Skip to content

Conversation

[ghstack-poisoned]
@pytorch-bot
Copy link

pytorch-bot bot commented Jan 8, 2026

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/3313

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

⏳ No Failures, 42 Pending

As of commit b3e4582 with merge base cc917ba (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[ghstack-poisoned]
vmoens added a commit that referenced this pull request Jan 8, 2026
@vmoens vmoens merged commit b3e4582 into gh/vmoens/191/base Jan 8, 2026
54 of 60 checks passed
@vmoens vmoens deleted the gh/vmoens/191/head branch January 8, 2026 11:18
@github-actions
Copy link

github-actions bot commented Jan 8, 2026

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

Total Benchmarks: 164. Improved: $\large\color{#35bf28}21$. Worsened: $\large\color{#d91a1a}10$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_tensor_to_bytestream_speed[pickle] 83.2040μs 82.3284μs 12.1465 KOps/s 12.3825 KOps/s $\color{#d91a1a}-1.91\%$
test_tensor_to_bytestream_speed[torch.save] 0.1408ms 0.1402ms 7.1336 KOps/s 7.1535 KOps/s $\color{#d91a1a}-0.28\%$
test_tensor_to_bytestream_speed[untyped_storage] 0.1161s 0.1156s 8.6482 Ops/s 8.7018 Ops/s $\color{#d91a1a}-0.62\%$
test_tensor_to_bytestream_speed[numpy] 2.6829μs 2.6740μs 373.9716 KOps/s 372.8270 KOps/s $\color{#35bf28}+0.31\%$
test_tensor_to_bytestream_speed[safetensors] 40.7911μs 40.2912μs 24.8193 KOps/s 24.5210 KOps/s $\color{#35bf28}+1.22\%$
test_simple 0.5544s 0.5465s 1.8298 Ops/s 1.7516 Ops/s $\color{#35bf28}+4.46\%$
test_transformed 1.1204s 1.1182s 0.8943 Ops/s 0.8720 Ops/s $\color{#35bf28}+2.56\%$
test_serial 1.6700s 1.6648s 0.6007 Ops/s 0.5948 Ops/s $\color{#35bf28}+0.98\%$
test_parallel 1.2652s 1.1181s 0.8944 Ops/s 0.8659 Ops/s $\color{#35bf28}+3.29\%$
test_step_mdp_speed[True-True-True-True-True] 0.2733ms 44.7184μs 22.3622 KOps/s 22.9271 KOps/s $\color{#d91a1a}-2.46\%$
test_step_mdp_speed[True-True-True-True-False] 55.1210μs 25.1724μs 39.7260 KOps/s 39.4844 KOps/s $\color{#35bf28}+0.61\%$
test_step_mdp_speed[True-True-True-False-True] 56.7810μs 25.0915μs 39.8541 KOps/s 39.5738 KOps/s $\color{#35bf28}+0.71\%$
test_step_mdp_speed[True-True-True-False-False] 44.6600μs 13.9357μs 71.7581 KOps/s 71.3902 KOps/s $\color{#35bf28}+0.52\%$
test_step_mdp_speed[True-True-False-True-True] 86.0720μs 47.7381μs 20.9476 KOps/s 20.6211 KOps/s $\color{#35bf28}+1.58\%$
test_step_mdp_speed[True-True-False-True-False] 75.0010μs 28.3502μs 35.2731 KOps/s 35.5273 KOps/s $\color{#d91a1a}-0.72\%$
test_step_mdp_speed[True-True-False-False-True] 63.7410μs 27.9521μs 35.7754 KOps/s 35.4614 KOps/s $\color{#35bf28}+0.89\%$
test_step_mdp_speed[True-True-False-False-False] 50.4410μs 16.6293μs 60.1347 KOps/s 59.8266 KOps/s $\color{#35bf28}+0.51\%$
test_step_mdp_speed[True-False-True-True-True] 0.1002ms 51.3968μs 19.4565 KOps/s 19.6509 KOps/s $\color{#d91a1a}-0.99\%$
test_step_mdp_speed[True-False-True-True-False] 67.2810μs 31.0042μs 32.2537 KOps/s 32.2960 KOps/s $\color{#d91a1a}-0.13\%$
test_step_mdp_speed[True-False-True-False-True] 69.9910μs 28.1455μs 35.5297 KOps/s 35.1647 KOps/s $\color{#35bf28}+1.04\%$
test_step_mdp_speed[True-False-True-False-False] 52.7810μs 16.6603μs 60.0229 KOps/s 58.9954 KOps/s $\color{#35bf28}+1.74\%$
test_step_mdp_speed[True-False-False-True-True] 92.2010μs 53.4142μs 18.7216 KOps/s 18.5713 KOps/s $\color{#35bf28}+0.81\%$
test_step_mdp_speed[True-False-False-True-False] 65.5210μs 33.5213μs 29.8318 KOps/s 29.7404 KOps/s $\color{#35bf28}+0.31\%$
test_step_mdp_speed[True-False-False-False-True] 64.2520μs 30.5064μs 32.7800 KOps/s 32.3998 KOps/s $\color{#35bf28}+1.17\%$
test_step_mdp_speed[True-False-False-False-False] 51.8010μs 19.5236μs 51.2201 KOps/s 51.0026 KOps/s $\color{#35bf28}+0.43\%$
test_step_mdp_speed[False-True-True-True-True] 85.8420μs 51.0472μs 19.5897 KOps/s 19.7437 KOps/s $\color{#d91a1a}-0.78\%$
test_step_mdp_speed[False-True-True-True-False] 92.1920μs 30.5173μs 32.7682 KOps/s 31.8522 KOps/s $\color{#35bf28}+2.88\%$
test_step_mdp_speed[False-True-True-False-True] 2.3087ms 31.7390μs 31.5070 KOps/s 31.2241 KOps/s $\color{#35bf28}+0.91\%$
test_step_mdp_speed[False-True-True-False-False] 78.7910μs 18.2151μs 54.8996 KOps/s 54.2419 KOps/s $\color{#35bf28}+1.21\%$
test_step_mdp_speed[False-True-False-True-True] 82.6910μs 53.2363μs 18.7842 KOps/s 18.6903 KOps/s $\color{#35bf28}+0.50\%$
test_step_mdp_speed[False-True-False-True-False] 60.9610μs 32.6772μs 30.6023 KOps/s 29.7005 KOps/s $\color{#35bf28}+3.04\%$
test_step_mdp_speed[False-True-False-False-True] 82.5310μs 33.5311μs 29.8231 KOps/s 28.9720 KOps/s $\color{#35bf28}+2.94\%$
test_step_mdp_speed[False-True-False-False-False] 50.8610μs 20.9257μs 47.7881 KOps/s 46.7080 KOps/s $\color{#35bf28}+2.31\%$
test_step_mdp_speed[False-False-True-True-True] 94.8620μs 55.6824μs 17.9590 KOps/s 17.7078 KOps/s $\color{#35bf28}+1.42\%$
test_step_mdp_speed[False-False-True-True-False] 66.0010μs 36.2327μs 27.5994 KOps/s 27.3696 KOps/s $\color{#35bf28}+0.84\%$
test_step_mdp_speed[False-False-True-False-True] 61.4210μs 34.4661μs 29.0140 KOps/s 29.3887 KOps/s $\color{#d91a1a}-1.27\%$
test_step_mdp_speed[False-False-True-False-False] 49.4610μs 20.9190μs 47.8033 KOps/s 47.1627 KOps/s $\color{#35bf28}+1.36\%$
test_step_mdp_speed[False-False-False-True-True] 0.1412ms 57.1393μs 17.5011 KOps/s 17.2035 KOps/s $\color{#35bf28}+1.73\%$
test_step_mdp_speed[False-False-False-True-False] 75.1410μs 38.4237μs 26.0256 KOps/s 25.4723 KOps/s $\color{#35bf28}+2.17\%$
test_step_mdp_speed[False-False-False-False-True] 0.1010ms 35.4749μs 28.1890 KOps/s 27.2261 KOps/s $\color{#35bf28}+3.54\%$
test_step_mdp_speed[False-False-False-False-False] 52.0910μs 23.5151μs 42.5258 KOps/s 42.0109 KOps/s $\color{#35bf28}+1.23\%$
test_non_tensor_env_rollout_speed[1000-single-True] 0.8658s 0.7689s 1.3005 Ops/s 1.3024 Ops/s $\color{#d91a1a}-0.15\%$
test_non_tensor_env_rollout_speed[1000-single-False] 0.7316s 0.6348s 1.5752 Ops/s 1.5822 Ops/s $\color{#d91a1a}-0.44\%$
test_non_tensor_env_rollout_speed[1000-serial-no-buffers-True] 1.7696s 1.6895s 0.5919 Ops/s 0.5950 Ops/s $\color{#d91a1a}-0.52\%$
test_non_tensor_env_rollout_speed[1000-serial-no-buffers-False] 1.5475s 1.4682s 0.6811 Ops/s 0.6812 Ops/s $-0.01\%$
test_non_tensor_env_rollout_speed[1000-serial-buffers-True] 2.0067s 1.9255s 0.5193 Ops/s 0.5201 Ops/s $\color{#d91a1a}-0.15\%$
test_non_tensor_env_rollout_speed[1000-serial-buffers-False] 1.8103s 1.7264s 0.5792 Ops/s 0.5894 Ops/s $\color{#d91a1a}-1.72\%$
test_non_tensor_env_rollout_speed[1000-parallel-no-buffers-True] 4.8390s 4.7051s 0.2125 Ops/s 0.2131 Ops/s $\color{#d91a1a}-0.25\%$
test_non_tensor_env_rollout_speed[1000-parallel-no-buffers-False] 4.5473s 4.4934s 0.2225 Ops/s 0.2243 Ops/s $\color{#d91a1a}-0.79\%$
test_non_tensor_env_rollout_speed[1000-parallel-buffers-True] 2.0573s 1.9771s 0.5058 Ops/s 0.5038 Ops/s $\color{#35bf28}+0.39\%$
test_non_tensor_env_rollout_speed[1000-parallel-buffers-False] 1.7711s 1.6857s 0.5932 Ops/s 0.5839 Ops/s $\color{#35bf28}+1.61\%$
test_values[generalized_advantage_estimate-True-True] 9.9270ms 9.6944ms 103.1526 Ops/s 102.3716 Ops/s $\color{#35bf28}+0.76\%$
test_values[vec_generalized_advantage_estimate-True-True] 19.6313ms 17.7544ms 56.3240 Ops/s 57.2304 Ops/s $\color{#d91a1a}-1.58\%$
test_values[td0_return_estimate-False-False] 0.2128ms 0.1254ms 7.9730 KOps/s 8.0501 KOps/s $\color{#d91a1a}-0.96\%$
test_values[td1_return_estimate-False-False] 26.7193ms 26.1952ms 38.1750 Ops/s 37.3439 Ops/s $\color{#35bf28}+2.23\%$
test_values[vec_td1_return_estimate-False-False] 18.7529ms 17.8113ms 56.1442 Ops/s 56.9485 Ops/s $\color{#d91a1a}-1.41\%$
test_values[td_lambda_return_estimate-True-False] 39.7677ms 39.0882ms 25.5832 Ops/s 25.4659 Ops/s $\color{#35bf28}+0.46\%$
test_values[vec_td_lambda_return_estimate-True-False] 18.9680ms 17.8269ms 56.0951 Ops/s 56.1025 Ops/s $\color{#d91a1a}-0.01\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.7611ms 8.6346ms 115.8138 Ops/s 113.1167 Ops/s $\color{#35bf28}+2.38\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.9619ms 1.4871ms 672.4654 Ops/s 657.7726 Ops/s $\color{#35bf28}+2.23\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4461ms 0.4013ms 2.4918 KOps/s 2.4429 KOps/s $\color{#35bf28}+2.00\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 35.0165ms 34.2756ms 29.1753 Ops/s 28.5104 Ops/s $\color{#35bf28}+2.33\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 1.9006ms 1.7204ms 581.2461 Ops/s 582.1973 Ops/s $\color{#d91a1a}-0.16\%$
test_dqn_speed[False-None] 1.7849ms 1.4058ms 711.3235 Ops/s 722.6334 Ops/s $\color{#d91a1a}-1.57\%$
test_dqn_speed[False-backward] 1.9760ms 1.9113ms 523.1905 Ops/s 525.7399 Ops/s $\color{#d91a1a}-0.48\%$
test_dqn_speed[True-None] 0.9098ms 0.5206ms 1.9208 KOps/s 1.9025 KOps/s $\color{#35bf28}+0.96\%$
test_dqn_speed[True-backward] 1.1082ms 0.9708ms 1.0301 KOps/s 918.6008 Ops/s $\textbf{\color{#35bf28}+12.14\%}$
test_dqn_speed[reduce-overhead-None] 0.9029ms 0.5179ms 1.9307 KOps/s 1.7249 KOps/s $\textbf{\color{#35bf28}+11.93\%}$
test_dqn_speed[reduce-overhead-backward] 0.9844ms 0.9534ms 1.0489 KOps/s 957.6536 Ops/s $\textbf{\color{#35bf28}+9.53\%}$
test_ddpg_speed[False-None] 3.2251ms 2.8411ms 351.9759 Ops/s 351.6776 Ops/s $\color{#35bf28}+0.08\%$
test_ddpg_speed[False-backward] 4.0651ms 3.9632ms 252.3218 Ops/s 247.7165 Ops/s $\color{#35bf28}+1.86\%$
test_ddpg_speed[True-None] 1.7699ms 1.3672ms 731.4450 Ops/s 719.4599 Ops/s $\color{#35bf28}+1.67\%$
test_ddpg_speed[True-backward] 2.3890ms 2.3376ms 427.7835 Ops/s 425.8640 Ops/s $\color{#35bf28}+0.45\%$
test_ddpg_speed[reduce-overhead-None] 1.7971ms 1.3935ms 717.6328 Ops/s 731.8811 Ops/s $\color{#d91a1a}-1.95\%$
test_ddpg_speed[reduce-overhead-backward] 2.7302ms 2.3263ms 429.8641 Ops/s 423.3271 Ops/s $\color{#35bf28}+1.54\%$
test_sac_speed[False-None] 8.4583ms 7.9288ms 126.1223 Ops/s 127.4806 Ops/s $\color{#d91a1a}-1.07\%$
test_sac_speed[False-backward] 11.5956ms 11.1481ms 89.7014 Ops/s 91.1865 Ops/s $\color{#d91a1a}-1.63\%$
test_sac_speed[True-None] 2.4805ms 2.1236ms 470.9017 Ops/s 460.2838 Ops/s $\color{#35bf28}+2.31\%$
test_sac_speed[True-backward] 4.3175ms 3.9338ms 254.2080 Ops/s 223.9536 Ops/s $\textbf{\color{#35bf28}+13.51\%}$
test_sac_speed[reduce-overhead-None] 2.3470ms 2.1100ms 473.9348 Ops/s 456.1989 Ops/s $\color{#35bf28}+3.89\%$
test_sac_speed[reduce-overhead-backward] 4.1462ms 3.9605ms 252.4924 Ops/s 232.0553 Ops/s $\textbf{\color{#35bf28}+8.81\%}$
test_redq_speed[False-None] 13.5888ms 10.3646ms 96.4825 Ops/s 95.1756 Ops/s $\color{#35bf28}+1.37\%$
test_redq_speed[False-backward] 18.3631ms 17.6898ms 56.5299 Ops/s 58.7528 Ops/s $\color{#d91a1a}-3.78\%$
test_redq_speed[True-None] 4.7781ms 4.4020ms 227.1694 Ops/s 223.0802 Ops/s $\color{#35bf28}+1.83\%$
test_redq_speed[True-backward] 9.9511ms 9.7138ms 102.9464 Ops/s 103.4683 Ops/s $\color{#d91a1a}-0.50\%$
test_redq_speed[reduce-overhead-None] 4.8662ms 4.3622ms 229.2403 Ops/s 217.9704 Ops/s $\textbf{\color{#35bf28}+5.17\%}$
test_redq_speed[reduce-overhead-backward] 10.2925ms 9.9554ms 100.4481 Ops/s 104.8005 Ops/s $\color{#d91a1a}-4.15\%$
test_redq_deprec_speed[False-None] 11.4385ms 10.8981ms 91.7589 Ops/s 90.2285 Ops/s $\color{#35bf28}+1.70\%$
test_redq_deprec_speed[False-backward] 16.2120ms 15.6696ms 63.8178 Ops/s 63.2355 Ops/s $\color{#35bf28}+0.92\%$
test_redq_deprec_speed[True-None] 3.9124ms 3.6569ms 273.4576 Ops/s 281.4698 Ops/s $\color{#d91a1a}-2.85\%$
test_redq_deprec_speed[True-backward] 7.8649ms 7.6517ms 130.6892 Ops/s 135.9511 Ops/s $\color{#d91a1a}-3.87\%$
test_redq_deprec_speed[reduce-overhead-None] 4.1346ms 3.6399ms 274.7323 Ops/s 256.0701 Ops/s $\textbf{\color{#35bf28}+7.29\%}$
test_redq_deprec_speed[reduce-overhead-backward] 7.7962ms 7.5981ms 131.6112 Ops/s 133.4723 Ops/s $\color{#d91a1a}-1.39\%$
test_td3_speed[False-None] 8.1672ms 7.9319ms 126.0725 Ops/s 126.1467 Ops/s $\color{#d91a1a}-0.06\%$
test_td3_speed[False-backward] 11.1765ms 10.7451ms 93.0658 Ops/s 51.7268 Ops/s $\textbf{\color{#35bf28}+79.92\%}$
test_td3_speed[True-None] 1.8641ms 1.7885ms 559.1231 Ops/s 549.3908 Ops/s $\color{#35bf28}+1.77\%$
test_td3_speed[True-backward] 3.7132ms 3.5495ms 281.7317 Ops/s 260.3397 Ops/s $\textbf{\color{#35bf28}+8.22\%}$
test_td3_speed[reduce-overhead-None] 1.8109ms 1.7634ms 567.0726 Ops/s 560.2856 Ops/s $\color{#35bf28}+1.21\%$
test_td3_speed[reduce-overhead-backward] 3.8545ms 3.6535ms 273.7070 Ops/s 239.5100 Ops/s $\textbf{\color{#35bf28}+14.28\%}$
test_cql_speed[False-None] 26.8838ms 25.8204ms 38.7290 Ops/s 38.5457 Ops/s $\color{#35bf28}+0.48\%$
test_cql_speed[False-backward] 35.6348ms 34.9064ms 28.6481 Ops/s 29.1746 Ops/s $\color{#d91a1a}-1.80\%$
test_cql_speed[True-None] 13.0678ms 12.3261ms 81.1288 Ops/s 82.9966 Ops/s $\color{#d91a1a}-2.25\%$
test_cql_speed[True-backward] 18.9837ms 18.1405ms 55.1251 Ops/s 58.1564 Ops/s $\textbf{\color{#d91a1a}-5.21\%}$
test_cql_speed[reduce-overhead-None] 12.9107ms 12.4367ms 80.4074 Ops/s 81.2353 Ops/s $\color{#d91a1a}-1.02\%$
test_cql_speed[reduce-overhead-backward] 18.9991ms 18.4400ms 54.2300 Ops/s 57.4298 Ops/s $\textbf{\color{#d91a1a}-5.57\%}$
test_a2c_speed[False-None] 5.7713ms 5.4821ms 182.4131 Ops/s 186.0671 Ops/s $\color{#d91a1a}-1.96\%$
test_a2c_speed[False-backward] 12.2151ms 11.7600ms 85.0343 Ops/s 84.6907 Ops/s $\color{#35bf28}+0.41\%$
test_a2c_speed[True-None] 3.8954ms 3.7322ms 267.9409 Ops/s 264.6769 Ops/s $\color{#35bf28}+1.23\%$
test_a2c_speed[True-backward] 8.6709ms 8.4596ms 118.2085 Ops/s 116.0633 Ops/s $\color{#35bf28}+1.85\%$
test_a2c_speed[reduce-overhead-None] 3.8862ms 3.7180ms 268.9592 Ops/s 270.3796 Ops/s $\color{#d91a1a}-0.53\%$
test_a2c_speed[reduce-overhead-backward] 10.4455ms 8.7777ms 113.9249 Ops/s 107.5282 Ops/s $\textbf{\color{#35bf28}+5.95\%}$
test_ppo_speed[False-None] 6.0283ms 5.8207ms 171.8007 Ops/s 168.5720 Ops/s $\color{#35bf28}+1.92\%$
test_ppo_speed[False-backward] 12.5395ms 12.3507ms 80.9672 Ops/s 80.9085 Ops/s $\color{#35bf28}+0.07\%$
test_ppo_speed[True-None] 3.7840ms 3.5921ms 278.3916 Ops/s 268.5879 Ops/s $\color{#35bf28}+3.65\%$
test_ppo_speed[True-backward] 8.6809ms 8.4561ms 118.2581 Ops/s 118.8598 Ops/s $\color{#d91a1a}-0.51\%$
test_ppo_speed[reduce-overhead-None] 3.7879ms 3.6038ms 277.4876 Ops/s 277.3854 Ops/s $\color{#35bf28}+0.04\%$
test_ppo_speed[reduce-overhead-backward] 8.7999ms 8.5708ms 116.6747 Ops/s 110.1149 Ops/s $\textbf{\color{#35bf28}+5.96\%}$
test_reinforce_speed[False-None] 4.7318ms 4.5343ms 220.5405 Ops/s 218.3534 Ops/s $\color{#35bf28}+1.00\%$
test_reinforce_speed[False-backward] 7.5669ms 7.3316ms 136.3960 Ops/s 135.3028 Ops/s $\color{#35bf28}+0.81\%$
test_reinforce_speed[True-None] 3.0738ms 2.8753ms 347.7914 Ops/s 342.9146 Ops/s $\color{#35bf28}+1.42\%$
test_reinforce_speed[True-backward] 7.9508ms 7.6788ms 130.2284 Ops/s 129.5995 Ops/s $\color{#35bf28}+0.49\%$
test_reinforce_speed[reduce-overhead-None] 3.1634ms 2.8616ms 349.4558 Ops/s 353.1381 Ops/s $\color{#d91a1a}-1.04\%$
test_reinforce_speed[reduce-overhead-backward] 8.1151ms 7.8868ms 126.7946 Ops/s 105.0483 Ops/s $\textbf{\color{#35bf28}+20.70\%}$
test_iql_speed[False-None] 20.5962ms 19.7145ms 50.7241 Ops/s 50.2735 Ops/s $\color{#35bf28}+0.90\%$
test_iql_speed[False-backward] 31.0537ms 30.1279ms 33.1918 Ops/s 33.1114 Ops/s $\color{#35bf28}+0.24\%$
test_iql_speed[True-None] 9.1525ms 8.5075ms 117.5439 Ops/s 117.0928 Ops/s $\color{#35bf28}+0.39\%$
test_iql_speed[True-backward] 17.1158ms 16.6961ms 59.8941 Ops/s 59.1127 Ops/s $\color{#35bf28}+1.32\%$
test_iql_speed[reduce-overhead-None] 9.1941ms 8.5183ms 117.3943 Ops/s 111.4087 Ops/s $\textbf{\color{#35bf28}+5.37\%}$
test_iql_speed[reduce-overhead-backward] 17.4741ms 17.1688ms 58.2453 Ops/s 58.0331 Ops/s $\color{#35bf28}+0.37\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 8.1527ms 6.1599ms 162.3391 Ops/s 164.5099 Ops/s $\color{#d91a1a}-1.32\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.5382ms 0.2886ms 3.4652 KOps/s 3.0589 KOps/s $\textbf{\color{#35bf28}+13.28\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5465ms 0.3069ms 3.2583 KOps/s 3.3210 KOps/s $\color{#d91a1a}-1.89\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.1983ms 5.9509ms 168.0420 Ops/s 169.2660 Ops/s $\color{#d91a1a}-0.72\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.7293ms 0.2785ms 3.5911 KOps/s 2.9218 KOps/s $\textbf{\color{#35bf28}+22.91\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5048ms 0.2617ms 3.8205 KOps/s 3.0414 KOps/s $\textbf{\color{#35bf28}+25.62\%}$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.5143ms 1.2361ms 808.9962 Ops/s 738.4080 Ops/s $\textbf{\color{#35bf28}+9.56\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.4211ms 1.1836ms 844.8753 Ops/s 785.2556 Ops/s $\textbf{\color{#35bf28}+7.59\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 9.9360ms 6.1793ms 161.8315 Ops/s 165.6505 Ops/s $\color{#d91a1a}-2.31\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 0.8016ms 0.4700ms 2.1276 KOps/s 2.0698 KOps/s $\color{#35bf28}+2.79\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7938ms 0.4175ms 2.3953 KOps/s 2.1237 KOps/s $\textbf{\color{#35bf28}+12.79\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.1083ms 5.8803ms 170.0589 Ops/s 169.5713 Ops/s $\color{#35bf28}+0.29\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.1355ms 0.3704ms 2.7000 KOps/s 2.8828 KOps/s $\textbf{\color{#d91a1a}-6.34\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5471ms 0.3576ms 2.7967 KOps/s 2.9768 KOps/s $\textbf{\color{#d91a1a}-6.05\%}$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.0598ms 5.7985ms 172.4595 Ops/s 170.8599 Ops/s $\color{#35bf28}+0.94\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 0.9446ms 0.3634ms 2.7518 KOps/s 2.6887 KOps/s $\color{#35bf28}+2.35\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.5524ms 0.3446ms 2.9016 KOps/s 3.0626 KOps/s $\textbf{\color{#d91a1a}-5.26\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.2381ms 5.9655ms 167.6293 Ops/s 166.1334 Ops/s $\color{#35bf28}+0.90\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.5335ms 0.5212ms 1.9188 KOps/s 1.9793 KOps/s $\color{#d91a1a}-3.06\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6868ms 0.4989ms 2.0044 KOps/s 2.0207 KOps/s $\color{#d91a1a}-0.80\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.4723ms 5.0082ms 199.6745 Ops/s 53.0702 Ops/s $\textbf{\color{#35bf28}+276.25\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 7.3935ms 2.3135ms 432.2461 Ops/s 473.9840 Ops/s $\textbf{\color{#d91a1a}-8.81\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 7.9949ms 1.2443ms 803.6944 Ops/s 895.5289 Ops/s $\textbf{\color{#d91a1a}-10.25\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.6167s 17.2968ms 57.8141 Ops/s 194.8311 Ops/s $\textbf{\color{#d91a1a}-70.33\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 9.5723ms 2.0834ms 479.9736 Ops/s 483.8505 Ops/s $\color{#d91a1a}-0.80\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 7.2484ms 1.1969ms 835.4797 Ops/s 824.8934 Ops/s $\color{#35bf28}+1.28\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 6.9715ms 5.2330ms 191.0954 Ops/s 188.7493 Ops/s $\color{#35bf28}+1.24\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 9.7983ms 2.2516ms 444.1346 Ops/s 450.1674 Ops/s $\color{#d91a1a}-1.34\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 6.8650ms 1.3531ms 739.0344 Ops/s 928.5769 Ops/s $\textbf{\color{#d91a1a}-20.41\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 39.8762ms 34.5540ms 28.9402 Ops/s 29.0051 Ops/s $\color{#d91a1a}-0.22\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 19.8181ms 17.7791ms 56.2457 Ops/s 56.5990 Ops/s $\color{#d91a1a}-0.62\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 38.2335ms 35.4312ms 28.2237 Ops/s 28.0198 Ops/s $\color{#35bf28}+0.73\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 19.9672ms 18.3315ms 54.5510 Ops/s 55.8523 Ops/s $\color{#d91a1a}-2.33\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 0.5749s 47.9023ms 20.8758 Ops/s 26.8836 Ops/s $\textbf{\color{#d91a1a}-22.35\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 21.2039ms 19.7705ms 50.5805 Ops/s 51.4472 Ops/s $\color{#d91a1a}-1.68\%$

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.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants