推理工程大师课：Baseten解析AI推理优化前沿
原标题：The Inference Engineering Masterclass — Philip Kiely & Ali Taha, Baseten
AI 摘要
Baseten在完成130亿美元融资后成为AI基础设施领域的独角兽，其团队成员Philip Kiely和Ali Taha在播客中深入探讨了推理工程这一新兴学科。他们讨论了缓存感知路由、预填充与解码分离、量化、投机解码等技术，以及如何通过优化将模型推理速度提升10倍。对话还涉及NVIDIA Dynamo、GPU并行、视频生成的计算瓶颈，以及训练与推理的融合趋势。
正文节选
We first covered Baseten last year when DeepSeek mania was at peak hype. Now they have raised a monster $13B round and become one of the new cohort of AI Infra decacorns that are (with Nvidia, Intel, and the semis complex) chief beneficiaries of the Inference Inflection. We return to Baseten at the peak of the 2026 edition of Open Weights debate. Ali has published a viral breakdown of Kimi K3: And since you last saw him, Philip has spoken at AI Engineer and written the definitive book on Inferen