Baseten 工程博客:LLM 推理可观测性、DeepSeek V4 Pro 0813 与 NVIDIA Nemotron 3.5
Blog
Baseten 工程博客列出多篇推理工程与模型文章,包括《领先平台如何保障 LLM 推理可观测性》、面向 DeepSeek V4 Pro 0813 的推理工程,以及 Baseten 为 You.com 提供开源推理。博客还介绍 NVIDIA Nemotron 3.5 Lightning 与 Nemotron 3.5 ASR Streaming,并收录 Laguna S 2.1、Qwen3-TTS 微调语音克隆、Kimi K3 路由等内容。
正文
Blog Inference engineering Infrastructure How leading platforms ensure observability for LLM inference Chloe Florit Model performance Inference engineering for DeepSeek V4 Pro 0813 Model Performance Team Community Baseten delivers open-source inference for You.com Marylise Tauzia 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 engineering Fine-tuning Qwen3-TTS for high-quality voice cloning Ian Carrasco Foundations 22,580: GPT-2 to Kimi K3, explained Ali Taha AI engineering How to run Kimi K3 in any harness: routing with Baseten Switch Zak Keener 1 other 1 2 3 4 ... 27 requestAnimationFrame(function(){$RT=performance.now()}); Popular models