Understand and Accelerate Memory Processing Pipeline for Disaggregated LLM Inference

• URL: http://arxiv.org/abs/2603.29002v1
• Date: Mon, 30 Mar 2026 21:03:39 GMT
• Title: Understand and Accelerate Memory Processing Pipeline for Disaggregated LLM Inference
• Abstract summary: Large language models rely on efficient long-context processing and generation mechanisms to support complex reasoning.<n>We show that these optimizations can be unified into a four-step memory processing pipeline: Prepare Memory, Compute Relevancy, Retrieval, and Apply to Inference.<n>Motivated by this insight, we argue that textbfheterogeneous systems are well-suited to accelerate memory processing and thus end-to-end inference.
• Score: 45.78442013449325
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex reasoning. We show that these optimizations can be unified into a four-step memory processing pipeline: Prepare Memory, Compute Relevancy, Retrieval, and Apply to Inference. Through systematic profiling, we identify a 22%-97% memory processing overhead in LLM inference and strong heterogeneity in its computational characteristics. Motivated by this insight, we argue that \textbf{heterogeneous systems} are well-suited to accelerate memory processing and thus end-to-end inference. We demonstrate this approach on a GPU-FPGA system by offloading sparse, irregular, and memory-bounded operations to FPGAs while retaining compute-intensive operations on GPUs. Evaluated on an AMD MI210 GPU and an Alveo U55C FPGA, our system is $1.04\sim2.2\times$ faster and requires $1.11\sim4.7\times$ less energy across multiple LLM inference optimizations than the GPU baseline (similar results hold on NVIDIA A100). These results establish heterogeneous systems as a practical direction for efficient LLM memory processing and inform future heterogeneous hardware design.

Related papers

• Spava: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention [63.69228529380251]
  Spava is a sequence-parallel framework with optimized attention for long-video inference.<n>Spava delivers speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB, without notable performance loss.
  arXiv  Detail & Related papers  (2026-01-29T09:23:13Z)
• Beyond GEMM-Centric NPUs: Enabling Efficient Diffusion LLM Sampling [14.471123653746275]
  Diffusion Large Language Models (dLLMs) introduce iterative denoising to enable parallel token generation.<n>Our design employs lightweight non-GEMM vector primitives, in-place memory reuse strategies, and a decoupled mixed-precision memory hierarchy.
  arXiv  Detail & Related papers  (2026-01-28T15:37:50Z)
• LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAs [14.676146518251185]
  We present LUT-LLM, the first FPGA accelerator enabling 1B+ LLM inference via vector-quantized memory operations.<n>LUT-LLM achieves 1.66x lower latency than AMD MI210 and 1.72x higher energy efficiency than NVIDIA A100, scaling to 32B models with 2.16x efficiency gain over A100.
  arXiv  Detail & Related papers  (2025-11-09T01:17:08Z)
• From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents [79.87304940020256]
  Large Language Models (LLMs) have been widely adopted in conversational agents.<n>MemGAS is a framework that enhances memory consolidation by constructing multi-granularity association, adaptive selection, and retrieval.<n> Experiments on four long-term memory benchmarks demonstrate that MemGAS outperforms state-of-the-art methods on both question answer and retrieval tasks.
  arXiv  Detail & Related papers  (2025-05-26T06:13:07Z)
• POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference [9.164093249308419]
  We present POD-Attention - the first GPU kernel that efficiently computes attention for hybrid batches.<n> POD-Attention aims to maximize the utilization of both compute and memory bandwidth by carefully allocating the GPU's resources.
  arXiv  Detail & Related papers  (2024-10-23T17:06:56Z)
• EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference [49.94169109038806]
  This paper introduces EPS-MoE, a novel expert pipeline scheduler for MoE that surpasses the existing parallelism schemes.<n>Our results demonstrate at most 52.4% improvement in prefill throughput compared to existing parallel inference methods.
  arXiv  Detail & Related papers  (2024-10-16T05:17:49Z)
• The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines [6.381783966294295]
  Open-source large language models (LLMs) enable developers to create AI-based solutions while maintaining control over aspects such as privacy and compliance. We analyze the performance, particularly the throughput (tokens generated per unit of time) of 20 LLMs using two inference libraries: vLLM and HuggingFace's pipelines.
  arXiv  Detail & Related papers  (2024-08-02T06:56:59Z)
• vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving [53.972175896814505]
  Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests.
  arXiv  Detail & Related papers  (2024-07-22T14:37:58Z)
• Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference [23.633481089469836]
  Auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance.<n>We propose a novel parallel prompt decoding that requires only $0.0002$% trainable parameters, enabling efficient training on a single A100-40GB GPU in just 16 hours.<n>Our approach demonstrates up to 2.49$times$ speedup and maintains a minimal memory overhead of just $0.0004$%.
  arXiv  Detail & Related papers  (2024-05-28T22:19:30Z)
• Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference [11.614722231006695]
  Large language models (LLMs) boasting billions of parameters have generated a significant demand for efficient deployment in inference workloads. This paper investigates the feasibility and potential of model-specific spatial acceleration for LLM inference on FPGAs.
  arXiv  Detail & Related papers  (2023-12-23T04:27:06Z)
• FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs [57.12856172329322]
  We envision a decentralized system unlocking the potential vast untapped consumer-level GPU. This system faces critical challenges, including limited CPU and GPU memory, low network bandwidth, the variability of peer and device heterogeneity.
  arXiv  Detail & Related papers  (2023-09-03T13:27:56Z)
• 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)

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.