公开(公告)号：US20240119283A1

公开(公告)日：2024-04-11

申请号：US18377315

申请日：2023-10-06

Applicant: MEDIATEK INC.

Inventor： Jui-Yang Hsu ,  Cheng-Sheng Chan ,  Jen-Chieh Tsai ,  Huai-Ting Li ,  Bo-Yu Kuo ,  Yen-Hao Chen ,  Kai-Ling Huang ,  Ping-Yuan Tseng ,  Tao Tu ,  Sheng-Je Hung

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A method of performing automatic tuning on a deep learning model includes: utilizing an instruction-based learned cost model to estimate a first type of operational performance metrics based on a tuned configuration of layer fusion and tensor tiling; utilizing statistical data gathered during a compilation process of the deep learning model to determine a second type of operational performance metrics based on the tuned configuration of layer fusion and tensor tiling; performing an auto-tuning process to obtain a plurality of optimal configurations based on the first type of operational performance metrics and the second type of operational performance metrics; and configure the deep learning model according to one of the plurality of optimal configurations.

公开(公告)号：US20250156708A1

公开(公告)日：2025-05-15

申请号：US18939492

申请日：2024-11-06

Applicant: MEDIATEK INC.

Inventor： Tzu-Yun Chien ,  Bo-Yu Kuo ,  Jui-Yang Hsu ,  Kai-Ling Huang ,  Sheng-Je Hung

IPC: G06N3/08

Abstract: A method for optimizing deep learning models includes: initializing a plurality of pools, each including a plurality of candidate solutions; concurrently performing a plurality of tuning algorithms respectively within the plurality of pools during a single tuning run, thereby obtaining a plurality of selected candidate solutions; and generating an optimized model configuration based on the plurality of selected candidate solutions.

公开(公告)号：US20250156043A1

公开(公告)日：2025-05-15

申请号：US18943973

申请日：2024-11-12

Applicant: MEDIATEK INC.

Inventor： Kai-Ling Huang ,  Ting-An Chien ,  Yun-Chan Tsai ,  Cheng-Sheng Chan ,  Sheng-Je Hung

IPC: G06F3/0484 ,  G06F3/04815 ,  G06F3/0482 ,  G06N3/126

Abstract: A method for controlling an auto-tuning process with aid of an interactive graphical user interface (GUI) and associated apparatus (e.g., a computer) for running the interactive GUI are provided. The method may include: executing, by using a processing circuit within an electronic device, the auto-tuning process, for tuning a plurality of genetic-algorithm parameters (GA parameters) of a predetermined genetic algorithm; and during tuning the plurality of GA parameters, utilizing the interactive GUI to consolidate and aggregate real-time tuning data from the auto-tuning process in order to visualize the auto-tuning process with the interactive GUI, wherein visualizing the auto-tuning process with the interactive GUI may include generating at least one plot illustrating at least the real-time tuning data, for facilitating and accelerating interaction between a user and the auto-tuning process.