PufferLib 5.0 Hits 60M Steps/Sec on a Single RTX 5090: How 5 Degrees of Parallelism Work

jsuarez · x · 2026-09-14

jsuarez explains how PufferLib 5.0 broke 60M steps/second of RL training on a single RTX 5090 — months of simulated data per second for most environments.

He notes they could exceed 100M SPS with a million environments but report maximum throughput under useful configurations.

Original post →

More from Infra

Infra channel →