Intel Unveils AI Inference-Focused GPU D Series, Up to 480GB LPDDR5 Memory

At the Open Compute Project (OCP) Global Summit today, Intel shared new technical details on the Intel GPU D-series, formerly code-named Crescent Island. Intel GPU D-series is designed to improve the economics of sustained, memory-intensive AI inference. Built on Intel's latest Xe3P architecture, the GPU combines up to 480 GB of LPDDR5X memory, 1.5 TB/s of memory bandwidth and 1.3 petaflops of FP8 compute within a 350-watt power envelope. Designed for large language models, long-context workloads and concurrent inference services, Intel GPU D-series supports models with up to 300 billion parameters on a single card and more than one trillion parameters in an eight-GPU system.