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] Remove raisers in specs #2651

Merged
merged 1 commit into from
Dec 14, 2024
Merged

[BugFix] Remove raisers in specs #2651

merged 1 commit into from
Dec 14, 2024

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Dec 14, 2024 •
edited
Loading

Stack from ghstack (oldest at bottom):

@vmoens
Update
a7295a5 
[ghstack-poisoned]
@pytorch-bot PyTorch Bot
Copy link

pytorch-bot bot commented Dec 14, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2651

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:

❌ 4 New Failures, 18 Unrelated Failures

As of commit a7295a5 with merge base 9e2d214 (image):

NEW FAILURES - The following jobs have failed:

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.

vmoens added a commit that referenced this pull request Dec 14, 2024
@vmoens
[BugFix] Remove raisers in specs
8f7dad1 
ghstack-source-id: a005a62847aa2ff1d286f2c4ad13fd14f9e631d3
Pull Request resolved: #2651
@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 Dec 14, 2024
@vmoens vmoens merged commit a7295a5 into gh/vmoens/53/base Dec 14, 2024
18 of 30 checks passed
vmoens added a commit that referenced this pull request Dec 14, 2024
@vmoens
[BugFix] Remove raisers in specs
bb6f87a 
ghstack-source-id: a005a62847aa2ff1d286f2c4ad13fd14f9e631d3
Pull Request resolved: #2651
@vmoens vmoens deleted the gh/vmoens/53/head branch December 14, 2024 23:06
@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}9$. Worsened: $\large\color{#d91a1a}3$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4301s 0.4280s 2.3362 Ops/s 2.2314 Ops/s $\color{#35bf28}+4.70\%$
test_transformed 0.6074s 0.6057s 1.6509 Ops/s 1.5869 Ops/s $\color{#35bf28}+4.03\%$
test_serial 1.3444s 1.3385s 0.7471 Ops/s 0.7378 Ops/s $\color{#35bf28}+1.26\%$
test_parallel 1.2880s 1.2767s 0.7832 Ops/s 0.7535 Ops/s $\color{#35bf28}+3.94\%$
test_step_mdp_speed[True-True-True-True-True] 0.2297ms 29.2246μs 34.2178 KOps/s 33.9285 KOps/s $\color{#35bf28}+0.85\%$
test_step_mdp_speed[True-True-True-True-False] 40.4160μs 17.0334μs 58.7083 KOps/s 57.5417 KOps/s $\color{#35bf28}+2.03\%$
test_step_mdp_speed[True-True-True-False-True] 71.0430μs 16.4167μs 60.9136 KOps/s 60.5858 KOps/s $\color{#35bf28}+0.54\%$
test_step_mdp_speed[True-True-True-False-False] 38.9430μs 9.7517μs 102.5466 KOps/s 103.9114 KOps/s $\color{#d91a1a}-1.31\%$
test_step_mdp_speed[True-True-False-True-True] 85.2990μs 30.9615μs 32.2982 KOps/s 31.4688 KOps/s $\color{#35bf28}+2.64\%$
test_step_mdp_speed[True-True-False-True-False] 59.5010μs 19.1169μs 52.3096 KOps/s 51.5893 KOps/s $\color{#35bf28}+1.40\%$
test_step_mdp_speed[True-True-False-False-True] 54.2020μs 17.9981μs 55.5613 KOps/s 53.7583 KOps/s $\color{#35bf28}+3.35\%$
test_step_mdp_speed[True-True-False-False-False] 84.3280μs 11.3408μs 88.1770 KOps/s 86.3767 KOps/s $\color{#35bf28}+2.08\%$
test_step_mdp_speed[True-False-True-True-True] 0.6282ms 34.3915μs 29.0769 KOps/s 29.5332 KOps/s $\color{#d91a1a}-1.55\%$
test_step_mdp_speed[True-False-True-True-False] 79.4990μs 20.2436μs 49.3984 KOps/s 46.9410 KOps/s $\textbf{\color{#35bf28}+5.24\%}$
test_step_mdp_speed[True-False-True-False-True] 44.1030μs 18.0658μs 55.3531 KOps/s 53.9027 KOps/s $\color{#35bf28}+2.69\%$
test_step_mdp_speed[True-False-True-False-False] 59.3310μs 11.1679μs 89.5420 KOps/s 85.4688 KOps/s $\color{#35bf28}+4.77\%$
test_step_mdp_speed[True-False-False-True-True] 88.0450μs 33.8687μs 29.5258 KOps/s 27.9425 KOps/s $\textbf{\color{#35bf28}+5.67\%}$
test_step_mdp_speed[True-False-False-True-False] 55.2030μs 21.9575μs 45.5426 KOps/s 43.3238 KOps/s $\textbf{\color{#35bf28}+5.12\%}$
test_step_mdp_speed[True-False-False-False-True] 84.1680μs 19.6840μs 50.8028 KOps/s 49.0359 KOps/s $\color{#35bf28}+3.60\%$
test_step_mdp_speed[True-False-False-False-False] 46.7370μs 12.8763μs 77.6621 KOps/s 76.0967 KOps/s $\color{#35bf28}+2.06\%$
test_step_mdp_speed[False-True-True-True-True] 92.2650μs 32.4706μs 30.7971 KOps/s 29.5294 KOps/s $\color{#35bf28}+4.29\%$
test_step_mdp_speed[False-True-True-True-False] 50.1240μs 20.5691μs 48.6166 KOps/s 46.8585 KOps/s $\color{#35bf28}+3.75\%$
test_step_mdp_speed[False-True-True-False-True] 60.3640μs 20.3853μs 49.0549 KOps/s 47.7417 KOps/s $\color{#35bf28}+2.75\%$
test_step_mdp_speed[False-True-True-False-False] 51.2160μs 12.6282μs 79.1876 KOps/s 76.6909 KOps/s $\color{#35bf28}+3.26\%$
test_step_mdp_speed[False-True-False-True-True] 84.3360μs 34.2384μs 29.2069 KOps/s 28.1990 KOps/s $\color{#35bf28}+3.57\%$
test_step_mdp_speed[False-True-False-True-False] 69.7210μs 22.1856μs 45.0742 KOps/s 43.5733 KOps/s $\color{#35bf28}+3.44\%$
test_step_mdp_speed[False-True-False-False-True] 2.8948ms 22.3422μs 44.7584 KOps/s 43.9078 KOps/s $\color{#35bf28}+1.94\%$
test_step_mdp_speed[False-True-False-False-False] 52.7990μs 14.2458μs 70.1959 KOps/s 68.2952 KOps/s $\color{#35bf28}+2.78\%$
test_step_mdp_speed[False-False-True-True-True] 96.5200μs 36.0841μs 27.7131 KOps/s 26.9119 KOps/s $\color{#35bf28}+2.98\%$
test_step_mdp_speed[False-False-True-True-False] 0.6429ms 23.8759μs 41.8833 KOps/s 40.9491 KOps/s $\color{#35bf28}+2.28\%$
test_step_mdp_speed[False-False-True-False-True] 72.6580μs 22.0596μs 45.3317 KOps/s 44.3531 KOps/s $\color{#35bf28}+2.21\%$
test_step_mdp_speed[False-False-True-False-False] 53.4600μs 14.1546μs 70.6484 KOps/s 68.5388 KOps/s $\color{#35bf28}+3.08\%$
test_step_mdp_speed[False-False-False-True-True] 91.8820μs 37.4468μs 26.7045 KOps/s 26.0349 KOps/s $\color{#35bf28}+2.57\%$
test_step_mdp_speed[False-False-False-True-False] 70.8120μs 25.3323μs 39.4752 KOps/s 37.9060 KOps/s $\color{#35bf28}+4.14\%$
test_step_mdp_speed[False-False-False-False-True] 63.4290μs 23.4309μs 42.6786 KOps/s 41.0614 KOps/s $\color{#35bf28}+3.94\%$
test_step_mdp_speed[False-False-False-False-False] 67.3860μs 15.7403μs 63.5311 KOps/s 61.0144 KOps/s $\color{#35bf28}+4.12\%$
test_values[generalized_advantage_estimate-True-True] 9.8425ms 9.3911ms 106.4836 Ops/s 106.7908 Ops/s $\color{#d91a1a}-0.29\%$
test_values[vec_generalized_advantage_estimate-True-True] 38.4317ms 36.4393ms 27.4429 Ops/s 29.6787 Ops/s $\textbf{\color{#d91a1a}-7.53\%}$
test_values[td0_return_estimate-False-False] 0.2377ms 0.1783ms 5.6075 KOps/s 5.6450 KOps/s $\color{#d91a1a}-0.66\%$
test_values[td1_return_estimate-False-False] 23.5221ms 23.2763ms 42.9621 Ops/s 41.2720 Ops/s $\color{#35bf28}+4.10\%$
test_values[vec_td1_return_estimate-False-False] 37.6142ms 35.9695ms 27.8014 Ops/s 29.7291 Ops/s $\textbf{\color{#d91a1a}-6.48\%}$
test_values[td_lambda_return_estimate-True-False] 36.7403ms 33.5454ms 29.8103 Ops/s 28.7227 Ops/s $\color{#35bf28}+3.79\%$
test_values[vec_td_lambda_return_estimate-True-False] 40.5591ms 36.1140ms 27.6901 Ops/s 29.7159 Ops/s $\textbf{\color{#d91a1a}-6.82\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.3453ms 8.1307ms 122.9913 Ops/s 120.9710 Ops/s $\color{#35bf28}+1.67\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 3.1814ms 2.0373ms 490.8574 Ops/s 502.3925 Ops/s $\color{#d91a1a}-2.30\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4934ms 0.3542ms 2.8234 KOps/s 2.7539 KOps/s $\color{#35bf28}+2.52\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 49.8421ms 47.6978ms 20.9653 Ops/s 21.5165 Ops/s $\color{#d91a1a}-2.56\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.1520ms 3.0167ms 331.4887 Ops/s 329.0898 Ops/s $\color{#35bf28}+0.73\%$
test_dqn_speed[False-None] 2.4149ms 1.4027ms 712.9149 Ops/s 716.8161 Ops/s $\color{#d91a1a}-0.54\%$
test_dqn_speed[False-backward] 2.0086ms 1.8630ms 536.7730 Ops/s 530.7744 Ops/s $\color{#35bf28}+1.13\%$
test_dqn_speed[True-None] 0.7324ms 0.4618ms 2.1654 KOps/s 2.1311 KOps/s $\color{#35bf28}+1.61\%$
test_dqn_speed[True-backward] 0.9021ms 0.8747ms 1.1433 KOps/s 1.1155 KOps/s $\color{#35bf28}+2.49\%$
test_dqn_speed[reduce-overhead-None] 0.6673ms 0.4632ms 2.1591 KOps/s 2.1153 KOps/s $\color{#35bf28}+2.07\%$
test_dqn_speed[reduce-overhead-backward] 0.9394ms 0.8812ms 1.1348 KOps/s 1.1187 KOps/s $\color{#35bf28}+1.44\%$
test_ddpg_speed[False-None] 3.6365ms 2.8557ms 350.1800 Ops/s 344.6240 Ops/s $\color{#35bf28}+1.61\%$
test_ddpg_speed[False-backward] 4.2328ms 3.9957ms 250.2669 Ops/s 245.4123 Ops/s $\color{#35bf28}+1.98\%$
test_ddpg_speed[True-None] 1.3887ms 0.9964ms 1.0036 KOps/s 995.4673 Ops/s $\color{#35bf28}+0.82\%$
test_ddpg_speed[True-backward] 1.9506ms 1.8727ms 533.9777 Ops/s 528.0316 Ops/s $\color{#35bf28}+1.13\%$
test_ddpg_speed[reduce-overhead-None] 1.1598ms 0.9911ms 1.0090 KOps/s 987.1008 Ops/s $\color{#35bf28}+2.21\%$
test_ddpg_speed[reduce-overhead-backward] 1.9398ms 1.8742ms 533.5563 Ops/s 525.2290 Ops/s $\color{#35bf28}+1.59\%$
test_sac_speed[False-None] 9.8596ms 7.9331ms 126.0538 Ops/s 123.7207 Ops/s $\color{#35bf28}+1.89\%$
test_sac_speed[False-backward] 12.5945ms 10.7894ms 92.6838 Ops/s 92.3211 Ops/s $\color{#35bf28}+0.39\%$
test_sac_speed[True-None] 2.6611ms 1.8261ms 547.6207 Ops/s 545.3240 Ops/s $\color{#35bf28}+0.42\%$
test_sac_speed[True-backward] 3.5667ms 3.4919ms 286.3789 Ops/s 284.3159 Ops/s $\color{#35bf28}+0.73\%$
test_sac_speed[reduce-overhead-None] 1.9167ms 1.8158ms 550.7210 Ops/s 541.8139 Ops/s $\color{#35bf28}+1.64\%$
test_sac_speed[reduce-overhead-backward] 3.7160ms 3.5095ms 284.9373 Ops/s 284.4927 Ops/s $\color{#35bf28}+0.16\%$
test_redq_speed[False-None] 18.8523ms 12.9482ms 77.2310 Ops/s 77.2852 Ops/s $\color{#d91a1a}-0.07\%$
test_redq_speed[False-backward] 23.7632ms 22.4236ms 44.5958 Ops/s 44.8257 Ops/s $\color{#d91a1a}-0.51\%$
test_redq_speed[True-None] 5.5407ms 4.7129ms 212.1821 Ops/s 217.2051 Ops/s $\color{#d91a1a}-2.31\%$
test_redq_speed[True-backward] 12.7214ms 12.0465ms 83.0115 Ops/s 79.5966 Ops/s $\color{#35bf28}+4.29\%$
test_redq_speed[reduce-overhead-None] 5.6011ms 4.6039ms 217.2072 Ops/s 214.7305 Ops/s $\color{#35bf28}+1.15\%$
test_redq_speed[reduce-overhead-backward] 12.9552ms 12.2366ms 81.7220 Ops/s 81.8927 Ops/s $\color{#d91a1a}-0.21\%$
test_redq_deprec_speed[False-None] 13.7690ms 12.6166ms 79.2605 Ops/s 76.3481 Ops/s $\color{#35bf28}+3.81\%$
test_redq_deprec_speed[False-backward] 18.9804ms 18.2340ms 54.8427 Ops/s 52.7335 Ops/s $\color{#35bf28}+4.00\%$
test_redq_deprec_speed[True-None] 4.2199ms 3.6039ms 277.4780 Ops/s 279.2459 Ops/s $\color{#d91a1a}-0.63\%$
test_redq_deprec_speed[True-backward] 8.3731ms 8.0296ms 124.5393 Ops/s 118.5432 Ops/s $\textbf{\color{#35bf28}+5.06\%}$
test_redq_deprec_speed[reduce-overhead-None] 4.4706ms 3.5832ms 279.0776 Ops/s 277.7883 Ops/s $\color{#35bf28}+0.46\%$
test_redq_deprec_speed[reduce-overhead-backward] 8.4297ms 8.0283ms 124.5591 Ops/s 123.1923 Ops/s $\color{#35bf28}+1.11\%$
test_td3_speed[False-None] 8.2698ms 7.9577ms 125.6642 Ops/s 123.0022 Ops/s $\color{#35bf28}+2.16\%$
test_td3_speed[False-backward] 11.4484ms 10.3802ms 96.3375 Ops/s 90.2668 Ops/s $\textbf{\color{#35bf28}+6.73\%}$
test_td3_speed[True-None] 1.9309ms 1.7151ms 583.0484 Ops/s 577.0559 Ops/s $\color{#35bf28}+1.04\%$
test_td3_speed[True-backward] 4.0991ms 3.3561ms 297.9636 Ops/s 280.1750 Ops/s $\textbf{\color{#35bf28}+6.35\%}$
test_td3_speed[reduce-overhead-None] 1.7952ms 1.7028ms 587.2647 Ops/s 579.2791 Ops/s $\color{#35bf28}+1.38\%$
test_td3_speed[reduce-overhead-backward] 3.9323ms 3.3707ms 296.6764 Ops/s 297.3556 Ops/s $\color{#d91a1a}-0.23\%$
test_cql_speed[False-None] 39.4932ms 36.6499ms 27.2852 Ops/s 27.0675 Ops/s $\color{#35bf28}+0.80\%$
test_cql_speed[False-backward] 48.5165ms 46.2784ms 21.6084 Ops/s 20.7845 Ops/s $\color{#35bf28}+3.96\%$
test_cql_speed[True-None] 16.4806ms 15.5519ms 64.3007 Ops/s 62.1783 Ops/s $\color{#35bf28}+3.41\%$
test_cql_speed[True-backward] 24.3440ms 22.4597ms 44.5242 Ops/s 43.5365 Ops/s $\color{#35bf28}+2.27\%$
test_cql_speed[reduce-overhead-None] 16.5332ms 15.7907ms 63.3285 Ops/s 62.7516 Ops/s $\color{#35bf28}+0.92\%$
test_cql_speed[reduce-overhead-backward] 24.0009ms 22.8849ms 43.6970 Ops/s 43.4751 Ops/s $\color{#35bf28}+0.51\%$
test_a2c_speed[False-None] 9.3259ms 7.3306ms 136.4150 Ops/s 134.4014 Ops/s $\color{#35bf28}+1.50\%$
test_a2c_speed[False-backward] 15.6551ms 14.7492ms 67.8003 Ops/s 66.2681 Ops/s $\color{#35bf28}+2.31\%$
test_a2c_speed[True-None] 4.9151ms 4.2093ms 237.5678 Ops/s 235.7897 Ops/s $\color{#35bf28}+0.75\%$
test_a2c_speed[True-backward] 11.5162ms 10.7465ms 93.0539 Ops/s 90.8970 Ops/s $\color{#35bf28}+2.37\%$
test_a2c_speed[reduce-overhead-None] 5.4604ms 4.2238ms 236.7520 Ops/s 232.9791 Ops/s $\color{#35bf28}+1.62\%$
test_a2c_speed[reduce-overhead-backward] 11.2015ms 10.6767ms 93.6618 Ops/s 90.0064 Ops/s $\color{#35bf28}+4.06\%$
test_ppo_speed[False-None] 8.3982ms 7.4691ms 133.8844 Ops/s 131.0381 Ops/s $\color{#35bf28}+2.17\%$
test_ppo_speed[False-backward] 16.3798ms 14.8555ms 67.3152 Ops/s 65.2805 Ops/s $\color{#35bf28}+3.12\%$
test_ppo_speed[True-None] 4.3490ms 3.6822ms 271.5734 Ops/s 266.3876 Ops/s $\color{#35bf28}+1.95\%$
test_ppo_speed[True-backward] 9.8858ms 9.5291ms 104.9421 Ops/s 103.3917 Ops/s $\color{#35bf28}+1.50\%$
test_ppo_speed[reduce-overhead-None] 4.3108ms 3.6861ms 271.2915 Ops/s 269.4493 Ops/s $\color{#35bf28}+0.68\%$
test_ppo_speed[reduce-overhead-backward] 10.6679ms 9.5778ms 104.4077 Ops/s 101.1046 Ops/s $\color{#35bf28}+3.27\%$
test_reinforce_speed[False-None] 7.1855ms 6.4973ms 153.9091 Ops/s 149.6562 Ops/s $\color{#35bf28}+2.84\%$
test_reinforce_speed[False-backward] 10.0841ms 9.7219ms 102.8604 Ops/s 98.0445 Ops/s $\color{#35bf28}+4.91\%$
test_reinforce_speed[True-None] 2.9906ms 2.6562ms 376.4839 Ops/s 371.4693 Ops/s $\color{#35bf28}+1.35\%$
test_reinforce_speed[True-backward] 9.7239ms 8.5865ms 116.4623 Ops/s 115.7462 Ops/s $\color{#35bf28}+0.62\%$
test_reinforce_speed[reduce-overhead-None] 3.2878ms 2.6481ms 377.6322 Ops/s 371.4437 Ops/s $\color{#35bf28}+1.67\%$
test_reinforce_speed[reduce-overhead-backward] 8.9758ms 8.5520ms 116.9314 Ops/s 115.7211 Ops/s $\color{#35bf28}+1.05\%$
test_iql_speed[False-None] 33.5134ms 32.1550ms 31.0994 Ops/s 30.0641 Ops/s $\color{#35bf28}+3.44\%$
test_iql_speed[False-backward] 46.3791ms 45.0975ms 22.1742 Ops/s 21.5904 Ops/s $\color{#35bf28}+2.70\%$
test_iql_speed[True-None] 11.4046ms 10.5749ms 94.5638 Ops/s 91.7664 Ops/s $\color{#35bf28}+3.05\%$
test_iql_speed[True-backward] 22.2296ms 21.5052ms 46.5004 Ops/s 46.3984 Ops/s $\color{#35bf28}+0.22\%$
test_iql_speed[reduce-overhead-None] 11.6529ms 10.7275ms 93.2182 Ops/s 92.8840 Ops/s $\color{#35bf28}+0.36\%$
test_iql_speed[reduce-overhead-backward] 23.7498ms 21.8327ms 45.8029 Ops/s 45.4906 Ops/s $\color{#35bf28}+0.69\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.3271ms 4.8799ms 204.9221 Ops/s 197.3216 Ops/s $\color{#35bf28}+3.85\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1591ms 0.5054ms 1.9784 KOps/s 1.9145 KOps/s $\color{#35bf28}+3.34\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7708ms 0.4874ms 2.0516 KOps/s 1.9978 KOps/s $\color{#35bf28}+2.69\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.2653ms 4.6967ms 212.9150 Ops/s 203.5899 Ops/s $\color{#35bf28}+4.58\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.8601ms 0.4954ms 2.0186 KOps/s 1.9975 KOps/s $\color{#35bf28}+1.05\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8039ms 0.4747ms 2.1066 KOps/s 2.0549 KOps/s $\color{#35bf28}+2.51\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.8435ms 1.6173ms 618.3060 Ops/s 602.3604 Ops/s $\color{#35bf28}+2.65\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.1614ms 1.5760ms 634.5089 Ops/s 622.7715 Ops/s $\color{#35bf28}+1.88\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.1391ms 4.8318ms 206.9634 Ops/s 204.3495 Ops/s $\color{#35bf28}+1.28\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.4586ms 0.6414ms 1.5590 KOps/s 1.5485 KOps/s $\color{#35bf28}+0.68\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.0092ms 0.6170ms 1.6208 KOps/s 1.5892 KOps/s $\color{#35bf28}+1.99\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 4.8882ms 4.6748ms 213.9149 Ops/s 209.5611 Ops/s $\color{#35bf28}+2.08\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8379ms 0.5074ms 1.9707 KOps/s 1.9055 KOps/s $\color{#35bf28}+3.42\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8346ms 0.4908ms 2.0374 KOps/s 2.0201 KOps/s $\color{#35bf28}+0.86\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 4.9893ms 4.6409ms 215.4734 Ops/s 209.4182 Ops/s $\color{#35bf28}+2.89\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.7755ms 0.4926ms 2.0300 KOps/s 2.0041 KOps/s $\color{#35bf28}+1.29\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7223ms 0.4715ms 2.1208 KOps/s 2.0087 KOps/s $\textbf{\color{#35bf28}+5.58\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.2207ms 4.7358ms 211.1582 Ops/s 202.3728 Ops/s $\color{#35bf28}+4.34\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.5389ms 0.6435ms 1.5540 KOps/s 1.5088 KOps/s $\color{#35bf28}+3.00\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9728ms 0.6245ms 1.6013 KOps/s 1.5972 KOps/s $\color{#35bf28}+0.26\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 5.3245ms 4.1328ms 241.9668 Ops/s 248.9133 Ops/s $\color{#d91a1a}-2.79\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 3.3740ms 2.1426ms 466.7260 Ops/s 432.2410 Ops/s $\textbf{\color{#35bf28}+7.98\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.2133ms 1.3878ms 720.5553 Ops/s 743.2017 Ops/s $\color{#d91a1a}-3.05\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.3993s 12.1394ms 82.3767 Ops/s 34.9619 Ops/s $\textbf{\color{#35bf28}+135.62\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 8.0287ms 2.2975ms 435.2650 Ops/s 424.4796 Ops/s $\color{#35bf28}+2.54\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.2986ms 1.3452ms 743.3952 Ops/s 763.6019 Ops/s $\color{#d91a1a}-2.65\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 5.6048ms 4.3732ms 228.6648 Ops/s 217.8138 Ops/s $\color{#35bf28}+4.98\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 7.9095ms 2.4573ms 406.9548 Ops/s 393.1099 Ops/s $\color{#35bf28}+3.52\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 3.9615ms 1.4211ms 703.6749 Ops/s 674.2212 Ops/s $\color{#35bf28}+4.37\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 12.8137ms 11.4207ms 87.5606 Ops/s 83.9113 Ops/s $\color{#35bf28}+4.35\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 18.0996ms 15.3453ms 65.1665 Ops/s 64.6929 Ops/s $\color{#35bf28}+0.73\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 20.2872ms 19.8995ms 50.2525 Ops/s 49.2245 Ops/s $\color{#35bf28}+2.09\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 16.9385ms 15.4655ms 64.6600 Ops/s 63.8531 Ops/s $\color{#35bf28}+1.26\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 21.2855ms 20.0641ms 49.8404 Ops/s 49.6525 Ops/s $\color{#35bf28}+0.38\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 18.4657ms 16.6830ms 59.9414 Ops/s 59.4825 Ops/s $\color{#35bf28}+0.77\%$

@github-actions GitHub Actions
Copy link

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}11$. Worsened: $\large\color{#d91a1a}12$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.7708s 0.7646s 1.3079 Ops/s 1.3199 Ops/s $\color{#d91a1a}-0.90\%$
test_transformed 1.0361s 1.0231s 0.9775 Ops/s 0.9899 Ops/s $\color{#d91a1a}-1.25\%$
test_serial 2.1768s 2.1740s 0.4600 Ops/s 0.4634 Ops/s $\color{#d91a1a}-0.74\%$
test_parallel 2.0388s 1.9870s 0.5033 Ops/s 0.4961 Ops/s $\color{#35bf28}+1.44\%$
test_step_mdp_speed[True-True-True-True-True] 0.1960ms 40.2541μs 24.8422 KOps/s 25.0591 KOps/s $\color{#d91a1a}-0.87\%$
test_step_mdp_speed[True-True-True-True-False] 49.7610μs 22.6202μs 44.2083 KOps/s 43.5811 KOps/s $\color{#35bf28}+1.44\%$
test_step_mdp_speed[True-True-True-False-True] 56.0910μs 21.8625μs 45.7405 KOps/s 46.8265 KOps/s $\color{#d91a1a}-2.32\%$
test_step_mdp_speed[True-True-True-False-False] 44.2610μs 12.5063μs 79.9595 KOps/s 77.9032 KOps/s $\color{#35bf28}+2.64\%$
test_step_mdp_speed[True-True-False-True-True] 72.2220μs 41.3924μs 24.1590 KOps/s 23.5636 KOps/s $\color{#35bf28}+2.53\%$
test_step_mdp_speed[True-True-False-True-False] 48.6600μs 24.6282μs 40.6039 KOps/s 40.4159 KOps/s $\color{#35bf28}+0.47\%$
test_step_mdp_speed[True-True-False-False-True] 60.1310μs 23.4631μs 42.6200 KOps/s 40.2953 KOps/s $\textbf{\color{#35bf28}+5.77\%}$
test_step_mdp_speed[True-True-False-False-False] 39.4710μs 14.5081μs 68.9270 KOps/s 67.1276 KOps/s $\color{#35bf28}+2.68\%$
test_step_mdp_speed[True-False-True-True-True] 80.3210μs 44.9224μs 22.2606 KOps/s 22.8059 KOps/s $\color{#d91a1a}-2.39\%$
test_step_mdp_speed[True-False-True-True-False] 59.9310μs 26.8798μs 37.2027 KOps/s 36.8688 KOps/s $\color{#35bf28}+0.91\%$
test_step_mdp_speed[True-False-True-False-True] 55.5110μs 24.0160μs 41.6389 KOps/s 41.8706 KOps/s $\color{#d91a1a}-0.55\%$
test_step_mdp_speed[True-False-True-False-False] 5.9778ms 14.7191μs 67.9388 KOps/s 66.8618 KOps/s $\color{#35bf28}+1.61\%$
test_step_mdp_speed[True-False-False-True-True] 73.4120μs 46.0641μs 21.7089 KOps/s 21.1426 KOps/s $\color{#35bf28}+2.68\%$
test_step_mdp_speed[True-False-False-True-False] 59.1910μs 29.0224μs 34.4561 KOps/s 33.6573 KOps/s $\color{#35bf28}+2.37\%$
test_step_mdp_speed[True-False-False-False-True] 50.9110μs 25.9469μs 38.5402 KOps/s 38.1037 KOps/s $\color{#35bf28}+1.15\%$
test_step_mdp_speed[True-False-False-False-False] 37.4410μs 16.7415μs 59.7318 KOps/s 58.1962 KOps/s $\color{#35bf28}+2.64\%$
test_step_mdp_speed[False-True-True-True-True] 75.1510μs 44.4499μs 22.4972 KOps/s 22.0789 KOps/s $\color{#35bf28}+1.89\%$
test_step_mdp_speed[False-True-True-True-False] 58.2310μs 26.8164μs 37.2907 KOps/s 36.5953 KOps/s $\color{#35bf28}+1.90\%$
test_step_mdp_speed[False-True-True-False-True] 56.4110μs 27.4917μs 36.3746 KOps/s 36.3645 KOps/s $\color{#35bf28}+0.03\%$
test_step_mdp_speed[False-True-True-False-False] 42.1810μs 16.3160μs 61.2897 KOps/s 60.0514 KOps/s $\color{#35bf28}+2.06\%$
test_step_mdp_speed[False-True-False-True-True] 77.5510μs 45.9479μs 21.7638 KOps/s 21.5925 KOps/s $\color{#35bf28}+0.79\%$
test_step_mdp_speed[False-True-False-True-False] 62.2310μs 29.1237μs 34.3363 KOps/s 33.8598 KOps/s $\color{#35bf28}+1.41\%$
test_step_mdp_speed[False-True-False-False-True] 3.2405ms 30.3102μs 32.9921 KOps/s 33.2314 KOps/s $\color{#d91a1a}-0.72\%$
test_step_mdp_speed[False-True-False-False-False] 57.6210μs 18.5187μs 53.9994 KOps/s 53.8656 KOps/s $\color{#35bf28}+0.25\%$
test_step_mdp_speed[False-False-True-True-True] 0.1018ms 48.2693μs 20.7171 KOps/s 20.2219 KOps/s $\color{#35bf28}+2.45\%$
test_step_mdp_speed[False-False-True-True-False] 69.7510μs 31.1655μs 32.0868 KOps/s 31.8551 KOps/s $\color{#35bf28}+0.73\%$
test_step_mdp_speed[False-False-True-False-True] 61.9410μs 30.0075μs 33.3250 KOps/s 33.5981 KOps/s $\color{#d91a1a}-0.81\%$
test_step_mdp_speed[False-False-True-False-False] 49.5710μs 18.3726μs 54.4290 KOps/s 53.6808 KOps/s $\color{#35bf28}+1.39\%$
test_step_mdp_speed[False-False-False-True-True] 86.5710μs 49.8304μs 20.0681 KOps/s 19.9327 KOps/s $\color{#35bf28}+0.68\%$
test_step_mdp_speed[False-False-False-True-False] 67.6610μs 33.4749μs 29.8732 KOps/s 29.9004 KOps/s $\color{#d91a1a}-0.09\%$
test_step_mdp_speed[False-False-False-False-True] 62.8110μs 31.3630μs 31.8847 KOps/s 31.9277 KOps/s $\color{#d91a1a}-0.13\%$
test_step_mdp_speed[False-False-False-False-False] 60.4310μs 20.5713μs 48.6115 KOps/s 49.7426 KOps/s $\color{#d91a1a}-2.27\%$
test_values[generalized_advantage_estimate-True-True] 27.2029ms 25.6629ms 38.9667 Ops/s 38.4613 Ops/s $\color{#35bf28}+1.31\%$
test_values[vec_generalized_advantage_estimate-True-True] 96.9044ms 2.8440ms 351.6149 Ops/s 329.5942 Ops/s $\textbf{\color{#35bf28}+6.68\%}$
test_values[td0_return_estimate-False-False] 0.1113ms 82.9937μs 12.0491 KOps/s 12.0502 KOps/s $-0.01\%$
test_values[td1_return_estimate-False-False] 56.8483ms 56.5459ms 17.6848 Ops/s 17.4526 Ops/s $\color{#35bf28}+1.33\%$
test_values[vec_td1_return_estimate-False-False] 1.3893ms 1.1003ms 908.8526 Ops/s 907.4141 Ops/s $\color{#35bf28}+0.16\%$
test_values[td_lambda_return_estimate-True-False] 95.1237ms 94.4724ms 10.5851 Ops/s 10.9671 Ops/s $\color{#d91a1a}-3.48\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.4241ms 1.0973ms 911.3650 Ops/s 908.3809 Ops/s $\color{#35bf28}+0.33\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 26.4857ms 25.2332ms 39.6304 Ops/s 39.5910 Ops/s $\color{#35bf28}+0.10\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0719ms 0.7641ms 1.3087 KOps/s 1.2970 KOps/s $\color{#35bf28}+0.91\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7765ms 0.6816ms 1.4671 KOps/s 1.4570 KOps/s $\color{#35bf28}+0.69\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5739ms 1.5041ms 664.8302 Ops/s 668.2482 Ops/s $\color{#d91a1a}-0.51\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7646ms 0.7223ms 1.3844 KOps/s 1.4245 KOps/s $\color{#d91a1a}-2.82\%$
test_dqn_speed[False-None] 6.9960ms 1.5250ms 655.7233 Ops/s 662.8387 Ops/s $\color{#d91a1a}-1.07\%$
test_dqn_speed[False-backward] 2.2955ms 2.1368ms 467.9910 Ops/s 471.7018 Ops/s $\color{#d91a1a}-0.79\%$
test_dqn_speed[True-None] 0.7215ms 0.5319ms 1.8801 KOps/s 1.8579 KOps/s $\color{#35bf28}+1.19\%$
test_dqn_speed[True-backward] 1.2952ms 1.2315ms 811.9998 Ops/s 892.1693 Ops/s $\textbf{\color{#d91a1a}-8.99\%}$
test_dqn_speed[reduce-overhead-None] 0.6456ms 0.5533ms 1.8072 KOps/s 1.7630 KOps/s $\color{#35bf28}+2.51\%$
test_dqn_speed[reduce-overhead-backward] 1.0990ms 1.0643ms 939.6274 Ops/s 1.0262 KOps/s $\textbf{\color{#d91a1a}-8.44\%}$
test_ddpg_speed[False-None] 3.1951ms 2.8707ms 348.3445 Ops/s 347.9369 Ops/s $\color{#35bf28}+0.12\%$
test_ddpg_speed[False-backward] 4.6929ms 4.2752ms 233.9088 Ops/s 240.6670 Ops/s $\color{#d91a1a}-2.81\%$
test_ddpg_speed[True-None] 1.2277ms 1.1290ms 885.7283 Ops/s 930.0723 Ops/s $\color{#d91a1a}-4.77\%$
test_ddpg_speed[True-backward] 2.3313ms 2.2973ms 435.2845 Ops/s 462.3873 Ops/s $\textbf{\color{#d91a1a}-5.86\%}$
test_ddpg_speed[reduce-overhead-None] 1.1421ms 1.0816ms 924.5175 Ops/s 887.3784 Ops/s $\color{#35bf28}+4.19\%$
test_ddpg_speed[reduce-overhead-backward] 1.7984ms 1.7596ms 568.2954 Ops/s 579.9509 Ops/s $\color{#d91a1a}-2.01\%$
test_sac_speed[False-None] 8.7693ms 8.2187ms 121.6737 Ops/s 121.8509 Ops/s $\color{#d91a1a}-0.15\%$
test_sac_speed[False-backward] 11.8880ms 11.4236ms 87.5382 Ops/s 88.3614 Ops/s $\color{#d91a1a}-0.93\%$
test_sac_speed[True-None] 1.6194ms 1.5281ms 654.4201 Ops/s 652.0844 Ops/s $\color{#35bf28}+0.36\%$
test_sac_speed[True-backward] 3.5176ms 3.4280ms 291.7190 Ops/s 308.7458 Ops/s $\textbf{\color{#d91a1a}-5.51\%}$
test_sac_speed[reduce-overhead-None] 23.1227ms 12.5658ms 79.5809 Ops/s 79.7755 Ops/s $\color{#d91a1a}-0.24\%$
test_sac_speed[reduce-overhead-backward] 1.6535ms 1.5126ms 661.0972 Ops/s 732.6338 Ops/s $\textbf{\color{#d91a1a}-9.76\%}$
test_redq_speed[False-None] 8.3612ms 7.5820ms 131.8920 Ops/s 130.1540 Ops/s $\color{#35bf28}+1.34\%$
test_redq_speed[False-backward] 12.6914ms 11.7552ms 85.0686 Ops/s 84.6416 Ops/s $\color{#35bf28}+0.50\%$
test_redq_speed[True-None] 2.3950ms 2.0107ms 497.3399 Ops/s 489.3878 Ops/s $\color{#35bf28}+1.62\%$
test_redq_speed[True-backward] 3.7564ms 3.7069ms 269.7659 Ops/s 268.3344 Ops/s $\color{#35bf28}+0.53\%$
test_redq_speed[reduce-overhead-None] 2.0820ms 2.0063ms 498.4222 Ops/s 489.9066 Ops/s $\color{#35bf28}+1.74\%$
test_redq_speed[reduce-overhead-backward] 4.0570ms 3.9157ms 255.3818 Ops/s 268.6092 Ops/s $\color{#d91a1a}-4.92\%$
test_redq_deprec_speed[False-None] 10.4313ms 9.5830ms 104.3519 Ops/s 107.1378 Ops/s $\color{#d91a1a}-2.60\%$
test_redq_deprec_speed[False-backward] 13.1686ms 12.6216ms 79.2290 Ops/s 79.2464 Ops/s $\color{#d91a1a}-0.02\%$
test_redq_deprec_speed[True-None] 2.4248ms 2.3461ms 426.2307 Ops/s 424.1315 Ops/s $\color{#35bf28}+0.49\%$
test_redq_deprec_speed[True-backward] 4.2483ms 4.1933ms 238.4765 Ops/s 246.7551 Ops/s $\color{#d91a1a}-3.35\%$
test_redq_deprec_speed[reduce-overhead-None] 2.6751ms 2.3637ms 423.0589 Ops/s 428.7549 Ops/s $\color{#d91a1a}-1.33\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.7210ms 4.2519ms 235.1915 Ops/s 248.2814 Ops/s $\textbf{\color{#d91a1a}-5.27\%}$
test_td3_speed[False-None] 34.7162ms 8.2785ms 120.7942 Ops/s 124.0762 Ops/s $\color{#d91a1a}-2.65\%$
test_td3_speed[False-backward] 11.3792ms 10.6435ms 93.9541 Ops/s 95.5738 Ops/s $\color{#d91a1a}-1.69\%$
test_td3_speed[True-None] 1.5978ms 1.5749ms 634.9465 Ops/s 638.8047 Ops/s $\color{#d91a1a}-0.60\%$
test_td3_speed[True-backward] 3.2263ms 3.1383ms 318.6458 Ops/s 321.9228 Ops/s $\color{#d91a1a}-1.02\%$
test_td3_speed[reduce-overhead-None] 50.2407ms 25.7721ms 38.8016 Ops/s 37.6427 Ops/s $\color{#35bf28}+3.08\%$
test_td3_speed[reduce-overhead-backward] 1.5284ms 1.4499ms 689.7013 Ops/s 686.1725 Ops/s $\color{#35bf28}+0.51\%$
test_cql_speed[False-None] 17.5791ms 16.9671ms 58.9374 Ops/s 58.6998 Ops/s $\color{#35bf28}+0.40\%$
test_cql_speed[False-backward] 23.1771ms 22.6157ms 44.2171 Ops/s 43.9866 Ops/s $\color{#35bf28}+0.52\%$
test_cql_speed[True-None] 3.3530ms 2.9554ms 338.3679 Ops/s 341.4054 Ops/s $\color{#d91a1a}-0.89\%$
test_cql_speed[True-backward] 5.3811ms 5.2734ms 189.6316 Ops/s 189.5170 Ops/s $\color{#35bf28}+0.06\%$
test_cql_speed[reduce-overhead-None] 21.3887ms 13.1565ms 76.0083 Ops/s 75.8922 Ops/s $\color{#35bf28}+0.15\%$
test_cql_speed[reduce-overhead-backward] 1.5914ms 1.5163ms 659.4868 Ops/s 646.5971 Ops/s $\color{#35bf28}+1.99\%$
test_a2c_speed[False-None] 3.4586ms 3.2444ms 308.2255 Ops/s 304.6846 Ops/s $\color{#35bf28}+1.16\%$
test_a2c_speed[False-backward] 6.6123ms 6.1736ms 161.9813 Ops/s 158.3947 Ops/s $\color{#35bf28}+2.26\%$
test_a2c_speed[True-None] 1.3813ms 1.0031ms 996.8978 Ops/s 994.9199 Ops/s $\color{#35bf28}+0.20\%$
test_a2c_speed[True-backward] 2.8115ms 2.7549ms 362.9869 Ops/s 359.8626 Ops/s $\color{#35bf28}+0.87\%$
test_a2c_speed[reduce-overhead-None] 21.6190ms 11.5506ms 86.5754 Ops/s 86.9476 Ops/s $\color{#d91a1a}-0.43\%$
test_a2c_speed[reduce-overhead-backward] 1.1734ms 1.1213ms 891.7942 Ops/s 867.6619 Ops/s $\color{#35bf28}+2.78\%$
test_ppo_speed[False-None] 4.0156ms 3.7543ms 266.3602 Ops/s 266.3031 Ops/s $\color{#35bf28}+0.02\%$
test_ppo_speed[False-backward] 7.5635ms 7.1848ms 139.1818 Ops/s 135.8776 Ops/s $\color{#35bf28}+2.43\%$
test_ppo_speed[True-None] 1.0621ms 0.9835ms 1.0168 KOps/s 1.0384 KOps/s $\color{#d91a1a}-2.08\%$
test_ppo_speed[True-backward] 2.7694ms 2.7068ms 369.4425 Ops/s 371.4516 Ops/s $\color{#d91a1a}-0.54\%$
test_ppo_speed[reduce-overhead-None] 0.6030ms 0.5081ms 1.9681 KOps/s 1.9002 KOps/s $\color{#35bf28}+3.57\%$
test_ppo_speed[reduce-overhead-backward] 1.1800ms 1.1132ms 898.3053 Ops/s 863.3759 Ops/s $\color{#35bf28}+4.05\%$
test_reinforce_speed[False-None] 2.3785ms 2.2858ms 437.4829 Ops/s 436.0569 Ops/s $\color{#35bf28}+0.33\%$
test_reinforce_speed[False-backward] 3.7859ms 3.3369ms 299.6765 Ops/s 287.5094 Ops/s $\color{#35bf28}+4.23\%$
test_reinforce_speed[True-None] 0.9707ms 0.8205ms 1.2187 KOps/s 1.1999 KOps/s $\color{#35bf28}+1.57\%$
test_reinforce_speed[True-backward] 2.9152ms 2.5615ms 390.3915 Ops/s 388.2328 Ops/s $\color{#35bf28}+0.56\%$
test_reinforce_speed[reduce-overhead-None] 21.4193ms 11.4648ms 87.2234 Ops/s 87.9323 Ops/s $\color{#d91a1a}-0.81\%$
test_reinforce_speed[reduce-overhead-backward] 1.2166ms 1.1705ms 854.3291 Ops/s 826.1052 Ops/s $\color{#35bf28}+3.42\%$
test_iql_speed[False-None] 9.8663ms 9.3562ms 106.8807 Ops/s 106.9833 Ops/s $\color{#d91a1a}-0.10\%$
test_iql_speed[False-backward] 14.1155ms 13.3950ms 74.6548 Ops/s 74.5014 Ops/s $\color{#35bf28}+0.21\%$
test_iql_speed[True-None] 1.8735ms 1.7594ms 568.3826 Ops/s 579.2199 Ops/s $\color{#d91a1a}-1.87\%$
test_iql_speed[True-backward] 4.7167ms 4.4385ms 225.2989 Ops/s 227.1128 Ops/s $\color{#d91a1a}-0.80\%$
test_iql_speed[reduce-overhead-None] 20.5775ms 11.6144ms 86.0998 Ops/s 87.5072 Ops/s $\color{#d91a1a}-1.61\%$
test_iql_speed[reduce-overhead-backward] 1.6731ms 1.6077ms 622.0125 Ops/s 622.3893 Ops/s $\color{#d91a1a}-0.06\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.9602ms 6.4135ms 155.9217 Ops/s 151.7850 Ops/s $\color{#35bf28}+2.73\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5998ms 0.3004ms 3.3290 KOps/s 3.0002 KOps/s $\textbf{\color{#35bf28}+10.96\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.4738ms 0.2888ms 3.4627 KOps/s 2.9390 KOps/s $\textbf{\color{#35bf28}+17.82\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3871ms 6.1643ms 162.2248 Ops/s 157.7568 Ops/s $\color{#35bf28}+2.83\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6852ms 0.3159ms 3.1654 KOps/s 3.8360 KOps/s $\textbf{\color{#d91a1a}-17.48\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5446ms 0.2763ms 3.6189 KOps/s 3.9250 KOps/s $\textbf{\color{#d91a1a}-7.80\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.5426ms 1.3281ms 752.9812 Ops/s 778.1544 Ops/s $\color{#d91a1a}-3.23\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4070ms 1.2131ms 824.3347 Ops/s 825.3771 Ops/s $\color{#d91a1a}-0.13\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5306ms 6.3696ms 156.9954 Ops/s 154.4620 Ops/s $\color{#35bf28}+1.64\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.8752ms 0.4703ms 2.1261 KOps/s 2.2263 KOps/s $\color{#d91a1a}-4.50\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7757ms 0.4314ms 2.3183 KOps/s 2.3587 KOps/s $\color{#d91a1a}-1.71\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 10.2188ms 6.3096ms 158.4876 Ops/s 159.6461 Ops/s $\color{#d91a1a}-0.73\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7124ms 0.3435ms 2.9109 KOps/s 2.7466 KOps/s $\textbf{\color{#35bf28}+5.98\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6108ms 0.3120ms 3.2055 KOps/s 2.6298 KOps/s $\textbf{\color{#35bf28}+21.89\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3975ms 6.1459ms 162.7089 Ops/s 159.7630 Ops/s $\color{#35bf28}+1.84\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.4910ms 0.3095ms 3.2312 KOps/s 2.9228 KOps/s $\textbf{\color{#35bf28}+10.55\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6304ms 0.3328ms 3.0044 KOps/s 2.8152 KOps/s $\textbf{\color{#35bf28}+6.72\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4813ms 6.3247ms 158.1104 Ops/s 155.6814 Ops/s $\color{#35bf28}+1.56\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8180ms 0.4759ms 2.1013 KOps/s 2.2560 KOps/s $\textbf{\color{#d91a1a}-6.86\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6844ms 0.4580ms 2.1836 KOps/s 2.3777 KOps/s $\textbf{\color{#d91a1a}-8.16\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.8747ms 5.2918ms 188.9709 Ops/s 188.0460 Ops/s $\color{#35bf28}+0.49\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 3.8979ms 1.7774ms 562.6057 Ops/s 432.2282 Ops/s $\textbf{\color{#35bf28}+30.16\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 8.2999ms 1.2460ms 802.5430 Ops/s 864.7287 Ops/s $\textbf{\color{#d91a1a}-7.19\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 7.6034ms 5.3669ms 186.3261 Ops/s 188.8816 Ops/s $\color{#d91a1a}-1.35\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 8.2521ms 2.0145ms 496.4040 Ops/s 479.6848 Ops/s $\color{#35bf28}+3.49\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.1491ms 1.2663ms 789.6929 Ops/s 773.8982 Ops/s $\color{#35bf28}+2.04\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 0.5038s 15.5501ms 64.3085 Ops/s 32.8982 Ops/s $\textbf{\color{#35bf28}+95.48\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 12.2398ms 2.1291ms 469.6914 Ops/s 511.9036 Ops/s $\textbf{\color{#d91a1a}-8.25\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.8785ms 1.3704ms 729.7262 Ops/s 734.7569 Ops/s $\color{#d91a1a}-0.68\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 14.3392ms 13.6344ms 73.3441 Ops/s 74.3426 Ops/s $\color{#d91a1a}-1.34\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 19.8749ms 17.8927ms 55.8888 Ops/s 56.4516 Ops/s $\color{#d91a1a}-1.00\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.7553ms 18.0037ms 55.5443 Ops/s 52.3357 Ops/s $\textbf{\color{#35bf28}+6.13\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 19.6507ms 17.7100ms 56.4651 Ops/s 56.2990 Ops/s $\color{#35bf28}+0.30\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 18.1340ms 17.6527ms 56.6484 Ops/s 54.9604 Ops/s $\color{#35bf28}+3.07\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 20.6964ms 18.8453ms 53.0638 Ops/s 51.7270 Ops/s $\color{#35bf28}+2.58\%$

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
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