Login / Signup
DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation.
Seongmin Hong
Seungjae Moon
Junsoo Kim
Sungjae Lee
Minsub Kim
Dongsoo Lee
Joo-Young Kim
Published in:
MICRO (2022)
Keyphrases
</>
low latency
text generation
high speed
natural language generation
real time
high bandwidth
highly efficient
high throughput
natural language
massive scale
virtual machine
low cost
continuous query processing
stream processing
expert systems
efficient implementation
data processing
information retrieval