MoE模型功耗优化新方案，将GPU功率从静态约束变为可控资源，提升能效
arXiv:2605.21427v1 Announce Type: new Abstract: Large language model (LLM) inference has become a dominant workload in modern data centers, driving si…
评估11款专有模型，揭示何时小模型更优，兼顾可持续性与成本效益
arXiv:2504.13217v3 Announce Type: replace Abstract: Large language models (LLMs) have become increasingly embedded in organizational workflows. This h…
实测对比：本地M5 MacBook Pro运行LLM每百万token成本约$1.5，而OpenRouter同类模型价格仅1/3且速度翻倍，揭示本地推理的真实经济账。
Article URL: https://www.williamangel.net/blog/2026/05/17/offline-llm-energy-use.html Comments URL: https://news.ycombinator.com/item?id=48168198 Poin…
无需新硬件，软件优化就能大幅降低AI能耗，绿色计算新思路来了。
Article URL: https://thenewstack.io/streaming-ai-energy-efficiency/ Comments URL: https://news.ycombinator.com/item?id=48161187 Points: 1 # Comments: …