FeedSources
⌘K
DB

d-Matrix Blog

9 articles total

Go to source

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

Go to source
  •  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?