wall-clock speedup of variance-controlled async RL vs synchronous at equal accuracy (~42h vs ~105h)

Name: wall-clock speedup of variance-controlled async RL vs synchronous at equal accuracy (~42h vs ~105h)
License: https://aidatacenterguide.com/terms#intellectual-property

2.5xobserved

Value kind	observed — Reported measurements, counts, and specifications keep the precision and scope stated by their source; an exact specification is not treated as a range.
As of	2026
Source	Stable Asynchrony / VCPO (arXiv 2602.17616) · Abstract: VCPO achieves up to 2.5x wall-clock speedup while matching synchronous-training accuracy
Review	checking…review by 2026-10-31 · standard cadence
Recorded changes	last 2026-06-29
Claim id	wall-clock-speedup-of-variance-controlled-async

Where the guide uses it

1.4 Post-Training, Fine-Tuning & RL: The Hybrid Middle

← Full numbers register — every date-stamped figure in the guide, with revision history.