d-Matrix Blog

14 articles total

Dive into d-Matrix's engineering blog for deep dives on disaggregated AI inference pipelines, hardware acceleration, and the future of agentic coding networks.

AI Accelerator vs GPU: Why the Future of Inference Is Both
Accelerating attention-FFN disaggregation with Corsair and Nvidia H100: inside the industry’s first ultra-low latency heterogeneous pipeline
Frontier class ultra-low-latency rack-scale inference with Raptor XPUs and NVLINK Fusion
Introducing d-Matrix Demo Cloud: Ultra Low Latency Inference, Ready to Test in Minutes
Model sizes are exploding—and new memory architectures are the way forward
How disaggregated AI inference pipelines generate less heat — and smaller bills
The new perf/TCO math: maximizing GPU utilization with disaggregated pipelines
Advancing Full-Model AI Inference on Corsair with Infinity
IA for AI: The New Reader That Doesn’t Use the Nav Bar
How accelerating feed-forward networks in disaggregated inference pipelines power next-generation AI
Building apps on the phone: how heterogeneous pipelines enable speech-to-code experiences
Where heterogeneous pipelines power an agentic coding future
How speculative decoding supercharged AI inference in disaggregated pipelines
What does success mean for agentic networks?