Boundless Expands Distributed GPU Compute Network To Support AI Inference Workloads

by
Alisa Davidson

Revealed: July 14, 2026 at 10:26 am Up to date: July 14, 2026 at 10:26 am

by Anastasiia O

Edited and fact-checked:
July 14, 2026 at 10:26 am

To enhance your local-language expertise, generally we make use of an auto-translation plugin. Please word auto-translation will not be correct, so learn original article for exact info.

Boundless has introduced its enlargement into the substitute intelligence sector, with plans to deploy its distributed GPU community to help the rising demand for AI inference. The transfer extends the corporate’s current infrastructure, which was initially developed to energy zero-knowledge (ZK) proving workloads for the cryptocurrency trade.

“4 years in the past, we got down to resolve one arduous compute downside,” mentioned Shiv Shankar, CEO of Boundless. “Within the course of, we constructed one thing larger: a community for coordinating distributed GPU capability. AI now wants the identical basis at a a lot bigger scale. Open fashions are giving groups extra management over what they construct, however manufacturing inference remains to be constrained by value, capability, and reliability. Boundless is constructed to alter that.”

The corporate’s ZK proving community was designed to coordinate distributed GPU assets, schedule compute-intensive duties, and keep environment friendly operations throughout a number of machines. Boundless said that the identical infrastructure is now being tailored to deal with growing demand for AI inference as organizations broaden the deployment of synthetic intelligence functions.

In response to the corporate, AI inference is rising as a big driver of computing demand, with infrastructure prices changing into an more and more essential consideration. Citing Gartner, Boundless famous that 55% of spending on AI-optimized infrastructure-as-a-service is anticipated to be allotted to inference in 2026, growing to greater than 65% by 2029.

Boundless Repurposes GPU Community for AI Inference

Boundless said that many AI inference workloads don’t require premium knowledge heart GPUs and might as an alternative function effectively on lower-cost {hardware}, together with consumer-grade graphics processors and GPUs initially acquired for compute-intensive functions comparable to cryptocurrency mining and ZK proving. The corporate mentioned it goals to establish and optimize this underutilized capability by integrating {hardware}, software program, and inference-serving programs.

The corporate at present operates a distributed community of roughly 4,000 GPUs that was initially developed for ZK proving. As a part of its AI technique, Boundless is optimizing the community to supply managed inference infrastructure, together with {hardware} optimization, workload adaptation, routing, batching, scheduling, monitoring, and operational help.

Boundless reported that early benchmarking signifies inference prices could possibly be decreased by as a lot as 50% in contrast with hyperscale cloud suppliers, with the best potential financial savings anticipated for asynchronous workloads. The corporate additionally plans to combine its native ZKC token into the AI community, with operators anticipated to stake the token to take part and with staking ranges linked to incomes potential.

Boundless said that the enlargement is meant to allow organizations to deploy AI inference workloads with decrease computing prices. The transition to AI infrastructure was introduced in the present day, whereas the total product launch is scheduled for later this summer season. The corporate added that it’s going to proceed working its zero-knowledge proving community alongside its AI inference providers.

Alisa, a devoted journalist on the MPost, focuses on crypto, AI, investments, and the expansive realm of Web3. With a eager eye for rising developments and applied sciences, she delivers complete protection to tell and interact readers within the ever-evolving panorama of digital finance.

• 
  
  
  

More articles