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] PPO compatibility with compile #2652

Merged
merged 41 commits into from
Dec 16, 2024
Merged

Conversation

vmoens
Copy link
Contributor

@vmoens vmoens commented Dec 15, 2024

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Dec 15, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2652

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

❌ 1 New Failure, 7 Unrelated Failures

As of commit 99db504 with merge base 6482766 (image):

NEW FAILURE - The following job has failed:

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 Dec 15, 2024
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: fc3b0261c1b59cd8cd7e04b3f173e423495be57e
Pull Request resolved: #2652
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: 9a510fb20f188302042f47cdaa813db46f795c69
Pull Request resolved: #2652
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: 1efb8533bafc4841ba881c7fd79e6d2e76bb7395
Pull Request resolved: #2652
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: 4f84b77e2fe21d0cd0e0cd64fcdc5fe9e86ce832
Pull Request resolved: #2652
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: f39abc21fa0b237302cbf49523dfd99f7d671a34
Pull Request resolved: #2652
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: 37d27cddfafbf3bca1c766965fa6c032307f6085
Pull Request resolved: #2652
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: ec5b0ec9d59bdb49a4b128f21d08d9ee334bfd6b
Pull Request resolved: #2652
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: e3a78ae27cd855969b1a5c3c84e6d95df6d410f4
Pull Request resolved: #2652
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: ecb24618390dc38ffb35499328e5a2a92a8c1651
Pull Request resolved: #2652
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: ada52e4e1f02e973e751bbbdaf5312cbf1dcf02c
Pull Request resolved: #2652
[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: 2948bd9374f18ef1b6f7d37863a0b9cf62db9685
Pull Request resolved: #2652
Copy link

github-actions bot commented Dec 15, 2024

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}16$. Worsened: $\large\color{#d91a1a}4$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.4345s 0.4328s 2.3104 Ops/s 2.1715 Ops/s $\textbf{\color{#35bf28}+6.40\%}$
test_transformed 0.6174s 0.6112s 1.6360 Ops/s 1.5547 Ops/s $\textbf{\color{#35bf28}+5.23\%}$
test_serial 1.3572s 1.3543s 0.7384 Ops/s 0.7207 Ops/s $\color{#35bf28}+2.46\%$
test_parallel 1.3950s 1.3038s 0.7670 Ops/s 0.7566 Ops/s $\color{#35bf28}+1.37\%$
test_step_mdp_speed[True-True-True-True-True] 0.2190ms 29.6000μs 33.7838 KOps/s 33.1924 KOps/s $\color{#35bf28}+1.78\%$
test_step_mdp_speed[True-True-True-True-False] 53.1900μs 17.4786μs 57.2128 KOps/s 56.5570 KOps/s $\color{#35bf28}+1.16\%$
test_step_mdp_speed[True-True-True-False-True] 45.6150μs 16.7632μs 59.6545 KOps/s 58.9490 KOps/s $\color{#35bf28}+1.20\%$
test_step_mdp_speed[True-True-True-False-False] 35.8970μs 9.8703μs 101.3145 KOps/s 100.9922 KOps/s $\color{#35bf28}+0.32\%$
test_step_mdp_speed[True-True-False-True-True] 86.2320μs 32.2136μs 31.0428 KOps/s 31.3547 KOps/s $\color{#d91a1a}-0.99\%$
test_step_mdp_speed[True-True-False-True-False] 55.5240μs 19.5343μs 51.1921 KOps/s 51.5512 KOps/s $\color{#d91a1a}-0.70\%$
test_step_mdp_speed[True-True-False-False-True] 49.8830μs 18.8519μs 53.0451 KOps/s 52.9004 KOps/s $\color{#35bf28}+0.27\%$
test_step_mdp_speed[True-True-False-False-False] 33.6230μs 11.8834μs 84.1513 KOps/s 85.1297 KOps/s $\color{#d91a1a}-1.15\%$
test_step_mdp_speed[True-False-True-True-True] 77.7250μs 33.7351μs 29.6427 KOps/s 29.1488 KOps/s $\color{#35bf28}+1.69\%$
test_step_mdp_speed[True-False-True-True-False] 59.7820μs 21.4186μs 46.6885 KOps/s 46.3797 KOps/s $\color{#35bf28}+0.67\%$
test_step_mdp_speed[True-False-True-False-True] 67.3060μs 19.0041μs 52.6203 KOps/s 52.2574 KOps/s $\color{#35bf28}+0.69\%$
test_step_mdp_speed[True-False-True-False-False] 45.7360μs 11.6293μs 85.9894 KOps/s 83.2994 KOps/s $\color{#35bf28}+3.23\%$
test_step_mdp_speed[True-False-False-True-True] 74.7900μs 35.7690μs 27.9572 KOps/s 27.6553 KOps/s $\color{#35bf28}+1.09\%$
test_step_mdp_speed[True-False-False-True-False] 59.3610μs 23.1849μs 43.1315 KOps/s 42.4846 KOps/s $\color{#35bf28}+1.52\%$
test_step_mdp_speed[True-False-False-False-True] 53.8100μs 20.8242μs 48.0211 KOps/s 48.3068 KOps/s $\color{#d91a1a}-0.59\%$
test_step_mdp_speed[True-False-False-False-False] 0.6963ms 13.3329μs 75.0024 KOps/s 73.9276 KOps/s $\color{#35bf28}+1.45\%$
test_step_mdp_speed[False-True-True-True-True] 74.8700μs 33.9372μs 29.4662 KOps/s 29.1145 KOps/s $\color{#35bf28}+1.21\%$
test_step_mdp_speed[False-True-True-True-False] 57.3370μs 21.4896μs 46.5342 KOps/s 46.1877 KOps/s $\color{#35bf28}+0.75\%$
test_step_mdp_speed[False-True-True-False-True] 55.8250μs 21.6960μs 46.0915 KOps/s 46.0560 KOps/s $\color{#35bf28}+0.08\%$
test_step_mdp_speed[False-True-True-False-False] 38.7530μs 13.0214μs 76.7965 KOps/s 75.6224 KOps/s $\color{#35bf28}+1.55\%$
test_step_mdp_speed[False-True-False-True-True] 78.2360μs 36.2121μs 27.6151 KOps/s 27.7079 KOps/s $\color{#d91a1a}-0.34\%$
test_step_mdp_speed[False-True-False-True-False] 71.0040μs 23.3997μs 42.7356 KOps/s 42.7511 KOps/s $\color{#d91a1a}-0.04\%$
test_step_mdp_speed[False-True-False-False-True] 2.6630ms 23.0071μs 43.4649 KOps/s 42.5185 KOps/s $\color{#35bf28}+2.23\%$
test_step_mdp_speed[False-True-False-False-False] 39.3230μs 14.8866μs 67.1744 KOps/s 66.3061 KOps/s $\color{#35bf28}+1.31\%$
test_step_mdp_speed[False-False-True-True-True] 81.4720μs 37.3267μs 26.7905 KOps/s 26.2777 KOps/s $\color{#35bf28}+1.95\%$
test_step_mdp_speed[False-False-True-True-False] 80.7790μs 24.9569μs 40.0690 KOps/s 39.4700 KOps/s $\color{#35bf28}+1.52\%$
test_step_mdp_speed[False-False-True-False-True] 52.5380μs 22.9945μs 43.4887 KOps/s 43.0719 KOps/s $\color{#35bf28}+0.97\%$
test_step_mdp_speed[False-False-True-False-False] 47.4990μs 14.8372μs 67.3980 KOps/s 66.0113 KOps/s $\color{#35bf28}+2.10\%$
test_step_mdp_speed[False-False-False-True-True] 73.1370μs 39.1084μs 25.5700 KOps/s 25.2742 KOps/s $\color{#35bf28}+1.17\%$
test_step_mdp_speed[False-False-False-True-False] 59.5410μs 26.9432μs 37.1151 KOps/s 37.2273 KOps/s $\color{#d91a1a}-0.30\%$
test_step_mdp_speed[False-False-False-False-True] 55.8350μs 24.4760μs 40.8563 KOps/s 40.2373 KOps/s $\color{#35bf28}+1.54\%$
test_step_mdp_speed[False-False-False-False-False] 76.2930μs 16.3240μs 61.2595 KOps/s 59.8124 KOps/s $\color{#35bf28}+2.42\%$
test_values[generalized_advantage_estimate-True-True] 12.0216ms 9.5232ms 105.0066 Ops/s 103.8931 Ops/s $\color{#35bf28}+1.07\%$
test_values[vec_generalized_advantage_estimate-True-True] 37.0907ms 33.5642ms 29.7937 Ops/s 27.5852 Ops/s $\textbf{\color{#35bf28}+8.01\%}$
test_values[td0_return_estimate-False-False] 0.2716ms 0.1786ms 5.5976 KOps/s 5.5582 KOps/s $\color{#35bf28}+0.71\%$
test_values[td1_return_estimate-False-False] 26.7450ms 23.8721ms 41.8899 Ops/s 41.2767 Ops/s $\color{#35bf28}+1.49\%$
test_values[vec_td1_return_estimate-False-False] 35.0410ms 33.6098ms 29.7533 Ops/s 27.5059 Ops/s $\textbf{\color{#35bf28}+8.17\%}$
test_values[td_lambda_return_estimate-True-False] 35.8194ms 34.3144ms 29.1423 Ops/s 28.9001 Ops/s $\color{#35bf28}+0.84\%$
test_values[vec_td_lambda_return_estimate-True-False] 35.5881ms 33.5775ms 29.7819 Ops/s 27.5773 Ops/s $\textbf{\color{#35bf28}+7.99\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.5471ms 8.2809ms 120.7600 Ops/s 120.0171 Ops/s $\color{#35bf28}+0.62\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.9731ms 1.9267ms 519.0341 Ops/s 408.2475 Ops/s $\textbf{\color{#35bf28}+27.14\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6052ms 0.3560ms 2.8086 KOps/s 2.7466 KOps/s $\color{#35bf28}+2.26\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 40.5701ms 39.4667ms 25.3378 Ops/s 21.8844 Ops/s $\textbf{\color{#35bf28}+15.78\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 3.8942ms 3.0506ms 327.8094 Ops/s 289.3194 Ops/s $\textbf{\color{#35bf28}+13.30\%}$
test_dqn_speed[False-None] 5.8617ms 1.3661ms 732.0286 Ops/s 715.7973 Ops/s $\color{#35bf28}+2.27\%$
test_dqn_speed[False-backward] 1.8986ms 1.8361ms 544.6238 Ops/s 533.1387 Ops/s $\color{#35bf28}+2.15\%$
test_dqn_speed[True-None] 0.7596ms 0.4613ms 2.1678 KOps/s 2.1363 KOps/s $\color{#35bf28}+1.48\%$
test_dqn_speed[True-backward] 0.9442ms 0.8742ms 1.1440 KOps/s 1.1228 KOps/s $\color{#35bf28}+1.89\%$
test_dqn_speed[reduce-overhead-None] 0.5583ms 0.4576ms 2.1852 KOps/s 2.1330 KOps/s $\color{#35bf28}+2.45\%$
test_dqn_speed[reduce-overhead-backward] 1.0009ms 0.8879ms 1.1263 KOps/s 1.0851 KOps/s $\color{#35bf28}+3.79\%$
test_ddpg_speed[False-None] 3.5558ms 2.8492ms 350.9717 Ops/s 342.9155 Ops/s $\color{#35bf28}+2.35\%$
test_ddpg_speed[False-backward] 4.3719ms 3.9762ms 251.4961 Ops/s 248.3760 Ops/s $\color{#35bf28}+1.26\%$
test_ddpg_speed[True-None] 1.3609ms 0.9929ms 1.0071 KOps/s 989.9345 Ops/s $\color{#35bf28}+1.74\%$
test_ddpg_speed[True-backward] 1.9740ms 1.8708ms 534.5353 Ops/s 513.0223 Ops/s $\color{#35bf28}+4.19\%$
test_ddpg_speed[reduce-overhead-None] 1.4247ms 0.9967ms 1.0033 KOps/s 983.0831 Ops/s $\color{#35bf28}+2.05\%$
test_ddpg_speed[reduce-overhead-backward] 1.9861ms 1.9027ms 525.5761 Ops/s 509.1473 Ops/s $\color{#35bf28}+3.23\%$
test_sac_speed[False-None] 8.5233ms 7.9597ms 125.6325 Ops/s 119.5938 Ops/s $\textbf{\color{#35bf28}+5.05\%}$
test_sac_speed[False-backward] 12.8377ms 10.7046ms 93.4178 Ops/s 85.6141 Ops/s $\textbf{\color{#35bf28}+9.11\%}$
test_sac_speed[True-None] 2.4484ms 1.8182ms 550.0092 Ops/s 545.3414 Ops/s $\color{#35bf28}+0.86\%$
test_sac_speed[True-backward] 3.7961ms 3.6077ms 277.1832 Ops/s 273.7977 Ops/s $\color{#35bf28}+1.24\%$
test_sac_speed[reduce-overhead-None] 2.5746ms 1.8643ms 536.3813 Ops/s 537.4816 Ops/s $\color{#d91a1a}-0.20\%$
test_sac_speed[reduce-overhead-backward] 3.7565ms 3.5873ms 278.7607 Ops/s 272.6579 Ops/s $\color{#35bf28}+2.24\%$
test_redq_speed[False-None] 0.2374s 15.6682ms 63.8234 Ops/s 63.1258 Ops/s $\color{#35bf28}+1.11\%$
test_redq_speed[False-backward] 23.4907ms 22.1962ms 45.0529 Ops/s 43.4212 Ops/s $\color{#35bf28}+3.76\%$
test_redq_speed[True-None] 5.8198ms 4.7751ms 209.4216 Ops/s 207.9806 Ops/s $\color{#35bf28}+0.69\%$
test_redq_speed[True-backward] 13.4462ms 12.1743ms 82.1401 Ops/s 80.2276 Ops/s $\color{#35bf28}+2.38\%$
test_redq_speed[reduce-overhead-None] 5.6438ms 4.8722ms 205.2478 Ops/s 205.4934 Ops/s $\color{#d91a1a}-0.12\%$
test_redq_speed[reduce-overhead-backward] 16.0275ms 12.5208ms 79.8668 Ops/s 79.0934 Ops/s $\color{#35bf28}+0.98\%$
test_redq_deprec_speed[False-None] 0.2501s 15.9043ms 62.8762 Ops/s 74.6227 Ops/s $\textbf{\color{#d91a1a}-15.74\%}$
test_redq_deprec_speed[False-backward] 19.3769ms 18.2765ms 54.7149 Ops/s 52.3114 Ops/s $\color{#35bf28}+4.59\%$
test_redq_deprec_speed[True-None] 3.9692ms 3.5892ms 278.6134 Ops/s 277.6641 Ops/s $\color{#35bf28}+0.34\%$
test_redq_deprec_speed[True-backward] 9.0902ms 8.0821ms 123.7297 Ops/s 118.7311 Ops/s $\color{#35bf28}+4.21\%$
test_redq_deprec_speed[reduce-overhead-None] 4.4919ms 3.5977ms 277.9538 Ops/s 273.0833 Ops/s $\color{#35bf28}+1.78\%$
test_redq_deprec_speed[reduce-overhead-backward] 9.1087ms 8.2611ms 121.0498 Ops/s 121.5866 Ops/s $\color{#d91a1a}-0.44\%$
test_td3_speed[False-None] 8.2077ms 7.9066ms 126.4763 Ops/s 120.9327 Ops/s $\color{#35bf28}+4.58\%$
test_td3_speed[False-backward] 11.4600ms 10.4195ms 95.9736 Ops/s 92.4879 Ops/s $\color{#35bf28}+3.77\%$
test_td3_speed[True-None] 1.8988ms 1.6984ms 588.8062 Ops/s 571.5676 Ops/s $\color{#35bf28}+3.02\%$
test_td3_speed[True-backward] 3.4231ms 3.3173ms 301.4538 Ops/s 294.9520 Ops/s $\color{#35bf28}+2.20\%$
test_td3_speed[reduce-overhead-None] 1.8671ms 1.6956ms 589.7580 Ops/s 572.3500 Ops/s $\color{#35bf28}+3.04\%$
test_td3_speed[reduce-overhead-backward] 3.4254ms 3.3063ms 302.4571 Ops/s 283.8285 Ops/s $\textbf{\color{#35bf28}+6.56\%}$
test_cql_speed[False-None] 38.4208ms 36.1417ms 27.6689 Ops/s 26.8267 Ops/s $\color{#35bf28}+3.14\%$
test_cql_speed[False-backward] 48.4618ms 46.0836ms 21.6997 Ops/s 20.9435 Ops/s $\color{#35bf28}+3.61\%$
test_cql_speed[True-None] 16.8671ms 15.7135ms 63.6394 Ops/s 62.4267 Ops/s $\color{#35bf28}+1.94\%$
test_cql_speed[True-backward] 23.7196ms 22.5873ms 44.2726 Ops/s 43.5132 Ops/s $\color{#35bf28}+1.75\%$
test_cql_speed[reduce-overhead-None] 16.5402ms 15.6905ms 63.7328 Ops/s 61.1337 Ops/s $\color{#35bf28}+4.25\%$
test_cql_speed[reduce-overhead-backward] 23.8140ms 22.6437ms 44.1623 Ops/s 44.2694 Ops/s $\color{#d91a1a}-0.24\%$
test_a2c_speed[False-None] 8.2212ms 7.5341ms 132.7298 Ops/s 135.4802 Ops/s $\color{#d91a1a}-2.03\%$
test_a2c_speed[False-backward] 16.2305ms 14.7506ms 67.7938 Ops/s 68.2936 Ops/s $\color{#d91a1a}-0.73\%$
test_a2c_speed[True-None] 5.1490ms 4.3307ms 230.9107 Ops/s 229.5436 Ops/s $\color{#35bf28}+0.60\%$
test_a2c_speed[True-backward] 11.4744ms 11.0876ms 90.1908 Ops/s 89.4545 Ops/s $\color{#35bf28}+0.82\%$
test_a2c_speed[reduce-overhead-None] 5.0120ms 4.2486ms 235.3695 Ops/s 233.5486 Ops/s $\color{#35bf28}+0.78\%$
test_a2c_speed[reduce-overhead-backward] 13.2784ms 11.4551ms 87.2975 Ops/s 89.6415 Ops/s $\color{#d91a1a}-2.61\%$
test_ppo_speed[False-None] 8.4754ms 7.6787ms 130.2310 Ops/s 131.2567 Ops/s $\color{#d91a1a}-0.78\%$
test_ppo_speed[False-backward] 15.8498ms 15.2448ms 65.5959 Ops/s 66.1193 Ops/s $\color{#d91a1a}-0.79\%$
test_ppo_speed[True-None] 4.2492ms 3.7661ms 265.5261 Ops/s 266.0304 Ops/s $\color{#d91a1a}-0.19\%$
test_ppo_speed[True-backward] 10.2798ms 9.8255ms 101.7755 Ops/s 101.2624 Ops/s $\color{#35bf28}+0.51\%$
test_ppo_speed[reduce-overhead-None] 4.4896ms 3.7825ms 264.3755 Ops/s 265.3683 Ops/s $\color{#d91a1a}-0.37\%$
test_ppo_speed[reduce-overhead-backward] 10.2887ms 9.8621ms 101.3987 Ops/s 103.4452 Ops/s $\color{#d91a1a}-1.98\%$
test_reinforce_speed[False-None] 7.4287ms 6.6629ms 150.0859 Ops/s 149.0026 Ops/s $\color{#35bf28}+0.73\%$
test_reinforce_speed[False-backward] 13.2482ms 10.1658ms 98.3689 Ops/s 98.7790 Ops/s $\color{#d91a1a}-0.42\%$
test_reinforce_speed[True-None] 3.3281ms 2.6472ms 377.7578 Ops/s 371.2639 Ops/s $\color{#35bf28}+1.75\%$
test_reinforce_speed[True-backward] 9.4411ms 8.6731ms 115.2992 Ops/s 113.6375 Ops/s $\color{#35bf28}+1.46\%$
test_reinforce_speed[reduce-overhead-None] 3.2013ms 2.6430ms 378.3510 Ops/s 364.7896 Ops/s $\color{#35bf28}+3.72\%$
test_reinforce_speed[reduce-overhead-backward] 9.1641ms 8.6222ms 115.9791 Ops/s 114.9219 Ops/s $\color{#35bf28}+0.92\%$
test_iql_speed[False-None] 35.3547ms 32.1442ms 31.1098 Ops/s 29.9856 Ops/s $\color{#35bf28}+3.75\%$
test_iql_speed[False-backward] 46.7584ms 45.0488ms 22.1982 Ops/s 21.3762 Ops/s $\color{#35bf28}+3.85\%$
test_iql_speed[True-None] 11.4830ms 10.7528ms 92.9987 Ops/s 91.4041 Ops/s $\color{#35bf28}+1.74\%$
test_iql_speed[True-backward] 22.9818ms 21.7866ms 45.8997 Ops/s 44.8201 Ops/s $\color{#35bf28}+2.41\%$
test_iql_speed[reduce-overhead-None] 12.4987ms 10.7572ms 92.9607 Ops/s 91.0896 Ops/s $\color{#35bf28}+2.05\%$
test_iql_speed[reduce-overhead-backward] 22.8505ms 21.8415ms 45.7845 Ops/s 45.1813 Ops/s $\color{#35bf28}+1.33\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.5130ms 4.9302ms 202.8307 Ops/s 193.6067 Ops/s $\color{#35bf28}+4.76\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.7157ms 0.5030ms 1.9879 KOps/s 1.8848 KOps/s $\textbf{\color{#35bf28}+5.47\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8093ms 0.4818ms 2.0755 KOps/s 2.0321 KOps/s $\color{#35bf28}+2.13\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.2964ms 4.8575ms 205.8661 Ops/s 200.9711 Ops/s $\color{#35bf28}+2.44\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.2807ms 0.4956ms 2.0177 KOps/s 1.8954 KOps/s $\textbf{\color{#35bf28}+6.45\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7266ms 0.4731ms 2.1139 KOps/s 2.1217 KOps/s $\color{#d91a1a}-0.37\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.8946ms 1.6055ms 622.8707 Ops/s 606.8028 Ops/s $\color{#35bf28}+2.65\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.3101ms 1.5660ms 638.5650 Ops/s 624.3099 Ops/s $\color{#35bf28}+2.28\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.2357ms 4.9078ms 203.7576 Ops/s 197.3372 Ops/s $\color{#35bf28}+3.25\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1972ms 0.6366ms 1.5708 KOps/s 1.5371 KOps/s $\color{#35bf28}+2.19\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.0022ms 0.6138ms 1.6291 KOps/s 1.6052 KOps/s $\color{#35bf28}+1.49\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.0559ms 4.7557ms 210.2756 Ops/s 205.8243 Ops/s $\color{#35bf28}+2.16\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.8145ms 0.5059ms 1.9767 KOps/s 1.9108 KOps/s $\color{#35bf28}+3.45\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8234ms 0.4869ms 2.0536 KOps/s 2.0725 KOps/s $\color{#d91a1a}-0.91\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 7.4838ms 4.7859ms 208.9453 Ops/s 206.3298 Ops/s $\color{#35bf28}+1.27\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.1138ms 0.4893ms 2.0436 KOps/s 2.0135 KOps/s $\color{#35bf28}+1.50\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6854ms 0.4679ms 2.1371 KOps/s 2.0662 KOps/s $\color{#35bf28}+3.43\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.1324ms 4.8640ms 205.5909 Ops/s 201.7711 Ops/s $\color{#35bf28}+1.89\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1953ms 0.6492ms 1.5404 KOps/s 1.5393 KOps/s $\color{#35bf28}+0.07\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8602ms 0.6122ms 1.6334 KOps/s 1.5736 KOps/s $\color{#35bf28}+3.80\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 5.5007ms 4.2277ms 236.5342 Ops/s 37.1477 Ops/s $\textbf{\color{#35bf28}+536.74\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 8.3579ms 2.4812ms 403.0309 Ops/s 427.5043 Ops/s $\textbf{\color{#d91a1a}-5.72\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.6762ms 1.3020ms 768.0231 Ops/s 780.0624 Ops/s $\color{#d91a1a}-1.54\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4446s 13.0612ms 76.5628 Ops/s 223.4738 Ops/s $\textbf{\color{#d91a1a}-65.74\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 3.4176ms 2.1719ms 460.4295 Ops/s 396.6475 Ops/s $\textbf{\color{#35bf28}+16.08\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 6.9964ms 1.3887ms 720.1010 Ops/s 789.0146 Ops/s $\textbf{\color{#d91a1a}-8.73\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 5.9587ms 4.4337ms 225.5467 Ops/s 230.4346 Ops/s $\color{#d91a1a}-2.12\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 6.7544ms 2.4335ms 410.9298 Ops/s 404.1934 Ops/s $\color{#35bf28}+1.67\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 5.7568ms 1.4768ms 677.1368 Ops/s 652.9999 Ops/s $\color{#35bf28}+3.70\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 12.7890ms 11.4606ms 87.2553 Ops/s 79.9413 Ops/s $\textbf{\color{#35bf28}+9.15\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 16.0692ms 14.9115ms 67.0621 Ops/s 64.3777 Ops/s $\color{#35bf28}+4.17\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 21.8820ms 20.1441ms 49.6423 Ops/s 47.9606 Ops/s $\color{#35bf28}+3.51\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 16.2705ms 15.2476ms 65.5840 Ops/s 64.1964 Ops/s $\color{#35bf28}+2.16\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 21.4038ms 20.2038ms 49.4956 Ops/s 49.3275 Ops/s $\color{#35bf28}+0.34\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 17.5656ms 16.4531ms 60.7788 Ops/s 58.6456 Ops/s $\color{#35bf28}+3.64\%$

[ghstack-poisoned]
vmoens added a commit that referenced this pull request Dec 15, 2024
ghstack-source-id: 2196886f08e9153a56203c8c5d01bd2155ce05ed
Pull Request resolved: #2652
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
@vmoens vmoens added the enhancement New feature or request label Dec 15, 2024
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
@vmoens vmoens merged commit 99db504 into gh/vmoens/53/base Dec 16, 2024
70 of 78 checks passed
vmoens added a commit that referenced this pull request Dec 16, 2024
ghstack-source-id: 0ed29f352fcd85f0dc0683d90e95bdbecf6c14f9
Pull Request resolved: #2652
@vmoens vmoens deleted the gh/vmoens/53/head branch December 16, 2024 01:15
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