Wiring and powering GPUs differently can swing AI latency by orders of magnitude, says CoreWeave
Neocloud buyers like LlamaIndex now weigh latency, burst capacity and openness over chip supply when renting compute from CoreWeave.
Via SiliconANGLE
Wiring and powering GPUs differently can swing AI latency by orders of magnitude, says CoreWeave
The neocloud market is moving past its origins as a stopgap for scarce graphics processing units. AI-native startups now choose their infrastructure on latency, burst capacity and openness, not just chip availability.
That shift is playing out at CoreWeave Inc., which is expanding beyond GPU compute into networking, storage and software as inference demand grows. At the same time, LlamaIndex Inc. has evolved from an…
Courtesy
This story was originally published by SiliconANGLE. All rights belong to the original publisher.
Read the original on siliconangle.com ↗