Understanding and Optimizing Multi-Stage AI Inference Pipelines

• URL: http://arxiv.org/abs/2504.09775v3
• Date: Sun, 20 Apr 2025 19:57:16 GMT
• Title: Understanding and Optimizing Multi-Stage AI Inference Pipelines
• Authors: Abhimanyu Rajeshkumar Bambhaniya, Hanjiang Wu, Suvinay Subramanian, Sudarshan Srinivasan, Souvik Kundu, Amir Yazdanbakhsh, Midhilesh Elavazhagan, Madhu Kumar, Tushar Krishna,
• Abstract summary: HERMES is a Heterogeneous Multi-stage LLM inference Execution Simulator.<n> HERMES supports heterogeneous clients executing multiple models concurrently unlike prior frameworks.<n>We explore the impact of reasoning stages on end-to-end latency, optimal strategies for hybrid pipelines, and the architectural implications of remote KV cache retrieval.
• Score: 11.254219071373319
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The rapid evolution of Large Language Models (LLMs) has driven the need for increasingly sophisticated inference pipelines and hardware platforms. Modern LLM serving extends beyond traditional prefill-decode workflows, incorporating multi-stage processes such as Retrieval Augmented Generation (RAG), key-value (KV) cache retrieval, dynamic model routing, and multi step reasoning. These stages exhibit diverse computational demands, requiring distributed systems that integrate GPUs, ASICs, CPUs, and memory-centric architectures. However, existing simulators lack the fidelity to model these heterogeneous, multi-engine workflows, limiting their ability to inform architectural decisions. To address this gap, we introduce HERMES, a Heterogeneous Multi-stage LLM inference Execution Simulator. HERMES models diverse request stages; including RAG, KV retrieval, reasoning, prefill, and decode across complex hardware hierarchies. HERMES supports heterogeneous clients executing multiple models concurrently unlike prior frameworks while incorporating advanced batching strategies and multi-level memory hierarchies. By integrating real hardware traces with analytical modeling, HERMES captures critical trade-offs such as memory bandwidth contention, inter-cluster communication latency, and batching efficiency in hybrid CPU-accelerator deployments. Through case studies, we explore the impact of reasoning stages on end-to-end latency, optimal batching strategies for hybrid pipelines, and the architectural implications of remote KV cache retrieval. HERMES empowers system designers to navigate the evolving landscape of LLM inference, providing actionable insights into optimizing hardware-software co-design for next-generation AI workloads.

Related papers

• Automatic Operator-level Parallelism Planning for Distributed Deep Learning -- A Mixed-Integer Programming Approach [6.449961842220686]
  We propose a bi-level solution framework balancing optimality with computational efficiency.<n>Our framework achieves comparable or superior performance, reducing computational bubbles by half under the same memory constraints.<n>Such capabilities position our solution as both a valuable research tool for exploring optimal parallelization strategies and a practical industrial solution for large-scale AI deployment.
  arXiv  Detail & Related papers  (2025-03-12T13:00:29Z)
• SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding [66.74446220401296]
  We propose SynerGen-VL, a simple yet powerful encoder-free MLLM capable of both image understanding and generation. We introduce the token folding mechanism and the vision-expert-based progressive alignment pretraining strategy, which effectively support high-resolution image understanding. Our code and models shall be released.
  arXiv  Detail & Related papers  (2024-12-12T18:59:26Z)
• Survey and Evaluation of Converging Architecture in LLMs based on Footsteps of Operations [3.355436702348694]
  Current state-of-the-art LLMs are very large, with parameters around 70 billion. As the model sizes are growing, the demand for substantial storage and computational capacity increases. This paper analyzes how these converged architectures perform in terms of layer configurations, operational mechanisms, and model sizes.
  arXiv  Detail & Related papers  (2024-10-15T08:19:24Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• Performance Modeling and Workload Analysis of Distributed Large Language Model Training and Inference [2.2231908139555734]
  We propose a general performance modeling methodology and workload analysis of distributed LLM training and inference. We validate our performance predictions with published data from literature and relevant industry vendors (e.g., NVIDIA)
  arXiv  Detail & Related papers  (2024-07-19T19:49:05Z)
• 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)
• Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models [8.02264001053969]
  Large language models (LLMs) have shown remarkable performance across a wide range of applications, often outperforming human experts. With constant innovation in LLM serving optimizations and model architecture evolving at breakneck speed, the hardware requirements to meet Service Level Objectives (SLOs) remain an open research question. We present an analytical tool, GenZ, to efficiently navigate the relationship between diverse LLM model architectures and AI platform design parameters.
  arXiv  Detail & Related papers  (2024-06-03T18:00:50Z)
• Mechanistic Design and Scaling of Hybrid Architectures [114.3129802943915]
  We identify and test new hybrid architectures constructed from a variety of computational primitives. We experimentally validate the resulting architectures via an extensive compute-optimal and a new state-optimal scaling law analysis. We find MAD synthetics to correlate with compute-optimal perplexity, enabling accurate evaluation of new architectures.
  arXiv  Detail & Related papers  (2024-03-26T16:33:12Z)
• 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)
• Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration [71.95914457415624]
  Microprocessor architects are increasingly resorting to domain-specific customization in the quest for high-performance and energy-efficiency. We propose an alternative formulation that leverages Multi-Agent RL (MARL) to tackle this problem. Our evaluation shows that the MARL formulation consistently outperforms single-agent RL baselines.
  arXiv  Detail & Related papers  (2022-11-29T17:10:24Z)

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.