A resource-aware mixed-precision quantization technique plus BRAM-efficient VHDL changes enabled deployment of five previously non-deployable Transformer configurations on Spartan-7 FPGAs with 3% resource estimate accuracy.
arXiv preprint arXiv:2401.02721 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Resource-aware Mixed-precision Quantization for Enhancing Deployability of Transformers for Time-series Forecasting on Embedded FPGAs
A resource-aware mixed-precision quantization technique plus BRAM-efficient VHDL changes enabled deployment of five previously non-deployable Transformer configurations on Spartan-7 FPGAs with 3% resource estimate accuracy.