#ServiceNow

1 articles about ServiceNow

vLLM V0 to V1: Correctness Before Corrections in RL
AI Research May 6, 2026

vLLM V0 to V1: Correctness Before Corrections in RL

ServiceNow details how its PipelineRL team moved RL rollout generation from vLLM V0 to V1 by fixing four backend gaps — logprob semantics, runtime defaults, inflight weight updates, and an fp32 lm_head — before changing the objective.