CoreWeave launches Forge to speed continuous AI post-training
CoreWeave announced CoreWeave Forge, which connects model deployment, evaluation and improvement into one loop; its reinforcement-learning Rollouts capability, now in preview, supports repeated cycles of generating training responses and updating models, with weight synchronization that hot-starts from nearby peers instead of pulling weights from object storage each time. CoreWeave AI Object Storage now supports cross-region writes so post-training jobs can write results back for others to use. You.com joined CoreWeave's partner network to give agents a search layer, and the companies say that working with NVIDIA they used RL Rollouts to post-train Nemotron 3.5 Lightning in eight hours with You.com's web search tools. You.com chief product officer Saurabh Sharma said the ceiling is no longer model intelligence but models' ability to use tools, and claimed customers get higher accuracy and lower total cost of ownership — a vendor claim without published figures.
Why it matters: Post-training cycle speed and GPU utilization are becoming a competitive layer in agent infrastructure, and shorter loops could let more teams customize models.
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.)
Post-training puts GPU utilization at the heart of the AI loop
CoreWeave has announced CoreWeave Forge, which connects model deployment, evaluation and improvement. Its reinforcement learning Rollouts capability, currently in preview, supports repeated cycles of generating training responses and updating models, Sanders explained.
“For the weight synchronization, this is an area that we’ve done a bunch of work to be able to bring the weights in sort of a hot start versus starting cold every time,” Sanders said. “Instead of the weight always coming from object storage, we now get weights from other peers nearby.”
Data movement also matters when the goal is keeping GPU utilization high between training rounds. CoreWeave AI Object Storage now supports cross-region writes, letting post-training jobs write results back for others to use, according to Sanders.
“There actually is core infrastructure like our object storage, which we’ve built around trying to get data into the GPU as fast and as easy as possible,” Sanders said. “You write like it’s a local machine. We treat it like it’s a global system.”
You.com, which runs its own web index, has joined CoreWeave’s partner network to give agents a search layer. Working with Nvidia, the companies used RL Rollouts to post-train Nemotron 3.5 Lightning in eight hours with You.com’s web search tools.
“What our customers are seeing is that … they are able to run their workloads with higher accuracy and lower total cost of ownership,” Sharma said. “If you can do this in eight hours, this is no longer something that only the frontier labs can do.”
Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of the Fully Connected event:
(* Disclosure: TheCUBE is a paid media partner for the Fully Connected event. Neither CoreWeave, the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)
Photo: SiliconANGLE
A message from John Furrier, co-founder of SiliconANGLE:
Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.
- 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more
- 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network
SiliconANGLE Media is a recognized leader in digital media innovation, uniting breakthrough technology, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios — with flagship locations in Silicon Valley and the New York Stock Exchange — SiliconANGLE Media operates at the intersection of media, technology and AI.
Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.
How we got here
- Lambda reportedly seeks $4B ahead of planned 2027 IPOTechCrunch AI · NVIDIA
- MasterClass bets on AI teaching agents to cut tutoring costsSiliconANGLE AI · CoreWeave
- Vast pitches tiered storage to ease AI agent memory pressureSiliconANGLE AI · Nvidia
- NVIDIA promotes open models for telecom AI and announces Nemotron 3 LTMNVIDIA Blog · NVIDIA
- OpenAI Brakes on Agent Safety as Meta Keeps Pushing虎嗅 AI · NVIDIA
- A16Z reports: AI usage is broad, but deep adoption remains concentrated虎嗅 AI · CoreWeave