d-Matrix Raptor 3D-DRAM Accelerator for Generative Inference at Hot Chips 2026
d-Matrix is presenting its new Raptor 3D-DRAM accelerator at Hot Chips 2026, aiming to solve bandwidth and capacity bottlenecks in generative AI inference. The technology stacks compute directly onto DRAM to overcome the limitations of traditional SRAM and HBM architectures.
Why it matters
This innovation addresses the critical hardware constraints currently limiting the scaling and efficiency of large-scale generative AI models.
Next up, d-Matrix is presenting its Raptor 3D-DRAM accelerator for generative inference at Hot Chips 2026. The company has made waves, and we have covered it before, including the d-Matrix Corsair In-Memory Computing for AI Inference at Hot Chips 2025 . We also found they were doing networking in The New d-Matrix JetStream 400G Ethernet Card for Data Center Scale AI Inference . Let us see what they have going on this year.
This is being done live, so please excuse typos.
Model weights keep growing, and the KV cache scales with context length multiplied by batch size. So 64 users at 1M context can mean roughly 935 GB of KV cache. Weights and cache together create a problem that is both a capacity problem and a bandwidth problem, and both sides keep growing.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in