Hugging Face Papers ↗ · 2026-11-06
Ensemble Routing for Prompt-Adaptive Cost-Aware LLM Inference
Media reports Hugging Face Papers Source language: Chinese
Excerpt
论文摘要(作者报告,未经本站复测):Large language models (LLMs) increasingly support Web-based services that must balance response quality and inference cost across heterogeneous requests. Conventional routing selects one model per prompt, while fixed ensembles cannot adapt their composition and cost to individual requests.
Short excerpt from the source — open the original for the full text.