Meta 發佈 Muse Spark Open，面向智能體編碼工作流
Scale Agentic Coding Workflows with Meta’s Muse Spark Open on NVIDIA GB300 NVL72
Meta 發佈 Muse Spark Open，這是一款面向智能體編碼的 816B MoE 模型，具備 42B 活躍參數及 1M token 上下文窗口。該模型在 NVIDIA GB300 NVL72 Blackwell Ultra 上訓練，原文稱其具備較高的首次嘗試準確率、可靠的工具調用能力，以及跨程式碼庫的深入理解能力。
Meta launches Muse Spark Open, a coding-optimized 816B mixture-of-experts (MoE) model with 42B active parameters and a 1M token context window. Trained on...
Meta launches Muse Spark Open, a coding-optimized 816B mixture-of-experts (MoE) model with 42B active parameters and a 1M token context window. Trained on NVIDIA GB300 NVL72 Blackwell Ultra specifically for agentic coding workflows, it delivers higher first attempt accuracy, reliable tool calling, and deep codebase understanding across repositories. The 1M token context window holds an entire…
來源：NVIDIA Technical Blog：Agentic AI / Generative AI · developer.nvidia.com