At the Open Compute Project Global Summit, Intel unveiled its D-Series GPU for AI inference, codenamed Crescent Island and named D270 on the product page. This accelerator card can be configured with up to 480GB of LPDDR5X memory. Intel stated that a single card can handle models with up to 300 billion parameters, while an eight-card system can run models with over 1 trillion parameters. Its design goal is to process long-context and multi-stream concurrent inference, rather than traditional gaming graphics rendering.
