Skip to main content
Back to News
MangoBoost and Preferred Networks to test heterogeneous AI inference architecture
Partnership
2 min read
JP

MangoBoost and Preferred Networks to test heterogeneous AI inference architecture

The AMW Read

The partnership proposes a specific heterogeneous hardware architecture, but its feasibility and performance remain unverified.
NoveltySignificance
AI Infra · Player MapSilicon Substrate

MangoBoost and Preferred Networks to test heterogeneous AI inference architecture

MangoBoost and Japan's Preferred Networks plan to collaborate on infrastructure that divides AI inference work across different processors. Under a memorandum of understanding announced for exchange at SC26 in Chicago, the companies intend to combine GPUs and Preferred Networks' MN-Core processors with MangoBoost's data processing units and memory and storage optimization technology. The proposed design assigns prompt processing, or prefill, to GPUs and token generation, or decode, to MN-Core processors.

The collaboration adds a proposed hardware configuration to the AI infrastructure market, where inference systems must coordinate compute, networking, memory, and storage. Separating prefill and decode gives each stage its own processor role, making the connections between those components central to the design. The companies intend to test whether this architecture is technically feasible; the announcement does not establish that it improves performance or lowers costs.

For builders and investors, the next evidence will come from system integration tests in a simulated environment. The partners plan to expand performance testing to physical equipment once samples of Preferred Networks' MN-Core L1000 are available. They may also publish joint research papers and technical materials, depending on the evaluation results. Until those tests are complete, the partnership is a research commitment rather than evidence of a production-ready system.

#AIInfrastructure #AIInference #Semiconductors #HeterogeneousComputing #MangoBoost

#MangoBoost#Preferred Networks#AI inference#heterogeneous computing#related:MangoBoost

How This Connects

Based on AI Infra · Player Map

  1. 4d agoMangoBoost and Preferred Networks to test heterogeneous AI inference architecture · THIS ARTICLE
  2. 3w agoNVIDIA opens Vera Rubin rack designs for denser AI data centersNVIDIA
  3. 1mo agoMicrosoft plans multigigawatt Maia deployment from 2027 with inference-focused Maia 300Microsoft
  4. 1mo agoMicrosoft announces Maia 300, targeting primary inference role in 2027Microsoft

More news from MangoBoost

Stay updated with the latest news and announcements from MangoBoost.

View all MangoBoost news

Discover AI Startups

Explore 5,000+ AI companies with VC-grade analysis, funding data, and investment insights.

Explore Dashboard