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 trunc normal device #1931

Merged
merged 12 commits into from
Feb 20, 2024
Merged

[BugFix] fix trunc normal device #1931

merged 12 commits into from
Feb 20, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Feb 19, 2024 •
edited
Loading

No description provided.

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Feb 19, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1931

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

✅ You can merge normally! (4 Unrelated Failures)

As of commit b06e272 with merge base 4fd0343 (image):

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

BROKEN TRUNK - The following job failed but were present on the merge base:

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

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

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Feb 19, 2024
@github-actions GitHub Actions
Copy link

github-actions bot commented Feb 19, 2024 •
edited
Loading

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

Total Benchmarks: 89. Improved: $\large\color{#35bf28}6$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 63.0294ms 61.4200ms 16.2814 Ops/s 15.5257 Ops/s $\color{#35bf28}+4.87\%$
test_sync 46.1573ms 33.6631ms 29.7062 Ops/s 28.9044 Ops/s $\color{#35bf28}+2.77\%$
test_async 62.0696ms 31.3758ms 31.8717 Ops/s 30.0028 Ops/s $\textbf{\color{#35bf28}+6.23\%}$
test_simple 0.4962s 0.4382s 2.2821 Ops/s 2.2795 Ops/s $\color{#35bf28}+0.11\%$
test_transformed 0.6583s 0.5939s 1.6837 Ops/s 1.7009 Ops/s $\color{#d91a1a}-1.01\%$
test_serial 1.4664s 1.4220s 0.7032 Ops/s 0.7002 Ops/s $\color{#35bf28}+0.44\%$
test_parallel 1.3991s 1.3547s 0.7382 Ops/s 0.7355 Ops/s $\color{#35bf28}+0.36\%$
test_step_mdp_speed[True-True-True-True-True] 0.1499ms 21.1825μs 47.2087 KOps/s 46.3786 KOps/s $\color{#35bf28}+1.79\%$
test_step_mdp_speed[True-True-True-True-False] 48.6100μs 13.0288μs 76.7532 KOps/s 76.9760 KOps/s $\color{#d91a1a}-0.29\%$
test_step_mdp_speed[True-True-True-False-True] 52.0900μs 12.5525μs 79.6652 KOps/s 78.9704 KOps/s $\color{#35bf28}+0.88\%$
test_step_mdp_speed[True-True-True-False-False] 46.7070μs 7.6201μs 131.2323 KOps/s 130.8175 KOps/s $\color{#35bf28}+0.32\%$
test_step_mdp_speed[True-True-False-True-True] 52.1170μs 22.7777μs 43.9026 KOps/s 43.9119 KOps/s $\color{#d91a1a}-0.02\%$
test_step_mdp_speed[True-True-False-True-False] 41.6870μs 14.2946μs 69.9562 KOps/s 69.6768 KOps/s $\color{#35bf28}+0.40\%$
test_step_mdp_speed[True-True-False-False-True] 53.9000μs 13.7188μs 72.8928 KOps/s 72.5406 KOps/s $\color{#35bf28}+0.49\%$
test_step_mdp_speed[True-True-False-False-False] 35.8370μs 8.9275μs 112.0135 KOps/s 113.4461 KOps/s $\color{#d91a1a}-1.26\%$
test_step_mdp_speed[True-False-True-True-True] 55.9140μs 23.8856μs 41.8662 KOps/s 41.2832 KOps/s $\color{#35bf28}+1.41\%$
test_step_mdp_speed[True-False-True-True-False] 55.1430μs 15.5864μs 64.1586 KOps/s 63.5489 KOps/s $\color{#35bf28}+0.96\%$
test_step_mdp_speed[True-False-True-False-True] 36.3280μs 13.7547μs 72.7025 KOps/s 72.3571 KOps/s $\color{#35bf28}+0.48\%$
test_step_mdp_speed[True-False-True-False-False] 31.6490μs 8.8553μs 112.9261 KOps/s 113.1233 KOps/s $\color{#d91a1a}-0.17\%$
test_step_mdp_speed[True-False-False-True-True] 53.9900μs 25.0794μs 39.8734 KOps/s 39.4096 KOps/s $\color{#35bf28}+1.18\%$
test_step_mdp_speed[True-False-False-True-False] 62.1850μs 16.8430μs 59.3719 KOps/s 59.0831 KOps/s $\color{#35bf28}+0.49\%$
test_step_mdp_speed[True-False-False-False-True] 42.3390μs 14.8720μs 67.2405 KOps/s 67.0259 KOps/s $\color{#35bf28}+0.32\%$
test_step_mdp_speed[True-False-False-False-False] 41.4370μs 9.9325μs 100.6797 KOps/s 98.9026 KOps/s $\color{#35bf28}+1.80\%$
test_step_mdp_speed[False-True-True-True-True] 56.6860μs 24.1120μs 41.4731 KOps/s 41.5051 KOps/s $\color{#d91a1a}-0.08\%$
test_step_mdp_speed[False-True-True-True-False] 40.3650μs 15.5449μs 64.3296 KOps/s 64.0563 KOps/s $\color{#35bf28}+0.43\%$
test_step_mdp_speed[False-True-True-False-True] 73.3160μs 15.7644μs 63.4341 KOps/s 62.0578 KOps/s $\color{#35bf28}+2.22\%$
test_step_mdp_speed[False-True-True-False-False] 35.9570μs 9.9907μs 100.0931 KOps/s 100.8890 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[False-True-False-True-True] 43.5310μs 25.5684μs 39.1108 KOps/s 38.5318 KOps/s $\color{#35bf28}+1.50\%$
test_step_mdp_speed[False-True-False-True-False] 52.6380μs 16.6928μs 59.9061 KOps/s 59.9889 KOps/s $\color{#d91a1a}-0.14\%$
test_step_mdp_speed[False-True-False-False-True] 51.8360μs 17.1633μs 58.2637 KOps/s 58.3116 KOps/s $\color{#d91a1a}-0.08\%$
test_step_mdp_speed[False-True-False-False-False] 73.9130μs 11.1514μs 89.6752 KOps/s 87.7789 KOps/s $\color{#35bf28}+2.16\%$
test_step_mdp_speed[False-False-True-True-True] 57.6170μs 26.1646μs 38.2196 KOps/s 37.4850 KOps/s $\color{#35bf28}+1.96\%$
test_step_mdp_speed[False-False-True-True-False] 57.2260μs 17.8551μs 56.0065 KOps/s 54.9952 KOps/s $\color{#35bf28}+1.84\%$
test_step_mdp_speed[False-False-True-False-True] 39.1930μs 17.0394μs 58.6873 KOps/s 57.7181 KOps/s $\color{#35bf28}+1.68\%$
test_step_mdp_speed[False-False-True-False-False] 50.2840μs 11.1885μs 89.3777 KOps/s 89.1806 KOps/s $\color{#35bf28}+0.22\%$
test_step_mdp_speed[False-False-False-True-True] 97.7520μs 27.2917μs 36.6412 KOps/s 36.4238 KOps/s $\color{#35bf28}+0.60\%$
test_step_mdp_speed[False-False-False-True-False] 55.9040μs 19.0295μs 52.5500 KOps/s 52.1007 KOps/s $\color{#35bf28}+0.86\%$
test_step_mdp_speed[False-False-False-False-True] 41.5970μs 18.1157μs 55.2007 KOps/s 55.1301 KOps/s $\color{#35bf28}+0.13\%$
test_step_mdp_speed[False-False-False-False-False] 44.4820μs 12.2406μs 81.6954 KOps/s 80.0964 KOps/s $\color{#35bf28}+2.00\%$
test_values[generalized_advantage_estimate-True-True] 11.2993ms 9.2130ms 108.5424 Ops/s 106.8327 Ops/s $\color{#35bf28}+1.60\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.8844ms 33.2123ms 30.1093 Ops/s 30.2511 Ops/s $\color{#d91a1a}-0.47\%$
test_values[td0_return_estimate-False-False] 0.2493ms 0.1657ms 6.0368 KOps/s 6.0121 KOps/s $\color{#35bf28}+0.41\%$
test_values[td1_return_estimate-False-False] 26.4225ms 23.4670ms 42.6131 Ops/s 43.0060 Ops/s $\color{#d91a1a}-0.91\%$
test_values[vec_td1_return_estimate-False-False] 35.0755ms 33.3113ms 30.0198 Ops/s 30.2109 Ops/s $\color{#d91a1a}-0.63\%$
test_values[td_lambda_return_estimate-True-False] 36.8961ms 33.7636ms 29.6177 Ops/s 29.6151 Ops/s $+0.01\%$
test_values[vec_td_lambda_return_estimate-True-False] 34.8115ms 33.2378ms 30.0862 Ops/s 30.1686 Ops/s $\color{#d91a1a}-0.27\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 10.4301ms 8.0809ms 123.7487 Ops/s 121.7987 Ops/s $\color{#35bf28}+1.60\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.2226ms 2.0181ms 495.5269 Ops/s 537.2623 Ops/s $\textbf{\color{#d91a1a}-7.77\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.5168ms 0.3552ms 2.8154 KOps/s 2.8494 KOps/s $\color{#d91a1a}-1.19\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 58.9115ms 46.8913ms 21.3259 Ops/s 24.2957 Ops/s $\textbf{\color{#d91a1a}-12.22\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.5201ms 3.0135ms 331.8430 Ops/s 323.4996 Ops/s $\color{#35bf28}+2.58\%$
test_dqn_speed 66.9691ms 1.4681ms 681.1704 Ops/s 732.1483 Ops/s $\textbf{\color{#d91a1a}-6.96\%}$
test_ddpg_speed 3.1004ms 2.7307ms 366.2078 Ops/s 360.8719 Ops/s $\color{#35bf28}+1.48\%$
test_sac_speed 10.2536ms 8.5064ms 117.5585 Ops/s 117.1482 Ops/s $\color{#35bf28}+0.35\%$
test_redq_speed 14.8151ms 13.1511ms 76.0395 Ops/s 73.3201 Ops/s $\color{#35bf28}+3.71\%$
test_redq_deprec_speed 14.9223ms 13.3131ms 75.1140 Ops/s 74.4352 Ops/s $\color{#35bf28}+0.91\%$
test_td3_speed 9.5270ms 8.5540ms 116.9044 Ops/s 116.8539 Ops/s $\color{#35bf28}+0.04\%$
test_cql_speed 38.8022ms 36.4946ms 27.4013 Ops/s 27.2009 Ops/s $\color{#35bf28}+0.74\%$
test_a2c_speed 8.2666ms 7.2887ms 137.1981 Ops/s 135.9661 Ops/s $\color{#35bf28}+0.91\%$
test_ppo_speed 8.1140ms 7.5533ms 132.3932 Ops/s 129.2184 Ops/s $\color{#35bf28}+2.46\%$
test_reinforce_speed 7.3578ms 6.5223ms 153.3212 Ops/s 152.1992 Ops/s $\color{#35bf28}+0.74\%$
test_iql_speed 33.6213ms 32.5967ms 30.6779 Ops/s 30.1386 Ops/s $\color{#35bf28}+1.79\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.0304ms 2.6141ms 382.5335 Ops/s 349.2292 Ops/s $\textbf{\color{#35bf28}+9.54\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8113ms 0.5132ms 1.9484 KOps/s 1.9412 KOps/s $\color{#35bf28}+0.37\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7310ms 0.4840ms 2.0662 KOps/s 2.0438 KOps/s $\color{#35bf28}+1.09\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.9057ms 2.6068ms 383.6164 Ops/s 349.8181 Ops/s $\textbf{\color{#35bf28}+9.66\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7363ms 0.5037ms 1.9854 KOps/s 1.9720 KOps/s $\color{#35bf28}+0.68\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5769ms 0.4769ms 2.0967 KOps/s 2.0715 KOps/s $\color{#35bf28}+1.22\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 4.0954ms 2.7281ms 366.5587 Ops/s 353.2383 Ops/s $\color{#35bf28}+3.77\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8872ms 0.6300ms 1.5873 KOps/s 1.5832 KOps/s $\color{#35bf28}+0.26\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9124ms 0.6030ms 1.6584 KOps/s 1.4836 KOps/s $\textbf{\color{#35bf28}+11.79\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 2.8688ms 2.6269ms 380.6712 Ops/s 381.0173 Ops/s $\color{#d91a1a}-0.09\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9397ms 0.5135ms 1.9475 KOps/s 1.9517 KOps/s $\color{#d91a1a}-0.21\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7931ms 0.4861ms 2.0572 KOps/s 2.0375 KOps/s $\color{#35bf28}+0.97\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.9139ms 2.5951ms 385.3343 Ops/s 376.6469 Ops/s $\color{#35bf28}+2.31\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8213ms 0.5095ms 1.9628 KOps/s 1.9783 KOps/s $\color{#d91a1a}-0.78\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 1.0882ms 0.5239ms 1.9089 KOps/s 2.0603 KOps/s $\textbf{\color{#d91a1a}-7.35\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 2.9457ms 2.7470ms 364.0395 Ops/s 363.7983 Ops/s $\color{#35bf28}+0.07\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.0422ms 0.6355ms 1.5736 KOps/s 1.5922 KOps/s $\color{#d91a1a}-1.16\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.1129ms 0.6042ms 1.6550 KOps/s 1.6597 KOps/s $\color{#d91a1a}-0.28\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 99.2428ms 7.9046ms 126.5080 Ops/s 109.9215 Ops/s $\textbf{\color{#35bf28}+15.09\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 21.0246ms 13.4258ms 74.4836 Ops/s 75.0604 Ops/s $\color{#d91a1a}-0.77\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 87.0534ms 4.2465ms 235.4875 Ops/s 392.2917 Ops/s $\textbf{\color{#d91a1a}-39.97\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 89.6823ms 7.4774ms 133.7365 Ops/s 108.7862 Ops/s $\textbf{\color{#35bf28}+22.94\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 15.2748ms 13.0443ms 76.6621 Ops/s 75.7647 Ops/s $\color{#35bf28}+1.18\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 4.8090ms 2.5355ms 394.3961 Ops/s 395.9262 Ops/s $\color{#d91a1a}-0.39\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 88.8461ms 9.3965ms 106.4220 Ops/s 106.7243 Ops/s $\color{#d91a1a}-0.28\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 15.3950ms 13.3277ms 75.0316 Ops/s 74.1520 Ops/s $\color{#35bf28}+1.19\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 5.0147ms 2.8078ms 356.1479 Ops/s 361.0250 Ops/s $\color{#d91a1a}-1.35\%$

@github-actions GitHub Actions
Copy link

github-actions bot commented Feb 19, 2024 •
edited
Loading

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

Total Benchmarks: 92. Improved: $\large\color{#35bf28}3$. Worsened: $\large\color{#d91a1a}1$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1191s 0.1182s 8.4567 Ops/s 8.3151 Ops/s $\color{#35bf28}+1.70\%$
test_sync 96.4111ms 96.0275ms 10.4137 Ops/s 10.3843 Ops/s $\color{#35bf28}+0.28\%$
test_async 0.1812s 91.7490ms 10.8993 Ops/s 10.9197 Ops/s $\color{#d91a1a}-0.19\%$
test_single_pixels 0.2098s 0.1466s 6.8229 Ops/s 7.0904 Ops/s $\color{#d91a1a}-3.77\%$
test_sync_pixels 83.0771ms 80.9351ms 12.3556 Ops/s 12.1495 Ops/s $\color{#35bf28}+1.70\%$
test_async_pixels 0.1538s 66.5716ms 15.0214 Ops/s 14.6807 Ops/s $\color{#35bf28}+2.32\%$
test_simple 0.8235s 0.8208s 1.2183 Ops/s 1.1925 Ops/s $\color{#35bf28}+2.16\%$
test_transformed 1.0432s 1.0426s 0.9591 Ops/s 0.9447 Ops/s $\color{#35bf28}+1.53\%$
test_serial 2.4643s 2.4045s 0.4159 Ops/s 0.4096 Ops/s $\color{#35bf28}+1.53\%$
test_parallel 2.1240s 2.0897s 0.4785 Ops/s 0.4780 Ops/s $\color{#35bf28}+0.12\%$
test_step_mdp_speed[True-True-True-True-True] 0.1203ms 33.6020μs 29.7601 KOps/s 30.2409 KOps/s $\color{#d91a1a}-1.59\%$
test_step_mdp_speed[True-True-True-True-False] 0.1997ms 20.4977μs 48.7859 KOps/s 50.0610 KOps/s $\color{#d91a1a}-2.55\%$
test_step_mdp_speed[True-True-True-False-True] 0.1559ms 18.9472μs 52.7782 KOps/s 53.4239 KOps/s $\color{#d91a1a}-1.21\%$
test_step_mdp_speed[True-True-True-False-False] 0.2052ms 11.5602μs 86.5039 KOps/s 88.6336 KOps/s $\color{#d91a1a}-2.40\%$
test_step_mdp_speed[True-True-False-True-True] 0.2031ms 35.9763μs 27.7961 KOps/s 28.4572 KOps/s $\color{#d91a1a}-2.32\%$
test_step_mdp_speed[True-True-False-True-False] 82.8520μs 22.0555μs 45.3401 KOps/s 45.7715 KOps/s $\color{#d91a1a}-0.94\%$
test_step_mdp_speed[True-True-False-False-True] 0.2163ms 20.9734μs 47.6795 KOps/s 48.5081 KOps/s $\color{#d91a1a}-1.71\%$
test_step_mdp_speed[True-True-False-False-False] 36.0610μs 13.5628μs 73.7310 KOps/s 75.8478 KOps/s $\color{#d91a1a}-2.79\%$
test_step_mdp_speed[True-False-True-True-True] 0.1130ms 38.0080μs 26.3103 KOps/s 26.7810 KOps/s $\color{#d91a1a}-1.76\%$
test_step_mdp_speed[True-False-True-True-False] 82.4420μs 24.1480μs 41.4114 KOps/s 42.1906 KOps/s $\color{#d91a1a}-1.85\%$
test_step_mdp_speed[True-False-True-False-True] 39.3700μs 20.9620μs 47.7053 KOps/s 48.7468 KOps/s $\color{#d91a1a}-2.14\%$
test_step_mdp_speed[True-False-True-False-False] 31.3700μs 13.5895μs 73.5863 KOps/s 76.2744 KOps/s $\color{#d91a1a}-3.52\%$
test_step_mdp_speed[True-False-False-True-True] 63.7110μs 39.4318μs 25.3603 KOps/s 25.4567 KOps/s $\color{#d91a1a}-0.38\%$
test_step_mdp_speed[True-False-False-True-False] 45.0900μs 26.0329μs 38.4129 KOps/s 38.5915 KOps/s $\color{#d91a1a}-0.46\%$
test_step_mdp_speed[True-False-False-False-True] 54.7510μs 22.6358μs 44.1778 KOps/s 44.7193 KOps/s $\color{#d91a1a}-1.21\%$
test_step_mdp_speed[True-False-False-False-False] 33.1600μs 15.4026μs 64.9240 KOps/s 66.2524 KOps/s $\color{#d91a1a}-2.01\%$
test_step_mdp_speed[False-True-True-True-True] 56.5510μs 37.7490μs 26.4908 KOps/s 26.8365 KOps/s $\color{#d91a1a}-1.29\%$
test_step_mdp_speed[False-True-True-True-False] 42.3100μs 24.0567μs 41.5685 KOps/s 41.8030 KOps/s $\color{#d91a1a}-0.56\%$
test_step_mdp_speed[False-True-True-False-True] 49.4600μs 25.3687μs 39.4187 KOps/s 41.3182 KOps/s $\color{#d91a1a}-4.60\%$
test_step_mdp_speed[False-True-True-False-False] 81.1410μs 15.2342μs 65.6419 KOps/s 66.2892 KOps/s $\color{#d91a1a}-0.98\%$
test_step_mdp_speed[False-True-False-True-True] 62.8210μs 39.7633μs 25.1488 KOps/s 25.2608 KOps/s $\color{#d91a1a}-0.44\%$
test_step_mdp_speed[False-True-False-True-False] 44.7200μs 26.1914μs 38.1805 KOps/s 38.7980 KOps/s $\color{#d91a1a}-1.59\%$
test_step_mdp_speed[False-True-False-False-True] 58.4810μs 27.1050μs 36.8936 KOps/s 37.5411 KOps/s $\color{#d91a1a}-1.72\%$
test_step_mdp_speed[False-True-False-False-False] 35.7510μs 17.0411μs 58.6815 KOps/s 59.2195 KOps/s $\color{#d91a1a}-0.91\%$
test_step_mdp_speed[False-False-True-True-True] 65.8910μs 41.7861μs 23.9314 KOps/s 24.2569 KOps/s $\color{#d91a1a}-1.34\%$
test_step_mdp_speed[False-False-True-True-False] 0.1089ms 28.0692μs 35.6263 KOps/s 36.2903 KOps/s $\color{#d91a1a}-1.83\%$
test_step_mdp_speed[False-False-True-False-True] 41.8810μs 27.1115μs 36.8847 KOps/s 38.3221 KOps/s $\color{#d91a1a}-3.75\%$
test_step_mdp_speed[False-False-True-False-False] 44.0510μs 17.1361μs 58.3563 KOps/s 58.8772 KOps/s $\color{#d91a1a}-0.88\%$
test_step_mdp_speed[False-False-False-True-True] 60.5110μs 42.5534μs 23.4999 KOps/s 23.5970 KOps/s $\color{#d91a1a}-0.41\%$
test_step_mdp_speed[False-False-False-True-False] 53.3810μs 30.0156μs 33.3161 KOps/s 33.5132 KOps/s $\color{#d91a1a}-0.59\%$
test_step_mdp_speed[False-False-False-False-True] 54.4910μs 28.4131μs 35.1950 KOps/s 35.7501 KOps/s $\color{#d91a1a}-1.55\%$
test_step_mdp_speed[False-False-False-False-False] 38.7900μs 18.8399μs 53.0789 KOps/s 54.0924 KOps/s $\color{#d91a1a}-1.87\%$
test_values[generalized_advantage_estimate-True-True] 25.6832ms 25.0949ms 39.8487 Ops/s 39.9994 Ops/s $\color{#d91a1a}-0.38\%$
test_values[vec_generalized_advantage_estimate-True-True] 84.2677ms 3.2585ms 306.8865 Ops/s 307.7763 Ops/s $\color{#d91a1a}-0.29\%$
test_values[td0_return_estimate-False-False] 0.1063ms 61.7312μs 16.1993 KOps/s 16.1528 KOps/s $\color{#35bf28}+0.29\%$
test_values[td1_return_estimate-False-False] 54.2755ms 53.8006ms 18.5872 Ops/s 18.7434 Ops/s $\color{#d91a1a}-0.83\%$
test_values[vec_td1_return_estimate-False-False] 2.1313ms 1.7707ms 564.7388 Ops/s 566.2772 Ops/s $\color{#d91a1a}-0.27\%$
test_values[td_lambda_return_estimate-True-False] 87.2372ms 85.8924ms 11.6425 Ops/s 11.7556 Ops/s $\color{#d91a1a}-0.96\%$
test_values[vec_td_lambda_return_estimate-True-False] 4.0906ms 1.8089ms 552.8326 Ops/s 530.6521 Ops/s $\color{#35bf28}+4.18\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.2524ms 23.9817ms 41.6985 Ops/s 42.2092 Ops/s $\color{#d91a1a}-1.21\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.9072ms 0.7184ms 1.3920 KOps/s 1.4153 KOps/s $\color{#d91a1a}-1.65\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.8018ms 0.6569ms 1.5223 KOps/s 1.5246 KOps/s $\color{#d91a1a}-0.15\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.6173ms 1.4636ms 683.2384 Ops/s 683.7703 Ops/s $\color{#d91a1a}-0.08\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.9637ms 0.6816ms 1.4671 KOps/s 1.4850 KOps/s $\color{#d91a1a}-1.20\%$
test_dqn_speed 8.6744ms 1.4283ms 700.1112 Ops/s 684.0549 Ops/s $\color{#35bf28}+2.35\%$
test_ddpg_speed 3.6277ms 2.6967ms 370.8193 Ops/s 358.4651 Ops/s $\color{#35bf28}+3.45\%$
test_sac_speed 8.9679ms 8.4679ms 118.0929 Ops/s 116.3123 Ops/s $\color{#35bf28}+1.53\%$
test_redq_speed 13.7446ms 10.7767ms 92.7926 Ops/s 92.2058 Ops/s $\color{#35bf28}+0.64\%$
test_redq_deprec_speed 12.3056ms 11.8404ms 84.4563 Ops/s 85.1586 Ops/s $\color{#d91a1a}-0.82\%$
test_td3_speed 8.7097ms 8.5481ms 116.9851 Ops/s 114.2888 Ops/s $\color{#35bf28}+2.36\%$
test_cql_speed 0.1086s 28.0811ms 35.6111 Ops/s 37.8925 Ops/s $\textbf{\color{#d91a1a}-6.02\%}$
test_a2c_speed 5.4415ms 5.1901ms 192.6740 Ops/s 179.2287 Ops/s $\textbf{\color{#35bf28}+7.50\%}$
test_ppo_speed 5.8476ms 5.5654ms 179.6823 Ops/s 169.0917 Ops/s $\textbf{\color{#35bf28}+6.26\%}$
test_reinforce_speed 4.5728ms 4.1842ms 238.9949 Ops/s 221.4038 Ops/s $\textbf{\color{#35bf28}+7.95\%}$
test_iql_speed 20.1495ms 19.4176ms 51.4998 Ops/s 49.5650 Ops/s $\color{#35bf28}+3.90\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.7195ms 3.5714ms 280.0024 Ops/s 283.3577 Ops/s $\color{#d91a1a}-1.18\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7631ms 0.5684ms 1.7595 KOps/s 1.7562 KOps/s $\color{#35bf28}+0.19\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7020ms 0.5447ms 1.8358 KOps/s 1.8487 KOps/s $\color{#d91a1a}-0.70\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.8708ms 3.6179ms 276.4019 Ops/s 277.2646 Ops/s $\color{#d91a1a}-0.31\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7350ms 0.5700ms 1.7545 KOps/s 1.7960 KOps/s $\color{#d91a1a}-2.31\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6995ms 0.5443ms 1.8373 KOps/s 1.8791 KOps/s $\color{#d91a1a}-2.22\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 3.9106ms 3.7063ms 269.8080 Ops/s 270.2111 Ops/s $\color{#d91a1a}-0.15\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 95.6087ms 0.7768ms 1.2873 KOps/s 1.2873 KOps/s $+0.00\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8397ms 0.6684ms 1.4962 KOps/s 1.5043 KOps/s $\color{#d91a1a}-0.54\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 3.7716ms 3.5855ms 278.8973 Ops/s 279.9069 Ops/s $\color{#d91a1a}-0.36\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7533ms 0.5789ms 1.7273 KOps/s 1.7717 KOps/s $\color{#d91a1a}-2.50\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8187ms 0.5477ms 1.8260 KOps/s 1.8489 KOps/s $\color{#d91a1a}-1.24\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 3.9979ms 3.6597ms 273.2439 Ops/s 276.7263 Ops/s $\color{#d91a1a}-1.26\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7593ms 0.5621ms 1.7790 KOps/s 1.7949 KOps/s $\color{#d91a1a}-0.88\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 94.7121ms 0.6435ms 1.5541 KOps/s 1.5769 KOps/s $\color{#d91a1a}-1.45\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 4.0575ms 3.7246ms 268.4841 Ops/s 269.8920 Ops/s $\color{#d91a1a}-0.52\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8950ms 0.6982ms 1.4323 KOps/s 1.4407 KOps/s $\color{#d91a1a}-0.58\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8581ms 0.6704ms 1.4916 KOps/s 1.5058 KOps/s $\color{#d91a1a}-0.95\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1070s 11.3400ms 88.1837 Ops/s 88.2186 Ops/s $\color{#d91a1a}-0.04\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 18.9478ms 16.5907ms 60.2746 Ops/s 62.1479 Ops/s $\color{#d91a1a}-3.01\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.6293ms 3.1807ms 314.3958 Ops/s 314.9632 Ops/s $\color{#d91a1a}-0.18\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1070s 11.3815ms 87.8618 Ops/s 88.8712 Ops/s $\color{#d91a1a}-1.14\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 19.0701ms 16.6220ms 60.1612 Ops/s 62.2503 Ops/s $\color{#d91a1a}-3.36\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.9674ms 3.1832ms 314.1468 Ops/s 321.6878 Ops/s $\color{#d91a1a}-2.34\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1042s 9.6885ms 103.2147 Ops/s 103.3308 Ops/s $\color{#d91a1a}-0.11\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 0.1139s 18.8000ms 53.1914 Ops/s 54.5781 Ops/s $\color{#d91a1a}-2.54\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 8.4211ms 3.4546ms 289.4686 Ops/s 294.1030 Ops/s $\color{#d91a1a}-1.58\%$

@vmoens vmoens added bug Something isn't working Suitable for minor Suitable to be integrated in minor release (no new feature) labels Feb 20, 2024
@vmoens
:wq
b06e272 
XxMerge remote-tracking branch 'origin/main' into fix-trunc-normal-tests
@vmoens vmoens merged commit 78b31a9 into main Feb 20, 2024
53 of 57 checks passed
@vmoens vmoens deleted the fix-trunc-normal-tests branch February 20, 2024 16:27
vmoens added a commit that referenced this pull request Feb 28, 2024
@vmoens
[BugFix] fix trunc normal device (#1931)
8b3f77b
@vmoens vmoens mentioned this pull request Feb 28, 2024
Closed
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. Suitable for minor Suitable to be integrated in minor release (no new feature)
Projects
None yet
Milestone
No milestone
Development

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