NuAxiSemiconductor trade intelligence
DDN, Nvidia team up to cut inference costs and boost GPU utilization
What happened
DDN and Nvidia announced a partnership to optimize AI inference, claiming up to 27x faster KV cache loading and double-digit cost reductions via software-defined storage and BlueField-4 DPUs. This collaboration aims to improve GPU utilization and reduce inference costs for enterprises. Watch: The technology breakthrough may reshape the cost structure of the AI inference market and impact hardware demand.
Impact and signal
Low impactImpact score: 25/100
Affected components and suppliers
GPUStorage SystemsKV CacheDPUsInfinia OS
partnershipinferenceoptimizationcost-reduction
Source and time
Source: Blocks & Files · 3/17/2026 · View original source
Open the NuAxi live feed →
Real-time pricing, supply signals and AI analysis for semiconductor traders