AI
Upgrade AI infra: Huawei OceanStor M900 offers 64PB KV cache to slash latency
Huawei unveiled a new storage platform at HUAWEI CONNECT 2026 that extends AI cache capacity and reduces data access delays for large models.
AI inference
Everything Vector Update has reported about AI inference: 2 stories, newest first. Part of our AI coverage.
AI
Intel reveals GPU D-Series specs for air-cooled AI inference servers
Intel names the Crescent Island chip the GPU D-Series, offering 1.3 PFLOPS FP8 performance in a standard server form factor.