KV-PRM

Researchers introduced KV-PRM, a novel Process Reward Model that leverages the KV cache to reduce scoring complexity from O(L^2) to O(L), achieving up to 5,000x reduction in FLOPs, 37x lower latency, …

Researchers introduced KV-PRM, a process reward model that reduces scoring cost from O(L²) to O(L) by leveraging KV cache from LLM generation, achieving up to 5,000x reduction in FLOPs and 37x reducti…