DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation.
Seongmin HongSeungjae MoonJunsoo KimSungjae LeeMinsub KimDongsoo LeeJoo-Young KimPublished in: CoRR (2022)
Keyphrases
- low latency
- text generation
- high speed
- real time
- natural language generation
- high bandwidth
- high throughput
- highly efficient
- continuous query processing
- natural language
- virtual machine
- massive scale
- theorem prover
- data acquisition
- stream processing
- low cost
- energy consumption
- multi dimensional
- data streams
- data mining