2 papers
cs.LG2026
GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
Jette Oberländer, Jan Finkbeiner, Catherine M. Schöfmann +1
Autoregressive decoding with LLMs is primarily bottlenecked by GPU memory bandwidth, especially in edge-computing settings. While quantization is essential for mitigating this bott…
cs.DC2026
Continuous benchmarking: Keeping pace with an evolving ecosystem of models and technologies
Jan Vogelsang, Melissa Lober, Catherine Mia Schöfmann +7
Drawing on ideas from continuous integration, we present concepts of an automated benchmarking pipeline for high performance applications. Customization and collaboration have been…