@dMatrix (@dmatrix_ai) 's Twitter Profile
@dMatrix

@dmatrix_ai

d-Matrix built a new energy efficient way to run data centers with fast AI inference, digital in-memory compute + ultra-high bandwidth throughput.

ID: 1496639770264584192

linkhttps://www.dmatrix.ai/ calendar_today24-02-2022 00:17:02

139 Tweet

440 Takipçi

177 Takip Edilen

@dMatrix (@dmatrix_ai) 's Twitter Profile Photo
@dMatrix
@dmatrix_ai

4 months ago

Delivering “ultra low-latency batched inference” meant rethinking AI accelerator design to achieve high memory bandwidth + high memory capacity in a no-compromise solution for the datacenter. More: lnkd.in/gsucDDzQ #inference #datacenter #energyefficient_AI