Nvidia Teams up with Chip Rival D-Matrix on Inference

Nvidia teams up with chip rival d-Matrix on inference

Nvidia has found a new way to handle its chip rivals: work with them. The GPU giant is combining its hardware with inference chips from the startup d-Matrix, The Information reported. The two will ship a joint system to run AI models. The AI-cloud firm Parasail will be its first customer, with the system due […] This story continues at The Next Web

Parasail to Combine NVIDIA AI Infrastructure with d-Matrix Accelerators to Achieve 10x Faster Token Generation

Open the article to view the coverage from AiThority

Parasail deploys d-Matrix accelerators for AI inference

Parasail and d-Matrix announced Parasail is deploying d-Matrix Corsair inference accelerators alongside the NVIDIA Hopper and NVIDIA Blackwell architectures to deliver up to 10x faster, more cost-efficient inference services to its customers. Parasail’s Corsair deployment marks one of the first commercial-scale examples of heterogeneous disaggregated inference in production, where NVIDIA AI infrastructure and d-Matrix’s purpose-built Corsair inf…

Nvidia and AI chip startup d-Matrix are combining their hardware in a new system to power AI models, the latest example of Nvidia partnering with rivals (Phoebe Liu/The Information)

Top news and commentary for technology's leaders, from all around the web.