Together AI 在原生云上支持 TorchForge RL 流水线
原标题：How to run TorchForge reinforcement learning pipelines in the Together AI Native Cloud
AI 摘要
Together AI 宣布其 Native Cloud 平台现已支持 TorchForge 强化学习（RL）流水线，提供分布式训练和沙箱环境，并发布了在 Instant Clusters 上运行 Qwen 1.5B 模型玩 BlackJack 的演示。该平台集成了 CodeSandbox 和 Code Interpreter，用于工具执行和代码评估，为即将推出的 RL 服务奠定基础。Together AI 正与 Meta 合作，在 PyTorch 生态中构建灵活的开源 RL 框架。
正文节选
TorchForge RL pipelines now run on Together AI’s Instant Clusters with support for distributed training and sandboxed environments. This blog provides a demo of a TorchForge RL pipeline along with guidance for configuring it for broader use cases. These capabilities will serve as the foundational components of Together AI’s upcoming RL service. The AI Native Cloud provides the foundation for a next-gen RL service Building flexible, scalable reinforcement learning (RL) systems requires compute, f