From SiliconANGLE · Jonathan Anthony · · 1m
CoreWeave launches Forge for AI inference stack
CoreWeave's Forge platform solves AI inference bottlenecks with full-stack optimization.
In brief
CoreWeave's Forge platform solves AI inference bottlenecks with full-stack optimization. CoreWeave launched Forge, a free AI inference platform with managed services for training, post-training, and inference, improving model reload latency by 15x for agentic models. Originally reported by SiliconANGLE.
CoreWeave targets AI inference bottlenecks
AI inference is fast becoming the workload that decides the economics of the AI boom.
“ai inference is fast becoming the workload that decides the economics of the ai boom”
CoreWeave offers full-stack managed services
CoreWeave layers managed services for training, post-training and inference atop its infrastructure.
“coreweave layers managed services for training posttraining and inference atop its infrastructure”
Chowdhary on developer needs
Chowdhary said developers want quick solutions with best performance and cost to scale.
“i think if you look at the ai developer's journey they're looking to solve a problem and they want to do it as quickly as they can with the best performance and the cost to scale”
Inference workload grows rapidly
Healthcare customer's inference share rose from 10% to 40% in two years with 50% expected in 12 months.
“one healthcare customer's inference workload share rose from about ten percent in the first year to forty percent in the second with a roughly fifty percent share expected within twelve months”
CoreWeave RL Rollouts capability
CoreWeave RL Rollouts loads new checkpoints into live deployments improving reload latency 15x.
“when you're doing rl rollouts you're continually creating new model checkpoints and versions and you want those to roll out into your inference setup so you can scale it independently”
Forge platform launched at Fully Connected
CoreWeave Forge connects serving, observability, post-training and evaluation with free tier and paid tiers.
“we want to create accessibility for these leading technologies even if you're an individual developer signing up today on your own you still get the best performance you still get the best reliability and you don't have to compromise”
What matters most
CoreWeave launched Forge, a free AI inference platform with managed services for training, post-training, and inference, improving model reload latency by 15x for agentic models.
