Nvidia And d-Matrix Announce Collaboration Roadmap For Fast Inference

Nvidia is partnering with d-Matrix on a disaggregated inference solution that pairs d-Matrix's SRAM-based chips for AI decode with Nvidia GPUs for encoding, according to Forbes contributor Karl Freund. The collaboration roadmap targets faster AI inference by splitting decode and encode work across the two vendors' hardware.

Nvidia And d-Matrix Announce Collaboration Roadmap For Fast Inference By Karl Freund, ContributorSource: Forbes Innovation https://www.forbes.com/innovation/ Nvidia /glossary/nvidia is partnering with d-Matrix to offer disaggregated inference /glossary/inference solution, utilizing d-Matrix's SRAM-based chips for AI decode alongside Nvidia GPUs for encoding. Get AI news in your inbox Daily digest of what matters in AI.