让大语言模型效率普及：从超大规模优化到通用部署
Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability
AI总结：
本文提出通过改进LLM的效率方法，使其在有限资源和专业知识下仍能有效运作，以实现更广泛的部署和公平性。
摘要：
大型语言模型（LLMs）已成为不可或缺的工具，但最受推崇的效率方法——专家混合（MoE）、推测解码和复杂检索增强生成（RAG）——最初是为拥有庞大基础设施和精英团队的超大规模提供商设计的。在其他环境下，这些方法的益处会转化为开销、脆弱性和浪费的碳排放。结果是，只有少数大科技公司受益，而成千上万的医院、学校、政府和企业却缺乏可行的选项。我们主张，下一步的前沿不是更大规模的复杂性，而是稳健的简单性：在有限资源和最低专业知识下仍能有效运作的效率。我们提出了一项新的研究议程：在预训练模型上采用更高效的架构而不进行重新训练，发明轻量级微调技术以保持对齐，使推理在长推理链中仍然经济，通过动态知识管理而不依赖重型RAG流程，以及采用过载意识效率（OAE）作为标准基准。通过将效率重新定义为包括采用成本、可持续性和公平性，我们可以使LLM部署普及化——确保优化减少不平等和碳浪费，而不是加剧它们。
英文摘要：
Large language models (LLMs) have become indispensable, but the most celebrated efficiency methods -- mixture-of-experts (MoE), speculative decoding, and complex retrieval-augmented generation (RAG) -- were built for hyperscale providers with vast infrastructure and elite teams. Outside that context, their benefits collapse into overhead, fragility, and wasted carbon. The result is that a handful of Big Tech companies benefit, while thousands of hospitals, schools, governments, and enterprises are left without viable options. We argue that the next frontier is not greater sophistication at scale, but robust simplicity: efficiency that thrives under modest resources and minimal expertise. We propose a new research agenda: retrofitting pretrained models with more efficient architectures without retraining, inventing lightweight fine-tuning that preserves alignment, making reasoning economical despite long chains of thought, enabling dynamic knowledge management without heavy RAG pipelines, and adopting Overhead-Aware Efficiency (OAE) as a standard benchmark. By redefining efficiency to include adoption cost, sustainability, and fairness, we can democratize LLM deployment -- ensuring that optimization reduces inequality and carbon waste rather than amplifying them.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
