# AI inference  

SAN JOSE, Calif.

SANTA CLARA, Calif.

The global shift from AI model training to large-scale inference has set off a sweeping upgrade cycle across data center memory — pushing demand well beyond graphics processors int......

The most significant software release in the company's history extends what's possible for agentic AI and other accelerated compute workloads. NeuralMesh 6 redefines inference economics with native multi-tenancy, a unified file-and-object protocol stack built on NVMe, intelligent data mobility with replication and remote caching support, always-on data reduction with performance guarantees, Kubernetes-native operations, and unified observability.

Joint benchmarks on OCI H100 infrastructure showed 10x more concurrent users, 10x higher token throughput, and 7x more tokens served without adding GPUs

Walk into any conversation about AI infrastructure and you will hear the same refrain: the bottleneck is GPU computing power. K.S. Pua (潘健成), chairman of Phison Electronics (群聯電子),......

Advanced Micro Devices CEO Lisa Su used a high-profile appearance in Taipei on Thursday to reframe the terms of competition in artificial intelligence infrastructure — arguing that......