Optimize the Cob, Then the Kernel: Optimizing Beam Search for Generative Recommendation Inference
arXiv:2611.23339v1 Announce Type: new Abstract: Generative recommendation (GR) inference differs substantially from conventional LLM serving, featuring long input sequences, wide beam search, and only a few fixed output tokens. Existing LLM serving engines such as vLLM process beams as batched independent sequences, causing redundant KV cache accesses over the shared prompt prefix. Furthermore, vLLM executes each beam search generation step as a separate engine invocation, incurring host-side beam processing overhead between decoding steps and substantial runtime KV block management in PagedAt
阅读原文 · arXiv 机器学习本文由 SoccerDream AI 自动聚合索引,内容版权归原作者与 arXiv 机器学习 所有。
本站仅作技术动态聚合,不构成任何形式的建议。
本站仅作技术动态聚合,不构成任何形式的建议。