Article 76BN1 GateGPT: 56k tokens per second Transformer (KV cache) on FPGA at 80 MHz

GateGPT: 56k tokens per second Transformer (KV cache) on FPGA at 80 MHz

by
from Hacker News on (#76BN1)
Story ImageComments
External Content
Source RSS or Atom Feed
Feed Location http://news.ycombinator.com/rss
Feed Title Hacker News
Feed Link https://news.ycombinator.com/
Reply 0 comments