Skip to content

[BugFix] Fix env.full_done_spec~s~ #2815

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

Merged
merged 3 commits into from
Mar 3, 2025
Merged

Conversation

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Feb 28, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2815

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

❌ 1 New Failure, 2 Unrelated Failures

As of commit caebdbe with merge base 8c9dc05 (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 Feb 28, 2025
@vmoens vmoens self-assigned this Feb 28, 2025
@vmoens vmoens added the bug Something isn't working label Feb 28, 2025
Copy link

github-actions bot commented Feb 28, 2025

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}34$. Worsened: $\large\color{#d91a1a}8$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.6333s 0.5368s 1.8627 Ops/s 1.9034 Ops/s $\color{#d91a1a}-2.14\%$
test_transformed 1.1426s 1.0412s 0.9605 Ops/s 0.9225 Ops/s $\color{#35bf28}+4.12\%$
test_serial 1.6639s 1.5570s 0.6423 Ops/s 0.6220 Ops/s $\color{#35bf28}+3.26\%$
test_parallel 1.4887s 1.3458s 0.7431 Ops/s 0.7437 Ops/s $\color{#d91a1a}-0.09\%$
test_step_mdp_speed[True-True-True-True-True] 0.2877ms 29.9524μs 33.3863 KOps/s 32.3686 KOps/s $\color{#35bf28}+3.14\%$
test_step_mdp_speed[True-True-True-True-False] 92.3540μs 17.5557μs 56.9614 KOps/s 54.1656 KOps/s $\textbf{\color{#35bf28}+5.16\%}$
test_step_mdp_speed[True-True-True-False-True] 82.2660μs 16.8042μs 59.5091 KOps/s 56.2401 KOps/s $\textbf{\color{#35bf28}+5.81\%}$
test_step_mdp_speed[True-True-True-False-False] 51.0760μs 9.8621μs 101.3978 KOps/s 97.1298 KOps/s $\color{#35bf28}+4.39\%$
test_step_mdp_speed[True-True-False-True-True] 72.7980μs 31.7859μs 31.4605 KOps/s 30.4202 KOps/s $\color{#35bf28}+3.42\%$
test_step_mdp_speed[True-True-False-True-False] 81.8950μs 19.2928μs 51.8328 KOps/s 49.2663 KOps/s $\textbf{\color{#35bf28}+5.21\%}$
test_step_mdp_speed[True-True-False-False-True] 57.7590μs 18.5642μs 53.8671 KOps/s 51.4811 KOps/s $\color{#35bf28}+4.63\%$
test_step_mdp_speed[True-True-False-False-False] 71.1750μs 11.6743μs 85.6581 KOps/s 81.1117 KOps/s $\textbf{\color{#35bf28}+5.61\%}$
test_step_mdp_speed[True-False-True-True-True] 98.2450μs 33.3448μs 29.9897 KOps/s 28.5310 KOps/s $\textbf{\color{#35bf28}+5.11\%}$
test_step_mdp_speed[True-False-True-True-False] 48.3810μs 21.2028μs 47.1636 KOps/s 45.0507 KOps/s $\color{#35bf28}+4.69\%$
test_step_mdp_speed[True-False-True-False-True] 72.7070μs 18.6520μs 53.6136 KOps/s 51.2905 KOps/s $\color{#35bf28}+4.53\%$
test_step_mdp_speed[True-False-True-False-False] 58.1000μs 11.7148μs 85.3624 KOps/s 81.6657 KOps/s $\color{#35bf28}+4.53\%$
test_step_mdp_speed[True-False-False-True-True] 99.1370μs 35.2379μs 28.3785 KOps/s 27.4867 KOps/s $\color{#35bf28}+3.24\%$
test_step_mdp_speed[True-False-False-True-False] 54.8430μs 22.9898μs 43.4975 KOps/s 41.4638 KOps/s $\color{#35bf28}+4.90\%$
test_step_mdp_speed[True-False-False-False-True] 0.5879ms 20.2271μs 49.4386 KOps/s 47.2833 KOps/s $\color{#35bf28}+4.56\%$
test_step_mdp_speed[True-False-False-False-False] 36.5790μs 13.4888μs 74.1354 KOps/s 70.9370 KOps/s $\color{#35bf28}+4.51\%$
test_step_mdp_speed[False-True-True-True-True] 77.0460μs 33.4472μs 29.8978 KOps/s 28.6189 KOps/s $\color{#35bf28}+4.47\%$
test_step_mdp_speed[False-True-True-True-False] 87.8060μs 21.2236μs 47.1173 KOps/s 44.6946 KOps/s $\textbf{\color{#35bf28}+5.42\%}$
test_step_mdp_speed[False-True-True-False-True] 74.2500μs 21.5384μs 46.4286 KOps/s 44.9412 KOps/s $\color{#35bf28}+3.31\%$
test_step_mdp_speed[False-True-True-False-False] 66.0240μs 13.0135μs 76.8431 KOps/s 72.5155 KOps/s $\textbf{\color{#35bf28}+5.97\%}$
test_step_mdp_speed[False-True-False-True-True] 66.9660μs 35.4479μs 28.2104 KOps/s 27.3594 KOps/s $\color{#35bf28}+3.11\%$
test_step_mdp_speed[False-True-False-True-False] 89.0480μs 23.0233μs 43.4344 KOps/s 41.6022 KOps/s $\color{#35bf28}+4.40\%$
test_step_mdp_speed[False-True-False-False-True] 3.0387ms 23.3502μs 42.8262 KOps/s 41.0495 KOps/s $\color{#35bf28}+4.33\%$
test_step_mdp_speed[False-True-False-False-False] 46.3580μs 14.7800μs 67.6591 KOps/s 64.2970 KOps/s $\textbf{\color{#35bf28}+5.23\%}$
test_step_mdp_speed[False-False-True-True-True] 0.1163ms 36.9457μs 27.0667 KOps/s 25.0849 KOps/s $\textbf{\color{#35bf28}+7.90\%}$
test_step_mdp_speed[False-False-True-True-False] 87.3080μs 24.6678μs 40.5387 KOps/s 38.5963 KOps/s $\textbf{\color{#35bf28}+5.03\%}$
test_step_mdp_speed[False-False-True-False-True] 82.5710μs 23.0068μs 43.4654 KOps/s 41.0932 KOps/s $\textbf{\color{#35bf28}+5.77\%}$
test_step_mdp_speed[False-False-True-False-False] 38.4330μs 14.8221μs 67.4666 KOps/s 64.1219 KOps/s $\textbf{\color{#35bf28}+5.22\%}$
test_step_mdp_speed[False-False-False-True-True] 0.1112ms 38.7239μs 25.8238 KOps/s 24.9189 KOps/s $\color{#35bf28}+3.63\%$
test_step_mdp_speed[False-False-False-True-False] 92.3040μs 26.6074μs 37.5836 KOps/s 36.1869 KOps/s $\color{#35bf28}+3.86\%$
test_step_mdp_speed[False-False-False-False-True] 53.8820μs 24.6038μs 40.6441 KOps/s 38.4789 KOps/s $\textbf{\color{#35bf28}+5.63\%}$
test_step_mdp_speed[False-False-False-False-False] 85.5910μs 16.4357μs 60.8433 KOps/s 57.7056 KOps/s $\textbf{\color{#35bf28}+5.44\%}$
test_values[generalized_advantage_estimate-True-True] 12.6664ms 10.3713ms 96.4202 Ops/s 102.4453 Ops/s $\textbf{\color{#d91a1a}-5.88\%}$
test_values[vec_generalized_advantage_estimate-True-True] 30.5589ms 27.6850ms 36.1206 Ops/s 39.9719 Ops/s $\textbf{\color{#d91a1a}-9.63\%}$
test_values[td0_return_estimate-False-False] 0.2500ms 0.1881ms 5.3169 KOps/s 4.5696 KOps/s $\textbf{\color{#35bf28}+16.35\%}$
test_values[td1_return_estimate-False-False] 29.1262ms 25.3961ms 39.3762 Ops/s 40.7372 Ops/s $\color{#d91a1a}-3.34\%$
test_values[vec_td1_return_estimate-False-False] 29.3753ms 27.5044ms 36.3579 Ops/s 39.8502 Ops/s $\textbf{\color{#d91a1a}-8.76\%}$
test_values[td_lambda_return_estimate-True-False] 36.9621ms 36.0715ms 27.7227 Ops/s 28.6201 Ops/s $\color{#d91a1a}-3.14\%$
test_values[vec_td_lambda_return_estimate-True-False] 30.3308ms 27.7826ms 35.9937 Ops/s 39.7487 Ops/s $\textbf{\color{#d91a1a}-9.45\%}$
test_gae_speed[generalized_advantage_estimate-False-1-512] 12.0185ms 8.6674ms 115.3743 Ops/s 119.1808 Ops/s $\color{#d91a1a}-3.19\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 3.0815ms 1.8329ms 545.5823 Ops/s 544.3117 Ops/s $\color{#35bf28}+0.23\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.6300ms 0.3841ms 2.6034 KOps/s 2.5469 KOps/s $\color{#35bf28}+2.22\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 46.0352ms 44.6773ms 22.3827 Ops/s 22.5782 Ops/s $\color{#d91a1a}-0.87\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 4.4924ms 3.4895ms 286.5706 Ops/s 283.2958 Ops/s $\color{#35bf28}+1.16\%$
test_dqn_speed[False-None] 5.8354ms 1.4563ms 686.6788 Ops/s 667.6530 Ops/s $\color{#35bf28}+2.85\%$
test_dqn_speed[False-backward] 2.0679ms 1.9463ms 513.7822 Ops/s 477.4597 Ops/s $\textbf{\color{#35bf28}+7.61\%}$
test_dqn_speed[True-None] 0.8484ms 0.4918ms 2.0332 KOps/s 1.9950 KOps/s $\color{#35bf28}+1.92\%$
test_dqn_speed[True-backward] 1.0879ms 0.9963ms 1.0037 KOps/s 972.2826 Ops/s $\color{#35bf28}+3.23\%$
test_dqn_speed[reduce-overhead-None] 0.7758ms 0.4936ms 2.0259 KOps/s 1.9695 KOps/s $\color{#35bf28}+2.86\%$
test_dqn_speed[reduce-overhead-backward] 1.0209ms 0.9518ms 1.0506 KOps/s 948.6657 Ops/s $\textbf{\color{#35bf28}+10.75\%}$
test_ddpg_speed[False-None] 3.8845ms 2.9875ms 334.7324 Ops/s 322.5660 Ops/s $\color{#35bf28}+3.77\%$
test_ddpg_speed[False-backward] 4.4883ms 4.1399ms 241.5522 Ops/s 219.2882 Ops/s $\textbf{\color{#35bf28}+10.15\%}$
test_ddpg_speed[True-None] 1.6319ms 1.2496ms 800.2846 Ops/s 788.0987 Ops/s $\color{#35bf28}+1.55\%$
test_ddpg_speed[True-backward] 2.3039ms 2.2099ms 452.5115 Ops/s 445.8429 Ops/s $\color{#35bf28}+1.50\%$
test_ddpg_speed[reduce-overhead-None] 1.7689ms 1.2533ms 797.9227 Ops/s 789.6666 Ops/s $\color{#35bf28}+1.05\%$
test_ddpg_speed[reduce-overhead-backward] 2.4217ms 2.2171ms 451.0312 Ops/s 439.2239 Ops/s $\color{#35bf28}+2.69\%$
test_sac_speed[False-None] 11.8395ms 8.7741ms 113.9717 Ops/s 113.7120 Ops/s $\color{#35bf28}+0.23\%$
test_sac_speed[False-backward] 12.6289ms 11.5959ms 86.2371 Ops/s 85.6506 Ops/s $\color{#35bf28}+0.68\%$
test_sac_speed[True-None] 2.9363ms 2.2058ms 453.3540 Ops/s 458.3440 Ops/s $\color{#d91a1a}-1.09\%$
test_sac_speed[True-backward] 5.5672ms 4.3329ms 230.7948 Ops/s 253.9545 Ops/s $\textbf{\color{#d91a1a}-9.12\%}$
test_sac_speed[reduce-overhead-None] 3.6649ms 2.1732ms 460.1613 Ops/s 450.6032 Ops/s $\color{#35bf28}+2.12\%$
test_sac_speed[reduce-overhead-backward] 4.1347ms 3.9261ms 254.7028 Ops/s 250.2448 Ops/s $\color{#35bf28}+1.78\%$
test_redq_speed[False-None] 22.2758ms 14.5882ms 68.5485 Ops/s 69.2362 Ops/s $\color{#d91a1a}-0.99\%$
test_redq_speed[False-backward] 28.7326ms 24.1935ms 41.3335 Ops/s 41.0690 Ops/s $\color{#35bf28}+0.64\%$
test_redq_speed[True-None] 6.8271ms 5.6530ms 176.8987 Ops/s 161.1610 Ops/s $\textbf{\color{#35bf28}+9.77\%}$
test_redq_speed[True-backward] 15.4227ms 13.7985ms 72.4715 Ops/s 69.4199 Ops/s $\color{#35bf28}+4.40\%$
test_redq_speed[reduce-overhead-None] 7.4790ms 5.8049ms 172.2687 Ops/s 160.7956 Ops/s $\textbf{\color{#35bf28}+7.14\%}$
test_redq_speed[reduce-overhead-backward] 14.9892ms 13.6930ms 73.0300 Ops/s 68.9092 Ops/s $\textbf{\color{#35bf28}+5.98\%}$
test_redq_deprec_speed[False-None] 16.8981ms 14.7836ms 67.6428 Ops/s 67.5266 Ops/s $\color{#35bf28}+0.17\%$
test_redq_deprec_speed[False-backward] 22.4965ms 20.4511ms 48.8972 Ops/s 45.9106 Ops/s $\textbf{\color{#35bf28}+6.51\%}$
test_redq_deprec_speed[True-None] 6.1929ms 4.3227ms 231.3347 Ops/s 215.5185 Ops/s $\textbf{\color{#35bf28}+7.34\%}$
test_redq_deprec_speed[True-backward] 10.9407ms 9.6340ms 103.7988 Ops/s 106.2458 Ops/s $\color{#d91a1a}-2.30\%$
test_redq_deprec_speed[reduce-overhead-None] 5.3427ms 4.3265ms 231.1320 Ops/s 231.1939 Ops/s $\color{#d91a1a}-0.03\%$
test_redq_deprec_speed[reduce-overhead-backward] 10.7118ms 9.7934ms 102.1097 Ops/s 103.6074 Ops/s $\color{#d91a1a}-1.45\%$
test_td3_speed[False-None] 9.2011ms 8.5552ms 116.8873 Ops/s 112.8751 Ops/s $\color{#35bf28}+3.55\%$
test_td3_speed[False-backward] 12.7563ms 11.2306ms 89.0425 Ops/s 85.2307 Ops/s $\color{#35bf28}+4.47\%$
test_td3_speed[True-None] 2.3453ms 1.9011ms 526.0093 Ops/s 538.7498 Ops/s $\color{#d91a1a}-2.36\%$
test_td3_speed[True-backward] 3.6282ms 3.5031ms 285.4603 Ops/s 267.8202 Ops/s $\textbf{\color{#35bf28}+6.59\%}$
test_td3_speed[reduce-overhead-None] 2.3368ms 1.8676ms 535.4454 Ops/s 528.4518 Ops/s $\color{#35bf28}+1.32\%$
test_td3_speed[reduce-overhead-backward] 4.5791ms 3.6272ms 275.6910 Ops/s 274.9024 Ops/s $\color{#35bf28}+0.29\%$
test_cql_speed[False-None] 41.2516ms 38.4031ms 26.0396 Ops/s 25.1879 Ops/s $\color{#35bf28}+3.38\%$
test_cql_speed[False-backward] 50.1778ms 48.3396ms 20.6870 Ops/s 20.0608 Ops/s $\color{#35bf28}+3.12\%$
test_cql_speed[True-None] 18.0785ms 16.9103ms 59.1354 Ops/s 58.3461 Ops/s $\color{#35bf28}+1.35\%$
test_cql_speed[True-backward] 31.1484ms 25.1491ms 39.7628 Ops/s 40.2170 Ops/s $\color{#d91a1a}-1.13\%$
test_cql_speed[reduce-overhead-None] 18.3271ms 17.2002ms 58.1389 Ops/s 58.8579 Ops/s $\color{#d91a1a}-1.22\%$
test_cql_speed[reduce-overhead-backward] 29.2906ms 24.9037ms 40.1547 Ops/s 39.7055 Ops/s $\color{#35bf28}+1.13\%$
test_a2c_speed[False-None] 9.2157ms 7.8342ms 127.6450 Ops/s 126.8183 Ops/s $\color{#35bf28}+0.65\%$
test_a2c_speed[False-backward] 16.9101ms 16.0822ms 62.1805 Ops/s 63.7431 Ops/s $\color{#d91a1a}-2.45\%$
test_a2c_speed[True-None] 4.5717ms 3.8774ms 257.9038 Ops/s 254.3205 Ops/s $\color{#35bf28}+1.41\%$
test_a2c_speed[True-backward] 11.8274ms 11.0278ms 90.6799 Ops/s 89.2651 Ops/s $\color{#35bf28}+1.59\%$
test_a2c_speed[reduce-overhead-None] 4.5774ms 3.9134ms 255.5339 Ops/s 245.9316 Ops/s $\color{#35bf28}+3.90\%$
test_a2c_speed[reduce-overhead-backward] 12.0022ms 11.0809ms 90.2455 Ops/s 92.2935 Ops/s $\color{#d91a1a}-2.22\%$
test_ppo_speed[False-None] 9.6216ms 8.0495ms 124.2314 Ops/s 126.5484 Ops/s $\color{#d91a1a}-1.83\%$
test_ppo_speed[False-backward] 18.6846ms 16.7524ms 59.6929 Ops/s 62.6890 Ops/s $\color{#d91a1a}-4.78\%$
test_ppo_speed[True-None] 5.1232ms 4.2878ms 233.2199 Ops/s 224.4901 Ops/s $\color{#35bf28}+3.89\%$
test_ppo_speed[True-backward] 11.5091ms 10.8254ms 92.3755 Ops/s 91.4299 Ops/s $\color{#35bf28}+1.03\%$
test_ppo_speed[reduce-overhead-None] 5.6148ms 4.4723ms 223.6002 Ops/s 224.8283 Ops/s $\color{#d91a1a}-0.55\%$
test_ppo_speed[reduce-overhead-backward] 12.4403ms 11.4527ms 87.3158 Ops/s 90.1136 Ops/s $\color{#d91a1a}-3.10\%$
test_reinforce_speed[False-None] 8.2851ms 7.0293ms 142.2613 Ops/s 139.4573 Ops/s $\color{#35bf28}+2.01\%$
test_reinforce_speed[False-backward] 11.2112ms 10.3015ms 97.0729 Ops/s 90.5757 Ops/s $\textbf{\color{#35bf28}+7.17\%}$
test_reinforce_speed[True-None] 4.4343ms 3.3857ms 295.3632 Ops/s 301.1783 Ops/s $\color{#d91a1a}-1.93\%$
test_reinforce_speed[True-backward] 9.9567ms 9.4433ms 105.8949 Ops/s 97.9467 Ops/s $\textbf{\color{#35bf28}+8.11\%}$
test_reinforce_speed[reduce-overhead-None] 3.7208ms 3.2447ms 308.1952 Ops/s 305.9617 Ops/s $\color{#35bf28}+0.73\%$
test_reinforce_speed[reduce-overhead-backward] 10.9328ms 9.9685ms 100.3164 Ops/s 98.7366 Ops/s $\color{#35bf28}+1.60\%$
test_iql_speed[False-None] 34.3198ms 33.3949ms 29.9447 Ops/s 29.5003 Ops/s $\color{#35bf28}+1.51\%$
test_iql_speed[False-backward] 49.7363ms 46.8161ms 21.3602 Ops/s 20.7608 Ops/s $\color{#35bf28}+2.89\%$
test_iql_speed[True-None] 13.4004ms 12.0796ms 82.7844 Ops/s 82.3929 Ops/s $\color{#35bf28}+0.48\%$
test_iql_speed[True-backward] 24.7920ms 23.5990ms 42.3746 Ops/s 40.9668 Ops/s $\color{#35bf28}+3.44\%$
test_iql_speed[reduce-overhead-None] 13.3835ms 12.2184ms 81.8439 Ops/s 80.9618 Ops/s $\color{#35bf28}+1.09\%$
test_iql_speed[reduce-overhead-backward] 28.2310ms 24.6468ms 40.5732 Ops/s 40.0152 Ops/s $\color{#35bf28}+1.39\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.3320ms 5.1267ms 195.0588 Ops/s 181.7834 Ops/s $\textbf{\color{#35bf28}+7.30\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8403ms 0.5278ms 1.8948 KOps/s 1.8283 KOps/s $\color{#35bf28}+3.64\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8094ms 0.5143ms 1.9446 KOps/s 1.9089 KOps/s $\color{#35bf28}+1.87\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.0785ms 5.1725ms 193.3291 Ops/s 192.0979 Ops/s $\color{#35bf28}+0.64\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 3.8501ms 0.5378ms 1.8595 KOps/s 1.8390 KOps/s $\color{#35bf28}+1.11\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.8227ms 0.5128ms 1.9501 KOps/s 1.9364 KOps/s $\color{#35bf28}+0.71\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 2.4962ms 1.7082ms 585.3965 Ops/s 586.2672 Ops/s $\color{#d91a1a}-0.15\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 2.2950ms 1.5960ms 626.5655 Ops/s 616.4120 Ops/s $\color{#35bf28}+1.65\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.4221ms 5.0139ms 199.4452 Ops/s 187.1386 Ops/s $\textbf{\color{#35bf28}+6.58\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2794ms 0.6784ms 1.4740 KOps/s 1.4695 KOps/s $\color{#35bf28}+0.30\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9588ms 0.6511ms 1.5360 KOps/s 1.5212 KOps/s $\color{#35bf28}+0.97\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.3059ms 5.2311ms 191.1630 Ops/s 187.9351 Ops/s $\color{#35bf28}+1.72\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.3485ms 0.5319ms 1.8802 KOps/s 1.7880 KOps/s $\textbf{\color{#35bf28}+5.16\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.9328ms 0.5190ms 1.9268 KOps/s 1.8760 KOps/s $\color{#35bf28}+2.71\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.4746ms 4.8954ms 204.2742 Ops/s 190.8964 Ops/s $\textbf{\color{#35bf28}+7.01\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.3463ms 0.5273ms 1.8966 KOps/s 1.8447 KOps/s $\color{#35bf28}+2.81\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7663ms 0.5033ms 1.9867 KOps/s 1.8918 KOps/s $\textbf{\color{#35bf28}+5.01\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 8.0879ms 5.2214ms 191.5204 Ops/s 188.6537 Ops/s $\color{#35bf28}+1.52\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.1808ms 0.6721ms 1.4880 KOps/s 1.4561 KOps/s $\color{#35bf28}+2.19\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.9328ms 0.6565ms 1.5232 KOps/s 1.5513 KOps/s $\color{#d91a1a}-1.81\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.2452ms 4.4848ms 222.9742 Ops/s 231.4517 Ops/s $\color{#d91a1a}-3.66\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 8.5206ms 2.4759ms 403.8889 Ops/s 409.5646 Ops/s $\color{#d91a1a}-1.39\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 2.0526ms 1.3697ms 730.1090 Ops/s 675.5820 Ops/s $\textbf{\color{#35bf28}+8.07\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 7.8799ms 5.0347ms 198.6211 Ops/s 233.0480 Ops/s $\textbf{\color{#d91a1a}-14.77\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 0.5919s 14.2488ms 70.1816 Ops/s 416.7806 Ops/s $\textbf{\color{#d91a1a}-83.16\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 8.0515ms 1.5299ms 653.6304 Ops/s 728.7156 Ops/s $\textbf{\color{#d91a1a}-10.30\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 8.1612ms 4.8916ms 204.4341 Ops/s 28.7114 Ops/s $\textbf{\color{#35bf28}+612.03\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.3938ms 2.7594ms 362.3967 Ops/s 365.5655 Ops/s $\color{#d91a1a}-0.87\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.4443ms 1.6451ms 607.8794 Ops/s 603.7303 Ops/s $\color{#35bf28}+0.69\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 12.6634ms 11.9654ms 83.5741 Ops/s 77.9678 Ops/s $\textbf{\color{#35bf28}+7.19\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 19.5555ms 15.0328ms 66.5212 Ops/s 67.1153 Ops/s $\color{#d91a1a}-0.89\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 21.2900ms 20.7268ms 48.2468 Ops/s 46.0681 Ops/s $\color{#35bf28}+4.73\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 17.3615ms 15.1993ms 65.7927 Ops/s 66.9399 Ops/s $\color{#d91a1a}-1.71\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 22.2725ms 20.8669ms 47.9229 Ops/s 46.6513 Ops/s $\color{#35bf28}+2.73\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 18.4256ms 16.5450ms 60.4412 Ops/s 61.2517 Ops/s $\color{#d91a1a}-1.32\%$

Copy link

github-actions bot commented Feb 28, 2025

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

Total Benchmarks: 149. Improved: $\large\color{#35bf28}15$. Worsened: $\large\color{#d91a1a}13$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_simple 0.8979s 0.8111s 1.2329 Ops/s 1.1941 Ops/s $\color{#35bf28}+3.25\%$
test_transformed 1.4873s 1.4032s 0.7126 Ops/s 0.6828 Ops/s $\color{#35bf28}+4.37\%$
test_serial 2.3768s 2.3024s 0.4343 Ops/s 0.4234 Ops/s $\color{#35bf28}+2.59\%$
test_parallel 1.9603s 1.8611s 0.5373 Ops/s 0.5315 Ops/s $\color{#35bf28}+1.11\%$
test_step_mdp_speed[True-True-True-True-True] 0.4162ms 40.0582μs 24.9636 KOps/s 24.8397 KOps/s $\color{#35bf28}+0.50\%$
test_step_mdp_speed[True-True-True-True-False] 50.2810μs 23.6170μs 42.3424 KOps/s 42.4082 KOps/s $\color{#d91a1a}-0.16\%$
test_step_mdp_speed[True-True-True-False-True] 0.4153ms 22.4244μs 44.5943 KOps/s 44.3868 KOps/s $\color{#35bf28}+0.47\%$
test_step_mdp_speed[True-True-True-False-False] 0.3986ms 13.0904μs 76.3918 KOps/s 76.6245 KOps/s $\color{#d91a1a}-0.30\%$
test_step_mdp_speed[True-True-False-True-True] 0.4356ms 42.6193μs 23.4635 KOps/s 23.6745 KOps/s $\color{#d91a1a}-0.89\%$
test_step_mdp_speed[True-True-False-True-False] 61.1510μs 25.8071μs 38.7490 KOps/s 38.7463 KOps/s $+0.01\%$
test_step_mdp_speed[True-True-False-False-True] 0.4142ms 25.0917μs 39.8538 KOps/s 40.2838 KOps/s $\color{#d91a1a}-1.07\%$
test_step_mdp_speed[True-True-False-False-False] 0.4032ms 15.5321μs 64.3827 KOps/s 65.0065 KOps/s $\color{#d91a1a}-0.96\%$
test_step_mdp_speed[True-False-True-True-True] 0.4333ms 44.7141μs 22.3643 KOps/s 22.3180 KOps/s $\color{#35bf28}+0.21\%$
test_step_mdp_speed[True-False-True-True-False] 58.7910μs 28.0938μs 35.5950 KOps/s 35.3709 KOps/s $\color{#35bf28}+0.63\%$
test_step_mdp_speed[True-False-True-False-True] 0.4104ms 24.8277μs 40.2776 KOps/s 40.6276 KOps/s $\color{#d91a1a}-0.86\%$
test_step_mdp_speed[True-False-True-False-False] 0.4149ms 15.3291μs 65.2355 KOps/s 64.5357 KOps/s $\color{#35bf28}+1.08\%$
test_step_mdp_speed[True-False-False-True-True] 0.4418ms 47.1256μs 21.2199 KOps/s 20.5732 KOps/s $\color{#35bf28}+3.14\%$
test_step_mdp_speed[True-False-False-True-False] 75.1000μs 30.2198μs 33.0909 KOps/s 32.2141 KOps/s $\color{#35bf28}+2.72\%$
test_step_mdp_speed[True-False-False-False-True] 0.4187ms 26.9152μs 37.1537 KOps/s 36.5922 KOps/s $\color{#35bf28}+1.53\%$
test_step_mdp_speed[True-False-False-False-False] 0.4073ms 17.6779μs 56.5676 KOps/s 55.8942 KOps/s $\color{#35bf28}+1.20\%$
test_step_mdp_speed[False-True-True-True-True] 77.1910μs 45.1956μs 22.1261 KOps/s 21.9412 KOps/s $\color{#35bf28}+0.84\%$
test_step_mdp_speed[False-True-True-True-False] 0.4177ms 28.2003μs 35.4606 KOps/s 35.3474 KOps/s $\color{#35bf28}+0.32\%$
test_step_mdp_speed[False-True-True-False-True] 53.2000μs 29.0685μs 34.4015 KOps/s 35.1598 KOps/s $\color{#d91a1a}-2.16\%$
test_step_mdp_speed[False-True-True-False-False] 0.4056ms 17.2553μs 57.9532 KOps/s 57.9926 KOps/s $\color{#d91a1a}-0.07\%$
test_step_mdp_speed[False-True-False-True-True] 0.4401ms 48.4139μs 20.6552 KOps/s 20.6541 KOps/s $+0.01\%$
test_step_mdp_speed[False-True-False-True-False] 0.4361ms 31.0424μs 32.2140 KOps/s 34.5004 KOps/s $\textbf{\color{#d91a1a}-6.63\%}$
test_step_mdp_speed[False-True-False-False-True] 3.1652ms 31.4802μs 31.7660 KOps/s 32.5775 KOps/s $\color{#d91a1a}-2.49\%$
test_step_mdp_speed[False-True-False-False-False] 0.4681ms 19.7542μs 50.6221 KOps/s 51.2367 KOps/s $\color{#d91a1a}-1.20\%$
test_step_mdp_speed[False-False-True-True-True] 0.4423ms 50.5172μs 19.7952 KOps/s 19.6593 KOps/s $\color{#35bf28}+0.69\%$
test_step_mdp_speed[False-False-True-True-False] 0.4194ms 33.1604μs 30.1564 KOps/s 29.9813 KOps/s $\color{#35bf28}+0.58\%$
test_step_mdp_speed[False-False-True-False-True] 74.8100μs 31.4209μs 31.8260 KOps/s 32.0341 KOps/s $\color{#d91a1a}-0.65\%$
test_step_mdp_speed[False-False-True-False-False] 0.4089ms 19.5256μs 51.2147 KOps/s 51.4111 KOps/s $\color{#d91a1a}-0.38\%$
test_step_mdp_speed[False-False-False-True-True] 0.4562ms 51.7564μs 19.3213 KOps/s 19.2023 KOps/s $\color{#35bf28}+0.62\%$
test_step_mdp_speed[False-False-False-True-False] 0.4414ms 34.8951μs 28.6573 KOps/s 28.4525 KOps/s $\color{#35bf28}+0.72\%$
test_step_mdp_speed[False-False-False-False-True] 67.7100μs 32.4564μs 30.8105 KOps/s 30.1073 KOps/s $\color{#35bf28}+2.34\%$
test_step_mdp_speed[False-False-False-False-False] 0.4144ms 21.5424μs 46.4201 KOps/s 46.7238 KOps/s $\color{#d91a1a}-0.65\%$
test_values[generalized_advantage_estimate-True-True] 26.5015ms 25.1663ms 39.7357 Ops/s 39.6333 Ops/s $\color{#35bf28}+0.26\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1074s 3.0447ms 328.4433 Ops/s 344.0243 Ops/s $\color{#d91a1a}-4.53\%$
test_values[td0_return_estimate-False-False] 0.1055ms 79.5964μs 12.5634 KOps/s 12.3663 KOps/s $\color{#35bf28}+1.59\%$
test_values[td1_return_estimate-False-False] 58.3380ms 55.5654ms 17.9968 Ops/s 17.7215 Ops/s $\color{#35bf28}+1.55\%$
test_values[vec_td1_return_estimate-False-False] 1.4955ms 1.0879ms 919.1845 Ops/s 918.6693 Ops/s $\color{#35bf28}+0.06\%$
test_values[td_lambda_return_estimate-True-False] 92.1669ms 89.0102ms 11.2347 Ops/s 11.2115 Ops/s $\color{#35bf28}+0.21\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.2932ms 1.0751ms 930.1805 Ops/s 915.9963 Ops/s $\color{#35bf28}+1.55\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 24.9680ms 24.5009ms 40.8148 Ops/s 39.3439 Ops/s $\color{#35bf28}+3.74\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0853ms 0.7672ms 1.3034 KOps/s 1.3098 KOps/s $\color{#d91a1a}-0.49\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 1.0863ms 0.6629ms 1.5085 KOps/s 1.4896 KOps/s $\color{#35bf28}+1.27\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.7860ms 1.4811ms 675.1892 Ops/s 668.8658 Ops/s $\color{#35bf28}+0.95\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7375ms 0.6777ms 1.4755 KOps/s 1.4588 KOps/s $\color{#35bf28}+1.14\%$
test_dqn_speed[False-None] 1.8782ms 1.4787ms 676.2735 Ops/s 660.3294 Ops/s $\color{#35bf28}+2.41\%$
test_dqn_speed[False-backward] 2.1345ms 2.0882ms 478.8855 Ops/s 463.9584 Ops/s $\color{#35bf28}+3.22\%$
test_dqn_speed[True-None] 0.7164ms 0.5449ms 1.8352 KOps/s 1.7348 KOps/s $\textbf{\color{#35bf28}+5.79\%}$
test_dqn_speed[True-backward] 1.3823ms 1.2281ms 814.2470 Ops/s 854.7217 Ops/s $\color{#d91a1a}-4.74\%$
test_dqn_speed[reduce-overhead-None] 0.6710ms 0.5639ms 1.7732 KOps/s 1.7458 KOps/s $\color{#35bf28}+1.57\%$
test_dqn_speed[reduce-overhead-backward] 1.1102ms 1.0556ms 947.3347 Ops/s 1.0208 KOps/s $\textbf{\color{#d91a1a}-7.20\%}$
test_ddpg_speed[False-None] 3.0699ms 2.7562ms 362.8199 Ops/s 351.6176 Ops/s $\color{#35bf28}+3.19\%$
test_ddpg_speed[False-backward] 4.5349ms 4.1315ms 242.0438 Ops/s 240.5921 Ops/s $\color{#35bf28}+0.60\%$
test_ddpg_speed[True-None] 1.4745ms 1.3322ms 750.6187 Ops/s 735.7514 Ops/s $\color{#35bf28}+2.02\%$
test_ddpg_speed[True-backward] 2.6419ms 2.5683ms 389.3641 Ops/s 393.4338 Ops/s $\color{#d91a1a}-1.03\%$
test_ddpg_speed[reduce-overhead-None] 1.4854ms 1.3449ms 743.5451 Ops/s 738.6184 Ops/s $\color{#35bf28}+0.67\%$
test_ddpg_speed[reduce-overhead-backward] 2.1024ms 2.0235ms 494.1877 Ops/s 521.4548 Ops/s $\textbf{\color{#d91a1a}-5.23\%}$
test_sac_speed[False-None] 8.3081ms 7.8929ms 126.6966 Ops/s 122.0896 Ops/s $\color{#35bf28}+3.77\%$
test_sac_speed[False-backward] 11.7093ms 11.0221ms 90.7267 Ops/s 89.4019 Ops/s $\color{#35bf28}+1.48\%$
test_sac_speed[True-None] 2.0252ms 1.8834ms 530.9616 Ops/s 539.9110 Ops/s $\color{#d91a1a}-1.66\%$
test_sac_speed[True-backward] 4.1798ms 3.7328ms 267.8923 Ops/s 259.8468 Ops/s $\color{#35bf28}+3.10\%$
test_sac_speed[reduce-overhead-None] 26.7645ms 12.2829ms 81.4140 Ops/s 82.7311 Ops/s $\color{#d91a1a}-1.59\%$
test_sac_speed[reduce-overhead-backward] 2.1116ms 1.7717ms 564.4415 Ops/s 550.6086 Ops/s $\color{#35bf28}+2.51\%$
test_redq_speed[False-None] 7.9645ms 7.5032ms 133.2769 Ops/s 127.3683 Ops/s $\color{#35bf28}+4.64\%$
test_redq_speed[False-backward] 12.1820ms 11.7177ms 85.3411 Ops/s 83.3725 Ops/s $\color{#35bf28}+2.36\%$
test_redq_speed[True-None] 2.5480ms 2.3696ms 422.0174 Ops/s 420.3917 Ops/s $\color{#35bf28}+0.39\%$
test_redq_speed[True-backward] 4.8818ms 4.3924ms 227.6634 Ops/s 231.1061 Ops/s $\color{#d91a1a}-1.49\%$
test_redq_speed[reduce-overhead-None] 2.7157ms 2.3422ms 426.9433 Ops/s 419.0865 Ops/s $\color{#35bf28}+1.87\%$
test_redq_speed[reduce-overhead-backward] 4.7531ms 4.3201ms 231.4768 Ops/s 240.1886 Ops/s $\color{#d91a1a}-3.63\%$
test_redq_deprec_speed[False-None] 9.7382ms 9.2436ms 108.1827 Ops/s 106.5113 Ops/s $\color{#35bf28}+1.57\%$
test_redq_deprec_speed[False-backward] 12.8304ms 12.2112ms 81.8921 Ops/s 80.8154 Ops/s $\color{#35bf28}+1.33\%$
test_redq_deprec_speed[True-None] 3.0165ms 2.6284ms 380.4538 Ops/s 364.1580 Ops/s $\color{#35bf28}+4.47\%$
test_redq_deprec_speed[True-backward] 4.5718ms 4.4677ms 223.8300 Ops/s 218.1276 Ops/s $\color{#35bf28}+2.61\%$
test_redq_deprec_speed[reduce-overhead-None] 3.1803ms 2.6766ms 373.6018 Ops/s 373.7052 Ops/s $\color{#d91a1a}-0.03\%$
test_redq_deprec_speed[reduce-overhead-backward] 4.9184ms 4.4966ms 222.3890 Ops/s 221.6618 Ops/s $\color{#35bf28}+0.33\%$
test_td3_speed[False-None] 8.1081ms 7.8474ms 127.4310 Ops/s 124.0825 Ops/s $\color{#35bf28}+2.70\%$
test_td3_speed[False-backward] 10.9675ms 10.3866ms 96.2779 Ops/s 96.3230 Ops/s $\color{#d91a1a}-0.05\%$
test_td3_speed[True-None] 1.6936ms 1.6216ms 616.6753 Ops/s 591.2555 Ops/s $\color{#35bf28}+4.30\%$
test_td3_speed[True-backward] 3.3937ms 3.3144ms 301.7157 Ops/s 306.6935 Ops/s $\color{#d91a1a}-1.62\%$
test_td3_speed[reduce-overhead-None] 51.4505ms 26.4135ms 37.8594 Ops/s 38.6785 Ops/s $\color{#d91a1a}-2.12\%$
test_td3_speed[reduce-overhead-backward] 1.5040ms 1.4479ms 690.6406 Ops/s 672.9501 Ops/s $\color{#35bf28}+2.63\%$
test_cql_speed[False-None] 17.0012ms 16.4720ms 60.7090 Ops/s 58.8923 Ops/s $\color{#35bf28}+3.08\%$
test_cql_speed[False-backward] 22.4119ms 21.8992ms 45.6637 Ops/s 44.4040 Ops/s $\color{#35bf28}+2.84\%$
test_cql_speed[True-None] 3.5428ms 3.3321ms 300.1089 Ops/s 301.3386 Ops/s $\color{#d91a1a}-0.41\%$
test_cql_speed[True-backward] 6.2168ms 5.5957ms 178.7075 Ops/s 173.3421 Ops/s $\color{#35bf28}+3.10\%$
test_cql_speed[reduce-overhead-None] 20.8201ms 13.1437ms 76.0823 Ops/s 74.9913 Ops/s $\color{#35bf28}+1.45\%$
test_cql_speed[reduce-overhead-backward] 2.0026ms 1.9246ms 519.5757 Ops/s 536.4317 Ops/s $\color{#d91a1a}-3.14\%$
test_a2c_speed[False-None] 3.2192ms 3.1045ms 322.1164 Ops/s 304.0063 Ops/s $\textbf{\color{#35bf28}+5.96\%}$
test_a2c_speed[False-backward] 6.9951ms 6.2184ms 160.8139 Ops/s 161.2731 Ops/s $\color{#d91a1a}-0.28\%$
test_a2c_speed[True-None] 1.5389ms 1.3448ms 743.6254 Ops/s 744.6843 Ops/s $\color{#d91a1a}-0.14\%$
test_a2c_speed[True-backward] 3.1990ms 3.0987ms 322.7144 Ops/s 337.7377 Ops/s $\color{#d91a1a}-4.45\%$
test_a2c_speed[reduce-overhead-None] 16.6714ms 9.2397ms 108.2290 Ops/s 111.9104 Ops/s $\color{#d91a1a}-3.29\%$
test_a2c_speed[reduce-overhead-backward] 1.6567ms 1.5543ms 643.3757 Ops/s 612.7152 Ops/s $\textbf{\color{#35bf28}+5.00\%}$
test_ppo_speed[False-None] 3.7141ms 3.5914ms 278.4423 Ops/s 268.2138 Ops/s $\color{#35bf28}+3.81\%$
test_ppo_speed[False-backward] 7.1140ms 6.8718ms 145.5222 Ops/s 139.2756 Ops/s $\color{#35bf28}+4.49\%$
test_ppo_speed[True-None] 1.5142ms 1.4133ms 707.5632 Ops/s 693.1756 Ops/s $\color{#35bf28}+2.08\%$
test_ppo_speed[True-backward] 3.1722ms 3.0914ms 323.4828 Ops/s 302.1998 Ops/s $\textbf{\color{#35bf28}+7.04\%}$
test_ppo_speed[reduce-overhead-None] 1.0557ms 0.9669ms 1.0342 KOps/s 1.0239 KOps/s $\color{#35bf28}+1.00\%$
test_ppo_speed[reduce-overhead-backward] 1.5050ms 1.4019ms 713.3280 Ops/s 614.7999 Ops/s $\textbf{\color{#35bf28}+16.03\%}$
test_reinforce_speed[False-None] 2.3350ms 2.2176ms 450.9430 Ops/s 434.9673 Ops/s $\color{#35bf28}+3.67\%$
test_reinforce_speed[False-backward] 3.6628ms 3.2320ms 309.4073 Ops/s 292.2389 Ops/s $\textbf{\color{#35bf28}+5.87\%}$
test_reinforce_speed[True-None] 1.4079ms 1.2915ms 774.3149 Ops/s 763.7915 Ops/s $\color{#35bf28}+1.38\%$
test_reinforce_speed[True-backward] 3.0107ms 2.9390ms 340.2470 Ops/s 323.1606 Ops/s $\textbf{\color{#35bf28}+5.29\%}$
test_reinforce_speed[reduce-overhead-None] 18.2888ms 10.1211ms 98.8032 Ops/s 99.5845 Ops/s $\color{#d91a1a}-0.78\%$
test_reinforce_speed[reduce-overhead-backward] 1.5910ms 1.5027ms 665.4626 Ops/s 594.7979 Ops/s $\textbf{\color{#35bf28}+11.88\%}$
test_iql_speed[False-None] 9.4632ms 9.0929ms 109.9760 Ops/s 105.6803 Ops/s $\color{#35bf28}+4.06\%$
test_iql_speed[False-backward] 13.5669ms 12.7201ms 78.6157 Ops/s 74.8400 Ops/s $\textbf{\color{#35bf28}+5.04\%}$
test_iql_speed[True-None] 2.4352ms 2.2964ms 435.4578 Ops/s 436.0021 Ops/s $\color{#d91a1a}-0.12\%$
test_iql_speed[True-backward] 5.1650ms 5.0028ms 199.8867 Ops/s 203.5197 Ops/s $\color{#d91a1a}-1.79\%$
test_iql_speed[reduce-overhead-None] 0.4839s 12.9775ms 77.0566 Ops/s 88.6780 Ops/s $\textbf{\color{#d91a1a}-13.11\%}$
test_iql_speed[reduce-overhead-backward] 1.9536ms 1.8953ms 527.6241 Ops/s 507.0922 Ops/s $\color{#35bf28}+4.05\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 7.6761ms 6.2363ms 160.3519 Ops/s 157.5931 Ops/s $\color{#35bf28}+1.75\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5760ms 0.3142ms 3.1825 KOps/s 3.7721 KOps/s $\textbf{\color{#d91a1a}-15.63\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5694ms 0.3006ms 3.3270 KOps/s 4.0112 KOps/s $\textbf{\color{#d91a1a}-17.06\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.2576ms 5.9679ms 167.5620 Ops/s 165.8371 Ops/s $\color{#35bf28}+1.04\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.2183ms 0.2857ms 3.5002 KOps/s 3.7672 KOps/s $\textbf{\color{#d91a1a}-7.09\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5162ms 0.2988ms 3.3472 KOps/s 3.3220 KOps/s $\color{#35bf28}+0.76\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.6556ms 1.3645ms 732.8437 Ops/s 671.6769 Ops/s $\textbf{\color{#35bf28}+9.11\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4525ms 1.2336ms 810.6074 Ops/s 819.7893 Ops/s $\color{#d91a1a}-1.12\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.4280ms 6.1422ms 162.8089 Ops/s 159.7076 Ops/s $\color{#35bf28}+1.94\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.9772ms 0.4601ms 2.1732 KOps/s 2.3624 KOps/s $\textbf{\color{#d91a1a}-8.01\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6083ms 0.3845ms 2.6011 KOps/s 2.5141 KOps/s $\color{#35bf28}+3.46\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.2590ms 6.0101ms 166.3857 Ops/s 163.6469 Ops/s $\color{#35bf28}+1.67\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.8957ms 0.3494ms 2.8622 KOps/s 3.0713 KOps/s $\textbf{\color{#d91a1a}-6.81\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5834ms 0.3481ms 2.8731 KOps/s 3.2517 KOps/s $\textbf{\color{#d91a1a}-11.64\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 9.4157ms 5.9913ms 166.9074 Ops/s 165.2617 Ops/s $\color{#35bf28}+1.00\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.8264ms 0.2745ms 3.6434 KOps/s 3.4995 KOps/s $\color{#35bf28}+4.11\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.4936ms 0.2859ms 3.4974 KOps/s 3.4944 KOps/s $\color{#35bf28}+0.09\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.5388ms 6.1624ms 162.2747 Ops/s 160.2939 Ops/s $\color{#35bf28}+1.24\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.2869ms 0.4844ms 2.0643 KOps/s 2.1688 KOps/s $\color{#d91a1a}-4.82\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6098ms 0.3811ms 2.6239 KOps/s 2.2601 KOps/s $\textbf{\color{#35bf28}+16.09\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 7.1410ms 5.5259ms 180.9676 Ops/s 179.7219 Ops/s $\color{#35bf28}+0.69\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 10.4739ms 2.0897ms 478.5397 Ops/s 428.4490 Ops/s $\textbf{\color{#35bf28}+11.69\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 6.6876ms 1.2131ms 824.3252 Ops/s 842.0095 Ops/s $\color{#d91a1a}-2.10\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.4579s 14.6328ms 68.3398 Ops/s 178.8177 Ops/s $\textbf{\color{#d91a1a}-61.78\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 5.8026ms 1.9982ms 500.4388 Ops/s 427.2945 Ops/s $\textbf{\color{#35bf28}+17.12\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 10.0778ms 1.2887ms 775.9563 Ops/s 828.5888 Ops/s $\textbf{\color{#d91a1a}-6.35\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 9.0685ms 5.7850ms 172.8595 Ops/s 31.1405 Ops/s $\textbf{\color{#35bf28}+455.09\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.4230ms 2.2079ms 452.9152 Ops/s 419.4009 Ops/s $\textbf{\color{#35bf28}+7.99\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 8.9170ms 1.3926ms 718.1057 Ops/s 778.2323 Ops/s $\textbf{\color{#d91a1a}-7.73\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 14.1104ms 13.4926ms 74.1147 Ops/s 71.8452 Ops/s $\color{#35bf28}+3.16\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 19.2295ms 17.4288ms 57.3762 Ops/s 58.4918 Ops/s $\color{#d91a1a}-1.91\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 18.8182ms 18.0958ms 55.2613 Ops/s 53.8256 Ops/s $\color{#35bf28}+2.67\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 19.2231ms 17.6444ms 56.6752 Ops/s 57.6713 Ops/s $\color{#d91a1a}-1.73\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 18.4488ms 17.9833ms 55.6071 Ops/s 53.6179 Ops/s $\color{#35bf28}+3.71\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 20.4620ms 19.0613ms 52.4623 Ops/s 53.0018 Ops/s $\color{#d91a1a}-1.02\%$

[ghstack-poisoned]
[ghstack-poisoned]
@vmoens vmoens merged commit caebdbe into gh/vmoens/93/base Mar 3, 2025
69 of 72 checks passed
vmoens added a commit that referenced this pull request Mar 3, 2025
ghstack-source-id: ba0d371d10b3f46ec1172fbec639ccc4d5559659
Pull Request resolved: #2815
@vmoens vmoens deleted the gh/vmoens/93/head branch March 3, 2025 15:50
vmoens added a commit that referenced this pull request Mar 8, 2025
ghstack-source-id: ba0d371d10b3f46ec1172fbec639ccc4d5559659
Pull Request resolved: #2815

(cherry picked from commit f5c0666)
vmoens added a commit that referenced this pull request Mar 10, 2025
ghstack-source-id: ba0d371d10b3f46ec1172fbec639ccc4d5559659
Pull Request resolved: #2815

(cherry picked from commit f5c0666)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants