KOps/s 57.8578 KOps/s $\color{#35bf28}+0.41\%$
test_step_mdp_speed[False-False-False-True-True] 78.8310μs 44.5336μs 22.4549 KOps/s 22.4235 KOps/s $\color{#35bf28}+0.14\%$
test_step_mdp_speed[False-False-False-True-False] 59.9010μs 29.9210μs 33.4213 KOps/s 33.7450 KOps/s $\color{#d91a1a}-0.96\%$
test_step_mdp_speed[False-False-False-False-True] 53.4810μs 28.9566μs 34.5344 KOps/s 35.3098 KOps/s $\color{#d91a1a}-2.20\%$
test_step_mdp_speed[False-False-False-False-False] 44.4810μs 18.8236μs 53.1249 KOps/s 52.2653 KOps/s $\color{#35bf28}+1.64\%$
test_values[generalized_advantage_estimate-True-True] 24.9399ms 24.1626ms 41.3863 Ops/s 41.2914 Ops/s $\color{#35bf28}+0.23\%$
test_values[vec_generalized_advantage_estimate-True-True] 92.8437ms 2.7630ms 361.9235 Ops/s 368.7191 Ops/s $\color{#d91a1a}-1.84\%$
test_values[td0_return_estimate-False-False] 94.4120μs 67.9926μs 14.7075 KOps/s 14.9150 KOps/s $\color{#d91a1a}-1.39\%$
test_values[td1_return_estimate-False-False] 57.4611ms 56.3707ms 17.7397 Ops/s 18.2744 Ops/s $\color{#d91a1a}-2.93\%$
test_values[vec_td1_return_estimate-False-False] 1.3935ms 1.0935ms 914.4863 Ops/s 915.1850 Ops/s $\color{#d91a1a}-0.08\%$
test_values[td_lambda_return_estimate-True-False] 92.5002ms 90.2882ms 11.0756 Ops/s 11.5151 Ops/s $\color{#d91a1a}-3.82\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.4890ms 1.1001ms 909.0057 Ops/s 913.8311 Ops/s $\color{#d91a1a}-0.53\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.7896ms 24.7791ms 40.3565 Ops/s 41.0244 Ops/s $\color{#d91a1a}-1.63\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.9485ms 0.7255ms 1.3783 KOps/s 1.3436 KOps/s $\color{#35bf28}+2.58\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.9043ms 0.6780ms 1.4749 KOps/s 1.4723 KOps/s $\color{#35bf28}+0.18\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.7862ms 1.4786ms 676.3006 Ops/s 678.5258 Ops/s $\color{#d91a1a}-0.33\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 1.0054ms 0.6946ms 1.4397 KOps/s 1.4390 KOps/s $\color{#35bf28}+0.05\%$
test_dqn_speed 9.1611ms 1.5204ms 657.7392 Ops/s 689.4284 Ops/s $\color{#d91a1a}-4.60\%$
test_ddpg_speed 3.4282ms 3.0459ms 328.3151 Ops/s 332.1401 Ops/s $\color{#d91a1a}-1.15\%$
test_sac_speed 8.8981ms 8.5386ms 117.1146 Ops/s 119.4085 Ops/s $\color{#d91a1a}-1.92\%$
test_redq_speed 13.0917ms 10.9475ms 91.3452 Ops/s 84.2605 Ops/s $\textbf{\color{#35bf28}+8.41\%}$
test_redq_deprec_speed 12.1988ms 11.7589ms 85.0418 Ops/s 83.5111 Ops/s $\color{#35bf28}+1.83\%$
test_td3_speed 17.3314ms 8.4952ms 117.7133 Ops/s 121.2375 Ops/s $\color{#d91a1a}-2.91\%$
test_cql_speed 27.3160ms 26.1791ms 38.1985 Ops/s 38.6267 Ops/s $\color{#d91a1a}-1.11\%$
test_a2c_speed 6.5518ms 5.6892ms 175.7725 Ops/s 171.7228 Ops/s $\color{#35bf28}+2.36\%$
test_ppo_speed 6.3848ms 6.0000ms 166.6662 Ops/s 163.1451 Ops/s $\color{#35bf28}+2.16\%$
test_reinforce_speed 5.0192ms 4.6587ms 214.6504 Ops/s 212.3183 Ops/s $\color{#35bf28}+1.10\%$
test_iql_speed 21.5072ms 20.3634ms 49.1077 Ops/s 50.3223 Ops/s $\color{#d91a1a}-2.41\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.0976ms 4.8235ms 207.3189 Ops/s 215.1717 Ops/s $\color{#d91a1a}-3.65\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7370ms 0.5958ms 1.6785 KOps/s 1.6721 KOps/s $\color{#35bf28}+0.38\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 4.4397ms 0.5755ms 1.7375 KOps/s 1.7411 KOps/s $\color{#d91a1a}-0.21\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.0333ms 4.7648ms 209.8719 Ops/s 214.5074 Ops/s $\color{#d91a1a}-2.16\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9761ms 0.5910ms 1.6920 KOps/s 1.6953 KOps/s $\color{#d91a1a}-0.19\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 4.3890ms 0.5692ms 1.7568 KOps/s 1.7512 KOps/s $\color{#35bf28}+0.32\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.4056ms 2.0550ms 486.6154 Ops/s 485.3422 Ops/s $\color{#35bf28}+0.26\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 5.8501ms 1.9781ms 505.5257 Ops/s 513.7287 Ops/s $\color{#d91a1a}-1.60\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.1415ms 4.9127ms 203.5542 Ops/s 209.5485 Ops/s $\color{#d91a1a}-2.86\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.5482ms 0.7371ms 1.3567 KOps/s 1.3880 KOps/s $\color{#d91a1a}-2.25\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.0726ms 0.7095ms 1.4094 KOps/s 1.4313 KOps/s $\color{#d91a1a}-1.53\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.9948ms 4.7746ms 209.4414 Ops/s 215.1377 Ops/s $\color{#d91a1a}-2.65\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.2796ms 0.6014ms 1.6628 KOps/s 1.6818 KOps/s $\color{#d91a1a}-1.13\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7292ms 0.5794ms 1.7260 KOps/s 1.7298 KOps/s $\color{#d91a1a}-0.22\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 4.9661ms 4.7189ms 211.9134 Ops/s 214.4318 Ops/s $\color{#d91a1a}-1.17\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7421ms 0.5939ms 1.6838 KOps/s 1.6979 KOps/s $\color{#d91a1a}-0.84\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7003ms 0.5701ms 1.7539 KOps/s 1.7633 KOps/s $\color{#d91a1a}-0.53\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.0671ms 4.8928ms 204.3833 Ops/s 208.7025 Ops/s $\color{#d91a1a}-2.07\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.3948ms 0.7274ms 1.3747 KOps/s 1.3807 KOps/s $\color{#d91a1a}-0.43\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.0728ms 0.7079ms 1.4126 KOps/s 1.4165 KOps/s $\color{#d91a1a}-0.28\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1334s 7.5638ms 132.2095 Ops/s 131.0945 Ops/s $\color{#35bf28}+0.85\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 18.4022ms 15.7765ms 63.3856 Ops/s 64.3731 Ops/s $\color{#d91a1a}-1.53\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.5129ms 1.5195ms 658.1064 Ops/s 749.9060 Ops/s $\textbf{\color{#d91a1a}-12.24\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1207s 7.3251ms 136.5167 Ops/s 104.3602 Ops/s $\textbf{\color{#35bf28}+30.81\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 18.3573ms 15.8298ms 63.1720 Ops/s 64.7863 Ops/s $\color{#d91a1a}-2.49\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.3392ms 1.3269ms 753.6219 Ops/s 741.6394 Ops/s $\color{#35bf28}+1.62\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1217s 9.8153ms 101.8817 Ops/s 136.2396 Ops/s $\textbf{\color{#d91a1a}-25.22\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 18.4225ms 15.8818ms 62.9650 Ops/s 64.2138 Ops/s $\color{#d91a1a}-1.94\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.1185ms 1.6079ms 621.9117 Ops/s 666.8354 Ops/s $\textbf{\color{#d91a1a}-6.74\%}$

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
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
Development

Successfully merging this pull request may close these issues.

2 participants