Up to 60% of GPU compute goes to recomputing context. Flash storage can put that capacity back to work
GPUs running large language model inference can spend up to 60% of their compute recalculating context they already processed, says Alan McSeveney, field CTO at WEKA. Speaking with VentureBeat lead analyst Rob Strechay at the latest stop in the VentureBeat AI Impact Series, McSeveney said the waste goes back to how large language models hold conversation history in GPU memory, arguing that fixing it lets companies serve several times more users on hardware they already own. The efficiencies WEKA customers struggle with most show up in infrastructure, separate from the application metrics each business tunes for its own domain.
VB Staff
Partner Content
Browser security’s buying spree rests on one engine, without a clear Plan B
Presented by CloudMosa
VB Staff
Partner Content
Agents need more than business process knowledge. They need to understand how your company actually works
Presented by SAP
VB Staff
Partner Content
AI agents can’t fix infrastructure failures they can’t diagnose
Presented by Virtana
VB Staff
Agentic security: Enterprises rely on OpenAI most to secure AI agents, and those that do are nearly three times as likely to say attackers are ahead
OpenAI's guardrails secure 40% of enterprise AI agents, but 43% of these organizations say attackers are ahead. 59% have faced security incidents or near-misses.
VB Staff
AI infrastructure and compute: 48% of organizations running AI in production name a Google platform as their primary AI platform, more than twice OpenAI's share
48% of enterprises running AI in production choose Google as their primary platform, outpacing OpenAI and Azure, according to a VentureBeat survey.
VB Staff
Agentic reliability and evaluations: Fewer enterprises plan to let AI agents ship production changes on automated checks alone — 56% allow it or plan to, down from 75% in July
56% of enterprises with AI agents allow automated production changes, down from 75% in July, highlighting trust issues in AI evaluations.
VB Staff
Agentic context layers: 64% of enterprises traced a confidently wrong AI agent answer to problems in their own company data in the past six months
64% of enterprises traced AI errors to data issues. Semantic layers help detect these errors, affecting decision-making processes.
VB Staff
Agentic orchestration: Model makers are selling their own AI agent platforms, but only 2% of enterprises say the model was the main reason they chose one
Survey shows 78% of enterprises value flexibility and control in AI platforms over model alignment, influencing orchestration decisions.
VB Staff
Partner Content
AI agents need more than access control — they need identity at runtime
Presented by Cisco
VB Staff
Partner Content
The defender's head start is gone. Cisco's Liz Centoni on the fight to get it back
Presented by Cisco
VB Staff