CoreWeave Forge发布，打通AI训练评估闭环
CoreWeave 在 Fully Connected 活动上推出 CoreWeave Forge 平台，把部署、观测、筛选、改进与评测串成一个可循环的流程，目标是让每次生产运行都反哺模型与智能体；其中 RL Rollouts（强化学习 rollout）尚处预览阶段，另有 Agent Lens 用于查看智能体行为、Registry 用于管理检查点与智能体配置，AI Object Storage 新增跨区域写入。公司强调该闭环对模型、框架和云保持开放，并宣布合作伙伴网络，You.com 以网页搜索层加入。据受访高管介绍，CoreWeave 联合 Nvidia 与 You.com，用 RL Rollouts 在 8 小时内完成了 Nemotron 3.5 Lightning 的后训练。
若后训练与智能体迭代真能压缩到数小时并向多框架开放，专用 AI 云之间的竞争将从 GPU 容量转向工具链与闭环效率。
CoreWeave targets GPU utilization in continuous AI post-training
GPU utilization during post-training depends partly on how efficiently infrastructure moves data and loads updated models. As enterprises continually refine AI agents, reducing delays between training rounds can help keep that process moving.
The need for continual improvement is pushing CoreWeave Inc. to build a full-stack AI cloud for the agent lifecycle. You.com Inc. provides web search tools for those agents, according to Saurabh Sharma (pictured, right), chief product officer of You.com.
“What we’re seeing is that the ceiling is no longer model intelligence,” Sharma said. “The models are getting more intelligent, but it’s their ability to use the tools that dictates the agent’s success.”
Sharma and Corey Sanders (left), senior vice president of product at CoreWeave, spoke with theCUBE Research’s Dave Vellante and John Furrier at the Fully Connected event, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed tool skills, graphics processing unit utilization and continuous model improvement. (* Disclosure below.)
#CoreWeave#CoreWeave Forge#You.com#Nvidia#Nemotron 3.5 Lightning#Agent Lens#RL Rollouts