| Mobile Web

Search results for vLLM

AI & Enterprise

Dinotisia unveils KV cache compression technology to ease AI computing bottlenecks

AI infrastructure company Dinotisia said on Wednesday it has released a paper and source code for KV cache compression technology that stores previously read context on GPUs to avoid recalculation by large language models. The company said its STAR-KV technology, a joint effort involving UC San Diego’s VVIP Lab and Dinotisia researchers, was selected as an ICML 2026 Spotlight paper. It said tests showed up to 75 percent reduction and up to 20-fold compression.

AI & Enterprise

Red Hat says shift from AI consumer to provider to control costs

Red Hat is reshaping its platform strategy for the era of AI agents, focusing on an open-source full-stack platform spanning hardware to agents. CTO Chris Wright said token prices are falling but enterprise token consumption is rising sharply, making reliance on external APIs and proprietary frontier models difficult to sustain. He urged firms to shift from paying for outside services to operating AI on their own infrastructure, backed by Red Hat AI Enterprise.

Crypto

AI infrastructure investment to grow; expectations rise for AI coins on Nvidia tailwind

Nvidia’s market value surpassing $5 trillion is directly affecting the cryptocurrency market as expectations grow for AI-linked tokens. Traders are watching Nvidia’s performance and AI equipment investment trends as key variables for tokens such as Bittensor (TAO), Render (RNDR) and Fetch.ai (FET). Nvidia shares recently traded around $222 to $230 and hit a record close of $236.74 on May 14. Big tech firms are expected to invest $660 billion in AI infrastructure in 2026.