scalable-prompt-routing-moe

【效率与协作】Route queries across frontier models using two-stage system: graph-based task discovery identifies ~332 latent task types via semantic similarity + preference patterns; MoE with task-specific adapters estimates quality for candidate models. Achieves <50% inference cost of strongest single model while exceeding its performance; applies when managing p…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准