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

[Feature] TensorDictMap Query module #2305

Open
wants to merge 4 commits into
base: gh/vmoens/2/base
Choose a base branch
from

Conversation

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Jul 22, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2305

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

❌ 3 New Failures, 2 Cancelled Jobs, 15 Unrelated Failures

As of commit 71ceadb with merge base 35a1c5b (image):

NEW FAILURES - The following jobs have failed:

CANCELLED JOBS - The following jobs were cancelled. Please retry:

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

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 Jul 22, 2024
@vmoens vmoens mentioned this pull request Jul 22, 2024
@vmoens vmoens added the enhancement New feature or request label Jul 22, 2024
[ghstack-poisoned]
Copy link

github-actions bot commented Jul 23, 2024

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 60.3390ms 58.8772ms 16.9845 Ops/s 17.1476 Ops/s $\color{#d91a1a}-0.95\%$
test_sync 33.1117ms 31.4462ms 31.8003 Ops/s 26.1018 Ops/s $\textbf{\color{#35bf28}+21.83\%}$
test_async 87.8023ms 30.4040ms 32.8904 Ops/s 33.2748 Ops/s $\color{#d91a1a}-1.16\%$
test_simple 0.4767s 0.4077s 2.4526 Ops/s 2.4249 Ops/s $\color{#35bf28}+1.14\%$
test_transformed 0.6258s 0.5651s 1.7697 Ops/s 1.7534 Ops/s $\color{#35bf28}+0.93\%$
test_serial 1.3072s 1.2498s 0.8001 Ops/s 0.7864 Ops/s $\color{#35bf28}+1.75\%$
test_parallel 1.1643s 1.0967s 0.9118 Ops/s 0.9113 Ops/s $\color{#35bf28}+0.06\%$
test_step_mdp_speed[True-True-True-True-True] 0.2745ms 24.1854μs 41.3472 KOps/s 41.5845 KOps/s $\color{#d91a1a}-0.57\%$
test_step_mdp_speed[True-True-True-True-False] 62.4960μs 14.2443μs 70.2034 KOps/s 70.7626 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[True-True-True-False-True] 40.9260μs 14.1668μs 70.5876 KOps/s 71.7021 KOps/s $\color{#d91a1a}-1.55\%$
test_step_mdp_speed[True-True-True-False-False] 52.4680μs 8.1066μs 123.3570 KOps/s 121.7608 KOps/s $\color{#35bf28}+1.31\%$
test_step_mdp_speed[True-True-False-True-True] 61.1650μs 25.8320μs 38.7117 KOps/s 39.0522 KOps/s $\color{#d91a1a}-0.87\%$
test_step_mdp_speed[True-True-False-True-False] 40.2950μs 15.5569μs 64.2801 KOps/s 64.4445 KOps/s $\color{#d91a1a}-0.26\%$
test_step_mdp_speed[True-True-False-False-True] 48.1800μs 15.6001μs 64.1020 KOps/s 64.9707 KOps/s $\color{#d91a1a}-1.34\%$
test_step_mdp_speed[True-True-False-False-False] 35.6870μs 9.5891μs 104.2853 KOps/s 104.9154 KOps/s $\color{#d91a1a}-0.60\%$
test_step_mdp_speed[True-False-True-True-True] 69.1090μs 27.1902μs 36.7779 KOps/s 36.6058 KOps/s $\color{#35bf28}+0.47\%$
test_step_mdp_speed[True-False-True-True-False] 38.8330μs 17.0893μs 58.5162 KOps/s 59.0397 KOps/s $\color{#d91a1a}-0.89\%$
test_step_mdp_speed[True-False-True-False-True] 50.8350μs 15.3384μs 65.1957 KOps/s 64.3123 KOps/s $\color{#35bf28}+1.37\%$
test_step_mdp_speed[True-False-True-False-False] 32.3600μs 9.6158μs 103.9955 KOps/s 103.7676 KOps/s $\color{#35bf28}+0.22\%$
test_step_mdp_speed[True-False-False-True-True] 70.5410μs 28.3290μs 35.2995 KOps/s 34.8286 KOps/s $\color{#35bf28}+1.35\%$
test_step_mdp_speed[True-False-False-True-False] 49.5020μs 18.3262μs 54.5668 KOps/s 54.1123 KOps/s $\color{#35bf28}+0.84\%$
test_step_mdp_speed[True-False-False-False-True] 56.2850μs 16.8429μs 59.3722 KOps/s 59.8452 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[True-False-False-False-False] 42.4790μs 10.9027μs 91.7204 KOps/s 91.6066 KOps/s $\color{#35bf28}+0.12\%$
test_step_mdp_speed[False-True-True-True-True] 61.1050μs 27.4096μs 36.4835 KOps/s 36.5433 KOps/s $\color{#d91a1a}-0.16\%$
test_step_mdp_speed[False-True-True-True-False] 53.1590μs 17.0427μs 58.6760 KOps/s 58.8548 KOps/s $\color{#d91a1a}-0.30\%$
test_step_mdp_speed[False-True-True-False-True] 57.2370μs 17.8292μs 56.0877 KOps/s 56.0744 KOps/s $\color{#35bf28}+0.02\%$
test_step_mdp_speed[False-True-True-False-False] 33.1220μs 10.8499μs 92.1664 KOps/s 92.2295 KOps/s $\color{#d91a1a}-0.07\%$
test_step_mdp_speed[False-True-False-True-True] 78.7270μs 28.6236μs 34.9362 KOps/s 34.9822 KOps/s $\color{#d91a1a}-0.13\%$
test_step_mdp_speed[False-True-False-True-False] 43.4510μs 18.3026μs 54.6370 KOps/s 54.3562 KOps/s $\color{#35bf28}+0.52\%$
test_step_mdp_speed[False-True-False-False-True] 83.0740μs 19.2396μs 51.9763 KOps/s 52.0869 KOps/s $\color{#d91a1a}-0.21\%$
test_step_mdp_speed[False-True-False-False-False] 35.9670μs 12.2043μs 81.9385 KOps/s 81.5411 KOps/s $\color{#35bf28}+0.49\%$
test_step_mdp_speed[False-False-True-True-True] 76.8009ms 33.1598μs 30.1570 KOps/s 33.2194 KOps/s $\textbf{\color{#d91a1a}-9.22\%}$
test_step_mdp_speed[False-False-True-True-False] 64.7900μs 19.5214μs 51.2257 KOps/s 50.2446 KOps/s $\color{#35bf28}+1.95\%$
test_step_mdp_speed[False-False-True-False-True] 58.7490μs 19.2291μs 52.0046 KOps/s 52.4927 KOps/s $\color{#d91a1a}-0.93\%$
test_step_mdp_speed[False-False-True-False-False] 48.1200μs 11.9912μs 83.3948 KOps/s 82.3527 KOps/s $\color{#35bf28}+1.27\%$
test_step_mdp_speed[False-False-False-True-True] 73.3970μs 31.1973μs 32.0540 KOps/s 32.0798 KOps/s $\color{#d91a1a}-0.08\%$
test_step_mdp_speed[False-False-False-True-False] 55.1630μs 20.9363μs 47.7639 KOps/s 47.5251 KOps/s $\color{#35bf28}+0.50\%$
test_step_mdp_speed[False-False-False-False-True] 55.1130μs 20.0751μs 49.8130 KOps/s 49.7161 KOps/s $\color{#35bf28}+0.19\%$
test_step_mdp_speed[False-False-False-False-False] 53.1590μs 13.4632μs 74.2763 KOps/s 74.9468 KOps/s $\color{#d91a1a}-0.89\%$
test_values[generalized_advantage_estimate-True-True] 11.3018ms 9.2905ms 107.6365 Ops/s 105.7400 Ops/s $\color{#35bf28}+1.79\%$
test_values[vec_generalized_advantage_estimate-True-True] 38.0646ms 35.9271ms 27.8341 Ops/s 30.2165 Ops/s $\textbf{\color{#d91a1a}-7.88\%}$
test_values[td0_return_estimate-False-False] 0.2475ms 0.1661ms 6.0190 KOps/s 5.9111 KOps/s $\color{#35bf28}+1.83\%$
test_values[td1_return_estimate-False-False] 26.5610ms 23.1713ms 43.1568 Ops/s 42.2428 Ops/s $\color{#35bf28}+2.16\%$
test_values[vec_td1_return_estimate-False-False] 37.0795ms 36.0380ms 27.7485 Ops/s 30.1738 Ops/s $\textbf{\color{#d91a1a}-8.04\%}$
test_values[td_lambda_return_estimate-True-False] 36.8981ms 33.4890ms 29.8606 Ops/s 29.3167 Ops/s $\color{#35bf28}+1.86\%$
test_values[vec_td_lambda_return_estimate-True-False] 38.0535ms 36.0679ms 27.7255 Ops/s 30.3372 Ops/s $\textbf{\color{#d91a1a}-8.61\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 10.0249ms 8.1272ms 123.0439 Ops/s 120.9742 Ops/s $\color{#35bf28}+1.71\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.4673ms 1.9706ms 507.4694 Ops/s 509.3678 Ops/s $\color{#d91a1a}-0.37\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6305ms 0.3559ms 2.8099 KOps/s 2.8105 KOps/s $\color{#d91a1a}-0.02\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 47.3114ms 45.1790ms 22.1342 Ops/s 25.1755 Ops/s $\textbf{\color{#d91a1a}-12.08\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.1962ms 3.0323ms 329.7830 Ops/s 330.0103 Ops/s $\color{#d91a1a}-0.07\%$
test_dqn_speed 1.7070ms 1.2856ms 777.8331 Ops/s 755.7053 Ops/s $\color{#35bf28}+2.93\%$
test_ddpg_speed 2.9843ms 2.6909ms 371.6169 Ops/s 370.5336 Ops/s $\color{#35bf28}+0.29\%$
test_sac_speed 9.2406ms 7.9107ms 126.4114 Ops/s 126.5855 Ops/s $\color{#d91a1a}-0.14\%$
test_redq_speed 13.7972ms 12.5601ms 79.6172 Ops/s 79.9664 Ops/s $\color{#d91a1a}-0.44\%$
test_redq_deprec_speed 14.5390ms 12.4988ms 80.0079 Ops/s 79.5954 Ops/s $\color{#35bf28}+0.52\%$
test_td3_speed 8.5039ms 7.8213ms 127.8560 Ops/s 128.0770 Ops/s $\color{#d91a1a}-0.17\%$
test_cql_speed 38.6844ms 36.2754ms 27.5669 Ops/s 28.3872 Ops/s $\color{#d91a1a}-2.89\%$
test_a2c_speed 7.9892ms 7.2038ms 138.8164 Ops/s 138.4840 Ops/s $\color{#35bf28}+0.24\%$
test_ppo_speed 8.6718ms 7.5014ms 133.3085 Ops/s 133.4895 Ops/s $\color{#d91a1a}-0.14\%$
test_reinforce_speed 7.1409ms 6.3876ms 156.5531 Ops/s 156.6303 Ops/s $\color{#d91a1a}-0.05\%$
test_iql_speed 33.4514ms 31.6729ms 31.5727 Ops/s 31.5259 Ops/s $\color{#35bf28}+0.15\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.4256ms 4.7694ms 209.6693 Ops/s 211.9973 Ops/s $\color{#d91a1a}-1.10\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5622ms 0.4677ms 2.1383 KOps/s 2.0984 KOps/s $\color{#35bf28}+1.90\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6079ms 0.4449ms 2.2475 KOps/s 2.2271 KOps/s $\color{#35bf28}+0.92\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.9323ms 4.7051ms 212.5345 Ops/s 215.6771 Ops/s $\color{#d91a1a}-1.46\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7574ms 0.4674ms 2.1393 KOps/s 1.8186 KOps/s $\textbf{\color{#35bf28}+17.64\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7083ms 0.4443ms 2.2509 KOps/s 2.2501 KOps/s $\color{#35bf28}+0.03\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.2063ms 1.6809ms 594.9209 Ops/s 598.1273 Ops/s $\color{#d91a1a}-0.54\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.1534ms 1.5920ms 628.1406 Ops/s 630.3179 Ops/s $\color{#d91a1a}-0.35\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.0713ms 4.9076ms 203.7656 Ops/s 207.0743 Ops/s $\color{#d91a1a}-1.60\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.4601ms 0.6014ms 1.6627 KOps/s 1.6356 KOps/s $\color{#35bf28}+1.66\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9157ms 0.5772ms 1.7326 KOps/s 1.6910 KOps/s $\color{#35bf28}+2.46\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.9678ms 4.7559ms 210.2659 Ops/s 211.8134 Ops/s $\color{#d91a1a}-0.73\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5497ms 0.4710ms 2.1233 KOps/s 2.1037 KOps/s $\color{#35bf28}+0.93\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 7.0733ms 0.4562ms 2.1921 KOps/s 2.2185 KOps/s $\color{#d91a1a}-1.19\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.0053ms 4.6571ms 214.7267 Ops/s 215.1169 Ops/s $\color{#d91a1a}-0.18\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.2015ms 0.4649ms 2.1510 KOps/s 2.1463 KOps/s $\color{#35bf28}+0.22\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6457ms 0.4458ms 2.2430 KOps/s 2.2570 KOps/s $\color{#d91a1a}-0.62\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.6016ms 4.8703ms 205.3254 Ops/s 203.1853 Ops/s $\color{#35bf28}+1.05\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8191ms 0.6027ms 1.6592 KOps/s 1.6421 KOps/s $\color{#35bf28}+1.04\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9067ms 0.5814ms 1.7200 KOps/s 1.7204 KOps/s $\color{#d91a1a}-0.02\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1258s 6.1724ms 162.0103 Ops/s 160.8139 Ops/s $\color{#35bf28}+0.74\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 17.1105ms 13.0297ms 76.7479 Ops/s 79.1991 Ops/s $\color{#d91a1a}-3.09\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 97.1946ms 3.0436ms 328.5558 Ops/s 877.2687 Ops/s $\textbf{\color{#d91a1a}-62.55\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1005s 5.6316ms 177.5707 Ops/s 172.3732 Ops/s $\color{#35bf28}+3.02\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 16.6682ms 12.9734ms 77.0808 Ops/s 79.0539 Ops/s $\color{#d91a1a}-2.50\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.6050ms 1.0570ms 946.1047 Ops/s 905.6743 Ops/s $\color{#35bf28}+4.46\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1043s 5.8347ms 171.3879 Ops/s 123.5779 Ops/s $\textbf{\color{#35bf28}+38.69\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 17.1684ms 13.1776ms 75.8865 Ops/s 78.1330 Ops/s $\color{#d91a1a}-2.88\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 5.1562ms 1.3002ms 769.1188 Ops/s 770.3753 Ops/s $\color{#d91a1a}-0.16\%$

Copy link

github-actions bot commented Jul 23, 2024

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

Total Benchmarks: 94. Improved: $\large\color{#35bf28}1$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1071s 0.1066s 9.3767 Ops/s 9.5617 Ops/s $\color{#d91a1a}-1.93\%$
test_sync 96.4532ms 93.5879ms 10.6851 Ops/s 10.6277 Ops/s $\color{#35bf28}+0.54\%$
test_async 0.1777s 87.1170ms 11.4788 Ops/s 11.5328 Ops/s $\color{#d91a1a}-0.47\%$
test_single_pixels 0.1186s 0.1181s 8.4678 Ops/s 8.6487 Ops/s $\color{#d91a1a}-2.09\%$
test_sync_pixels 84.4146ms 77.0640ms 12.9762 Ops/s 13.0832 Ops/s $\color{#d91a1a}-0.82\%$
test_async_pixels 0.1410s 71.4899ms 13.9880 Ops/s 14.1742 Ops/s $\color{#d91a1a}-1.31\%$
test_simple 0.7629s 0.7624s 1.3117 Ops/s 1.3138 Ops/s $\color{#d91a1a}-0.16\%$
test_transformed 1.0852s 1.0134s 0.9867 Ops/s 1.0165 Ops/s $\color{#d91a1a}-2.93\%$
test_serial 2.2708s 2.2030s 0.4539 Ops/s 0.4649 Ops/s $\color{#d91a1a}-2.35\%$
test_parallel 1.9578s 1.8898s 0.5292 Ops/s 0.5279 Ops/s $\color{#35bf28}+0.24\%$
test_step_mdp_speed[True-True-True-True-True] 88.4520μs 36.1809μs 27.6389 KOps/s 27.9812 KOps/s $\color{#d91a1a}-1.22\%$
test_step_mdp_speed[True-True-True-True-False] 41.5620μs 21.0048μs 47.6082 KOps/s 48.2128 KOps/s $\color{#d91a1a}-1.25\%$
test_step_mdp_speed[True-True-True-False-True] 40.7610μs 20.4062μs 49.0048 KOps/s 50.4436 KOps/s $\color{#d91a1a}-2.85\%$
test_step_mdp_speed[True-True-True-False-False] 36.8110μs 11.8874μs 84.1226 KOps/s 86.1193 KOps/s $\color{#d91a1a}-2.32\%$
test_step_mdp_speed[True-True-False-True-True] 56.0910μs 38.4784μs 25.9886 KOps/s 26.4561 KOps/s $\color{#d91a1a}-1.77\%$
test_step_mdp_speed[True-True-False-True-False] 42.7510μs 22.8505μs 43.7627 KOps/s 43.8856 KOps/s $\color{#d91a1a}-0.28\%$
test_step_mdp_speed[True-True-False-False-True] 44.1310μs 22.4502μs 44.5429 KOps/s 45.4996 KOps/s $\color{#d91a1a}-2.10\%$
test_step_mdp_speed[True-True-False-False-False] 46.5300μs 13.9964μs 71.4469 KOps/s 72.5343 KOps/s $\color{#d91a1a}-1.50\%$
test_step_mdp_speed[True-False-True-True-True] 58.0010μs 39.6216μs 25.2387 KOps/s 25.1996 KOps/s $\color{#35bf28}+0.16\%$
test_step_mdp_speed[True-False-True-True-False] 48.3900μs 25.1329μs 39.7885 KOps/s 40.4341 KOps/s $\color{#d91a1a}-1.60\%$
test_step_mdp_speed[True-False-True-False-True] 42.0420μs 22.5517μs 44.3426 KOps/s 45.7616 KOps/s $\color{#d91a1a}-3.10\%$
test_step_mdp_speed[True-False-True-False-False] 30.9110μs 14.0210μs 71.3217 KOps/s 72.5758 KOps/s $\color{#d91a1a}-1.73\%$
test_step_mdp_speed[True-False-False-True-True] 62.1510μs 41.7485μs 23.9529 KOps/s 23.7050 KOps/s $\color{#35bf28}+1.05\%$
test_step_mdp_speed[True-False-False-True-False] 0.1037ms 27.1505μs 36.8317 KOps/s 36.8002 KOps/s $\color{#35bf28}+0.09\%$
test_step_mdp_speed[True-False-False-False-True] 49.3810μs 24.6780μs 40.5219 KOps/s 40.7350 KOps/s $\color{#d91a1a}-0.52\%$
test_step_mdp_speed[True-False-False-False-False] 31.6210μs 16.3403μs 61.1984 KOps/s 63.5121 KOps/s $\color{#d91a1a}-3.64\%$
test_step_mdp_speed[False-True-True-True-True] 59.8510μs 39.7565μs 25.1531 KOps/s 25.1312 KOps/s $\color{#35bf28}+0.09\%$
test_step_mdp_speed[False-True-True-True-False] 52.7220μs 25.2114μs 39.6646 KOps/s 40.4660 KOps/s $\color{#d91a1a}-1.98\%$
test_step_mdp_speed[False-True-True-False-True] 51.4210μs 26.7805μs 37.3406 KOps/s 38.1062 KOps/s $\color{#d91a1a}-2.01\%$
test_step_mdp_speed[False-True-True-False-False] 38.7010μs 15.6714μs 63.8106 KOps/s 63.3442 KOps/s $\color{#35bf28}+0.74\%$
test_step_mdp_speed[False-True-False-True-True] 64.8210μs 41.8101μs 23.9177 KOps/s 24.1666 KOps/s $\color{#d91a1a}-1.03\%$
test_step_mdp_speed[False-True-False-True-False] 48.5810μs 27.0982μs 36.9028 KOps/s 37.2105 KOps/s $\color{#d91a1a}-0.83\%$
test_step_mdp_speed[False-True-False-False-True] 45.3820μs 28.3708μs 35.2475 KOps/s 35.1085 KOps/s $\color{#35bf28}+0.40\%$
test_step_mdp_speed[False-True-False-False-False] 33.5910μs 17.9257μs 55.7858 KOps/s 56.6592 KOps/s $\color{#d91a1a}-1.54\%$
test_step_mdp_speed[False-False-True-True-True] 4.0772ms 44.8606μs 22.2913 KOps/s 22.4434 KOps/s $\color{#d91a1a}-0.68\%$
test_step_mdp_speed[False-False-True-True-False] 55.6610μs 29.9094μs 33.4343 KOps/s 34.0010 KOps/s $\color{#d91a1a}-1.67\%$
test_step_mdp_speed[False-False-True-False-True] 48.5010μs 28.8069μs 34.7140 KOps/s 34.8774 KOps/s $\color{#d91a1a}-0.47\%$
test_step_mdp_speed[False-False-True-False-False] 33.4900μs 18.0164μs 55.5049 KOps/s 55.5189 KOps/s $\color{#d91a1a}-0.03\%$
test_step_mdp_speed[False-False-False-True-True] 67.1420μs 46.0340μs 21.7231 KOps/s 21.7392 KOps/s $\color{#d91a1a}-0.07\%$
test_step_mdp_speed[False-False-False-True-False] 49.4010μs 31.5076μs 31.7383 KOps/s 32.2425 KOps/s $\color{#d91a1a}-1.56\%$
test_step_mdp_speed[False-False-False-False-True] 55.7310μs 30.2047μs 33.1074 KOps/s 32.8030 KOps/s $\color{#35bf28}+0.93\%$
test_step_mdp_speed[False-False-False-False-False] 40.1910μs 19.8649μs 50.3400 KOps/s 50.1448 KOps/s $\color{#35bf28}+0.39\%$
test_values[generalized_advantage_estimate-True-True] 25.1960ms 24.5312ms 40.7644 Ops/s 41.5326 Ops/s $\color{#d91a1a}-1.85\%$
test_values[vec_generalized_advantage_estimate-True-True] 91.2298ms 2.7250ms 366.9720 Ops/s 372.2005 Ops/s $\color{#d91a1a}-1.40\%$
test_values[td0_return_estimate-False-False] 93.4220μs 66.7968μs 14.9708 KOps/s 15.5316 KOps/s $\color{#d91a1a}-3.61\%$
test_values[td1_return_estimate-False-False] 55.4362ms 55.1375ms 18.1365 Ops/s 18.7280 Ops/s $\color{#d91a1a}-3.16\%$
test_values[vec_td1_return_estimate-False-False] 1.3797ms 1.0877ms 919.3320 Ops/s 928.0694 Ops/s $\color{#d91a1a}-0.94\%$
test_values[td_lambda_return_estimate-True-False] 87.6923ms 87.2108ms 11.4665 Ops/s 11.8196 Ops/s $\color{#d91a1a}-2.99\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.4180ms 1.0858ms 920.9450 Ops/s 930.7556 Ops/s $\color{#d91a1a}-1.05\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.5721ms 24.2162ms 41.2948 Ops/s 42.4348 Ops/s $\color{#d91a1a}-2.69\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.9755ms 0.7237ms 1.3819 KOps/s 1.4036 KOps/s $\color{#d91a1a}-1.55\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7562ms 0.6726ms 1.4867 KOps/s 1.5104 KOps/s $\color{#d91a1a}-1.57\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5301ms 1.4711ms 679.7564 Ops/s 684.4602 Ops/s $\color{#d91a1a}-0.69\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7485ms 0.6884ms 1.4527 KOps/s 1.4794 KOps/s $\color{#d91a1a}-1.81\%$
test_dqn_speed 7.3588ms 1.3551ms 737.9270 Ops/s 758.3242 Ops/s $\color{#d91a1a}-2.69\%$
test_ddpg_speed 3.0097ms 2.7624ms 362.0000 Ops/s 371.2379 Ops/s $\color{#d91a1a}-2.49\%$
test_sac_speed 8.2130ms 7.9621ms 125.5953 Ops/s 127.6585 Ops/s $\color{#d91a1a}-1.62\%$
test_redq_speed 12.3632ms 10.1069ms 98.9423 Ops/s 99.9850 Ops/s $\color{#d91a1a}-1.04\%$
test_redq_deprec_speed 11.1841ms 10.9304ms 91.4880 Ops/s 90.2813 Ops/s $\color{#35bf28}+1.34\%$
test_td3_speed 7.9930ms 7.9327ms 126.0602 Ops/s 129.1294 Ops/s $\color{#d91a1a}-2.38\%$
test_cql_speed 26.4267ms 25.2588ms 39.5902 Ops/s 40.2291 Ops/s $\color{#d91a1a}-1.59\%$
test_a2c_speed 6.2464ms 5.5631ms 179.7572 Ops/s 181.4860 Ops/s $\color{#d91a1a}-0.95\%$
test_ppo_speed 6.1600ms 5.9191ms 168.9446 Ops/s 170.5873 Ops/s $\color{#d91a1a}-0.96\%$
test_reinforce_speed 4.6704ms 4.4137ms 226.5663 Ops/s 221.2425 Ops/s $\color{#35bf28}+2.41\%$
test_iql_speed 19.2470ms 18.9242ms 52.8425 Ops/s 51.6947 Ops/s $\color{#35bf28}+2.22\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.8040ms 6.7254ms 148.6894 Ops/s 153.4119 Ops/s $\color{#d91a1a}-3.08\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.9624ms 0.5236ms 1.9097 KOps/s 1.9568 KOps/s $\color{#d91a1a}-2.40\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6517ms 0.4984ms 2.0063 KOps/s 2.0305 KOps/s $\color{#d91a1a}-1.19\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.8933ms 6.6243ms 150.9594 Ops/s 156.5894 Ops/s $\color{#d91a1a}-3.60\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.1816ms 0.5093ms 1.9637 KOps/s 1.9578 KOps/s $\color{#35bf28}+0.30\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6788ms 0.4921ms 2.0321 KOps/s 2.0526 KOps/s $\color{#d91a1a}-1.00\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.1540ms 1.9794ms 505.2015 Ops/s 517.9004 Ops/s $\color{#d91a1a}-2.45\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.0445ms 1.8940ms 527.9914 Ops/s 544.1847 Ops/s $\color{#d91a1a}-2.98\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.8838ms 6.8011ms 147.0351 Ops/s 150.3203 Ops/s $\color{#d91a1a}-2.19\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0840ms 0.6636ms 1.5070 KOps/s 1.5159 KOps/s $\color{#d91a1a}-0.59\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8450ms 0.6533ms 1.5308 KOps/s 1.5541 KOps/s $\color{#d91a1a}-1.50\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.8327ms 6.7014ms 149.2220 Ops/s 153.4463 Ops/s $\color{#d91a1a}-2.75\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.0194ms 0.5167ms 1.9355 KOps/s 1.9556 KOps/s $\color{#d91a1a}-1.03\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6791ms 0.4968ms 2.0131 KOps/s 2.0228 KOps/s $\color{#d91a1a}-0.48\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.8352ms 6.6009ms 151.4947 Ops/s 154.5941 Ops/s $\color{#d91a1a}-2.00\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.1240s 0.6784ms 1.4740 KOps/s 1.9803 KOps/s $\textbf{\color{#d91a1a}-25.57\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6917ms 0.4897ms 2.0419 KOps/s 2.0485 KOps/s $\color{#d91a1a}-0.32\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.9705ms 6.8396ms 146.2081 Ops/s 151.1932 Ops/s $\color{#d91a1a}-3.30\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8821ms 0.6694ms 1.4939 KOps/s 1.2081 KOps/s $\textbf{\color{#35bf28}+23.65\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 4.5890ms 0.6536ms 1.5300 KOps/s 1.5721 KOps/s $\color{#d91a1a}-2.68\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1295s 7.6142ms 131.3343 Ops/s 130.5077 Ops/s $\color{#35bf28}+0.63\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 18.8942ms 16.4929ms 60.6320 Ops/s 63.5751 Ops/s $\color{#d91a1a}-4.63\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.2653ms 1.2545ms 797.1137 Ops/s 763.8964 Ops/s $\color{#35bf28}+4.35\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1249s 7.5492ms 132.4636 Ops/s 133.2743 Ops/s $\color{#d91a1a}-0.61\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.1375s 18.7652ms 53.2901 Ops/s 63.6500 Ops/s $\textbf{\color{#d91a1a}-16.28\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.0212ms 1.3431ms 744.5286 Ops/s 797.9400 Ops/s $\textbf{\color{#d91a1a}-6.69\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1246s 7.7569ms 128.9174 Ops/s 128.5718 Ops/s $\color{#35bf28}+0.27\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 18.9507ms 16.5766ms 60.3259 Ops/s 63.3611 Ops/s $\color{#d91a1a}-4.79\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.2493ms 1.5184ms 658.5982 Ops/s 711.3550 Ops/s $\textbf{\color{#d91a1a}-7.42\%}$

[ghstack-poisoned]
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Aug 7, 2024
ghstack-source-id: 9d70a3ea62402ee0619822c87dc9c05d8219101b
Pull Request resolved: #2305
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. enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants