Dynamische, Schlanke Transformatoren

Details

Veröffentlichungs-Nr.

EP4733956

Anmeldetag

15. April 2025

Veröffentlichung

29. April 2026

Rechtsraum

EP

IPC

G06F16/903, G06N20/00

Abstract

A system and method for dynamically optimizing large language model (LLM) inference by selectively deactivating layers based on query complexity. A multi-label classifier is trained on diverse user queries and their optimal layer configurations. During inference, the classifier analyzes incoming queries to predict which LLM layers can be safely deactivated without compromising output quality. The system processes user queries through the LLM with the predicted layer configuration, reducing computational resources while maintaining accuracy. A database stores historical queries, layer configurations, and performance metrics for continuous system improvement.

Anmelder

Firma

Intuit Inc.

Land

🇺🇸 USA

Fachgebiete