D-Matrix Raptor 3D-DRAM Accelerator for Generative Inference at Hot Chips 2026

D-Matrix unveiled Raptor, a 3D-DRAM accelerator for generative inference, at Hot Chips 2026. It uses stacked DRAM instead of HBM to cut latency and cost. The post doesn't disclose performance figures or a ship date, but positions it as a dedicated inference chip, not a general-purpose GPU.