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

init #2322

Merged
merged 3 commits into from
Jul 25, 2024
Merged

init #2322

merged 3 commits into from
Jul 25, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Jul 25, 2024

No description provided.

@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Jul 25, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2322

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

⏳ 2 Pending, 16 Unrelated Failures

As of commit c3b5276 with merge base c6ef080 (image):

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 Jul 25, 2024
@vmoens vmoens added the bug Something isn't working label Jul 25, 2024
@vmoens vmoens merged commit 94abb50 into main Jul 25, 2024
22 of 39 checks passed
@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 91. Improved: $\large\color{#35bf28}1$. Worsened: $\large\color{#d91a1a}8$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 59.5144ms 56.8901ms 17.5778 Ops/s 17.2034 Ops/s $\color{#35bf28}+2.18\%$
test_sync 49.6832ms 33.1638ms 30.1534 Ops/s 31.0780 Ops/s $\color{#d91a1a}-2.98\%$
test_async 45.6046ms 30.3593ms 32.9388 Ops/s 32.4552 Ops/s $\color{#35bf28}+1.49\%$
test_simple 0.4845s 0.4117s 2.4290 Ops/s 2.4078 Ops/s $\color{#35bf28}+0.88\%$
test_transformed 0.6399s 0.5699s 1.7548 Ops/s 1.7858 Ops/s $\color{#d91a1a}-1.73\%$
test_serial 1.3450s 1.2646s 0.7907 Ops/s 0.7845 Ops/s $\color{#35bf28}+0.79\%$
test_parallel 1.2656s 1.1434s 0.8746 Ops/s 0.9144 Ops/s $\color{#d91a1a}-4.35\%$
test_step_mdp_speed[True-True-True-True-True] 0.1078ms 24.7233μs 40.4476 KOps/s 41.7658 KOps/s $\color{#d91a1a}-3.16\%$
test_step_mdp_speed[True-True-True-True-False] 41.9390μs 14.5720μs 68.6249 KOps/s 70.6871 KOps/s $\color{#d91a1a}-2.92\%$
test_step_mdp_speed[True-True-True-False-True] 48.4800μs 14.4625μs 69.1446 KOps/s 72.4822 KOps/s $\color{#d91a1a}-4.60\%$
test_step_mdp_speed[True-True-True-False-False] 51.3060μs 8.4630μs 118.1619 KOps/s 123.5700 KOps/s $\color{#d91a1a}-4.38\%$
test_step_mdp_speed[True-True-False-True-True] 66.2430μs 26.4969μs 37.7403 KOps/s 39.1570 KOps/s $\color{#d91a1a}-3.62\%$
test_step_mdp_speed[True-True-False-True-False] 42.0690μs 16.0834μs 62.1757 KOps/s 64.7981 KOps/s $\color{#d91a1a}-4.05\%$
test_step_mdp_speed[True-True-False-False-True] 46.7970μs 16.0129μs 62.4495 KOps/s 65.5178 KOps/s $\color{#d91a1a}-4.68\%$
test_step_mdp_speed[True-True-False-False-False] 42.4290μs 9.9812μs 100.1886 KOps/s 105.1203 KOps/s $\color{#d91a1a}-4.69\%$
test_step_mdp_speed[True-False-True-True-True] 53.7500μs 28.1661μs 35.5037 KOps/s 36.8179 KOps/s $\color{#d91a1a}-3.57\%$
test_step_mdp_speed[True-False-True-True-False] 42.5190μs 17.5594μs 56.9494 KOps/s 59.8993 KOps/s $\color{#d91a1a}-4.92\%$
test_step_mdp_speed[True-False-True-False-True] 53.7200μs 16.0433μs 62.3314 KOps/s 65.8154 KOps/s $\textbf{\color{#d91a1a}-5.29\%}$
test_step_mdp_speed[True-False-True-False-False] 38.4520μs 9.9975μs 100.0253 KOps/s 105.6069 KOps/s $\textbf{\color{#d91a1a}-5.29\%}$
test_step_mdp_speed[True-False-False-True-True] 80.2700μs 29.7540μs 33.6089 KOps/s 35.3098 KOps/s $\color{#d91a1a}-4.82\%$
test_step_mdp_speed[True-False-False-True-False] 59.6210μs 19.0187μs 52.5797 KOps/s 54.4667 KOps/s $\color{#d91a1a}-3.46\%$
test_step_mdp_speed[True-False-False-False-True] 56.0040μs 17.4002μs 57.4707 KOps/s 59.9415 KOps/s $\color{#d91a1a}-4.12\%$
test_step_mdp_speed[True-False-False-False-False] 37.8000μs 11.3765μs 87.9007 KOps/s 91.9246 KOps/s $\color{#d91a1a}-4.38\%$
test_step_mdp_speed[False-True-True-True-True] 62.9980μs 28.0857μs 35.6053 KOps/s 37.0798 KOps/s $\color{#d91a1a}-3.98\%$
test_step_mdp_speed[False-True-True-True-False] 55.2730μs 17.4993μs 57.1452 KOps/s 58.7864 KOps/s $\color{#d91a1a}-2.79\%$
test_step_mdp_speed[False-True-True-False-True] 61.7460μs 18.2696μs 54.7358 KOps/s 56.9996 KOps/s $\color{#d91a1a}-3.97\%$
test_step_mdp_speed[False-True-True-False-False] 37.5200μs 11.2594μs 88.8147 KOps/s 92.6721 KOps/s $\color{#d91a1a}-4.16\%$
test_step_mdp_speed[False-True-False-True-True] 64.4500μs 29.3969μs 34.0172 KOps/s 35.0820 KOps/s $\color{#d91a1a}-3.04\%$
test_step_mdp_speed[False-True-False-True-False] 62.3760μs 18.7872μs 53.2277 KOps/s 54.5860 KOps/s $\color{#d91a1a}-2.49\%$
test_step_mdp_speed[False-True-False-False-True] 46.4270μs 19.9627μs 50.0934 KOps/s 52.8516 KOps/s $\textbf{\color{#d91a1a}-5.22\%}$
test_step_mdp_speed[False-True-False-False-False] 39.9940μs 12.5778μs 79.5054 KOps/s 82.7940 KOps/s $\color{#d91a1a}-3.97\%$
test_step_mdp_speed[False-False-True-True-True] 3.4230ms 31.1903μs 32.0612 KOps/s 33.1673 KOps/s $\color{#d91a1a}-3.33\%$
test_step_mdp_speed[False-False-True-True-False] 65.7820μs 20.2337μs 49.4226 KOps/s 50.4365 KOps/s $\color{#d91a1a}-2.01\%$
test_step_mdp_speed[False-False-True-False-True] 49.5620μs 19.7966μs 50.5137 KOps/s 53.3758 KOps/s $\textbf{\color{#d91a1a}-5.36\%}$
test_step_mdp_speed[False-False-True-False-False] 46.7970μs 12.6033μs 79.3443 KOps/s 82.4340 KOps/s $\color{#d91a1a}-3.75\%$
test_step_mdp_speed[False-False-False-True-True] 70.7620μs 32.1212μs 31.1321 KOps/s 32.0753 KOps/s $\color{#d91a1a}-2.94\%$
test_step_mdp_speed[False-False-False-True-False] 49.6830μs 21.5118μs 46.4861 KOps/s 47.6602 KOps/s $\color{#d91a1a}-2.46\%$
test_step_mdp_speed[False-False-False-False-True] 47.6490μs 21.0734μs 47.4532 KOps/s 49.3934 KOps/s $\color{#d91a1a}-3.93\%$
test_step_mdp_speed[False-False-False-False-False] 39.8240μs 13.8448μs 72.2294 KOps/s 75.0448 KOps/s $\color{#d91a1a}-3.75\%$
test_values[generalized_advantage_estimate-True-True] 9.9353ms 9.6236ms 103.9116 Ops/s 103.9904 Ops/s $\color{#d91a1a}-0.08\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.8782ms 35.9272ms 27.8340 Ops/s 27.6313 Ops/s $\color{#35bf28}+0.73\%$
test_values[td0_return_estimate-False-False] 0.2165ms 0.1742ms 5.7389 KOps/s 5.8162 KOps/s $\color{#d91a1a}-1.33\%$
test_values[td1_return_estimate-False-False] 34.9504ms 24.4257ms 40.9405 Ops/s 42.0630 Ops/s $\color{#d91a1a}-2.67\%$
test_values[vec_td1_return_estimate-False-False] 42.7124ms 36.2255ms 27.6048 Ops/s 28.1765 Ops/s $\color{#d91a1a}-2.03\%$
test_values[td_lambda_return_estimate-True-False] 36.9803ms 34.4413ms 29.0349 Ops/s 29.2210 Ops/s $\color{#d91a1a}-0.64\%$
test_values[vec_td_lambda_return_estimate-True-False] 40.8296ms 36.0195ms 27.7627 Ops/s 28.1823 Ops/s $\color{#d91a1a}-1.49\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.6439ms 8.4775ms 117.9586 Ops/s 118.6321 Ops/s $\color{#d91a1a}-0.57\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.4931ms 2.0602ms 485.3939 Ops/s 490.9384 Ops/s $\color{#d91a1a}-1.13\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6527ms 0.3693ms 2.7081 KOps/s 2.7932 KOps/s $\color{#d91a1a}-3.05\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 50.4513ms 48.0642ms 20.8055 Ops/s 20.8335 Ops/s $\color{#d91a1a}-0.13\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8981ms 3.0462ms 328.2784 Ops/s 328.3592 Ops/s $\color{#d91a1a}-0.02\%$
test_dqn_speed 1.8650ms 1.3684ms 730.7921 Ops/s 727.4315 Ops/s $\color{#35bf28}+0.46\%$
test_ddpg_speed 3.2592ms 2.9077ms 343.9178 Ops/s 344.6329 Ops/s $\color{#d91a1a}-0.21\%$
test_sac_speed 10.0253ms 8.4330ms 118.5812 Ops/s 119.1136 Ops/s $\color{#d91a1a}-0.45\%$
test_redq_speed 14.7360ms 13.5842ms 73.6150 Ops/s 72.9053 Ops/s $\color{#35bf28}+0.97\%$
test_redq_deprec_speed 14.8535ms 13.4201ms 74.5153 Ops/s 72.4072 Ops/s $\color{#35bf28}+2.91\%$
test_td3_speed 8.7834ms 8.3689ms 119.4898 Ops/s 116.1579 Ops/s $\color{#35bf28}+2.87\%$
test_cql_speed 37.3569ms 36.5085ms 27.3909 Ops/s 26.5748 Ops/s $\color{#35bf28}+3.07\%$
test_a2c_speed 9.1791ms 7.4714ms 133.8440 Ops/s 132.6012 Ops/s $\color{#35bf28}+0.94\%$
test_ppo_speed 8.9269ms 7.9783ms 125.3393 Ops/s 127.0626 Ops/s $\color{#d91a1a}-1.36\%$
test_reinforce_speed 7.6222ms 6.5613ms 152.4090 Ops/s 147.8732 Ops/s $\color{#35bf28}+3.07\%$
test_iql_speed 34.4831ms 32.9384ms 30.3597 Ops/s 30.2917 Ops/s $\color{#35bf28}+0.22\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.1984ms 4.8598ms 205.7698 Ops/s 205.3910 Ops/s $\color{#35bf28}+0.18\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.5519ms 0.4791ms 2.0874 KOps/s 2.0602 KOps/s $\color{#35bf28}+1.32\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6714ms 0.4515ms 2.2149 KOps/s 2.1902 KOps/s $\color{#35bf28}+1.12\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.1443ms 4.8103ms 207.8873 Ops/s 206.1572 Ops/s $\color{#35bf28}+0.84\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.1124s 0.5531ms 1.8080 KOps/s 2.1131 KOps/s $\textbf{\color{#d91a1a}-14.44\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7536ms 0.4545ms 2.2004 KOps/s 2.2445 KOps/s $\color{#d91a1a}-1.97\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.3663ms 1.6923ms 590.9026 Ops/s 589.0400 Ops/s $\color{#35bf28}+0.32\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.0633ms 1.6007ms 624.7411 Ops/s 621.1173 Ops/s $\color{#35bf28}+0.58\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 7.6155ms 5.0016ms 199.9341 Ops/s 203.4567 Ops/s $\color{#d91a1a}-1.73\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.9174ms 0.6142ms 1.6281 KOps/s 1.6173 KOps/s $\color{#35bf28}+0.67\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8122ms 0.5909ms 1.6923 KOps/s 1.6892 KOps/s $\color{#35bf28}+0.18\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.2732ms 4.8813ms 204.8634 Ops/s 202.8288 Ops/s $\color{#35bf28}+1.00\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.9303ms 0.4867ms 2.0546 KOps/s 2.0979 KOps/s $\color{#d91a1a}-2.06\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7369ms 0.4662ms 2.1451 KOps/s 2.1671 KOps/s $\color{#d91a1a}-1.02\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.7698ms 4.8623ms 205.6654 Ops/s 206.9021 Ops/s $\color{#d91a1a}-0.60\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.4837ms 0.4756ms 2.1025 KOps/s 2.1225 KOps/s $\color{#d91a1a}-0.94\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6604ms 0.4600ms 2.1741 KOps/s 2.2276 KOps/s $\color{#d91a1a}-2.40\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.9789ms 5.1234ms 195.1838 Ops/s 203.5766 Ops/s $\color{#d91a1a}-4.12\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.7318ms 0.6201ms 1.6127 KOps/s 1.6207 KOps/s $\color{#d91a1a}-0.49\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 11.7492ms 0.6188ms 1.6160 KOps/s 1.6922 KOps/s $\color{#d91a1a}-4.50\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1342s 6.3962ms 156.3440 Ops/s 119.5413 Ops/s $\textbf{\color{#35bf28}+30.79\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 17.2088ms 12.8384ms 77.8912 Ops/s 76.9815 Ops/s $\color{#35bf28}+1.18\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.1780ms 1.2117ms 825.3014 Ops/s 877.0090 Ops/s $\textbf{\color{#d91a1a}-5.90\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1138s 5.8955ms 169.6211 Ops/s 171.9613 Ops/s $\color{#d91a1a}-1.36\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.1247s 15.1552ms 65.9841 Ops/s 76.8744 Ops/s $\textbf{\color{#d91a1a}-14.17\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.8409ms 1.0995ms 909.4927 Ops/s 903.9211 Ops/s $\color{#35bf28}+0.62\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1145s 6.1037ms 163.8343 Ops/s 168.5714 Ops/s $\color{#d91a1a}-2.81\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 17.4707ms 13.1543ms 76.0207 Ops/s 75.8937 Ops/s $\color{#35bf28}+0.17\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 5.3235ms 1.3213ms 756.8395 Ops/s 801.7147 Ops/s $\textbf{\color{#d91a1a}-5.60\%}$

@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 94. Improved: $\large\color{#35bf28}9$. Worsened: $\large\color{#d91a1a}6$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_single 0.1086s 0.1083s 9.2331 Ops/s 9.2270 Ops/s $\color{#35bf28}+0.07\%$
test_sync 95.0773ms 93.7407ms 10.6677 Ops/s 10.5072 Ops/s $\color{#35bf28}+1.53\%$
test_async 0.1774s 90.1272ms 11.0954 Ops/s 11.0643 Ops/s $\color{#35bf28}+0.28\%$
test_single_pixels 0.1186s 0.1177s 8.4966 Ops/s 8.4410 Ops/s $\color{#35bf28}+0.66\%$
test_sync_pixels 76.0296ms 74.9025ms 13.3507 Ops/s 13.5045 Ops/s $\color{#d91a1a}-1.14\%$
test_async_pixels 0.1329s 67.6938ms 14.7724 Ops/s 14.2042 Ops/s $\color{#35bf28}+4.00\%$
test_simple 0.8722s 0.8009s 1.2486 Ops/s 1.2524 Ops/s $\color{#d91a1a}-0.30\%$
test_transformed 1.1145s 1.0400s 0.9615 Ops/s 0.9856 Ops/s $\color{#d91a1a}-2.44\%$
test_serial 2.3277s 2.2585s 0.4428 Ops/s 0.4431 Ops/s $\color{#d91a1a}-0.08\%$
test_parallel 2.0267s 1.9736s 0.5067 Ops/s 0.5030 Ops/s $\color{#35bf28}+0.74\%$
test_step_mdp_speed[True-True-True-True-True] 97.5540μs 36.3409μs 27.5172 KOps/s 26.9414 KOps/s $\color{#35bf28}+2.14\%$
test_step_mdp_speed[True-True-True-True-False] 36.9820μs 20.7286μs 48.2424 KOps/s 47.2644 KOps/s $\color{#35bf28}+2.07\%$
test_step_mdp_speed[True-True-True-False-True] 42.8220μs 20.3320μs 49.1834 KOps/s 47.5198 KOps/s $\color{#35bf28}+3.50\%$
test_step_mdp_speed[True-True-True-False-False] 31.7110μs 11.6497μs 85.8388 KOps/s 84.7459 KOps/s $\color{#35bf28}+1.29\%$
test_step_mdp_speed[True-True-False-True-True] 64.8020μs 37.3385μs 26.7820 KOps/s 25.8996 KOps/s $\color{#35bf28}+3.41\%$
test_step_mdp_speed[True-True-False-True-False] 46.5220μs 22.2634μs 44.9168 KOps/s 43.4756 KOps/s $\color{#35bf28}+3.31\%$
test_step_mdp_speed[True-True-False-False-True] 47.4720μs 22.4346μs 44.5740 KOps/s 43.9199 KOps/s $\color{#35bf28}+1.49\%$
test_step_mdp_speed[True-True-False-False-False] 36.6210μs 13.6452μs 73.2861 KOps/s 70.7378 KOps/s $\color{#35bf28}+3.60\%$
test_step_mdp_speed[True-False-True-True-True] 70.8930μs 39.1701μs 25.5297 KOps/s 23.8540 KOps/s $\textbf{\color{#35bf28}+7.03\%}$
test_step_mdp_speed[True-False-True-True-False] 50.6530μs 24.4292μs 40.9346 KOps/s 39.0124 KOps/s $\color{#35bf28}+4.93\%$
test_step_mdp_speed[True-False-True-False-True] 46.9320μs 22.1162μs 45.2158 KOps/s 43.5553 KOps/s $\color{#35bf28}+3.81\%$
test_step_mdp_speed[True-False-True-False-False] 32.1710μs 13.6023μs 73.5167 KOps/s 70.7097 KOps/s $\color{#35bf28}+3.97\%$
test_step_mdp_speed[True-False-False-True-True] 69.5630μs 41.5088μs 24.0913 KOps/s 22.6543 KOps/s $\textbf{\color{#35bf28}+6.34\%}$
test_step_mdp_speed[True-False-False-True-False] 47.3820μs 26.4321μs 37.8329 KOps/s 36.1802 KOps/s $\color{#35bf28}+4.57\%$
test_step_mdp_speed[True-False-False-False-True] 50.3520μs 23.9493μs 41.7549 KOps/s 39.8881 KOps/s $\color{#35bf28}+4.68\%$
test_step_mdp_speed[True-False-False-False-False] 40.7220μs 15.6005μs 64.1004 KOps/s 61.4581 KOps/s $\color{#35bf28}+4.30\%$
test_step_mdp_speed[False-True-True-True-True] 71.3330μs 39.2126μs 25.5020 KOps/s 24.2861 KOps/s $\textbf{\color{#35bf28}+5.01\%}$
test_step_mdp_speed[False-True-True-True-False] 55.8520μs 24.3178μs 41.1222 KOps/s 39.4358 KOps/s $\color{#35bf28}+4.28\%$
test_step_mdp_speed[False-True-True-False-True] 50.2820μs 26.3305μs 37.9787 KOps/s 37.0820 KOps/s $\color{#35bf28}+2.42\%$
test_step_mdp_speed[False-True-True-False-False] 37.9220μs 15.5588μs 64.2722 KOps/s 62.4830 KOps/s $\color{#35bf28}+2.86\%$
test_step_mdp_speed[False-True-False-True-True] 84.1140μs 41.3931μs 24.1586 KOps/s 23.0140 KOps/s $\color{#35bf28}+4.97\%$
test_step_mdp_speed[False-True-False-True-False] 51.7620μs 26.2361μs 38.1154 KOps/s 36.0198 KOps/s $\textbf{\color{#35bf28}+5.82\%}$
test_step_mdp_speed[False-True-False-False-True] 50.4520μs 28.1619μs 35.5089 KOps/s 34.0454 KOps/s $\color{#35bf28}+4.30\%$
test_step_mdp_speed[False-True-False-False-False] 34.7610μs 17.4250μs 57.3887 KOps/s 54.8171 KOps/s $\color{#35bf28}+4.69\%$
test_step_mdp_speed[False-False-True-True-True] 4.2304ms 44.3988μs 22.5231 KOps/s 21.5664 KOps/s $\color{#35bf28}+4.44\%$
test_step_mdp_speed[False-False-True-True-False] 56.5430μs 28.8419μs 34.6717 KOps/s 33.2040 KOps/s $\color{#35bf28}+4.42\%$
test_step_mdp_speed[False-False-True-False-True] 55.5520μs 28.4305μs 35.1735 KOps/s 34.2778 KOps/s $\color{#35bf28}+2.61\%$
test_step_mdp_speed[False-False-True-False-False] 43.3720μs 17.6734μs 56.5823 KOps/s 54.9860 KOps/s $\color{#35bf28}+2.90\%$
test_step_mdp_speed[False-False-False-True-True] 71.7930μs 46.0653μs 21.7083 KOps/s 21.0307 KOps/s $\color{#35bf28}+3.22\%$
test_step_mdp_speed[False-False-False-True-False] 54.1720μs 30.8345μs 32.4312 KOps/s 30.6796 KOps/s $\textbf{\color{#35bf28}+5.71\%}$
test_step_mdp_speed[False-False-False-False-True] 54.3520μs 30.1510μs 33.1664 KOps/s 32.1861 KOps/s $\color{#35bf28}+3.05\%$
test_step_mdp_speed[False-False-False-False-False] 38.7520μs 19.4119μs 51.5148 KOps/s 49.6536 KOps/s $\color{#35bf28}+3.75\%$
test_values[generalized_advantage_estimate-True-True] 25.3919ms 24.6652ms 40.5429 Ops/s 41.1110 Ops/s $\color{#d91a1a}-1.38\%$
test_values[vec_generalized_advantage_estimate-True-True] 89.9236ms 2.6990ms 370.5100 Ops/s 352.8484 Ops/s $\textbf{\color{#35bf28}+5.01\%}$
test_values[td0_return_estimate-False-False] 90.3140μs 65.5396μs 15.2580 KOps/s 15.1607 KOps/s $\color{#35bf28}+0.64\%$
test_values[td1_return_estimate-False-False] 55.7005ms 55.1974ms 18.1168 Ops/s 18.2760 Ops/s $\color{#d91a1a}-0.87\%$
test_values[vec_td1_return_estimate-False-False] 1.3979ms 1.0914ms 916.2347 Ops/s 920.5829 Ops/s $\color{#d91a1a}-0.47\%$
test_values[td_lambda_return_estimate-True-False] 91.5481ms 88.9717ms 11.2395 Ops/s 11.5201 Ops/s $\color{#d91a1a}-2.44\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.4305ms 1.0895ms 917.8849 Ops/s 921.9477 Ops/s $\color{#d91a1a}-0.44\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 25.0783ms 24.8985ms 40.1631 Ops/s 40.0870 Ops/s $\color{#35bf28}+0.19\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 0.9556ms 0.7280ms 1.3736 KOps/s 1.3349 KOps/s $\color{#35bf28}+2.90\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7446ms 0.6750ms 1.4816 KOps/s 1.4862 KOps/s $\color{#d91a1a}-0.31\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5081ms 1.4729ms 678.9518 Ops/s 678.9650 Ops/s $-0.00\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7743ms 0.6897ms 1.4499 KOps/s 1.4539 KOps/s $\color{#d91a1a}-0.27\%$
test_dqn_speed 7.2996ms 1.4454ms 691.8398 Ops/s 702.1243 Ops/s $\color{#d91a1a}-1.46\%$
test_ddpg_speed 3.2057ms 2.9526ms 338.6864 Ops/s 339.4472 Ops/s $\color{#d91a1a}-0.22\%$
test_sac_speed 0.1019s 9.1198ms 109.6515 Ops/s 119.5903 Ops/s $\textbf{\color{#d91a1a}-8.31\%}$
test_redq_speed 11.6068ms 10.8403ms 92.2483 Ops/s 92.0351 Ops/s $\color{#35bf28}+0.23\%$
test_redq_deprec_speed 11.9034ms 11.2670ms 88.7545 Ops/s 87.7212 Ops/s $\color{#35bf28}+1.18\%$
test_td3_speed 11.7885ms 8.3369ms 119.9480 Ops/s 120.0181 Ops/s $\color{#d91a1a}-0.06\%$
test_cql_speed 26.1703ms 25.2780ms 39.5601 Ops/s 38.3904 Ops/s $\color{#35bf28}+3.05\%$
test_a2c_speed 5.8630ms 5.6015ms 178.5243 Ops/s 174.6812 Ops/s $\color{#35bf28}+2.20\%$
test_ppo_speed 6.2017ms 5.9817ms 167.1763 Ops/s 165.9084 Ops/s $\color{#35bf28}+0.76\%$
test_reinforce_speed 4.8668ms 4.5000ms 222.2203 Ops/s 216.7802 Ops/s $\color{#35bf28}+2.51\%$
test_iql_speed 20.2923ms 19.6710ms 50.8363 Ops/s 50.9773 Ops/s $\color{#d91a1a}-0.28\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.7823ms 6.6071ms 151.3534 Ops/s 149.7277 Ops/s $\color{#35bf28}+1.09\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.1105s 0.5792ms 1.7265 KOps/s 1.9375 KOps/s $\textbf{\color{#d91a1a}-10.89\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6725ms 0.4879ms 2.0494 KOps/s 2.0326 KOps/s $\color{#35bf28}+0.83\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.7705ms 6.5594ms 152.4532 Ops/s 150.7143 Ops/s $\color{#35bf28}+1.15\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.0710ms 0.5051ms 1.9799 KOps/s 1.9824 KOps/s $\color{#d91a1a}-0.12\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6808ms 0.4860ms 2.0577 KOps/s 2.0539 KOps/s $\color{#35bf28}+0.18\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.1766ms 1.9420ms 514.9222 Ops/s 513.9472 Ops/s $\color{#35bf28}+0.19\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.7347ms 1.9243ms 519.6773 Ops/s 541.6287 Ops/s $\color{#d91a1a}-4.05\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.8478ms 6.7115ms 148.9990 Ops/s 147.0782 Ops/s $\color{#35bf28}+1.31\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.1287s 0.7719ms 1.2955 KOps/s 1.4943 KOps/s $\textbf{\color{#d91a1a}-13.30\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8036ms 0.6387ms 1.5657 KOps/s 1.5530 KOps/s $\color{#35bf28}+0.82\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.7670ms 6.6503ms 150.3682 Ops/s 149.8327 Ops/s $\color{#35bf28}+0.36\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7041ms 0.5078ms 1.9691 KOps/s 1.4713 KOps/s $\textbf{\color{#35bf28}+33.84\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 3.9888ms 0.4967ms 2.0134 KOps/s 2.0378 KOps/s $\color{#d91a1a}-1.20\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.8709ms 6.5607ms 152.4235 Ops/s 151.0703 Ops/s $\color{#35bf28}+0.90\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.1278s 0.6824ms 1.4654 KOps/s 1.9630 KOps/s $\textbf{\color{#d91a1a}-25.35\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6737ms 0.4866ms 2.0552 KOps/s 2.0445 KOps/s $\color{#35bf28}+0.53\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.8615ms 6.7595ms 147.9399 Ops/s 146.6429 Ops/s $\color{#35bf28}+0.88\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.9776ms 0.6639ms 1.5063 KOps/s 1.2195 KOps/s $\textbf{\color{#35bf28}+23.51\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8037ms 0.6458ms 1.5485 KOps/s 1.5577 KOps/s $\color{#d91a1a}-0.59\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 0.1289s 7.5423ms 132.5847 Ops/s 130.4881 Ops/s $\color{#35bf28}+1.61\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 18.8473ms 16.2296ms 61.6160 Ops/s 61.0698 Ops/s $\color{#35bf28}+0.89\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.1421ms 1.1632ms 859.6836 Ops/s 769.8388 Ops/s $\textbf{\color{#35bf28}+11.67\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.1265s 9.9277ms 100.7285 Ops/s 133.4788 Ops/s $\textbf{\color{#d91a1a}-24.54\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 18.6854ms 16.2844ms 61.4084 Ops/s 61.0996 Ops/s $\color{#35bf28}+0.51\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.5739ms 1.3485ms 741.5891 Ops/s 809.9097 Ops/s $\textbf{\color{#d91a1a}-8.44\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.1243s 7.6688ms 130.3992 Ops/s 128.7996 Ops/s $\color{#35bf28}+1.24\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 18.7966ms 16.4346ms 60.8473 Ops/s 60.1428 Ops/s $\color{#35bf28}+1.17\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 5.9868ms 1.4577ms 686.0303 Ops/s 712.8407 Ops/s $\color{#d91a1a}-3.76\%$

@vmoens vmoens deleted the fix-impl branch August 7, 2024 01:39
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