现在你可以把 Devin 跑在自己的 GPU 上了，NVIDIA Brev 直接集成了 Outposts，写代码调试都更方便。
Cognition 公司的 AI 编程智能体 Devin 推出 Outposts 功能，现已集成到 NVIDIA Brev 平台。用户可以通过 Brev 编写和 profiling 内核、运行实验、部署和微调开源模型，并在真实硬件上测试。Outposts 支持将 Devin 运行在任何机器上，包括 Mac mini、实验室 GPU 盒、私有网络 VM 或 Kubernetes 集群。该集成降低了 Devin 的部署门槛，允许开发者在自己控制的基础设施上使用。
Devin Outposts are now available on NVIDIA Brev. Write and profile kernels, run experiments, serve ...
Devin Outposts are now available on NVIDIA Brev. Write and profile kernels, run experiments, serve and fine-tune OSS models, and test against real hardware. Try it out: brev.nvidia.com/launchable/dep… Cognition @cognition Introducing Devin Outposts: run Devin on any machine. Your Mac mini, a GPU box in your lab, a VM inside your private network, or a Kubernetes cluster next to your internal services. 🔗 View Quoted Tweet 💬 4 🔄 0 ❤️ 8 👀 2382 📊 4 ⚡