Baseten 工程博客 AI 模型文章列表
AI models | Blog
Baseten 工程博客的 AI 模型栏目汇集多篇模型与推理工程文章，包括 NVIDIA Nemotron 3 Diarization 实现每音频小时一美分的实时说话人标注、DeepSeek-V4.1-Flash 面向编码智能体的更高效 prefill，以及 NVIDIA Nemotron 3.5 Lightning、Nemotron 3.5 ASR Streaming、Nemotron 3 Embed 等新模型介绍。此外还涵盖 GLM-5.3 后训练扩展、GLM 5.2 视觉能力、Laguna S 2.1 与开源后训练模型推荐等主题。
正文
Blog Inference engineering AI models NVIDIA Nemotron 3 Diarization: real-time speaker labels at a cent per audio hour Ansel Erol AI models DeepSeek-V4.1-Flash: more efficient prefill for coding agents Albert Lee 2 others AI models Best open-source models for post-training Chloe Florit AI models GLM-5.3: Scaling with post-training, intuitively explained Chloe Florit 1 other AI models Introducing NVIDIA Nemotron 3.5 Lightning Marylise Tauzia 1 other AI models Introducing NVIDIA Nemotron 3.5 ASR Streaming Ansel Erol 1 other AI models Laguna S 2.1 goes Greek: a repository-scale game transformation Albert Lee AI models GLM 5.2 with vision Harry Partridge AI models Fast, accurate retrieval with NVIDIA Nemotron 3 Embed Albert Lee 1 2 3 requestAnimationFrame(function(){$RT=performance.now()}); Popular models