LLM Inference Acceleration Using Parallel Submodels and Accelerators

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The increasing size of large language models (LLMs) leads to significant computational demands, resulting in prolonged inference times that adversely affect task execution efficiency.

Innovation Solution

Deploy LLMs on multiple hardware accelerators and segment them into submodels, performing first processing on input data through the LLMs and subsequent processing on the results through submodels until a stop inference condition is met, utilizing data and model parallelism to accelerate inference.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the size of the LLM model is increased to improve task execution capability, then the model's processing power and accuracy are improved, but the computational demands increase and inference time is prolonged

Engineering Contradiction:
Improvetask execution accuracyVSAvoidinference time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent divides the LLM into multiple submodels and deploys them across multiple hardware accelerators. During the prefilling stage, input data is segmented and processed in parallel by multiple LLMs. During the decoding stage, the model is segmented into submodels that process data in parallel. This segmentation enables concurrent processing without sacrificing model accuracy, thereby reducing inference time while maintaining task execution capability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from single-model sequential processing to multi-model parallel processing across multiple hardware accelerators. By introducing the dimension of parallelism across multiple devices, the system achieves faster inference speeds while maintaining the computational power of large models. The staged hybrid approach combines data parallelism and model parallelism to optimize inference across different stages.

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

2Productivity

If LLMs are deployed on multiple hardware accelerators to increase processing capacity, then inference speed is improved, but system complexity increases

Engineering Contradiction:
Improveinference speedVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the LLM into submodels and distributes them across multiple hardware accelerators, with each accelerator handling specific submodels or data portions. This segmentation enables parallel processing that improves inference speed while managing system complexity through structured distribution of computational tasks across independent units.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements dynamic task distribution where the system adapts its processing strategy based on the inference stage. During prefilling, data parallelism is used with multiple LLMs processing segmented input data. During decoding, model parallelism is used with submodels processing results sequentially. This dynamic adaptation optimizes performance while managing complexity through stage-specific strategies.

Inventive Principle:
Principle #15Dynamics

3Speed

If data parallelism is used during prefilling stage to process input data in parallel, then prefilling speed is improved, but communication overhead between hardware accelerators increases

Engineering Contradiction:
Improveprefilling speedVSAvoidcommunication overhead
Core Design Contradiction:
SpeedVSLoss of energy

Solution Approach 1:

The patent segments input data into multiple portions and distributes them across multiple hardware accelerators for parallel prefilling processing. Each accelerator processes its assigned data segment independently, then results are aggregated. This segmentation enables faster prefilling while managing communication overhead through structured data distribution and result collection protocols.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs data segmentation and distribution before the actual prefilling computation begins. By preparing the data distribution structure in advance, the system minimizes communication overhead during the computationally intensive prefilling stage, as data is already positioned for parallel processing without requiring dynamic communication during computation.

Inventive Principle:
Principle #10Preliminary action

4Speed

If model parallelism is used during decoding stage to process data through submodels in parallel, then decoding speed is improved, but memory requirements and system coordination complexity increase

Engineering Contradiction:
Improvedecoding speedVSAvoidsystem coordination complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The patent divides the LLM model into multiple submodels and distributes them across different hardware accelerators for parallel decoding processing. Each submodel handles specific portions of the decoding task, enabling faster inference while managing memory requirements through distributed storage and computation across multiple devices.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4708137A1Large language model-based inference acceleration method and apparatus, medium, and device
Publication Date: 2026.03.11 XG TECHNOLOGIES PTE LTD
  • EP4708137A1 patent drawingFigure 1
  • EP4708137A1 patent drawingFigure 2~3
  • EP4708137A1 patent drawingFigure 4

AI summary

A large language model (LLM)-based inference acceleration method and apparatus, a medium, and a device are disclosed. The method includes: determining (201) LLMs deployed on a plurality of first hardware accelerators, multiple submodels obtained through segmenting the LLMs and respectively deployed on a plurality of second hardware accelerators, and input data of a to-be-executed task; performing (202) first processing on the input data through the plurality of LLMs to obtain a first processing result; performing (203) second processing on the first processing result through the multiple submodels to obtain a second processing result; and determining (204) an execution result of the to-be-executed task in response to the second processing result meeting a stop inference condition.