COMPILER-BASED DEEP LEARNING MODEL PRUNING APPARATUS AND METHOD
Number of patents in Portfolio can not be more than 2000
United States of America
Stats
-
N/A
Issued Date -
Apr 10, 2025
app pub date -
Mar 21, 2024
filing date -
Mar 21, 2024
priority date (Note) -
Published
status (Latency Note)
Importance
Abstract
Disclosed herein are a compiler-based deep learning model pruning apparatus and method. The compiler-based deep learning model pruning method includes extracting multiple subgraphs from a first deep learning model, generating programs representing respective tasks allocated to the extracted multiple subgraphs, compiling the first deep learning model based on selected programs and measuring execution times of tasks of the first deep learning model on respective devices, and creating a second deep learning model by pruning a subgraph corresponding to at least one task selected from among the tasks from the first deep learning model based on the execution times on the respective devices.
First Claim
Other Claims data not available