Each chip delivers up to 12.1 TB/s of internal bandwidth (96.8 Terabits) to the AI cores, but the data is fed to the CS-2 processors via 100 GbE networking spread across 124 server nodes in 16 racks, which is nice. https://t.co/m4JX2kJFLm
— Tren Griffin (@trengriffin) Nov 15, 2022
from Twitter https://twitter.com/trengriffin
November 15, 2022 at 08:09AM
via IFTTT
No comments:
Post a Comment