Large language model (LLM) control based on device temperature
Temperature-based control of LLMs addresses overheating issues by pausing or adjusting generation rates, ensuring comfortable device operation and efficient response output.
WO2026128163A1PCT designated stage Publication Date: 2026-06-18QUALCOMM INC
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- QUALCOMM INC
- Filing Date
- 2025-11-13
- Publication Date
- 2026-06-18
AI Technical Summary
⚠Technical Problem
Running large language models (LLMs) for multiple queries and large responses can lead to a rapid increase in device temperature, causing user discomfort due to higher surface temperatures.
⚗Method used
Implementing temperature-based control mechanisms that pause or adjust the generation of output data by the LLM based on sensor feedback, including pausing generation, adjusting generation rates, or modifying response lengths to manage device temperature.
🎯Benefits of technology
Reduces device temperature and improves performance by preventing overheating while maintaining effective response generation.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure US2025055406_18062026_PF_FP_ABST
Abstract
A device includes a memory device configured to store output data of a large language model (LLM). The device also includes one or more processors configured to obtain, from a temperature sensor, a first sensor output indicating a first temperature associated with the device. The one or more processors are configured to, based on the first temperature and first output data of the LLM, control generation of second output data by the LLM.
Need to check novelty before this filing date? Find Prior Art