How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF

Title:How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF

Abstract:In RLHF pipelines, reward scoring blocks policy updates. Slow scoring bottlenecks the entire loop, since no update runs until every rollout gets a score. And yet most setups just default to PyTorch eager mode or this http URL, no one checks if that's actually fastest. Scoring itself is small. Rollout generation eats far more of a typical RLHF step. But scoring and generation fight over the same CPU and GPU resources, so a faster scoring engine doesn't shrink step time on its own. It mainly frees up capacity generation can use instead. We built a native C++ inference engine on ONNX Runtime. First step: confirm correctness. Output matched the PyTorch reference to 5.7 x 10^-6 on CPU and 4.2 x 10^-3 on GPU, close enough to trust. Then we tested it against PyTorch eager mode, this http URL, and FastAPI, on both CPU and GPU. CPU was decisive. Our engine beat every baseline, confidence intervals didn't even overlap. GPU gave a different view: we beat PyTorch and FastAPI, but this http URL came out ahead. Further testing traced the speedup to ONNX Runtime itself, not C++ as a language. And batching strategy mattered more than either the language or the runtime choice, more than we expected. The results are from repeated, independent runs, since single runs just aren't reliable enough to trust.

Machine Learning (cs.LG)

arXiv:2607.19712 [cs.LG]

(or arXiv:2607.19712v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.19712 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.