Intel Reveals GPU D-series Details and Introduces New Xeon Rack Design
Understand the story
At the OCP Global Summit, Intel announced via an official release new advances toward open infrastructure for the Agentic AI era, centered on technical details of its GPU D-series (codenamed Crescent Island). The GPU is based on the Xe3P architecture, with up to 480 GB of LPDDR5X memory, 1.5 TB/s memory bandwidth, 1.3 petaflops of FP8 compute, and 350 W power consumption. According to the announcement, a single card can run models with 300 billion parameters, and an 8-card system can support models exceeding 1 trillion parameters. The information comes directly from Intel's official announcement and is the latest development on this event.
AI overview of reporting · Updated 6 days ago
Reporting timeline
Explore different aspects of the story through its reporting.
- Intel Official AnnouncementsIntel Accelerates Open Infrastructure for the Agentic AI Era
At the OCP Global Summit, Intel detailed its GPU D-series (codenamed Crescent Island), built on the Xe3P architecture with up to 480 GB LPDDR5X memory, 1.5 TB/s memory bandwidth and 1.3 petaflops of FP8 compute at 350 watts; a single card supports 300-billion-parameter models and an 8-card system supports over 1 trillion parameters.
Story heat trend
Current heat3·Comparable peak10（10/13 04:00）·Comparable change over 24 hours -51%
The trend compares the same continuously observed sources, which may cover fewer sources than the current heat score. Hover or select the chart to inspect each hour; use the left and right arrow keys to navigate.