Generation of Mixed-Precision Kernels for Quantized Transformer Encoders with Exo

Adrián Castelló 0001, Héctor Martínez 0002, Francisco D. Igual, Enrique S. Quintana-Ortí. Generation of Mixed-Precision Kernels for Quantized Transformer Encoders with Exo. In Sarah Neuwirth, Arnab Kumar Paul, Tobias Weinzierl, Erin Claire Carson, editors, High Performance Computing - ISC High Performance 2025 International Workshops, Hamburg, Germany, June 10-13, 2025, Revised Selected Papers. Volume 16091 of Lecture Notes in Computer Science, pages 431-443, Springer, 2025. [doi]

Abstract

Abstract is missing.