HeteroLLM: Accelerating Large Language Model Inference on Mobile SoCs platform with Heterogeneous AI Accelerators

• URL: http://arxiv.org/abs/2501.14794v1
• Date: Sat, 11 Jan 2025 02:42:02 GMT
• Title: HeteroLLM: Accelerating Large Language Model Inference on Mobile SoCs platform with Heterogeneous AI Accelerators
• Authors: Le Chen, Dahu Feng, Erhu Feng, Rong Zhao, Yingrui Wang, Yubin Xia, Haibo Chen, Pinjie Xu,
• Abstract summary: HeteroLLM is the fastest LLM inference engine in mobile devices which supports both layer-level and tensor-level heterogeneous execution. Evaluation results show that HeteroLLM achieves 9.99 and 4.36 performance improvement over other mobile-side LLM inference engines.
• Score: 7.377592753635839
• License:
• Abstract: With the rapid advancement of artificial intelligence technologies such as ChatGPT, AI agents and video generation,contemporary mobile systems have begun integrating these AI capabilities on local devices to enhance privacy and reduce response latency. To meet the computational demands of AI tasks, current mobile SoCs are equipped with diverse AI accelerators, including GPUs and Neural Processing Units (NPUs). However, there has not been a comprehensive characterization of these heterogeneous processors, and existing designs typically only leverage a single AI accelerator for LLM inference, leading to suboptimal use of computational resources and memory bandwidth. In this paper, we first summarize key performance characteristics of mobile SoC, including heterogeneous processors, unified memory, synchronization, etc. Drawing on these observations, we propose different tensor partition strategies to fulfill the distinct requirements of the prefill and decoding phases. We further design a fast synchronization mechanism that leverages the unified memory address provided by mobile SoCs. By employing these techniques, we present HeteroLLM, the fastest LLM inference engine in mobile devices which supports both layer-level and tensor-level heterogeneous execution. Evaluation results show that HeteroLLM achieves 9.99 and 4.36 performance improvement over other mobile-side LLM inference engines: MLC and MNN.

Related papers

• Inference Optimization of Foundation Models on AI Accelerators [68.24450520773688]
  Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI. As the number of model parameters reaches to hundreds of billions, their deployment incurs prohibitive inference costs and high latency in real-world scenarios. This tutorial offers a comprehensive discussion on complementary inference optimization techniques using AI accelerators.
  arXiv  Detail & Related papers  (2024-07-12T09:24:34Z)
• Memory Is All You Need: An Overview of Compute-in-Memory Architectures for Accelerating Large Language Model Inference [2.9302211589186244]
  Large language models (LLMs) have transformed natural language processing, enabling machines to generate human-like text and engage in meaningful conversations. Developments in computing and memory capabilities are lagging behind, exacerbated by the discontinuation of Moore's law. compute-in-memory (CIM) technologies offer a promising solution for accelerating AI inference by directly performing analog computations in memory.
  arXiv  Detail & Related papers  (2024-06-12T16:57:58Z)
• Deep Learning Inference on Heterogeneous Mobile Processors: Potentials and Pitfalls [22.49750818224266]
  A growing demand to deploy computation-intensive deep learning (DL) models on resource-constrained mobile devices for real-time intelligent applications. Mobile devices hold potential to accelerate DL inference via parallel execution across heterogeneous processors. This paper presents a holistic empirical study to assess the capabilities and challenges associated with parallel DL inference on heterogeneous mobile processors.
  arXiv  Detail & Related papers  (2024-05-03T04:47:23Z)
• Efficient and Economic Large Language Model Inference with Attention Offloading [11.698376311689456]
  Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but introduce significant challenges in real-world serving. This mismatch arises from the autoregressive nature of LLMs, where the generation phase comprises operators with varying resource demands. To enhance the efficiency and cost-effectiveness of LLM serving, we introduce the concept of attention offloading.
  arXiv  Detail & Related papers  (2024-05-03T02:15:15Z)
• MELTing point: Mobile Evaluation of Language Transformers [8.238355633015068]
  We explore the current state of mobile execution of Large Language Models (LLMs) We have created our own automation infrastructure, MELT, which supports the headless execution and benchmarking of LLMs on device. We evaluate popular instruction fine-tuned LLMs and leverage different frameworks to measure their end-to-end and granular performance.
  arXiv  Detail & Related papers  (2024-03-19T15:51:21Z)
• Using the Abstract Computer Architecture Description Language to Model AI Hardware Accelerators [77.89070422157178]
  Manufacturers of AI-integrated products face a critical challenge: selecting an accelerator that aligns with their product's performance requirements. The Abstract Computer Architecture Description Language (ACADL) is a concise formalization of computer architecture block diagrams. In this paper, we demonstrate how to use the ACADL to model AI hardware accelerators, use their ACADL description to map DNNs onto them, and explain the timing simulation semantics to gather performance results.
  arXiv  Detail & Related papers  (2024-01-30T19:27:16Z)
• Machine Learning Insides OptVerse AI Solver: Design Principles and Applications [74.67495900436728]
  We present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI solver. We showcase our methods for generating complex SAT and MILP instances utilizing generative models that mirror multifaceted structures of real-world problem. We detail the incorporation of state-of-the-art parameter tuning algorithms which markedly elevate solver performance.
  arXiv  Detail & Related papers  (2024-01-11T15:02:15Z)
• Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures [68.91874045918112]
  adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks. We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
  arXiv  Detail & Related papers  (2023-03-25T14:40:59Z)
• Asynchronous Parallel Incremental Block-Coordinate Descent for Decentralized Machine Learning [55.198301429316125]
  Machine learning (ML) is a key technique for big-data-driven modelling and analysis of massive Internet of Things (IoT) based intelligent and ubiquitous computing. For fast-increasing applications and data amounts, distributed learning is a promising emerging paradigm since it is often impractical or inefficient to share/aggregate data. This paper studies the problem of training an ML model over decentralized systems, where data are distributed over many user devices.
  arXiv  Detail & Related papers  (2022-02-07T15:04:15Z)
• How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures [7.085772863979686]
  Deep neural networks (DNNs) have led to large strides in various Artificial Intelligence (AI) inference tasks, such as object and speech recognition. deploying such AI models across commodity devices faces significant challenges. We present techniques for achieving real-time performance following a cross-stack approach.
  arXiv  Detail & Related papers  (2021-06-21T11:23:12Z)
• Reconfigurable Intelligent Surface Assisted Mobile Edge Computing with Heterogeneous Learning Tasks [53.1636151439562]
  Mobile edge computing (MEC) provides a natural platform for AI applications. We present an infrastructure to perform machine learning tasks at an MEC with the assistance of a reconfigurable intelligent surface (RIS) Specifically, we minimize the learning error of all participating users by jointly optimizing transmit power of mobile users, beamforming vectors of the base station, and the phase-shift matrix of the RIS.
  arXiv  Detail & Related papers  (2020-12-25T07:08:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.