In a development that aligns with the industry-wide trend of building upon existing infrastructure nodes, Apple is reportedly looking to pair its upcoming “Baltra” ASIC with NVIDIA’s bespoke low-latency connectivity solution, which then opens up sizable optionality for Apple’s Private Compute inference architecture. Apple is reportedly going all-in on NVIDIA’s NVLink connectivity solution to maintain interoperability with its own M8 chip-based servers We already know that Apple has been working with Broadcom on its first AI server chip, which bears the internal codename “Baltra.” The Information has previously reported that the ASIC could leverage TSMC’s 3nm ‘N3E’ process, and bear […]
Read full article at https://wccftech.com/apple-eyes-nvidias-nvlink-fusion-for-its-m8-based-baltra-servers-signaling-a-return-to-enterprise-hardware-after-2011-exit/