LLM Tensor Network Compression for Resource Efficiency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Large Language Models (LLMs) require significant computational resources for training and operation, making it challenging to run them on classical computing devices due to high memory and energy demands.

Innovation Solution

The method involves integrating pre-trained layers of LLM architectures into tensor network layers, which reduces the parameter space by representing some parameters as compilations of others, using tensor networks to efficiently store and process model parameters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If LLM uses massive amounts of parameters for training, then language understanding and generation abilities are improved, but computational resources and energy consumption increase

Engineering Contradiction:
Improvelanguage understanding and generation abilitiesVSAvoidcomputational resources and energy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent segments the LLM parameters into tensor network components, decomposing the weight matrices into a set of tensors connected by contraction operations. This segmentation allows the model to represent parameters more efficiently by sharing computational structures across different layers, reducing the total number of parameters needed while maintaining language understanding and generation capabilities.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the representation of parameters from traditional dense weight matrices to tensor network formulations. By transforming parameters into a different mathematical representation with shared structures, the model achieves parameter efficiency without sacrificing performance, directly addressing the contradiction between model capability and resource consumption.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If LLM uses massive amounts of parameters, then model accuracy is improved, but storage requirements and device complexity increase

Engineering Contradiction:
Improvemodel accuracyVSAvoidstorage requirements and device complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges parameter representations across different layers by using shared tensors in the tensor network. Instead of storing independent weight matrices for each layer, the model uses a unified tensor network structure where tensors are shared and contracted across layers, significantly reducing storage requirements while maintaining model accuracy.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent transitions from a traditional matrix-based parameter representation to a multi-dimensional tensor network structure. This dimensional transformation allows for more efficient parameter organization and storage, reducing the complexity of device requirements while preserving the model's accuracy through the tensor contraction operations.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Device complexity

If LLM parameters are compressed using traditional methods, then storage requirements are reduced, but model accuracy deteriorates

Engineering Contradiction:
Improvestorage requirementsVSAvoidmodel accuracy
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent performs preliminary action by pre-computing and storing the tensor network decomposition of weight matrices. This preliminary processing allows the model to achieve compression benefits during inference without sacrificing accuracy, as the tensor network structure preserves the essential computational relationships needed for accurate language processing.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent creates a compressed representation of the model parameters through tensor network copying, where the essential computational information is replicated in a more efficient format. This copying process maintains model accuracy by preserving the functional relationships between parameters while reducing storage requirements through the tensor network's shared structure.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4535234A1System and method for compressing large language model using tensor networks
Publication Date: 2025.04.09 MULTIVERSE COMPUTING SL
  • EP4535234A1 patent drawingFigure 1
  • EP4535234A1 patent drawingFigure 2
  • EP4535234A1 patent drawingFigure 3

AI summary

A computer implemented method for compressing pre-trained of a large language model (LLM) comprising identifying (S101) layers of the LLM (47) with the weight matrices (48), decomposing (S 104a) the weight matrices (48) of the LLM (47) into a tensor network (49), compressing (S104b) the tensor network (49), and storing (S104c) the compressed tensor network (49) in a data storage unit (40).