Generation of Mixed-Precision Kernels for Quantized Transformer Encoders with Exo
- 24 November 2025
- book chapter
- Published by Springer Nature
- p. 431-443
Abstract
No abstract availableKeywords
This publication has 9 references indexed in Scilit:
- Portable, High Performance Matrix Multiplication Micro-Kernels for RISC-V with ExO2025
- Inference with Transformer Encoders on ARM and RISC-V Multicore Processors2024
- Tackling the Matrix Multiplication Micro-Kernel Generation with Exo2024
- Automatic Generation of Micro-kernels for Performance Portability of Matrix Multiplication on RISC-V Vector Processors2023
- Exocompilation for productive programming of hardware accelerators2022
- Analytical Modeling Is Enough for High-Performance BLISACM Transactions on Mathematical Software, 2016
- The BLIS FrameworkACM Transactions on Mathematical Software, 2016
- Anatomy of High-Performance Many-Threaded Matrix Multiplication2014
- Anatomy of high-performance matrix multiplicationACM Transactions on Mathematical Software, 2008