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

[Doc] Add docstring for MCTSForest.extend #2795

Merged
merged 3 commits into from
Feb 25, 2025

Conversation

kurtamohler
Copy link
Collaborator

@kurtamohler kurtamohler commented Feb 19, 2025

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Feb 19, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2795

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

❌ 3 New Failures, 2 Unrelated Failures

As of commit 248c871 with merge base d4f8846 (image):

NEW FAILURES - The following jobs have 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 Feb 19, 2025
kurtamohler added a commit to kurtamohler/torchrl that referenced this pull request Feb 19, 2025
ghstack-source-id: dbef5e48ea55db6ba7867e1b24eb4711ad08af61
Pull Request resolved: pytorch#2795
@kurtamohler kurtamohler requested a review from vmoens February 19, 2025 21:39
kurtamohler added a commit to kurtamohler/torchrl that referenced this pull request Feb 19, 2025
ghstack-source-id: dbef5e48ea55db6ba7867e1b24eb4711ad08af61
Pull Request resolved: pytorch#2795
Copy link

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}13$. Worsened: $\large\color{#d91a1a}5$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.6042s 0.5125s 1.9511 Ops/s 1.9033 Ops/s $\color{#35bf28}+2.51\%$
test_transformed 1.0953s 0.9991s 1.0009 Ops/s 0.9570 Ops/s $\color{#35bf28}+4.59\%$
test_serial 1.5946s 1.4944s 0.6692 Ops/s 0.6545 Ops/s $\color{#35bf28}+2.25\%$
test_parallel 1.3801s 1.2919s 0.7740 Ops/s 0.7562 Ops/s $\color{#35bf28}+2.36\%$
test_step_mdp_speed[True-True-True-True-True] 0.3676ms 29.8943μs 33.4512 KOps/s 32.9366 KOps/s $\color{#35bf28}+1.56\%$
test_step_mdp_speed[True-True-True-True-False] 41.7280μs 17.5650μs 56.9314 KOps/s 56.2846 KOps/s $\color{#35bf28}+1.15\%$
test_step_mdp_speed[True-True-True-False-True] 49.1110μs 16.6258μs 60.1475 KOps/s 58.5714 KOps/s $\color{#35bf28}+2.69\%$
test_step_mdp_speed[True-True-True-False-False] 37.6510μs 9.8388μs 101.6385 KOps/s 100.6982 KOps/s $\color{#35bf28}+0.93\%$
test_step_mdp_speed[True-True-False-True-True] 60.9130μs 31.5580μs 31.6877 KOps/s 30.9390 KOps/s $\color{#35bf28}+2.42\%$
test_step_mdp_speed[True-True-False-True-False] 47.6080μs 19.3628μs 51.6455 KOps/s 51.2130 KOps/s $\color{#35bf28}+0.84\%$
test_step_mdp_speed[True-True-False-False-True] 46.0060μs 18.5114μs 54.0207 KOps/s 52.7570 KOps/s $\color{#35bf28}+2.40\%$
test_step_mdp_speed[True-True-False-False-False] 51.5670μs 11.7052μs 85.4321 KOps/s 85.6146 KOps/s $\color{#d91a1a}-0.21\%$
test_step_mdp_speed[True-False-True-True-True] 82.5230μs 33.8984μs 29.5000 KOps/s 29.7849 KOps/s $\color{#d91a1a}-0.96\%$
test_step_mdp_speed[True-False-True-True-False] 63.2370μs 21.2790μs 46.9946 KOps/s 46.5932 KOps/s $\color{#35bf28}+0.86\%$
test_step_mdp_speed[True-False-True-False-True] 56.4860μs 18.5428μs 53.9293 KOps/s 53.0035 KOps/s $\color{#35bf28}+1.75\%$
test_step_mdp_speed[True-False-True-False-False] 0.4969ms 11.7178μs 85.3404 KOps/s 84.4468 KOps/s $\color{#35bf28}+1.06\%$
test_step_mdp_speed[True-False-False-True-True] 92.3220μs 35.1326μs 28.4636 KOps/s 27.9900 KOps/s $\color{#35bf28}+1.69\%$
test_step_mdp_speed[True-False-False-True-False] 53.1790μs 23.0017μs 43.4751 KOps/s 42.8864 KOps/s $\color{#35bf28}+1.37\%$
test_step_mdp_speed[True-False-False-False-True] 67.1660μs 20.0459μs 49.8856 KOps/s 48.2458 KOps/s $\color{#35bf28}+3.40\%$
test_step_mdp_speed[True-False-False-False-False] 42.6590μs 13.3965μs 74.6466 KOps/s 73.5298 KOps/s $\color{#35bf28}+1.52\%$
test_step_mdp_speed[False-True-True-True-True] 64.7400μs 33.4028μs 29.9376 KOps/s 29.5941 KOps/s $\color{#35bf28}+1.16\%$
test_step_mdp_speed[False-True-True-True-False] 59.3100μs 21.1016μs 47.3897 KOps/s 46.3894 KOps/s $\color{#35bf28}+2.16\%$
test_step_mdp_speed[False-True-True-False-True] 49.2220μs 21.4585μs 46.6015 KOps/s 46.5421 KOps/s $\color{#35bf28}+0.13\%$
test_step_mdp_speed[False-True-True-False-False] 34.9750μs 13.1303μs 76.1595 KOps/s 75.8115 KOps/s $\color{#35bf28}+0.46\%$
test_step_mdp_speed[False-True-False-True-True] 75.3000μs 35.1447μs 28.4538 KOps/s 26.5957 KOps/s $\textbf{\color{#35bf28}+6.99\%}$
test_step_mdp_speed[False-True-False-True-False] 55.5930μs 23.0150μs 43.4500 KOps/s 42.9695 KOps/s $\color{#35bf28}+1.12\%$
test_step_mdp_speed[False-True-False-False-True] 3.0045ms 23.7385μs 42.1256 KOps/s 42.7983 KOps/s $\color{#d91a1a}-1.57\%$
test_step_mdp_speed[False-True-False-False-False] 47.5290μs 14.7923μs 67.6028 KOps/s 66.4032 KOps/s $\color{#35bf28}+1.81\%$
test_step_mdp_speed[False-False-True-True-True] 0.1009ms 37.0038μs 27.0243 KOps/s 26.5444 KOps/s $\color{#35bf28}+1.81\%$
test_step_mdp_speed[False-False-True-True-False] 48.9600μs 24.8572μs 40.2298 KOps/s 39.8616 KOps/s $\color{#35bf28}+0.92\%$
test_step_mdp_speed[False-False-True-False-True] 66.6940μs 23.1223μs 43.2483 KOps/s 42.9940 KOps/s $\color{#35bf28}+0.59\%$
test_step_mdp_speed[False-False-True-False-False] 56.9660μs 14.7007μs 68.0240 KOps/s 66.6144 KOps/s $\color{#35bf28}+2.12\%$
test_step_mdp_speed[False-False-False-True-True] 0.6369ms 38.3881μs 26.0497 KOps/s 25.8750 KOps/s $\color{#35bf28}+0.68\%$
test_step_mdp_speed[False-False-False-True-False] 60.1920μs 26.3152μs 38.0008 KOps/s 37.3995 KOps/s $\color{#35bf28}+1.61\%$
test_step_mdp_speed[False-False-False-False-True] 64.6500μs 24.1714μs 41.3712 KOps/s 40.3040 KOps/s $\color{#35bf28}+2.65\%$
test_step_mdp_speed[False-False-False-False-False] 62.4560μs 16.2418μs 61.5694 KOps/s 60.0309 KOps/s $\color{#35bf28}+2.56\%$
test_values[generalized_advantage_estimate-True-True] 10.6847ms 9.8442ms 101.5824 Ops/s 102.4028 Ops/s $\color{#d91a1a}-0.80\%$
test_values[vec_generalized_advantage_estimate-True-True] 28.4245ms 27.0001ms 37.0369 Ops/s 37.8682 Ops/s $\color{#d91a1a}-2.20\%$
test_values[td0_return_estimate-False-False] 0.2280ms 0.1896ms 5.2730 KOps/s 5.4410 KOps/s $\color{#d91a1a}-3.09\%$
test_values[td1_return_estimate-False-False] 25.8586ms 24.4554ms 40.8907 Ops/s 40.7275 Ops/s $\color{#35bf28}+0.40\%$
test_values[vec_td1_return_estimate-False-False] 28.7832ms 27.2349ms 36.7176 Ops/s 37.6369 Ops/s $\color{#d91a1a}-2.44\%$
test_values[td_lambda_return_estimate-True-False] 36.5995ms 35.1469ms 28.4520 Ops/s 28.2922 Ops/s $\color{#35bf28}+0.56\%$
test_values[vec_td_lambda_return_estimate-True-False] 29.3303ms 27.0586ms 36.9569 Ops/s 37.6949 Ops/s $\color{#d91a1a}-1.96\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.7999ms 8.5373ms 117.1325 Ops/s 118.2315 Ops/s $\color{#d91a1a}-0.93\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 2.3918ms 1.9275ms 518.8019 Ops/s 555.5476 Ops/s $\textbf{\color{#d91a1a}-6.61\%}$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4677ms 0.3644ms 2.7444 KOps/s 2.7465 KOps/s $\color{#d91a1a}-0.08\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 47.1183ms 43.9995ms 22.7275 Ops/s 21.8219 Ops/s $\color{#35bf28}+4.15\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.4212ms 3.4478ms 290.0411 Ops/s 287.4255 Ops/s $\color{#35bf28}+0.91\%$
test_dqn_speed[False-None] 6.4597ms 1.3895ms 719.6926 Ops/s 700.5537 Ops/s $\color{#35bf28}+2.73\%$
test_dqn_speed[False-backward] 1.9061ms 1.8551ms 539.0508 Ops/s 518.9435 Ops/s $\color{#35bf28}+3.87\%$
test_dqn_speed[True-None] 0.7455ms 0.4924ms 2.0307 KOps/s 2.0004 KOps/s $\color{#35bf28}+1.51\%$
test_dqn_speed[True-backward] 0.9453ms 0.9052ms 1.1047 KOps/s 1.0720 KOps/s $\color{#35bf28}+3.06\%$
test_dqn_speed[reduce-overhead-None] 0.6259ms 0.4913ms 2.0355 KOps/s 1.9928 KOps/s $\color{#35bf28}+2.15\%$
test_dqn_speed[reduce-overhead-backward] 0.9480ms 0.9086ms 1.1006 KOps/s 1.0727 KOps/s $\color{#35bf28}+2.60\%$
test_ddpg_speed[False-None] 4.5067ms 2.9341ms 340.8173 Ops/s 339.1377 Ops/s $\color{#35bf28}+0.50\%$
test_ddpg_speed[False-backward] 5.2794ms 4.1106ms 243.2719 Ops/s 245.3380 Ops/s $\color{#d91a1a}-0.84\%$
test_ddpg_speed[True-None] 1.7370ms 1.2454ms 802.9735 Ops/s 793.9750 Ops/s $\color{#35bf28}+1.13\%$
test_ddpg_speed[True-backward] 2.2429ms 2.1589ms 463.2067 Ops/s 449.0036 Ops/s $\color{#35bf28}+3.16\%$
test_ddpg_speed[reduce-overhead-None] 1.9016ms 1.2408ms 805.9311 Ops/s 792.9399 Ops/s $\color{#35bf28}+1.64\%$
test_ddpg_speed[reduce-overhead-backward] 2.2314ms 2.1428ms 466.6791 Ops/s 458.1661 Ops/s $\color{#35bf28}+1.86\%$
test_sac_speed[False-None] 9.2066ms 8.0657ms 123.9819 Ops/s 121.3313 Ops/s $\color{#35bf28}+2.18\%$
test_sac_speed[False-backward] 12.0004ms 10.9137ms 91.6278 Ops/s 90.4441 Ops/s $\color{#35bf28}+1.31\%$
test_sac_speed[True-None] 2.6505ms 2.1489ms 465.3651 Ops/s 459.6354 Ops/s $\color{#35bf28}+1.25\%$
test_sac_speed[True-backward] 4.0336ms 3.8538ms 259.4863 Ops/s 250.4820 Ops/s $\color{#35bf28}+3.59\%$
test_sac_speed[reduce-overhead-None] 2.4258ms 2.1381ms 467.6955 Ops/s 447.0121 Ops/s $\color{#35bf28}+4.63\%$
test_sac_speed[reduce-overhead-backward] 4.0381ms 3.8486ms 259.8332 Ops/s 237.8950 Ops/s $\textbf{\color{#35bf28}+9.22\%}$
test_redq_speed[False-None] 15.1015ms 13.3312ms 75.0119 Ops/s 71.8338 Ops/s $\color{#35bf28}+4.42\%$
test_redq_speed[False-backward] 25.1917ms 22.7728ms 43.9120 Ops/s 39.7623 Ops/s $\textbf{\color{#35bf28}+10.44\%}$
test_redq_speed[True-None] 6.5729ms 5.3067ms 188.4423 Ops/s 179.7683 Ops/s $\color{#35bf28}+4.83\%$
test_redq_speed[True-backward] 13.8706ms 13.2472ms 75.4877 Ops/s 74.4687 Ops/s $\color{#35bf28}+1.37\%$
test_redq_speed[reduce-overhead-None] 6.4426ms 5.3968ms 185.2944 Ops/s 175.4710 Ops/s $\textbf{\color{#35bf28}+5.60\%}$
test_redq_speed[reduce-overhead-backward] 14.0220ms 13.0415ms 76.6782 Ops/s 74.2342 Ops/s $\color{#35bf28}+3.29\%$
test_redq_deprec_speed[False-None] 14.2092ms 13.1356ms 76.1289 Ops/s 69.9165 Ops/s $\textbf{\color{#35bf28}+8.89\%}$
test_redq_deprec_speed[False-backward] 20.8389ms 19.1860ms 52.1214 Ops/s 50.4985 Ops/s $\color{#35bf28}+3.21\%$
test_redq_deprec_speed[True-None] 5.1114ms 4.1514ms 240.8823 Ops/s 235.7954 Ops/s $\color{#35bf28}+2.16\%$
test_redq_deprec_speed[True-backward] 10.4446ms 9.0603ms 110.3719 Ops/s 111.3437 Ops/s $\color{#d91a1a}-0.87\%$
test_redq_deprec_speed[reduce-overhead-None] 4.5246ms 4.0606ms 246.2663 Ops/s 238.3202 Ops/s $\color{#35bf28}+3.33\%$
test_redq_deprec_speed[reduce-overhead-backward] 9.5206ms 8.9255ms 112.0389 Ops/s 104.8003 Ops/s $\textbf{\color{#35bf28}+6.91\%}$
test_td3_speed[False-None] 8.5299ms 8.0647ms 123.9973 Ops/s 118.5797 Ops/s $\color{#35bf28}+4.57\%$
test_td3_speed[False-backward] 11.1805ms 10.5531ms 94.7588 Ops/s 90.9817 Ops/s $\color{#35bf28}+4.15\%$
test_td3_speed[True-None] 1.9430ms 1.8151ms 550.9335 Ops/s 521.7234 Ops/s $\textbf{\color{#35bf28}+5.60\%}$
test_td3_speed[True-backward] 3.5642ms 3.4226ms 292.1745 Ops/s 281.0710 Ops/s $\color{#35bf28}+3.95\%$
test_td3_speed[reduce-overhead-None] 2.1650ms 1.8278ms 547.1029 Ops/s 520.9636 Ops/s $\textbf{\color{#35bf28}+5.02\%}$
test_td3_speed[reduce-overhead-backward] 3.5312ms 3.4153ms 292.7985 Ops/s 265.0832 Ops/s $\textbf{\color{#35bf28}+10.46\%}$
test_cql_speed[False-None] 40.1785ms 36.8972ms 27.1023 Ops/s 26.5958 Ops/s $\color{#35bf28}+1.90\%$
test_cql_speed[False-backward] 57.1110ms 47.8421ms 20.9021 Ops/s 20.5607 Ops/s $\color{#35bf28}+1.66\%$
test_cql_speed[True-None] 16.9578ms 16.4457ms 60.8060 Ops/s 59.3759 Ops/s $\color{#35bf28}+2.41\%$
test_cql_speed[True-backward] 24.7435ms 23.5739ms 42.4199 Ops/s 41.8189 Ops/s $\color{#35bf28}+1.44\%$
test_cql_speed[reduce-overhead-None] 16.9586ms 16.4492ms 60.7933 Ops/s 59.7087 Ops/s $\color{#35bf28}+1.82\%$
test_cql_speed[reduce-overhead-backward] 25.5232ms 23.5339ms 42.4920 Ops/s 41.9674 Ops/s $\color{#35bf28}+1.25\%$
test_a2c_speed[False-None] 8.3771ms 7.6263ms 131.1253 Ops/s 131.3581 Ops/s $\color{#d91a1a}-0.18\%$
test_a2c_speed[False-backward] 16.4271ms 15.0546ms 66.4248 Ops/s 66.0451 Ops/s $\color{#35bf28}+0.57\%$
test_a2c_speed[True-None] 4.3522ms 3.7504ms 266.6371 Ops/s 260.5822 Ops/s $\color{#35bf28}+2.32\%$
test_a2c_speed[True-backward] 11.0045ms 10.6023ms 94.3193 Ops/s 95.0835 Ops/s $\color{#d91a1a}-0.80\%$
test_a2c_speed[reduce-overhead-None] 4.4677ms 3.7266ms 268.3411 Ops/s 263.7866 Ops/s $\color{#35bf28}+1.73\%$
test_a2c_speed[reduce-overhead-backward] 11.4577ms 10.4849ms 95.3755 Ops/s 94.1326 Ops/s $\color{#35bf28}+1.32\%$
test_ppo_speed[False-None] 8.5535ms 7.6038ms 131.5131 Ops/s 129.1158 Ops/s $\color{#35bf28}+1.86\%$
test_ppo_speed[False-backward] 16.5753ms 15.4723ms 64.6318 Ops/s 64.2198 Ops/s $\color{#35bf28}+0.64\%$
test_ppo_speed[True-None] 4.9753ms 4.1391ms 241.5998 Ops/s 236.1033 Ops/s $\color{#35bf28}+2.33\%$
test_ppo_speed[True-backward] 11.1248ms 10.5404ms 94.8729 Ops/s 96.4693 Ops/s $\color{#d91a1a}-1.65\%$
test_ppo_speed[reduce-overhead-None] 4.5950ms 4.1527ms 240.8050 Ops/s 235.9362 Ops/s $\color{#35bf28}+2.06\%$
test_ppo_speed[reduce-overhead-backward] 11.1580ms 10.4629ms 95.5760 Ops/s 95.7262 Ops/s $\color{#d91a1a}-0.16\%$
test_reinforce_speed[False-None] 7.8335ms 6.6538ms 150.2893 Ops/s 148.2302 Ops/s $\color{#35bf28}+1.39\%$
test_reinforce_speed[False-backward] 10.4844ms 9.9684ms 100.3173 Ops/s 97.8347 Ops/s $\color{#35bf28}+2.54\%$
test_reinforce_speed[True-None] 3.7835ms 3.1261ms 319.8898 Ops/s 312.2798 Ops/s $\color{#35bf28}+2.44\%$
test_reinforce_speed[True-backward] 9.8307ms 9.3981ms 106.4047 Ops/s 102.6241 Ops/s $\color{#35bf28}+3.68\%$
test_reinforce_speed[reduce-overhead-None] 3.5051ms 3.1500ms 317.4585 Ops/s 317.0844 Ops/s $\color{#35bf28}+0.12\%$
test_reinforce_speed[reduce-overhead-backward] 10.4290ms 9.4723ms 105.5710 Ops/s 105.8387 Ops/s $\color{#d91a1a}-0.25\%$
test_iql_speed[False-None] 35.9561ms 32.9403ms 30.3580 Ops/s 29.6123 Ops/s $\color{#35bf28}+2.52\%$
test_iql_speed[False-backward] 0.3963s 53.5808ms 18.6634 Ops/s 21.4324 Ops/s $\textbf{\color{#d91a1a}-12.92\%}$
test_iql_speed[True-None] 12.9935ms 11.7330ms 85.2295 Ops/s 83.9686 Ops/s $\color{#35bf28}+1.50\%$
test_iql_speed[True-backward] 24.3180ms 23.2192ms 43.0678 Ops/s 42.6952 Ops/s $\color{#35bf28}+0.87\%$
test_iql_speed[reduce-overhead-None] 12.2363ms 11.7119ms 85.3832 Ops/s 84.1885 Ops/s $\color{#35bf28}+1.42\%$
test_iql_speed[reduce-overhead-backward] 24.8307ms 23.1626ms 43.1730 Ops/s 42.5760 Ops/s $\color{#35bf28}+1.40\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.4966ms 4.9669ms 201.3313 Ops/s 192.5197 Ops/s $\color{#35bf28}+4.58\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.4695ms 0.5412ms 1.8478 KOps/s 1.7838 KOps/s $\color{#35bf28}+3.59\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.9111ms 0.5148ms 1.9425 KOps/s 1.8668 KOps/s $\color{#35bf28}+4.05\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.2799ms 4.7826ms 209.0928 Ops/s 204.4535 Ops/s $\color{#35bf28}+2.27\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.8521ms 0.5311ms 1.8827 KOps/s 1.8314 KOps/s $\color{#35bf28}+2.80\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8527ms 0.5047ms 1.9815 KOps/s 1.9261 KOps/s $\color{#35bf28}+2.88\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.5028ms 1.7039ms 586.9046 Ops/s 572.9359 Ops/s $\color{#35bf28}+2.44\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.2673ms 1.6171ms 618.4068 Ops/s 606.6393 Ops/s $\color{#35bf28}+1.94\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.1915ms 4.9032ms 203.9480 Ops/s 194.8478 Ops/s $\color{#35bf28}+4.67\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.0542ms 0.6745ms 1.4826 KOps/s 1.4605 KOps/s $\color{#35bf28}+1.51\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 1.1481ms 0.6570ms 1.5221 KOps/s 1.5085 KOps/s $\color{#35bf28}+0.90\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.1548ms 4.8097ms 207.9149 Ops/s 202.7496 Ops/s $\color{#35bf28}+2.55\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.9007ms 0.5418ms 1.8456 KOps/s 1.8256 KOps/s $\color{#35bf28}+1.10\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.7018ms 0.5118ms 1.9538 KOps/s 1.8808 KOps/s $\color{#35bf28}+3.88\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.1576ms 4.7612ms 210.0289 Ops/s 200.8776 Ops/s $\color{#35bf28}+4.56\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.5257ms 0.5392ms 1.8546 KOps/s 1.8398 KOps/s $\color{#35bf28}+0.80\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7240ms 0.5064ms 1.9748 KOps/s 1.8945 KOps/s $\color{#35bf28}+4.24\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.2456ms 4.9311ms 202.7943 Ops/s 196.5650 Ops/s $\color{#35bf28}+3.17\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.4826ms 0.6862ms 1.4573 KOps/s 1.4356 KOps/s $\color{#35bf28}+1.51\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.8907ms 0.6526ms 1.5324 KOps/s 1.5117 KOps/s $\color{#35bf28}+1.37\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.1262ms 4.2687ms 234.2621 Ops/s 220.5030 Ops/s $\textbf{\color{#35bf28}+6.24\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 3.5477ms 2.2364ms 447.1481 Ops/s 407.6989 Ops/s $\textbf{\color{#35bf28}+9.68\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.4728ms 1.4488ms 690.2461 Ops/s 743.5102 Ops/s $\textbf{\color{#d91a1a}-7.16\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 5.7525ms 4.3655ms 229.0678 Ops/s 232.0902 Ops/s $\color{#d91a1a}-1.30\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.5120s 12.5894ms 79.4319 Ops/s 434.8800 Ops/s $\textbf{\color{#d91a1a}-81.73\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 5.9755ms 1.4120ms 708.2298 Ops/s 750.8669 Ops/s $\textbf{\color{#d91a1a}-5.68\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 5.7660ms 4.4196ms 226.2640 Ops/s 30.4244 Ops/s $\textbf{\color{#35bf28}+643.69\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 7.6175ms 2.5053ms 399.1594 Ops/s 386.6023 Ops/s $\color{#35bf28}+3.25\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 4.3854ms 1.5039ms 664.9428 Ops/s 647.9113 Ops/s $\color{#35bf28}+2.63\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 12.0313ms 11.5586ms 86.5159 Ops/s 78.7145 Ops/s $\textbf{\color{#35bf28}+9.91\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 15.4602ms 14.2226ms 70.3108 Ops/s 68.5819 Ops/s $\color{#35bf28}+2.52\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 21.1427ms 20.5292ms 48.7110 Ops/s 46.7803 Ops/s $\color{#35bf28}+4.13\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 15.3590ms 14.4310ms 69.2953 Ops/s 66.9617 Ops/s $\color{#35bf28}+3.48\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 22.1936ms 20.4301ms 48.9473 Ops/s 46.8326 Ops/s $\color{#35bf28}+4.52\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 16.9527ms 15.8142ms 63.2344 Ops/s 62.2564 Ops/s $\color{#35bf28}+1.57\%$

Copy link

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}17$. Worsened: $\large\color{#d91a1a}11$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.9095s 0.8216s 1.2172 Ops/s 1.2557 Ops/s $\color{#d91a1a}-3.06\%$
test_transformed 1.5249s 1.4390s 0.6949 Ops/s 0.7073 Ops/s $\color{#d91a1a}-1.75\%$
test_serial 2.3030s 2.2985s 0.4351 Ops/s 0.4361 Ops/s $\color{#d91a1a}-0.24\%$
test_parallel 1.8540s 1.8257s 0.5477 Ops/s 0.5337 Ops/s $\color{#35bf28}+2.63\%$
test_step_mdp_speed[True-True-True-True-True] 0.4224ms 39.2262μs 25.4932 KOps/s 24.2731 KOps/s $\textbf{\color{#35bf28}+5.03\%}$
test_step_mdp_speed[True-True-True-True-False] 55.5740μs 23.5897μs 42.3914 KOps/s 42.3363 KOps/s $\color{#35bf28}+0.13\%$
test_step_mdp_speed[True-True-True-False-True] 0.4180ms 22.1587μs 45.1290 KOps/s 44.6391 KOps/s $\color{#35bf28}+1.10\%$
test_step_mdp_speed[True-True-True-False-False] 60.5640μs 13.0797μs 76.4543 KOps/s 76.4492 KOps/s $+0.01\%$
test_step_mdp_speed[True-True-False-True-True] 0.4237ms 43.5114μs 22.9825 KOps/s 23.3258 KOps/s $\color{#d91a1a}-1.47\%$
test_step_mdp_speed[True-True-False-True-False] 0.4123ms 26.3209μs 37.9926 KOps/s 38.5012 KOps/s $\color{#d91a1a}-1.32\%$
test_step_mdp_speed[True-True-False-False-True] 0.4150ms 24.5766μs 40.6892 KOps/s 39.8299 KOps/s $\color{#35bf28}+2.16\%$
test_step_mdp_speed[True-True-False-False-False] 45.4040μs 15.6197μs 64.0219 KOps/s 64.5300 KOps/s $\color{#d91a1a}-0.79\%$
test_step_mdp_speed[True-False-True-True-True] 0.4359ms 46.0199μs 21.7297 KOps/s 21.8042 KOps/s $\color{#d91a1a}-0.34\%$
test_step_mdp_speed[True-False-True-True-False] 0.4194ms 28.6510μs 34.9028 KOps/s 35.1935 KOps/s $\color{#d91a1a}-0.83\%$
test_step_mdp_speed[True-False-True-False-True] 0.1010ms 23.7652μs 42.0783 KOps/s 40.1243 KOps/s $\color{#35bf28}+4.87\%$
test_step_mdp_speed[True-False-True-False-False] 43.3430μs 15.5616μs 64.2607 KOps/s 64.4998 KOps/s $\color{#d91a1a}-0.37\%$
test_step_mdp_speed[True-False-False-True-True] 0.1701ms 47.7765μs 20.9308 KOps/s 21.0174 KOps/s $\color{#d91a1a}-0.41\%$
test_step_mdp_speed[True-False-False-True-False] 60.7350μs 30.6149μs 32.6638 KOps/s 32.8311 KOps/s $\color{#d91a1a}-0.51\%$
test_step_mdp_speed[True-False-False-False-True] 62.4440μs 27.0127μs 37.0196 KOps/s 36.9065 KOps/s $\color{#35bf28}+0.31\%$
test_step_mdp_speed[True-False-False-False-False] 53.1640μs 17.8132μs 56.1382 KOps/s 56.3526 KOps/s $\color{#d91a1a}-0.38\%$
test_step_mdp_speed[False-True-True-True-True] 97.7670μs 44.4773μs 22.4834 KOps/s 21.8563 KOps/s $\color{#35bf28}+2.87\%$
test_step_mdp_speed[False-True-True-True-False] 68.5150μs 28.1219μs 35.5595 KOps/s 34.9975 KOps/s $\color{#35bf28}+1.61\%$
test_step_mdp_speed[False-True-True-False-True] 2.5268ms 29.0128μs 34.4675 KOps/s 34.4069 KOps/s $\color{#35bf28}+0.18\%$
test_step_mdp_speed[False-True-True-False-False] 47.0340μs 17.4628μs 57.2647 KOps/s 58.3570 KOps/s $\color{#d91a1a}-1.87\%$
test_step_mdp_speed[False-True-False-True-True] 88.2360μs 47.7767μs 20.9307 KOps/s 20.8860 KOps/s $\color{#35bf28}+0.21\%$
test_step_mdp_speed[False-True-False-True-False] 62.0640μs 30.5269μs 32.7580 KOps/s 32.8013 KOps/s $\color{#d91a1a}-0.13\%$
test_step_mdp_speed[False-True-False-False-True] 63.1950μs 31.1281μs 32.1253 KOps/s 32.1434 KOps/s $\color{#d91a1a}-0.06\%$
test_step_mdp_speed[False-True-False-False-False] 0.1992ms 19.3089μs 51.7895 KOps/s 51.3598 KOps/s $\color{#35bf28}+0.84\%$
test_step_mdp_speed[False-False-True-True-True] 0.1087ms 49.4526μs 20.2214 KOps/s 20.1428 KOps/s $\color{#35bf28}+0.39\%$
test_step_mdp_speed[False-False-True-True-False] 0.1252ms 32.9486μs 30.3503 KOps/s 30.2773 KOps/s $\color{#35bf28}+0.24\%$
test_step_mdp_speed[False-False-True-False-True] 74.7760μs 30.5335μs 32.7509 KOps/s 32.2849 KOps/s $\color{#35bf28}+1.44\%$
test_step_mdp_speed[False-False-True-False-False] 0.1321ms 19.3807μs 51.5978 KOps/s 52.3331 KOps/s $\color{#d91a1a}-1.41\%$
test_step_mdp_speed[False-False-False-True-True] 0.1410ms 51.6809μs 19.3495 KOps/s 19.6709 KOps/s $\color{#d91a1a}-1.63\%$
test_step_mdp_speed[False-False-False-True-False] 0.2088ms 35.3448μs 28.2927 KOps/s 29.0718 KOps/s $\color{#d91a1a}-2.68\%$
test_step_mdp_speed[False-False-False-False-True] 62.9240μs 32.9281μs 30.3692 KOps/s 30.7805 KOps/s $\color{#d91a1a}-1.34\%$
test_step_mdp_speed[False-False-False-False-False] 63.6250μs 21.4692μs 46.5784 KOps/s 45.9769 KOps/s $\color{#35bf28}+1.31\%$
test_values[generalized_advantage_estimate-True-True] 25.1721ms 24.7684ms 40.3741 Ops/s 40.6574 Ops/s $\color{#d91a1a}-0.70\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1022s 2.9407ms 340.0494 Ops/s 298.9241 Ops/s $\textbf{\color{#35bf28}+13.76\%}$
test_values[td0_return_estimate-False-False] 0.1065ms 80.5350μs 12.4170 KOps/s 12.5753 KOps/s $\color{#d91a1a}-1.26\%$
test_values[td1_return_estimate-False-False] 58.0634ms 55.9819ms 17.8629 Ops/s 17.8592 Ops/s $\color{#35bf28}+0.02\%$
test_values[vec_td1_return_estimate-False-False] 1.3453ms 1.0861ms 920.7294 Ops/s 913.8383 Ops/s $\color{#35bf28}+0.75\%$
test_values[td_lambda_return_estimate-True-False] 93.0987ms 89.9283ms 11.1200 Ops/s 11.2417 Ops/s $\color{#d91a1a}-1.08\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.3518ms 1.0872ms 919.7830 Ops/s 929.1235 Ops/s $\color{#d91a1a}-1.01\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.6255ms 24.3985ms 40.9861 Ops/s 40.9355 Ops/s $\color{#35bf28}+0.12\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0189ms 0.7515ms 1.3306 KOps/s 1.3474 KOps/s $\color{#d91a1a}-1.25\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.7886ms 0.6648ms 1.5042 KOps/s 1.5012 KOps/s $\color{#35bf28}+0.20\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.6315ms 1.4802ms 675.5640 Ops/s 674.0578 Ops/s $\color{#35bf28}+0.22\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.8271ms 0.6800ms 1.4705 KOps/s 1.4447 KOps/s $\color{#35bf28}+1.79\%$
test_dqn_speed[False-None] 6.8164ms 1.5200ms 657.9018 Ops/s 655.7005 Ops/s $\color{#35bf28}+0.34\%$
test_dqn_speed[False-backward] 2.2682ms 2.1243ms 470.7527 Ops/s 468.5715 Ops/s $\color{#35bf28}+0.47\%$
test_dqn_speed[True-None] 0.1596s 0.6700ms 1.4925 KOps/s 1.7418 KOps/s $\textbf{\color{#d91a1a}-14.31\%}$
test_dqn_speed[True-backward] 1.2267ms 1.1370ms 879.5426 Ops/s 795.2463 Ops/s $\textbf{\color{#35bf28}+10.60\%}$
test_dqn_speed[reduce-overhead-None] 0.7332ms 0.5901ms 1.6946 KOps/s 1.6822 KOps/s $\color{#35bf28}+0.74\%$
test_dqn_speed[reduce-overhead-backward] 1.1462ms 0.9784ms 1.0221 KOps/s 1.0164 KOps/s $\color{#35bf28}+0.56\%$
test_ddpg_speed[False-None] 3.2077ms 2.9211ms 342.3406 Ops/s 345.2424 Ops/s $\color{#d91a1a}-0.84\%$
test_ddpg_speed[False-backward] 4.5060ms 4.1584ms 240.4792 Ops/s 241.0312 Ops/s $\color{#d91a1a}-0.23\%$
test_ddpg_speed[True-None] 1.5492ms 1.3663ms 731.8978 Ops/s 737.0050 Ops/s $\color{#d91a1a}-0.69\%$
test_ddpg_speed[True-backward] 2.5821ms 2.4234ms 412.6414 Ops/s 407.1869 Ops/s $\color{#35bf28}+1.34\%$
test_ddpg_speed[reduce-overhead-None] 1.5335ms 1.3550ms 738.0168 Ops/s 722.4869 Ops/s $\color{#35bf28}+2.15\%$
test_ddpg_speed[reduce-overhead-backward] 2.0317ms 1.8938ms 528.0391 Ops/s 523.3414 Ops/s $\color{#35bf28}+0.90\%$
test_sac_speed[False-None] 8.3304ms 8.0582ms 124.0977 Ops/s 123.2701 Ops/s $\color{#35bf28}+0.67\%$
test_sac_speed[False-backward] 11.4760ms 10.9595ms 91.2448 Ops/s 91.6866 Ops/s $\color{#d91a1a}-0.48\%$
test_sac_speed[True-None] 2.0765ms 1.8776ms 532.6066 Ops/s 524.3074 Ops/s $\color{#35bf28}+1.58\%$
test_sac_speed[True-backward] 3.7266ms 3.5511ms 281.6009 Ops/s 281.2951 Ops/s $\color{#35bf28}+0.11\%$
test_sac_speed[reduce-overhead-None] 19.9506ms 11.6366ms 85.9354 Ops/s 85.0744 Ops/s $\color{#35bf28}+1.01\%$
test_sac_speed[reduce-overhead-backward] 1.7946ms 1.6601ms 602.3572 Ops/s 594.0231 Ops/s $\color{#35bf28}+1.40\%$
test_redq_speed[False-None] 7.8949ms 7.4809ms 133.6730 Ops/s 131.4905 Ops/s $\color{#35bf28}+1.66\%$
test_redq_speed[False-backward] 11.7884ms 11.1844ms 89.4100 Ops/s 88.6665 Ops/s $\color{#35bf28}+0.84\%$
test_redq_speed[True-None] 2.7693ms 2.3560ms 424.4498 Ops/s 424.8617 Ops/s $\color{#d91a1a}-0.10\%$
test_redq_speed[True-backward] 4.1389ms 3.9541ms 252.9046 Ops/s 249.9186 Ops/s $\color{#35bf28}+1.19\%$
test_redq_speed[reduce-overhead-None] 2.6092ms 2.3653ms 422.7743 Ops/s 408.4015 Ops/s $\color{#35bf28}+3.52\%$
test_redq_speed[reduce-overhead-backward] 4.1603ms 3.9883ms 250.7365 Ops/s 233.8907 Ops/s $\textbf{\color{#35bf28}+7.20\%}$
test_redq_deprec_speed[False-None] 9.3781ms 9.0096ms 110.9929 Ops/s 110.6443 Ops/s $\color{#35bf28}+0.32\%$
test_redq_deprec_speed[False-backward] 12.5559ms 12.0058ms 83.2932 Ops/s 81.5955 Ops/s $\color{#35bf28}+2.08\%$
test_redq_deprec_speed[True-None] 2.9039ms 2.6730ms 374.1093 Ops/s 368.3104 Ops/s $\color{#35bf28}+1.57\%$
test_redq_deprec_speed[True-backward] 4.4838ms 4.2528ms 235.1377 Ops/s 230.4054 Ops/s $\color{#35bf28}+2.05\%$
test_redq_deprec_speed[reduce-overhead-None] 2.8074ms 2.6136ms 382.6153 Ops/s 367.0063 Ops/s $\color{#35bf28}+4.25\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.5857ms 4.2156ms 237.2129 Ops/s 231.4551 Ops/s $\color{#35bf28}+2.49\%$
test_td3_speed[False-None] 7.8746ms 7.8329ms 127.6666 Ops/s 125.6699 Ops/s $\color{#35bf28}+1.59\%$
test_td3_speed[False-backward] 10.6995ms 10.1003ms 99.0071 Ops/s 98.3905 Ops/s $\color{#35bf28}+0.63\%$
test_td3_speed[True-None] 1.7141ms 1.6599ms 602.4293 Ops/s 580.0229 Ops/s $\color{#35bf28}+3.86\%$
test_td3_speed[True-backward] 3.3094ms 3.1292ms 319.5710 Ops/s 293.0737 Ops/s $\textbf{\color{#35bf28}+9.04\%}$
test_td3_speed[reduce-overhead-None] 50.4020ms 25.7794ms 38.7907 Ops/s 38.7487 Ops/s $\color{#35bf28}+0.11\%$
test_td3_speed[reduce-overhead-backward] 1.4590ms 1.3841ms 722.4759 Ops/s 641.4732 Ops/s $\textbf{\color{#35bf28}+12.63\%}$
test_cql_speed[False-None] 16.9935ms 16.5037ms 60.5924 Ops/s 59.1963 Ops/s $\color{#35bf28}+2.36\%$
test_cql_speed[False-backward] 22.1846ms 21.5268ms 46.4537 Ops/s 44.7611 Ops/s $\color{#35bf28}+3.78\%$
test_cql_speed[True-None] 3.4887ms 3.2827ms 304.6292 Ops/s 303.9590 Ops/s $\color{#35bf28}+0.22\%$
test_cql_speed[True-backward] 5.8491ms 5.4343ms 184.0158 Ops/s 185.2464 Ops/s $\color{#d91a1a}-0.66\%$
test_cql_speed[reduce-overhead-None] 21.7290ms 13.1471ms 76.0622 Ops/s 77.4855 Ops/s $\color{#d91a1a}-1.84\%$
test_cql_speed[reduce-overhead-backward] 2.2022ms 2.0407ms 490.0318 Ops/s 527.3774 Ops/s $\textbf{\color{#d91a1a}-7.08\%}$
test_a2c_speed[False-None] 3.4725ms 3.2428ms 308.3732 Ops/s 309.0024 Ops/s $\color{#d91a1a}-0.20\%$
test_a2c_speed[False-backward] 7.0177ms 6.3985ms 156.2876 Ops/s 164.1984 Ops/s $\color{#d91a1a}-4.82\%$
test_a2c_speed[True-None] 1.5169ms 1.3479ms 741.9222 Ops/s 722.4688 Ops/s $\color{#35bf28}+2.69\%$
test_a2c_speed[True-backward] 3.2138ms 3.0080ms 332.4444 Ops/s 341.6108 Ops/s $\color{#d91a1a}-2.68\%$
test_a2c_speed[reduce-overhead-None] 15.6822ms 8.9421ms 111.8306 Ops/s 112.1405 Ops/s $\color{#d91a1a}-0.28\%$
test_a2c_speed[reduce-overhead-backward] 1.7665ms 1.5570ms 642.2612 Ops/s 669.0591 Ops/s $\color{#d91a1a}-4.01\%$
test_ppo_speed[False-None] 3.8968ms 3.6960ms 270.5630 Ops/s 272.5503 Ops/s $\color{#d91a1a}-0.73\%$
test_ppo_speed[False-backward] 7.2818ms 6.9149ms 144.6151 Ops/s 148.8933 Ops/s $\color{#d91a1a}-2.87\%$
test_ppo_speed[True-None] 1.5771ms 1.4347ms 697.0256 Ops/s 689.8706 Ops/s $\color{#35bf28}+1.04\%$
test_ppo_speed[True-backward] 3.2383ms 3.1471ms 317.7557 Ops/s 319.0847 Ops/s $\color{#d91a1a}-0.42\%$
test_ppo_speed[reduce-overhead-None] 1.1787ms 1.0006ms 999.3879 Ops/s 1.0096 KOps/s $\color{#d91a1a}-1.01\%$
test_ppo_speed[reduce-overhead-backward] 1.6343ms 1.5183ms 658.6271 Ops/s 677.0645 Ops/s $\color{#d91a1a}-2.72\%$
test_reinforce_speed[False-None] 2.4920ms 2.2783ms 438.9268 Ops/s 439.9590 Ops/s $\color{#d91a1a}-0.23\%$
test_reinforce_speed[False-backward] 3.5982ms 3.3704ms 296.7045 Ops/s 305.3462 Ops/s $\color{#d91a1a}-2.83\%$
test_reinforce_speed[True-None] 1.5158ms 1.3230ms 755.8791 Ops/s 737.6886 Ops/s $\color{#35bf28}+2.47\%$
test_reinforce_speed[True-backward] 3.1820ms 3.0393ms 329.0267 Ops/s 342.0243 Ops/s $\color{#d91a1a}-3.80\%$
test_reinforce_speed[reduce-overhead-None] 18.3277ms 10.1697ms 98.3311 Ops/s 101.0889 Ops/s $\color{#d91a1a}-2.73\%$
test_reinforce_speed[reduce-overhead-backward] 1.7047ms 1.5951ms 626.9059 Ops/s 639.5567 Ops/s $\color{#d91a1a}-1.98\%$
test_iql_speed[False-None] 9.5498ms 9.1930ms 108.7788 Ops/s 108.7154 Ops/s $\color{#35bf28}+0.06\%$
test_iql_speed[False-backward] 13.1178ms 12.8094ms 78.0676 Ops/s 77.7107 Ops/s $\color{#35bf28}+0.46\%$
test_iql_speed[True-None] 2.5074ms 2.2617ms 442.1477 Ops/s 423.2639 Ops/s $\color{#35bf28}+4.46\%$
test_iql_speed[True-backward] 4.9228ms 4.8233ms 207.3271 Ops/s 196.6144 Ops/s $\textbf{\color{#35bf28}+5.45\%}$
test_iql_speed[reduce-overhead-None] 0.4900s 12.8391ms 77.8868 Ops/s 90.8656 Ops/s $\textbf{\color{#d91a1a}-14.28\%}$
test_iql_speed[reduce-overhead-backward] 2.1794ms 2.0207ms 494.8784 Ops/s 457.5843 Ops/s $\textbf{\color{#35bf28}+8.15\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 8.0215ms 6.3348ms 157.8585 Ops/s 154.7925 Ops/s $\color{#35bf28}+1.98\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5007ms 0.2978ms 3.3579 KOps/s 2.7084 KOps/s $\textbf{\color{#35bf28}+23.98\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6810ms 0.2799ms 3.5721 KOps/s 2.8610 KOps/s $\textbf{\color{#35bf28}+24.86\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3878ms 6.0402ms 165.5587 Ops/s 163.3435 Ops/s $\color{#35bf28}+1.36\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.6951ms 0.2615ms 3.8235 KOps/s 3.3903 KOps/s $\textbf{\color{#35bf28}+12.78\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5461ms 0.2417ms 4.1372 KOps/s 3.3699 KOps/s $\textbf{\color{#35bf28}+22.77\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6210ms 1.2673ms 789.0540 Ops/s 788.3180 Ops/s $\color{#35bf28}+0.09\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4912ms 1.2795ms 781.5447 Ops/s 855.8441 Ops/s $\textbf{\color{#d91a1a}-8.68\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5298ms 6.3239ms 158.1294 Ops/s 158.4338 Ops/s $\color{#d91a1a}-0.19\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1584ms 0.4612ms 2.1682 KOps/s 2.3757 KOps/s $\textbf{\color{#d91a1a}-8.73\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6632ms 0.4125ms 2.4241 KOps/s 2.3287 KOps/s $\color{#35bf28}+4.10\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.3083ms 6.1043ms 163.8202 Ops/s 162.7625 Ops/s $\color{#35bf28}+0.65\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.8796ms 0.3162ms 3.1627 KOps/s 3.7171 KOps/s $\textbf{\color{#d91a1a}-14.92\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.4838ms 0.2650ms 3.7738 KOps/s 4.0543 KOps/s $\textbf{\color{#d91a1a}-6.92\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.3359ms 6.0176ms 166.1801 Ops/s 163.1341 Ops/s $\color{#35bf28}+1.87\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.0011ms 0.2639ms 3.7900 KOps/s 2.8889 KOps/s $\textbf{\color{#35bf28}+31.19\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.4569ms 0.2427ms 4.1200 KOps/s 3.4915 KOps/s $\textbf{\color{#35bf28}+18.00\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4722ms 6.2246ms 160.6521 Ops/s 158.9941 Ops/s $\color{#35bf28}+1.04\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.7666ms 0.4387ms 2.2794 KOps/s 2.2461 KOps/s $\color{#35bf28}+1.48\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6796ms 0.4700ms 2.1276 KOps/s 2.2182 KOps/s $\color{#d91a1a}-4.08\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 7.1033ms 5.4952ms 181.9777 Ops/s 179.1016 Ops/s $\color{#35bf28}+1.61\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 11.1081ms 2.0754ms 481.8431 Ops/s 434.3434 Ops/s $\textbf{\color{#35bf28}+10.94\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.1246ms 1.1411ms 876.3139 Ops/s 838.6460 Ops/s $\color{#35bf28}+4.49\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4507s 14.4974ms 68.9778 Ops/s 179.5537 Ops/s $\textbf{\color{#d91a1a}-61.58\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 3.9296ms 1.7899ms 558.6783 Ops/s 431.2598 Ops/s $\textbf{\color{#35bf28}+29.55\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 8.8786ms 1.2865ms 777.2754 Ops/s 826.4696 Ops/s $\textbf{\color{#d91a1a}-5.95\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 8.5850ms 5.7190ms 174.8571 Ops/s 31.3346 Ops/s $\textbf{\color{#35bf28}+458.03\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.1342ms 2.2532ms 443.8125 Ops/s 500.0299 Ops/s $\textbf{\color{#d91a1a}-11.24\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 7.5645ms 1.4273ms 700.6279 Ops/s 822.3054 Ops/s $\textbf{\color{#d91a1a}-14.80\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 14.2043ms 13.1420ms 76.0921 Ops/s 73.6834 Ops/s $\color{#35bf28}+3.27\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 18.4955ms 16.6653ms 60.0048 Ops/s 58.5314 Ops/s $\color{#35bf28}+2.52\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.4210ms 17.7074ms 56.4737 Ops/s 54.0164 Ops/s $\color{#35bf28}+4.55\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 18.5620ms 16.8295ms 59.4196 Ops/s 57.2790 Ops/s $\color{#35bf28}+3.74\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 18.1504ms 17.7094ms 56.4673 Ops/s 54.8707 Ops/s $\color{#35bf28}+2.91\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 19.5683ms 18.2221ms 54.8783 Ops/s 53.4923 Ops/s $\color{#35bf28}+2.59\%$

kurtamohler added a commit to kurtamohler/torchrl that referenced this pull request Feb 19, 2025
ghstack-source-id: dbef5e48ea55db6ba7867e1b24eb4711ad08af61
Pull Request resolved: pytorch#2795
Copy link
Contributor

@vmoens vmoens left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Do we have a quick example that could be copy pasted for here? I think it brings a lot of value for users if users can just do that and run a simple forest in a notebook

@vmoens vmoens added the documentation Improvements or additions to documentation label Feb 20, 2025
kurtamohler added a commit to kurtamohler/torchrl that referenced this pull request Feb 25, 2025
ghstack-source-id: dbef5e48ea55db6ba7867e1b24eb4711ad08af61
Pull Request resolved: pytorch#2795
kurtamohler added a commit to kurtamohler/torchrl that referenced this pull request Feb 25, 2025
ghstack-source-id: dbef5e48ea55db6ba7867e1b24eb4711ad08af61
Pull Request resolved: pytorch#2795
kurtamohler added a commit to kurtamohler/torchrl that referenced this pull request Feb 25, 2025
ghstack-source-id: dbef5e48ea55db6ba7867e1b24eb4711ad08af61
Pull Request resolved: pytorch#2795
[ghstack-poisoned]
kurtamohler added a commit to kurtamohler/torchrl that referenced this pull request Feb 25, 2025
ghstack-source-id: d62a57bc55c906c590de88e8d8862a6686bd3938
Pull Request resolved: pytorch#2795
[ghstack-poisoned]
@kurtamohler
Copy link
Collaborator Author

I've added an example

Copy link
Contributor

@vmoens vmoens left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM thanks a mil!

@vmoens vmoens merged commit 248c871 into gh/kurtamohler/4/base Feb 25, 2025
71 of 76 checks passed
vmoens pushed a commit that referenced this pull request Feb 25, 2025
ghstack-source-id: 7fa8834376a1afd9187d7f1d43a97f70d713a160
Pull Request resolved: #2795
@vmoens vmoens deleted the gh/kurtamohler/4/head branch February 25, 2025 21:34
vmoens pushed a commit that referenced this pull request Mar 8, 2025
ghstack-source-id: 7fa8834376a1afd9187d7f1d43a97f70d713a160
Pull Request resolved: #2795

(cherry picked from commit a3a1ebe)
vmoens pushed a commit that referenced this pull request Mar 10, 2025
ghstack-source-id: 7fa8834376a1afd9187d7f1d43a97f70d713a160
Pull Request resolved: #2795

(cherry picked from commit a3a1ebe)
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. documentation Improvements or additions to documentation
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants