Skip to content

Bump transformers from 4.52.4 to 5.0.0rc3 in /sota-implementations/expert-iteration#3601

Open
dependabot[bot] wants to merge 1 commit intomainfrom
dependabot/pip/sota-implementations/expert-iteration/transformers-5.0.0rc3
Open

Bump transformers from 4.52.4 to 5.0.0rc3 in /sota-implementations/expert-iteration#3601
dependabot[bot] wants to merge 1 commit intomainfrom
dependabot/pip/sota-implementations/expert-iteration/transformers-5.0.0rc3

Conversation

@dependabot
Copy link
Copy Markdown
Contributor

@dependabot dependabot Bot commented on behalf of github Apr 8, 2026

Bumps transformers from 4.52.4 to 5.0.0rc3.

Release notes

Sourced from transformers's releases.

Release candidate v5.0.0rc3

New models:

What's Changed

We are getting closer and closer to the official release! This RC is focused on removing more of the deprecated stuff, fixing some minors issues, doc updates.

... (truncated)

Commits

Dependabot compatibility score

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

  • @dependabot rebase will rebase this PR
  • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
  • @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
  • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
  • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
  • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    You can disable automated security fix PRs for this repo from the Security Alerts page.

Bumps [transformers](https://github.com/huggingface/transformers) from 4.52.4 to 5.0.0rc3.
- [Release notes](https://github.com/huggingface/transformers/releases)
- [Commits](huggingface/transformers@v4.52.4...v5.0.0rc3)

---
updated-dependencies:
- dependency-name: transformers
  dependency-version: 5.0.0rc3
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
@dependabot dependabot Bot added Dependencies Pull requests that update a dependency file python Pull requests that update python code labels Apr 8, 2026
@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Apr 8, 2026

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/3601

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

❌ 2 New Failures, 1 Unrelated Failure

As of commit 625740c with merge base f54a7c7 (image):

NEW FAILURES - The following jobs have failed:

BROKEN TRUNK - The following job 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.

@meta-cla meta-cla 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 Apr 8, 2026
@github-actions
Copy link
Copy Markdown
Contributor

github-actions Bot commented Apr 8, 2026

⚠️ PR Title Label Error

PR title must start with a label prefix in brackets (e.g., [BugFix]).

Current title: Bump transformers from 4.52.4 to 5.0.0rc3 in /sota-implementations/expert-iteration

Supported Prefixes (case-sensitive)

Your PR title must start with exactly one of these prefixes:

Prefix Label Applied Example
[BugFix] BugFix [BugFix] Fix memory leak in collector
[Feature] Feature [Feature] Add new optimizer
[Doc] or [Docs] Documentation [Doc] Update installation guide
[Refactor] Refactoring [Refactor] Clean up module imports
[CI] CI [CI] Fix workflow permissions
[Test] or [Tests] Tests [Tests] Add unit tests for buffer
[Environment] or [Environments] Environments [Environments] Add Gymnasium support
[Data] Data [Data] Fix replay buffer sampling
[Performance] or [Perf] Performance [Performance] Optimize tensor ops
[BC-Breaking] bc breaking [BC-Breaking] Remove deprecated API
[Deprecation] Deprecation [Deprecation] Mark old function
[Quality] Quality [Quality] Fix typos and add codespell

Note: Common variations like singular/plural are supported (e.g., [Doc] or [Docs]).

@github-actions
Copy link
Copy Markdown
Contributor

github-actions Bot commented Apr 8, 2026

$\color{#D29922}\textsf{\Large&amp;#x26A0;\kern{0.2cm}\normalsize Warning}$ Result of CPU Benchmark Tests

Total Benchmarks: 172. Improved: $\large\color{#35bf28}9$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_tensor_to_bytestream_speed[pickle] 79.5158μs 78.7006μs 12.7064 KOps/s 12.6761 KOps/s $\color{#35bf28}+0.24\%$
test_tensor_to_bytestream_speed[torch.save] 0.1367ms 0.1361ms 7.3502 KOps/s 7.3426 KOps/s $\color{#35bf28}+0.10\%$
test_tensor_to_bytestream_speed[untyped_storage] 99.9536ms 99.5290ms 10.0473 Ops/s 10.1380 Ops/s $\color{#d91a1a}-0.89\%$
test_tensor_to_bytestream_speed[numpy] 2.4829μs 2.4799μs 403.2400 KOps/s 397.8397 KOps/s $\color{#35bf28}+1.36\%$
test_tensor_to_bytestream_speed[safetensors] 36.1574μs 35.7715μs 27.9552 KOps/s 27.8570 KOps/s $\color{#35bf28}+0.35\%$
test_simple 0.5333s 0.5325s 1.8781 Ops/s 1.7714 Ops/s $\textbf{\color{#35bf28}+6.02\%}$
test_transformed 1.1830s 1.0796s 0.9263 Ops/s 0.9141 Ops/s $\color{#35bf28}+1.33\%$
test_serial 1.6470s 1.6446s 0.6081 Ops/s 0.5936 Ops/s $\color{#35bf28}+2.43\%$
test_parallel 1.0199s 1.0035s 0.9965 Ops/s 0.9697 Ops/s $\color{#35bf28}+2.76\%$
test_step_mdp_speed[True-True-True-True-True] 0.2593ms 40.3019μs 24.8127 KOps/s 24.9283 KOps/s $\color{#d91a1a}-0.46\%$
test_step_mdp_speed[True-True-True-True-False] 78.8940μs 22.2008μs 45.0435 KOps/s 44.7680 KOps/s $\color{#35bf28}+0.62\%$
test_step_mdp_speed[True-True-True-False-True] 47.5020μs 22.7617μs 43.9334 KOps/s 43.1166 KOps/s $\color{#35bf28}+1.89\%$
test_step_mdp_speed[True-True-True-False-False] 40.9020μs 12.4021μs 80.6316 KOps/s 80.9987 KOps/s $\color{#d91a1a}-0.45\%$
test_step_mdp_speed[True-True-False-True-True] 73.7630μs 43.0888μs 23.2079 KOps/s 23.0671 KOps/s $\color{#35bf28}+0.61\%$
test_step_mdp_speed[True-True-False-True-False] 50.6020μs 24.6306μs 40.6000 KOps/s 40.0275 KOps/s $\color{#35bf28}+1.43\%$
test_step_mdp_speed[True-True-False-False-True] 50.5630μs 25.1046μs 39.8334 KOps/s 39.0112 KOps/s $\color{#35bf28}+2.11\%$
test_step_mdp_speed[True-True-False-False-False] 41.1020μs 14.6081μs 68.4553 KOps/s 67.8614 KOps/s $\color{#35bf28}+0.88\%$
test_step_mdp_speed[True-False-True-True-True] 75.6630μs 45.2385μs 22.1051 KOps/s 22.3182 KOps/s $\color{#d91a1a}-0.95\%$
test_step_mdp_speed[True-False-True-True-False] 52.1520μs 26.8435μs 37.2529 KOps/s 36.6702 KOps/s $\color{#35bf28}+1.59\%$
test_step_mdp_speed[True-False-True-False-True] 70.0930μs 25.2461μs 39.6101 KOps/s 39.3444 KOps/s $\color{#35bf28}+0.68\%$
test_step_mdp_speed[True-False-True-False-False] 42.1320μs 14.8087μs 67.5278 KOps/s 66.9559 KOps/s $\color{#35bf28}+0.85\%$
test_step_mdp_speed[True-False-False-True-True] 78.9640μs 47.0467μs 21.2555 KOps/s 20.6562 KOps/s $\color{#35bf28}+2.90\%$
test_step_mdp_speed[True-False-False-True-False] 73.9440μs 29.1419μs 34.3148 KOps/s 33.3079 KOps/s $\color{#35bf28}+3.02\%$
test_step_mdp_speed[True-False-False-False-True] 60.3520μs 27.0337μs 36.9908 KOps/s 35.2758 KOps/s $\color{#35bf28}+4.86\%$
test_step_mdp_speed[True-False-False-False-False] 0.1637ms 17.0249μs 58.7374 KOps/s 58.1202 KOps/s $\color{#35bf28}+1.06\%$
test_step_mdp_speed[False-True-True-True-True] 86.3740μs 45.0973μs 22.1743 KOps/s 21.6782 KOps/s $\color{#35bf28}+2.29\%$
test_step_mdp_speed[False-True-True-True-False] 56.2120μs 26.9347μs 37.1269 KOps/s 36.2438 KOps/s $\color{#35bf28}+2.44\%$
test_step_mdp_speed[False-True-True-False-True] 2.4884ms 28.9832μs 34.5028 KOps/s 33.6316 KOps/s $\color{#35bf28}+2.59\%$
test_step_mdp_speed[False-True-True-False-False] 47.9820μs 16.5312μs 60.4916 KOps/s 60.0461 KOps/s $\color{#35bf28}+0.74\%$
test_step_mdp_speed[False-True-False-True-True] 83.2240μs 47.4199μs 21.0882 KOps/s 20.4770 KOps/s $\color{#35bf28}+2.98\%$
test_step_mdp_speed[False-True-False-True-False] 72.9730μs 29.2841μs 34.1482 KOps/s 33.2833 KOps/s $\color{#35bf28}+2.60\%$
test_step_mdp_speed[False-True-False-False-True] 97.8640μs 30.6353μs 32.6421 KOps/s 31.2416 KOps/s $\color{#35bf28}+4.48\%$
test_step_mdp_speed[False-True-False-False-False] 63.0530μs 18.8293μs 53.1087 KOps/s 52.1825 KOps/s $\color{#35bf28}+1.77\%$
test_step_mdp_speed[False-False-True-True-True] 96.0840μs 50.4533μs 19.8203 KOps/s 19.7579 KOps/s $\color{#35bf28}+0.32\%$
test_step_mdp_speed[False-False-True-True-False] 81.4040μs 32.2666μs 30.9918 KOps/s 31.3224 KOps/s $\color{#d91a1a}-1.06\%$
test_step_mdp_speed[False-False-True-False-True] 61.6720μs 31.1963μs 32.0551 KOps/s 32.0226 KOps/s $\color{#35bf28}+0.10\%$
test_step_mdp_speed[False-False-True-False-False] 81.0730μs 18.3903μs 54.3765 KOps/s 52.8841 KOps/s $\color{#35bf28}+2.82\%$
test_step_mdp_speed[False-False-False-True-True] 87.4730μs 51.3919μs 19.4583 KOps/s 18.8119 KOps/s $\color{#35bf28}+3.44\%$
test_step_mdp_speed[False-False-False-True-False] 79.7040μs 34.0158μs 29.3981 KOps/s 28.1603 KOps/s $\color{#35bf28}+4.40\%$
test_step_mdp_speed[False-False-False-False-True] 62.5530μs 32.5628μs 30.7099 KOps/s 30.2707 KOps/s $\color{#35bf28}+1.45\%$
test_step_mdp_speed[False-False-False-False-False] 64.3920μs 21.0409μs 47.5265 KOps/s 46.8369 KOps/s $\color{#35bf28}+1.47\%$
test_non_tensor_env_rollout_speed[1000-single-True] 0.8352s 0.7308s 1.3683 Ops/s 1.3671 Ops/s $\color{#35bf28}+0.09\%$
test_non_tensor_env_rollout_speed[1000-single-False] 0.7011s 0.6000s 1.6668 Ops/s 1.6691 Ops/s $\color{#d91a1a}-0.14\%$
test_non_tensor_env_rollout_speed[1000-serial-no-buffers-True] 1.7167s 1.6276s 0.6144 Ops/s 0.6209 Ops/s $\color{#d91a1a}-1.05\%$
test_non_tensor_env_rollout_speed[1000-serial-no-buffers-False] 1.4804s 1.3988s 0.7149 Ops/s 0.7176 Ops/s $\color{#d91a1a}-0.37\%$
test_non_tensor_env_rollout_speed[1000-serial-buffers-True] 1.9826s 1.8860s 0.5302 Ops/s 0.5388 Ops/s $\color{#d91a1a}-1.60\%$
test_non_tensor_env_rollout_speed[1000-serial-buffers-False] 1.7477s 1.6594s 0.6026 Ops/s 0.6121 Ops/s $\color{#d91a1a}-1.55\%$
test_non_tensor_env_rollout_speed[1000-parallel-no-buffers-True] 4.6788s 4.5076s 0.2218 Ops/s 0.2194 Ops/s $\color{#35bf28}+1.10\%$
test_non_tensor_env_rollout_speed[1000-parallel-no-buffers-False] 4.4575s 4.3684s 0.2289 Ops/s 0.2270 Ops/s $\color{#35bf28}+0.85\%$
test_non_tensor_env_rollout_speed[1000-parallel-buffers-True] 1.9779s 1.8604s 0.5375 Ops/s 0.5472 Ops/s $\color{#d91a1a}-1.78\%$
test_non_tensor_env_rollout_speed[1000-parallel-buffers-False] 1.6340s 1.5466s 0.6466 Ops/s 0.6444 Ops/s $\color{#35bf28}+0.33\%$
test_values[generalized_advantage_estimate-True-True] 10.0753ms 9.7289ms 102.7866 Ops/s 102.8166 Ops/s $\color{#d91a1a}-0.03\%$
test_values[vec_generalized_advantage_estimate-True-True] 19.6416ms 17.5670ms 56.9250 Ops/s 57.4935 Ops/s $\color{#d91a1a}-0.99\%$
test_values[td0_return_estimate-False-False] 0.2103ms 0.1231ms 8.1204 KOps/s 7.7143 KOps/s $\textbf{\color{#35bf28}+5.26\%}$
test_values[td1_return_estimate-False-False] 26.6781ms 26.3472ms 37.9547 Ops/s 37.4916 Ops/s $\color{#35bf28}+1.24\%$
test_values[vec_td1_return_estimate-False-False] 18.5402ms 17.5976ms 56.8258 Ops/s 57.1138 Ops/s $\color{#d91a1a}-0.50\%$
test_values[td_lambda_return_estimate-True-False] 39.6813ms 39.1198ms 25.5625 Ops/s 25.1618 Ops/s $\color{#35bf28}+1.59\%$
test_values[vec_td_lambda_return_estimate-True-False] 18.2090ms 17.5315ms 57.0401 Ops/s 57.1745 Ops/s $\color{#d91a1a}-0.24\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 8.6365ms 8.4757ms 117.9840 Ops/s 117.2242 Ops/s $\color{#35bf28}+0.65\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.7239ms 1.5309ms 653.2081 Ops/s 650.3760 Ops/s $\color{#35bf28}+0.44\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.4614ms 0.4089ms 2.4455 KOps/s 2.3561 KOps/s $\color{#35bf28}+3.79\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 35.1204ms 34.7178ms 28.8037 Ops/s 28.7302 Ops/s $\color{#35bf28}+0.26\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 1.8529ms 1.7000ms 588.2320 Ops/s 586.9117 Ops/s $\color{#35bf28}+0.22\%$
test_dqn_speed[False-None] 1.5173ms 1.3765ms 726.4719 Ops/s 725.9177 Ops/s $\color{#35bf28}+0.08\%$
test_dqn_speed[False-backward] 1.9736ms 1.9117ms 523.1009 Ops/s 526.6793 Ops/s $\color{#d91a1a}-0.68\%$
test_dqn_speed[True-None] 0.6438ms 0.5595ms 1.7872 KOps/s 1.7238 KOps/s $\color{#35bf28}+3.68\%$
test_dqn_speed[True-backward] 1.0611ms 1.0253ms 975.2803 Ops/s 936.9399 Ops/s $\color{#35bf28}+4.09\%$
test_dqn_speed[reduce-overhead-None] 0.7532ms 0.5486ms 1.8227 KOps/s 1.7714 KOps/s $\color{#35bf28}+2.90\%$
test_ddpg_speed[False-None] 3.2007ms 2.8381ms 352.3496 Ops/s 352.5735 Ops/s $\color{#d91a1a}-0.06\%$
test_ddpg_speed[False-backward] 4.1369ms 4.0272ms 248.3095 Ops/s 243.1434 Ops/s $\color{#35bf28}+2.12\%$
test_ddpg_speed[True-None] 1.6215ms 1.4572ms 686.2661 Ops/s 683.9015 Ops/s $\color{#35bf28}+0.35\%$
test_ddpg_speed[True-backward] 2.5172ms 2.4360ms 410.5170 Ops/s 411.8826 Ops/s $\color{#d91a1a}-0.33\%$
test_ddpg_speed[reduce-overhead-None] 1.4938ms 1.4141ms 707.1580 Ops/s 705.1943 Ops/s $\color{#35bf28}+0.28\%$
test_sac_speed[False-None] 8.8264ms 8.0418ms 124.3507 Ops/s 125.2076 Ops/s $\color{#d91a1a}-0.68\%$
test_sac_speed[False-backward] 11.8001ms 11.3197ms 88.3419 Ops/s 88.6526 Ops/s $\color{#d91a1a}-0.35\%$
test_sac_speed[True-None] 2.3226ms 2.1850ms 457.6750 Ops/s 446.0491 Ops/s $\color{#35bf28}+2.61\%$
test_sac_speed[True-backward] 4.2147ms 4.0981ms 244.0142 Ops/s 243.8768 Ops/s $\color{#35bf28}+0.06\%$
test_sac_speed[reduce-overhead-None] 2.3300ms 2.1645ms 461.9913 Ops/s 464.3727 Ops/s $\color{#d91a1a}-0.51\%$
test_redq_speed[False-None] 15.6834ms 11.0801ms 90.2521 Ops/s 91.2771 Ops/s $\color{#d91a1a}-1.12\%$
test_redq_speed[False-backward] 22.2199ms 18.0190ms 55.4970 Ops/s 56.7247 Ops/s $\color{#d91a1a}-2.16\%$
test_redq_speed[True-None] 5.1827ms 4.6342ms 215.7892 Ops/s 206.2726 Ops/s $\color{#35bf28}+4.61\%$
test_redq_speed[reduce-overhead-None] 5.8838ms 4.6615ms 214.5237 Ops/s 216.6712 Ops/s $\color{#d91a1a}-0.99\%$
test_redq_deprec_speed[False-None] 11.3916ms 10.8179ms 92.4398 Ops/s 89.9417 Ops/s $\color{#35bf28}+2.78\%$
test_redq_deprec_speed[False-backward] 15.8502ms 15.5871ms 64.1557 Ops/s 62.0275 Ops/s $\color{#35bf28}+3.43\%$
test_redq_deprec_speed[True-None] 3.7883ms 3.5716ms 279.9847 Ops/s 278.2017 Ops/s $\color{#35bf28}+0.64\%$
test_redq_deprec_speed[True-backward] 7.5402ms 7.2343ms 138.2309 Ops/s 136.5524 Ops/s $\color{#35bf28}+1.23\%$
test_redq_deprec_speed[reduce-overhead-None] 3.7716ms 3.5721ms 279.9456 Ops/s 268.9045 Ops/s $\color{#35bf28}+4.11\%$
test_td3_speed[False-None] 8.1986ms 7.9966ms 125.0536 Ops/s 123.1071 Ops/s $\color{#35bf28}+1.58\%$
test_td3_speed[False-backward] 13.1078ms 10.9795ms 91.0790 Ops/s 91.1208 Ops/s $\color{#d91a1a}-0.05\%$
test_td3_speed[True-None] 1.8730ms 1.8260ms 547.6411 Ops/s 538.2932 Ops/s $\color{#35bf28}+1.74\%$
test_td3_speed[True-backward] 3.7861ms 3.6261ms 275.7784 Ops/s 278.6962 Ops/s $\color{#d91a1a}-1.05\%$
test_td3_speed[reduce-overhead-None] 1.8271ms 1.7896ms 558.7700 Ops/s 551.3195 Ops/s $\color{#35bf28}+1.35\%$
test_cql_speed[False-None] 29.2513ms 26.1183ms 38.2873 Ops/s 37.7979 Ops/s $\color{#35bf28}+1.29\%$
test_cql_speed[False-backward] 39.1804ms 35.4782ms 28.1863 Ops/s 27.6258 Ops/s $\color{#35bf28}+2.03\%$
test_cql_speed[True-None] 13.1952ms 12.4932ms 80.0433 Ops/s 79.8325 Ops/s $\color{#35bf28}+0.26\%$
test_cql_speed[True-backward] 18.2325ms 17.8370ms 56.0632 Ops/s 57.2697 Ops/s $\color{#d91a1a}-2.11\%$
test_cql_speed[reduce-overhead-None] 12.9328ms 12.5132ms 79.9159 Ops/s 80.6171 Ops/s $\color{#d91a1a}-0.87\%$
test_a2c_speed[False-None] 5.6847ms 5.3421ms 187.1929 Ops/s 186.8261 Ops/s $\color{#35bf28}+0.20\%$
test_a2c_speed[False-backward] 12.4096ms 11.9033ms 84.0101 Ops/s 84.5542 Ops/s $\color{#d91a1a}-0.64\%$
test_a2c_speed[True-None] 4.2757ms 3.8294ms 261.1382 Ops/s 261.9342 Ops/s $\color{#d91a1a}-0.30\%$
test_a2c_speed[True-backward] 9.2792ms 8.8607ms 112.8585 Ops/s 103.8195 Ops/s $\textbf{\color{#35bf28}+8.71\%}$
test_a2c_speed[reduce-overhead-None] 4.1705ms 3.8031ms 262.9456 Ops/s 277.8815 Ops/s $\textbf{\color{#d91a1a}-5.37\%}$
test_ppo_speed[False-None] 6.2272ms 5.8956ms 169.6185 Ops/s 175.9483 Ops/s $\color{#d91a1a}-3.60\%$
test_ppo_speed[False-backward] 12.7251ms 12.4390ms 80.3924 Ops/s 80.3421 Ops/s $\color{#35bf28}+0.06\%$
test_ppo_speed[True-None] 3.9857ms 3.8308ms 261.0443 Ops/s 255.4252 Ops/s $\color{#35bf28}+2.20\%$
test_ppo_speed[True-backward] 9.0100ms 8.7620ms 114.1297 Ops/s 114.5214 Ops/s $\color{#d91a1a}-0.34\%$
test_ppo_speed[reduce-overhead-None] 4.1395ms 3.7804ms 264.5253 Ops/s 264.4952 Ops/s $\color{#35bf28}+0.01\%$
test_reinforce_speed[False-None] 4.8487ms 4.5321ms 220.6484 Ops/s 218.8490 Ops/s $\color{#35bf28}+0.82\%$
test_reinforce_speed[False-backward] 7.6647ms 7.4153ms 134.8564 Ops/s 134.5467 Ops/s $\color{#35bf28}+0.23\%$
test_reinforce_speed[True-None] 3.2971ms 2.9926ms 334.1547 Ops/s 348.3619 Ops/s $\color{#d91a1a}-4.08\%$
test_reinforce_speed[True-backward] 8.4163ms 7.9399ms 125.9465 Ops/s 117.0841 Ops/s $\textbf{\color{#35bf28}+7.57\%}$
test_reinforce_speed[reduce-overhead-None] 3.4337ms 2.9893ms 334.5310 Ops/s 322.0552 Ops/s $\color{#35bf28}+3.87\%$
test_iql_speed[False-None] 26.0178ms 20.5729ms 48.6075 Ops/s 49.9822 Ops/s $\color{#d91a1a}-2.75\%$
test_iql_speed[False-backward] 31.3587ms 30.4168ms 32.8766 Ops/s 32.3517 Ops/s $\color{#35bf28}+1.62\%$
test_iql_speed[True-None] 9.1434ms 8.5561ms 116.8757 Ops/s 116.3730 Ops/s $\color{#35bf28}+0.43\%$
test_iql_speed[True-backward] 17.0751ms 16.7758ms 59.6098 Ops/s 59.6391 Ops/s $\color{#d91a1a}-0.05\%$
test_iql_speed[reduce-overhead-None] 9.0178ms 8.5770ms 116.5903 Ops/s 115.5658 Ops/s $\color{#35bf28}+0.89\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.0579ms 5.8506ms 170.9237 Ops/s 168.3270 Ops/s $\color{#35bf28}+1.54\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.9242ms 0.3225ms 3.1004 KOps/s 3.4264 KOps/s $\textbf{\color{#d91a1a}-9.51\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.8131ms 0.3295ms 3.0346 KOps/s 3.4984 KOps/s $\textbf{\color{#d91a1a}-13.26\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.8966ms 5.6237ms 177.8173 Ops/s 177.2169 Ops/s $\color{#35bf28}+0.34\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 1.7629ms 0.3027ms 3.3033 KOps/s 2.9831 KOps/s $\textbf{\color{#35bf28}+10.73\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6681ms 0.3319ms 3.0128 KOps/s 3.0283 KOps/s $\color{#d91a1a}-0.51\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 1.4820ms 1.2820ms 780.0103 Ops/s 717.2952 Ops/s $\textbf{\color{#35bf28}+8.74\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.5727ms 1.3625ms 733.9517 Ops/s 778.2296 Ops/s $\textbf{\color{#d91a1a}-5.69\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 9.7626ms 5.8814ms 170.0285 Ops/s 171.4841 Ops/s $\color{#d91a1a}-0.85\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 1.9215ms 0.4968ms 2.0130 KOps/s 1.9313 KOps/s $\color{#35bf28}+4.23\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7632ms 0.4839ms 2.0667 KOps/s 2.0083 KOps/s $\color{#35bf28}+2.91\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 5.7577ms 5.5833ms 179.1070 Ops/s 176.6784 Ops/s $\color{#35bf28}+1.37\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 0.6062ms 0.3722ms 2.6869 KOps/s 2.6906 KOps/s $\color{#d91a1a}-0.14\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5711ms 0.3645ms 2.7439 KOps/s 2.6459 KOps/s $\color{#35bf28}+3.70\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 5.7832ms 5.5572ms 179.9469 Ops/s 178.5449 Ops/s $\color{#35bf28}+0.79\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.1896ms 0.3450ms 2.8987 KOps/s 2.8754 KOps/s $\color{#35bf28}+0.81\%$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7332ms 0.3577ms 2.7957 KOps/s 2.8437 KOps/s $\color{#d91a1a}-1.69\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 5.9926ms 5.7276ms 174.5933 Ops/s 171.8188 Ops/s $\color{#35bf28}+1.61\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.0003ms 0.4775ms 2.0943 KOps/s 1.9920 KOps/s $\textbf{\color{#35bf28}+5.14\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6773ms 0.4636ms 2.1572 KOps/s 2.1101 KOps/s $\color{#35bf28}+2.23\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.3574ms 4.9633ms 201.4797 Ops/s 200.4402 Ops/s $\color{#35bf28}+0.52\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 9.3778ms 2.1328ms 468.8736 Ops/s 494.7394 Ops/s $\textbf{\color{#d91a1a}-5.23\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 9.0046ms 1.2315ms 812.0070 Ops/s 1.0363 KOps/s $\textbf{\color{#d91a1a}-21.64\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.6305s 17.5764ms 56.8944 Ops/s 197.1057 Ops/s $\textbf{\color{#d91a1a}-71.14\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 3.8903ms 1.7605ms 568.0087 Ops/s 570.2875 Ops/s $\color{#d91a1a}-0.40\%$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 1.0893ms 0.8877ms 1.1265 KOps/s 834.5772 Ops/s $\textbf{\color{#35bf28}+34.98\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 7.1419ms 5.2401ms 190.8364 Ops/s 191.1278 Ops/s $\color{#d91a1a}-0.15\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 11.9869ms 2.0497ms 487.8714 Ops/s 482.3730 Ops/s $\color{#35bf28}+1.14\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 3.4842ms 1.1277ms 886.7913 Ops/s 954.0531 Ops/s $\textbf{\color{#d91a1a}-7.05\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 42.7155ms 38.5680ms 25.9283 Ops/s 25.4127 Ops/s $\color{#35bf28}+2.03\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 19.5271ms 18.1028ms 55.2400 Ops/s 52.7393 Ops/s $\color{#35bf28}+4.74\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 44.0162ms 39.6455ms 25.2235 Ops/s 24.4498 Ops/s $\color{#35bf28}+3.16\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 20.0632ms 18.2421ms 54.8184 Ops/s 31.0205 Ops/s $\textbf{\color{#35bf28}+76.72\%}$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 43.3544ms 41.3750ms 24.1692 Ops/s 23.6858 Ops/s $\color{#35bf28}+2.04\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 20.9789ms 19.6208ms 50.9663 Ops/s 49.7179 Ops/s $\color{#35bf28}+2.51\%$
test_storage_write_lazystack[50-img_shape0-small] 0.8266ms 0.2245ms 4.4546 KOps/s 4.5822 KOps/s $\color{#d91a1a}-2.78\%$
test_storage_write_lazystack[100-img_shape1-atari] 1.6767ms 1.3593ms 735.6525 Ops/s 702.0458 Ops/s $\color{#35bf28}+4.79\%$
test_storage_write_lazystack[100-img_shape2-large_img] 2.4860ms 2.3530ms 424.9817 Ops/s 424.2894 Ops/s $\color{#35bf28}+0.16\%$
test_storage_write_lazystack[200-img_shape3-large_batch] 3.1131ms 2.9330ms 340.9426 Ops/s 336.4745 Ops/s $\color{#35bf28}+1.33\%$
test_storage_write_contiguous[50-img_shape0-small] 0.2158ms 0.1321ms 7.5713 KOps/s 7.6291 KOps/s $\color{#d91a1a}-0.76\%$
test_storage_write_contiguous[100-img_shape1-atari] 0.3434ms 0.1893ms 5.2828 KOps/s 5.4232 KOps/s $\color{#d91a1a}-2.59\%$
test_storage_write_contiguous[100-img_shape2-large_img] 1.9068ms 1.7804ms 561.6741 Ops/s 565.6133 Ops/s $\color{#d91a1a}-0.70\%$
test_storage_write_contiguous[200-img_shape3-large_batch] 1.5483ms 1.3908ms 719.0173 Ops/s 771.2541 Ops/s $\textbf{\color{#d91a1a}-6.77\%}$
test_collector_stack_then_write[50-img_shape0-small] 1.2079ms 1.0918ms 915.8996 Ops/s 914.7868 Ops/s $\color{#35bf28}+0.12\%$
test_collector_stack_then_write[100-img_shape1-atari] 3.6443ms 3.4786ms 287.4732 Ops/s 286.8830 Ops/s $\color{#35bf28}+0.21\%$
test_collector_stack_then_write[100-img_shape2-large_img] 10.1146ms 5.7307ms 174.4973 Ops/s 173.3632 Ops/s $\color{#35bf28}+0.65\%$
test_collector_stack_then_write[200-img_shape3-large_batch] 14.9420ms 6.9193ms 144.5237 Ops/s 145.8985 Ops/s $\color{#d91a1a}-0.94\%$
test_collector_lazystack_then_write[50-img_shape0-small] 0.4138ms 0.2726ms 3.6688 KOps/s 3.5617 KOps/s $\color{#35bf28}+3.01\%$
test_collector_lazystack_then_write[100-img_shape1-atari] 1.6741ms 1.5226ms 656.7897 Ops/s 640.9670 Ops/s $\color{#35bf28}+2.47\%$
test_collector_lazystack_then_write[100-img_shape2-large_img] 2.6398ms 2.4675ms 405.2700 Ops/s 405.0856 Ops/s $\color{#35bf28}+0.05\%$
test_collector_lazystack_then_write[200-img_shape3-large_batch] 3.3252ms 3.1410ms 318.3740 Ops/s 313.7609 Ops/s $\color{#35bf28}+1.47\%$
test_collector_without_rb[100-img_shape0-atari] 33.3400ms 32.4766ms 30.7914 Ops/s 30.7124 Ops/s $\color{#35bf28}+0.26\%$
test_collector_without_rb[200-img_shape1-large_batch] 66.0229ms 65.2837ms 15.3178 Ops/s 15.6560 Ops/s $\color{#d91a1a}-2.16\%$
test_collector_with_rb[100-img_shape0-atari] 39.3468ms 37.5334ms 26.6429 Ops/s 26.9996 Ops/s $\color{#d91a1a}-1.32\%$
test_collector_with_rb[200-img_shape1-large_batch] 74.3526ms 72.3099ms 13.8294 Ops/s 13.8132 Ops/s $\color{#35bf28}+0.12\%$

@github-actions
Copy link
Copy Markdown
Contributor

github-actions Bot commented Apr 8, 2026

$\color{#D29922}\textsf{\Large&amp;#x26A0;\kern{0.2cm}\normalsize Warning}$ Result of GPU Benchmark Tests

Total Benchmarks: 172. Improved: $\large\color{#35bf28}7$. Worsened: $\large\color{#d91a1a}9$.

Expand to view detailed results
Name Max Mean Ops Ops on Repo HEAD Change
test_tensor_to_bytestream_speed[pickle] 86.1729μs 85.2988μs 11.7235 KOps/s 11.9268 KOps/s $\color{#d91a1a}-1.70\%$
test_tensor_to_bytestream_speed[torch.save] 0.1476ms 0.1470ms 6.8020 KOps/s 6.9591 KOps/s $\color{#d91a1a}-2.26\%$
test_tensor_to_bytestream_speed[untyped_storage] 0.1153s 0.1145s 8.7354 Ops/s 8.8712 Ops/s $\color{#d91a1a}-1.53\%$
test_tensor_to_bytestream_speed[numpy] 2.6275μs 2.6235μs 381.1722 KOps/s 379.0790 KOps/s $\color{#35bf28}+0.55\%$
test_tensor_to_bytestream_speed[safetensors] 40.1557μs 39.9491μs 25.0318 KOps/s 26.1925 KOps/s $\color{#d91a1a}-4.43\%$
test_simple 0.9392s 0.8324s 1.2014 Ops/s 1.1895 Ops/s $\color{#35bf28}+1.00\%$
test_transformed 1.4346s 1.4209s 0.7038 Ops/s 0.6983 Ops/s $\color{#35bf28}+0.79\%$
test_serial 2.4336s 2.4265s 0.4121 Ops/s 0.4181 Ops/s $\color{#d91a1a}-1.43\%$
test_parallel 1.9397s 1.8512s 0.5402 Ops/s 0.5534 Ops/s $\color{#d91a1a}-2.38\%$
test_step_mdp_speed[True-True-True-True-True] 0.3257ms 43.1340μs 23.1836 KOps/s 23.7279 KOps/s $\color{#d91a1a}-2.29\%$
test_step_mdp_speed[True-True-True-True-False] 52.2330μs 23.2571μs 42.9977 KOps/s 43.7083 KOps/s $\color{#d91a1a}-1.63\%$
test_step_mdp_speed[True-True-True-False-True] 49.6320μs 23.7161μs 42.1655 KOps/s 42.7457 KOps/s $\color{#d91a1a}-1.36\%$
test_step_mdp_speed[True-True-True-False-False] 36.4410μs 12.6413μs 79.1059 KOps/s 78.3580 KOps/s $\color{#35bf28}+0.95\%$
test_step_mdp_speed[True-True-False-True-True] 78.1440μs 44.7039μs 22.3694 KOps/s 22.1436 KOps/s $\color{#35bf28}+1.02\%$
test_step_mdp_speed[True-True-False-True-False] 67.3230μs 27.8179μs 35.9481 KOps/s 39.6284 KOps/s $\textbf{\color{#d91a1a}-9.29\%}$
test_step_mdp_speed[True-True-False-False-True] 67.7940μs 26.9145μs 37.1547 KOps/s 38.0606 KOps/s $\color{#d91a1a}-2.38\%$
test_step_mdp_speed[True-True-False-False-False] 42.7520μs 15.3148μs 65.2962 KOps/s 64.5491 KOps/s $\color{#35bf28}+1.16\%$
test_step_mdp_speed[True-False-True-True-True] 87.1150μs 47.5696μs 21.0218 KOps/s 21.0432 KOps/s $\color{#d91a1a}-0.10\%$
test_step_mdp_speed[True-False-True-True-False] 0.1080ms 27.4966μs 36.3681 KOps/s 35.9958 KOps/s $\color{#35bf28}+1.03\%$
test_step_mdp_speed[True-False-True-False-True] 62.2130μs 25.9567μs 38.5257 KOps/s 37.6413 KOps/s $\color{#35bf28}+2.35\%$
test_step_mdp_speed[True-False-True-False-False] 47.3120μs 15.2658μs 65.5060 KOps/s 64.8061 KOps/s $\color{#35bf28}+1.08\%$
test_step_mdp_speed[True-False-False-True-True] 87.1450μs 50.4379μs 19.8264 KOps/s 19.7242 KOps/s $\color{#35bf28}+0.52\%$
test_step_mdp_speed[True-False-False-True-False] 73.2830μs 30.4078μs 32.8863 KOps/s 32.2388 KOps/s $\color{#35bf28}+2.01\%$
test_step_mdp_speed[True-False-False-False-True] 59.8930μs 28.6424μs 34.9132 KOps/s 34.2606 KOps/s $\color{#35bf28}+1.90\%$
test_step_mdp_speed[True-False-False-False-False] 41.6620μs 17.8554μs 56.0054 KOps/s 56.1753 KOps/s $\color{#d91a1a}-0.30\%$
test_step_mdp_speed[False-True-True-True-True] 80.3940μs 48.8085μs 20.4882 KOps/s 21.0280 KOps/s $\color{#d91a1a}-2.57\%$
test_step_mdp_speed[False-True-True-True-False] 52.7930μs 27.8268μs 35.9365 KOps/s 35.5583 KOps/s $\color{#35bf28}+1.06\%$
test_step_mdp_speed[False-True-True-False-True] 2.4043ms 29.9753μs 33.3608 KOps/s 32.5985 KOps/s $\color{#35bf28}+2.34\%$
test_step_mdp_speed[False-True-True-False-False] 47.4920μs 17.3939μs 57.4915 KOps/s 59.8198 KOps/s $\color{#d91a1a}-3.89\%$
test_step_mdp_speed[False-True-False-True-True] 82.9940μs 49.3211μs 20.2753 KOps/s 19.7151 KOps/s $\color{#35bf28}+2.84\%$
test_step_mdp_speed[False-True-False-True-False] 60.8430μs 30.1075μs 33.2143 KOps/s 32.6090 KOps/s $\color{#35bf28}+1.86\%$
test_step_mdp_speed[False-True-False-False-True] 62.5230μs 32.0787μs 31.1734 KOps/s 30.3301 KOps/s $\color{#35bf28}+2.78\%$
test_step_mdp_speed[False-True-False-False-False] 44.4420μs 19.1409μs 52.2442 KOps/s 51.3640 KOps/s $\color{#35bf28}+1.71\%$
test_step_mdp_speed[False-False-True-True-True] 84.7540μs 52.4391μs 19.0698 KOps/s 19.3089 KOps/s $\color{#d91a1a}-1.24\%$
test_step_mdp_speed[False-False-True-True-False] 63.7440μs 32.7901μs 30.4970 KOps/s 29.7875 KOps/s $\color{#35bf28}+2.38\%$
test_step_mdp_speed[False-False-True-False-True] 63.1830μs 31.5813μs 31.6644 KOps/s 31.4029 KOps/s $\color{#35bf28}+0.83\%$
test_step_mdp_speed[False-False-True-False-False] 36.5920μs 19.1985μs 52.0874 KOps/s 51.7396 KOps/s $\color{#35bf28}+0.67\%$
test_step_mdp_speed[False-False-False-True-True] 87.4540μs 53.8496μs 18.5702 KOps/s 18.4223 KOps/s $\color{#35bf28}+0.80\%$
test_step_mdp_speed[False-False-False-True-False] 62.7330μs 35.1798μs 28.4254 KOps/s 28.0793 KOps/s $\color{#35bf28}+1.23\%$
test_step_mdp_speed[False-False-False-False-True] 66.7940μs 33.9673μs 29.4401 KOps/s 29.8122 KOps/s $\color{#d91a1a}-1.25\%$
test_step_mdp_speed[False-False-False-False-False] 55.3330μs 21.5751μs 46.3497 KOps/s 45.2558 KOps/s $\color{#35bf28}+2.42\%$
test_non_tensor_env_rollout_speed[1000-single-True] 0.7449s 0.7311s 1.3678 Ops/s 1.3420 Ops/s $\color{#35bf28}+1.92\%$
test_non_tensor_env_rollout_speed[1000-single-False] 0.7249s 0.6158s 1.6239 Ops/s 1.6353 Ops/s $\color{#d91a1a}-0.70\%$
test_non_tensor_env_rollout_speed[1000-serial-no-buffers-True] 1.7835s 1.6798s 0.5953 Ops/s 0.6057 Ops/s $\color{#d91a1a}-1.72\%$
test_non_tensor_env_rollout_speed[1000-serial-no-buffers-False] 1.5256s 1.4463s 0.6914 Ops/s 0.7020 Ops/s $\color{#d91a1a}-1.51\%$
test_non_tensor_env_rollout_speed[1000-serial-buffers-True] 2.0459s 1.9463s 0.5138 Ops/s 0.5261 Ops/s $\color{#d91a1a}-2.34\%$
test_non_tensor_env_rollout_speed[1000-serial-buffers-False] 1.8209s 1.7188s 0.5818 Ops/s 0.5966 Ops/s $\color{#d91a1a}-2.48\%$
test_non_tensor_env_rollout_speed[1000-parallel-no-buffers-True] 4.6969s 4.6186s 0.2165 Ops/s 0.2154 Ops/s $\color{#35bf28}+0.53\%$
test_non_tensor_env_rollout_speed[1000-parallel-no-buffers-False] 4.4536s 4.3767s 0.2285 Ops/s 0.2224 Ops/s $\color{#35bf28}+2.73\%$
test_non_tensor_env_rollout_speed[1000-parallel-buffers-True] 2.0952s 1.9562s 0.5112 Ops/s 0.5293 Ops/s $\color{#d91a1a}-3.41\%$
test_non_tensor_env_rollout_speed[1000-parallel-buffers-False] 1.7940s 1.6394s 0.6100 Ops/s 0.6285 Ops/s $\color{#d91a1a}-2.94\%$
test_values[generalized_advantage_estimate-True-True] 21.9481ms 21.2705ms 47.0136 Ops/s 48.5274 Ops/s $\color{#d91a1a}-3.12\%$
test_values[vec_generalized_advantage_estimate-True-True] 0.1290s 3.5091ms 284.9722 Ops/s 279.7017 Ops/s $\color{#35bf28}+1.88\%$
test_values[td0_return_estimate-False-False] 0.1308ms 85.3262μs 11.7197 KOps/s 11.8622 KOps/s $\color{#d91a1a}-1.20\%$
test_values[td1_return_estimate-False-False] 52.9387ms 51.3604ms 19.4703 Ops/s 20.4528 Ops/s $\color{#d91a1a}-4.80\%$
test_values[vec_td1_return_estimate-False-False] 1.3545ms 1.1069ms 903.4549 Ops/s 909.3176 Ops/s $\color{#d91a1a}-0.64\%$
test_values[td_lambda_return_estimate-True-False] 85.9059ms 83.6605ms 11.9531 Ops/s 12.2962 Ops/s $\color{#d91a1a}-2.79\%$
test_values[vec_td_lambda_return_estimate-True-False] 1.3244ms 1.0973ms 911.3353 Ops/s 912.9191 Ops/s $\color{#d91a1a}-0.17\%$
test_gae_speed[generalized_advantage_estimate-False-1-512] 22.5588ms 22.0766ms 45.2969 Ops/s 47.5906 Ops/s $\color{#d91a1a}-4.82\%$
test_gae_speed[vec_generalized_advantage_estimate-True-1-512] 1.0388ms 0.7733ms 1.2932 KOps/s 1.3061 KOps/s $\color{#d91a1a}-0.99\%$
test_gae_speed[vec_generalized_advantage_estimate-False-1-512] 0.8560ms 0.7135ms 1.4015 KOps/s 1.4136 KOps/s $\color{#d91a1a}-0.86\%$
test_gae_speed[vec_generalized_advantage_estimate-True-32-512] 1.5815ms 1.5044ms 664.7104 Ops/s 666.3356 Ops/s $\color{#d91a1a}-0.24\%$
test_gae_speed[vec_generalized_advantage_estimate-False-32-512] 0.7816ms 0.7255ms 1.3783 KOps/s 1.4322 KOps/s $\color{#d91a1a}-3.76\%$
test_dqn_speed[False-None] 1.7489ms 1.6268ms 614.7108 Ops/s 626.6972 Ops/s $\color{#d91a1a}-1.91\%$
test_dqn_speed[False-backward] 2.4235ms 2.2564ms 443.1793 Ops/s 445.0839 Ops/s $\color{#d91a1a}-0.43\%$
test_dqn_speed[True-None] 0.7175ms 0.6250ms 1.5999 KOps/s 1.5902 KOps/s $\color{#35bf28}+0.61\%$
test_dqn_speed[True-backward] 1.3383ms 1.3025ms 767.7320 Ops/s 747.7143 Ops/s $\color{#35bf28}+2.68\%$
test_dqn_speed[reduce-overhead-None] 0.8670ms 0.6242ms 1.6021 KOps/s 1.4992 KOps/s $\textbf{\color{#35bf28}+6.87\%}$
test_ddpg_speed[False-None] 3.4190ms 3.0135ms 331.8354 Ops/s 331.3858 Ops/s $\color{#35bf28}+0.14\%$
test_ddpg_speed[False-backward] 4.8243ms 4.4223ms 226.1261 Ops/s 226.9789 Ops/s $\color{#d91a1a}-0.38\%$
test_ddpg_speed[True-None] 1.6917ms 1.4434ms 692.8052 Ops/s 683.4647 Ops/s $\color{#35bf28}+1.37\%$
test_ddpg_speed[True-backward] 3.0585ms 2.6588ms 376.1041 Ops/s 394.2959 Ops/s $\color{#d91a1a}-4.61\%$
test_ddpg_speed[reduce-overhead-None] 1.5104ms 1.4128ms 707.8109 Ops/s 694.1702 Ops/s $\color{#35bf28}+1.97\%$
test_sac_speed[False-None] 8.9330ms 8.5156ms 117.4316 Ops/s 117.5620 Ops/s $\color{#d91a1a}-0.11\%$
test_sac_speed[False-backward] 12.0984ms 11.6187ms 86.0683 Ops/s 87.4885 Ops/s $\color{#d91a1a}-1.62\%$
test_sac_speed[True-None] 2.0804ms 1.9848ms 503.8282 Ops/s 496.6996 Ops/s $\color{#35bf28}+1.44\%$
test_sac_speed[True-backward] 3.8617ms 3.8145ms 262.1558 Ops/s 269.7662 Ops/s $\color{#d91a1a}-2.82\%$
test_sac_speed[reduce-overhead-None] 16.6533ms 10.1173ms 98.8403 Ops/s 98.2432 Ops/s $\color{#35bf28}+0.61\%$
test_redq_deprec_speed[False-None] 10.2517ms 9.4917ms 105.3547 Ops/s 105.1124 Ops/s $\color{#35bf28}+0.23\%$
test_redq_deprec_speed[False-backward] 13.1540ms 12.7347ms 78.5256 Ops/s 79.8033 Ops/s $\color{#d91a1a}-1.60\%$
test_redq_deprec_speed[True-None] 2.8935ms 2.7658ms 361.5637 Ops/s 353.0237 Ops/s $\color{#35bf28}+2.42\%$
test_redq_deprec_speed[True-backward] 4.8203ms 4.5253ms 220.9818 Ops/s 218.3119 Ops/s $\color{#35bf28}+1.22\%$
test_redq_deprec_speed[reduce-overhead-None] 14.7022ms 9.6929ms 103.1680 Ops/s 102.5255 Ops/s $\color{#35bf28}+0.63\%$
test_td3_speed[False-None] 8.3877ms 8.3251ms 120.1180 Ops/s 119.5015 Ops/s $\color{#35bf28}+0.52\%$
test_td3_speed[False-backward] 11.3751ms 10.8825ms 91.8910 Ops/s 91.6655 Ops/s $\color{#35bf28}+0.25\%$
test_td3_speed[True-None] 1.7838ms 1.7613ms 567.7643 Ops/s 556.4071 Ops/s $\color{#35bf28}+2.04\%$
test_td3_speed[True-backward] 3.7902ms 3.3647ms 297.2036 Ops/s 304.5422 Ops/s $\color{#d91a1a}-2.41\%$
test_td3_speed[reduce-overhead-None] 49.8732ms 25.7130ms 38.8909 Ops/s 37.4278 Ops/s $\color{#35bf28}+3.91\%$
test_cql_speed[False-None] 18.1757ms 17.7389ms 56.3734 Ops/s 56.4300 Ops/s $\color{#d91a1a}-0.10\%$
test_cql_speed[False-backward] 23.8499ms 23.2006ms 43.1024 Ops/s 43.6954 Ops/s $\color{#d91a1a}-1.36\%$
test_cql_speed[True-None] 3.6966ms 3.5511ms 281.6055 Ops/s 274.1713 Ops/s $\color{#35bf28}+2.71\%$
test_cql_speed[True-backward] 6.3216ms 5.9105ms 169.1908 Ops/s 169.0125 Ops/s $\color{#35bf28}+0.11\%$
test_cql_speed[reduce-overhead-None] 17.3333ms 11.6609ms 85.7565 Ops/s 81.9270 Ops/s $\color{#35bf28}+4.67\%$
test_a2c_speed[False-None] 4.3639ms 3.3916ms 294.8483 Ops/s 296.8094 Ops/s $\color{#d91a1a}-0.66\%$
test_a2c_speed[False-backward] 6.9064ms 6.5173ms 153.4389 Ops/s 158.8333 Ops/s $\color{#d91a1a}-3.40\%$
test_a2c_speed[True-None] 1.6304ms 1.5173ms 659.0761 Ops/s 648.9060 Ops/s $\color{#35bf28}+1.57\%$
test_a2c_speed[True-backward] 3.4883ms 3.4042ms 293.7511 Ops/s 288.8122 Ops/s $\color{#35bf28}+1.71\%$
test_a2c_speed[reduce-overhead-None] 1.2746ms 1.1041ms 905.7479 Ops/s 898.9273 Ops/s $\color{#35bf28}+0.76\%$
test_ppo_speed[False-None] 4.1600ms 4.0202ms 248.7427 Ops/s 249.6402 Ops/s $\color{#d91a1a}-0.36\%$
test_ppo_speed[False-backward] 7.8271ms 7.3469ms 136.1119 Ops/s 134.7269 Ops/s $\color{#35bf28}+1.03\%$
test_ppo_speed[True-None] 1.7412ms 1.6085ms 621.7133 Ops/s 610.9821 Ops/s $\color{#35bf28}+1.76\%$
test_ppo_speed[True-backward] 3.6852ms 3.5811ms 279.2470 Ops/s 276.8111 Ops/s $\color{#35bf28}+0.88\%$
test_ppo_speed[reduce-overhead-None] 1.2728ms 1.1699ms 854.7543 Ops/s 833.7838 Ops/s $\color{#35bf28}+2.52\%$
test_reinforce_speed[False-None] 2.5740ms 2.3961ms 417.3387 Ops/s 403.3585 Ops/s $\color{#35bf28}+3.47\%$
test_reinforce_speed[False-backward] 3.9669ms 3.5247ms 283.7134 Ops/s 287.8904 Ops/s $\color{#d91a1a}-1.45\%$
test_reinforce_speed[True-None] 1.6069ms 1.4913ms 670.5780 Ops/s 683.5197 Ops/s $\color{#d91a1a}-1.89\%$
test_reinforce_speed[True-backward] 3.4630ms 3.3453ms 298.9295 Ops/s 304.3481 Ops/s $\color{#d91a1a}-1.78\%$
test_reinforce_speed[reduce-overhead-None] 15.7172ms 8.8488ms 113.0102 Ops/s 111.8795 Ops/s $\color{#35bf28}+1.01\%$
test_iql_speed[False-None] 10.1281ms 9.6812ms 103.2926 Ops/s 103.0149 Ops/s $\color{#35bf28}+0.27\%$
test_iql_speed[False-backward] 13.8688ms 13.5163ms 73.9845 Ops/s 75.2165 Ops/s $\color{#d91a1a}-1.64\%$
test_iql_speed[True-None] 2.6489ms 2.3901ms 418.3852 Ops/s 413.2774 Ops/s $\color{#35bf28}+1.24\%$
test_iql_speed[True-backward] 5.3976ms 5.1925ms 192.5838 Ops/s 195.6100 Ops/s $\color{#d91a1a}-1.55\%$
test_iql_speed[reduce-overhead-None] 17.3743ms 10.1809ms 98.2227 Ops/s 97.3369 Ops/s $\color{#35bf28}+0.91\%$
test_rb_sample[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.2067ms 6.0676ms 164.8093 Ops/s 165.9406 Ops/s $\color{#d91a1a}-0.68\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 2.7111ms 0.3735ms 2.6773 KOps/s 2.6737 KOps/s $\color{#35bf28}+0.13\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.6853ms 0.2719ms 3.6784 KOps/s 2.8204 KOps/s $\textbf{\color{#35bf28}+30.42\%}$
test_rb_sample[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.1366ms 5.8529ms 170.8540 Ops/s 171.6432 Ops/s $\color{#d91a1a}-0.46\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.2345ms 0.3689ms 2.7110 KOps/s 2.7487 KOps/s $\color{#d91a1a}-1.37\%$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.7874ms 0.3581ms 2.7927 KOps/s 2.8307 KOps/s $\color{#d91a1a}-1.34\%$
test_rb_sample[TensorDictReplayBuffer-LazyMemmapStorage-sampler6-10000] 0.8873s 3.3905ms 294.9382 Ops/s 788.8868 Ops/s $\textbf{\color{#d91a1a}-62.61\%}$
test_rb_sample[TensorDictReplayBuffer-LazyTensorStorage-sampler7-10000] 1.6952ms 1.2494ms 800.3537 Ops/s 839.6507 Ops/s $\color{#d91a1a}-4.68\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.2740ms 6.1319ms 163.0823 Ops/s 170.1009 Ops/s $\color{#d91a1a}-4.13\%$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.2375ms 0.5404ms 1.8505 KOps/s 2.2692 KOps/s $\textbf{\color{#d91a1a}-18.45\%}$
test_rb_sample[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.6694ms 0.4209ms 2.3757 KOps/s 2.4061 KOps/s $\color{#d91a1a}-1.26\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-RandomSampler-4000] 6.2126ms 5.9580ms 167.8403 Ops/s 174.8438 Ops/s $\color{#d91a1a}-4.01\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-10000] 1.8313ms 0.3504ms 2.8543 KOps/s 3.4826 KOps/s $\textbf{\color{#d91a1a}-18.04\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-10000] 0.5117ms 0.3220ms 3.1053 KOps/s 3.0505 KOps/s $\color{#35bf28}+1.80\%$
test_rb_iterate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-4000] 6.1733ms 5.9317ms 168.5864 Ops/s 174.0524 Ops/s $\color{#d91a1a}-3.14\%$
test_rb_iterate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-10000] 2.1404ms 0.3244ms 3.0827 KOps/s 2.7654 KOps/s $\textbf{\color{#35bf28}+11.47\%}$
test_rb_iterate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-10000] 0.6647ms 0.2898ms 3.4512 KOps/s 3.7352 KOps/s $\textbf{\color{#d91a1a}-7.60\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-ListStorage-None-4000] 6.2297ms 6.0738ms 164.6429 Ops/s 166.2918 Ops/s $\color{#d91a1a}-0.99\%$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-10000] 2.2246ms 0.4888ms 2.0456 KOps/s 2.2068 KOps/s $\textbf{\color{#d91a1a}-7.30\%}$
test_rb_iterate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-10000] 0.7905ms 0.5275ms 1.8956 KOps/s 2.1960 KOps/s $\textbf{\color{#d91a1a}-13.68\%}$
test_rb_populate[TensorDictReplayBuffer-ListStorage-RandomSampler-400] 6.6832ms 5.1222ms 195.2268 Ops/s 195.9814 Ops/s $\color{#d91a1a}-0.39\%$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-RandomSampler-400] 4.1760ms 2.1048ms 475.1075 Ops/s 435.2528 Ops/s $\textbf{\color{#35bf28}+9.16\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-RandomSampler-400] 1.1767ms 1.0162ms 984.0812 Ops/s 987.6109 Ops/s $\color{#d91a1a}-0.36\%$
test_rb_populate[TensorDictReplayBuffer-ListStorage-SamplerWithoutReplacement-400] 0.6853s 18.7660ms 53.2878 Ops/s 195.3104 Ops/s $\textbf{\color{#d91a1a}-72.72\%}$
test_rb_populate[TensorDictReplayBuffer-LazyMemmapStorage-SamplerWithoutReplacement-400] 3.9319ms 1.9124ms 522.9119 Ops/s 451.7265 Ops/s $\textbf{\color{#35bf28}+15.76\%}$
test_rb_populate[TensorDictReplayBuffer-LazyTensorStorage-SamplerWithoutReplacement-400] 2.0667ms 1.1428ms 875.0545 Ops/s 992.9399 Ops/s $\textbf{\color{#d91a1a}-11.87\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-ListStorage-None-400] 8.1224ms 5.2623ms 190.0301 Ops/s 44.5055 Ops/s $\textbf{\color{#35bf28}+326.98\%}$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyMemmapStorage-None-400] 8.7588ms 2.1212ms 471.4388 Ops/s 468.6973 Ops/s $\color{#35bf28}+0.58\%$
test_rb_populate[TensorDictPrioritizedReplayBuffer-LazyTensorStorage-None-400] 1.4365ms 1.1145ms 897.3013 Ops/s 871.0865 Ops/s $\color{#35bf28}+3.01\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-True] 44.0873ms 40.3891ms 24.7591 Ops/s 24.5841 Ops/s $\color{#35bf28}+0.71\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-10000-10000-100-False] 20.5823ms 19.0310ms 52.5457 Ops/s 55.1261 Ops/s $\color{#d91a1a}-4.68\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-True] 46.5053ms 41.9205ms 23.8547 Ops/s 24.1188 Ops/s $\color{#d91a1a}-1.10\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-100000-10000-100-False] 21.0627ms 19.2569ms 51.9295 Ops/s 53.5385 Ops/s $\color{#d91a1a}-3.01\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-True] 46.4364ms 44.0584ms 22.6971 Ops/s 22.9541 Ops/s $\color{#d91a1a}-1.12\%$
test_rb_extend_sample[ReplayBuffer-LazyTensorStorage-RandomSampler-1000000-10000-100-False] 22.0716ms 20.9424ms 47.7501 Ops/s 49.7665 Ops/s $\color{#d91a1a}-4.05\%$
test_storage_write_lazystack[50-img_shape0-small] 0.9042ms 0.2273ms 4.4004 KOps/s 4.2897 KOps/s $\color{#35bf28}+2.58\%$
test_storage_write_lazystack[100-img_shape1-atari] 1.7397ms 1.4217ms 703.4053 Ops/s 712.2586 Ops/s $\color{#d91a1a}-1.24\%$
test_storage_write_lazystack[100-img_shape2-large_img] 2.7204ms 2.3110ms 432.7126 Ops/s 424.8821 Ops/s $\color{#35bf28}+1.84\%$
test_storage_write_lazystack[200-img_shape3-large_batch] 3.1191ms 2.9215ms 342.2864 Ops/s 336.6438 Ops/s $\color{#35bf28}+1.68\%$
test_storage_write_contiguous[50-img_shape0-small] 0.4467ms 0.1666ms 6.0032 KOps/s 6.0978 KOps/s $\color{#d91a1a}-1.55\%$
test_storage_write_contiguous[100-img_shape1-atari] 0.3621ms 0.2238ms 4.4680 KOps/s 4.5341 KOps/s $\color{#d91a1a}-1.46\%$
test_storage_write_contiguous[100-img_shape2-large_img] 1.9710ms 1.8348ms 545.0084 Ops/s 544.8587 Ops/s $\color{#35bf28}+0.03\%$
test_storage_write_contiguous[200-img_shape3-large_batch] 1.8602ms 1.4384ms 695.2299 Ops/s 711.9425 Ops/s $\color{#d91a1a}-2.35\%$
test_collector_stack_then_write[50-img_shape0-small] 1.3389ms 1.1778ms 849.0307 Ops/s 858.5723 Ops/s $\color{#d91a1a}-1.11\%$
test_collector_stack_then_write[100-img_shape1-atari] 3.8792ms 3.6969ms 270.4981 Ops/s 274.7455 Ops/s $\color{#d91a1a}-1.55\%$
test_collector_stack_then_write[100-img_shape2-large_img] 6.0992ms 5.8853ms 169.9159 Ops/s 168.7010 Ops/s $\color{#35bf28}+0.72\%$
test_collector_stack_then_write[200-img_shape3-large_batch] 7.7020ms 7.1775ms 139.3239 Ops/s 132.0626 Ops/s $\textbf{\color{#35bf28}+5.50\%}$
test_collector_lazystack_then_write[50-img_shape0-small] 0.4631ms 0.2836ms 3.5260 KOps/s 3.5966 KOps/s $\color{#d91a1a}-1.96\%$
test_collector_lazystack_then_write[100-img_shape1-atari] 1.7086ms 1.5298ms 653.6916 Ops/s 660.4559 Ops/s $\color{#d91a1a}-1.02\%$
test_collector_lazystack_then_write[100-img_shape2-large_img] 2.6582ms 2.4694ms 404.9492 Ops/s 405.7630 Ops/s $\color{#d91a1a}-0.20\%$
test_collector_lazystack_then_write[200-img_shape3-large_batch] 3.3216ms 3.1566ms 316.7954 Ops/s 314.7294 Ops/s $\color{#35bf28}+0.66\%$
test_collector_without_rb[100-img_shape0-atari] 34.7514ms 33.5106ms 29.8413 Ops/s 30.1278 Ops/s $\color{#d91a1a}-0.95\%$
test_collector_without_rb[200-img_shape1-large_batch] 67.1013ms 65.9493ms 15.1632 Ops/s 15.2411 Ops/s $\color{#d91a1a}-0.51\%$
test_collector_with_rb[100-img_shape0-atari] 38.5980ms 38.0156ms 26.3050 Ops/s 26.3809 Ops/s $\color{#d91a1a}-0.29\%$
test_collector_with_rb[200-img_shape1-large_batch] 76.4205ms 75.0556ms 13.3235 Ops/s 13.4598 Ops/s $\color{#d91a1a}-1.01\%$
test_collector_without_rb_cuda[100-img_shape0-atari] 58.7144ms 57.1026ms 17.5123 Ops/s 17.8655 Ops/s $\color{#d91a1a}-1.98\%$
test_collector_without_rb_cuda[200-img_shape1-large_batch] 0.1164s 0.1144s 8.7431 Ops/s 8.9688 Ops/s $\color{#d91a1a}-2.52\%$
test_collector_with_rb_cuda[100-img_shape0-atari] 60.8392ms 59.3001ms 16.8634 Ops/s 17.2516 Ops/s $\color{#d91a1a}-2.25\%$
test_collector_with_rb_cuda[200-img_shape1-large_batch] 0.1210s 0.1195s 8.3652 Ops/s 8.6882 Ops/s $\color{#d91a1a}-3.72\%$

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. Dependencies Pull requests that update a dependency file python Pull requests that update python code sota-implementations/

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants