LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure

• URL: http://arxiv.org/abs/2602.23036v1
• Date: Thu, 26 Feb 2026 14:22:17 GMT
• Title: LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
• Authors: Jaehong Cho, Hyunmin Choi, Guseul Heo, Jongse Park,
• Abstract summary: Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneous and disaggregation.<n>This paper presents LLMServingSim 2.0, a unified system-level simulator designed to make runtime-driven hardware-software interactions explicit and analyzable.
• Score: 4.1898448424363695
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneity and disaggregation. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing significant hardware heterogeneity, while system software increasingly separates computation, memory, and model components across distributed resources to improve scalability and efficiency. As a result, LLM serving performance is no longer determined by hardware or software choices in isolation, but by their runtime interaction through scheduling, data movement, and interconnect behavior. However, understanding these interactions remains challenging, as existing simulators lack the ability to jointly model heterogeneous hardware and disaggregated serving techniques within a unified, runtime-driven framework. This paper presents LLMServingSim 2.0, a unified system-level simulator designed to make runtime-driven hardware-software interactions in heterogeneous and disaggregated LLM serving infrastructures explicit and analyzable. LLMServingSim 2.0 embeds serving decisions and hardware behavior into a single runtime loop, enabling interaction-aware modeling of batching, routing, offloading, memory, and power. The simulator supports extensible integration of emerging accelerators and memory systems through profile-based modeling, while capturing dynamic serving behavior and system-level effects. We validate LLMServingSim 2.0 against real deployments, showing that it reproduces key performance, memory, and power metrics with an average error of 0.97%, while maintaining simulation times of around 10 minutes even for complex configurations. These results demonstrate that LLMServingSim 2.0 provides a practical bridge between hardware innovation and serving-system design, enabling systematic exploration and co-design for next-generation LLM serving infrastructures.

Related papers

• LLMServingSim2.0: A Unified Simulator for Heterogeneous Hardware and Serving Techniques in LLM Infrastructure [4.382902234869111]
  This paper introduces LLMServingSim2.0, a system simulator designed for exploring heterogeneous hardware in large-scale LLM serving systems.<n>It addresses two key limitations of its predecessor: (1) integrating hardware models into system-level simulators is non-trivial due to the lack of a clear abstraction, and (2) existing simulators support only a narrow subset of serving techniques.
  arXiv  Detail & Related papers  (2025-11-10T15:47:53Z)
• CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks [57.95170323315603]
  We introduce CollaPipe, a distributed learning framework that integrates collaborative pipeline parallelism with federated aggregation to support self-evolving networks.<n>In CollaPipe, the encoder part is adaptively partitioned into variable-sized segments and deployed across mobile devices for pipeline-parallel training, while the decoder is deployed on edge servers to handle generative tasks.<n>To enhance training efficiency, we formulate a joint optimization problem that adaptively allocates model segments, micro-batches, bandwidth, and transmission power.
  arXiv  Detail & Related papers  (2025-09-24T07:54:01Z)
• Scalable Engine and the Performance of Different LLM Models in a SLURM based HPC architecture [3.746889836344766]
  This work elaborates on a High performance computing architecture based on Simple Linux Utility for Resource Management (SLURM)<n> Dynamic resource scheduling and seamless integration of containerized have been leveraged to manage CPU, GPU, and memory efficiently in multi-node clusters.<n>The obtained results pave ways for significantly more efficient, responsive, and fault-tolerant LLM inference on large-scale HPC infrastructures.
  arXiv  Detail & Related papers  (2025-08-25T09:11:27Z)
• Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition [95.54406667705999]
  Pangu Embedded is an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs)<n>It addresses the significant computational costs and inference latency challenges prevalent in existing reasoning-optimized LLMs.<n>It delivers rapid responses and state-of-the-art reasoning quality within a single, unified model architecture.
  arXiv  Detail & Related papers  (2025-05-28T14:03:02Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• AutoHete: An Automatic and Efficient Heterogeneous Training System for LLMs [68.99086112477565]
  Transformer-based large language models (LLMs) have demonstrated exceptional capabilities in sequence modeling and text generation.<n>Existing heterogeneous training methods significantly expand the scale of trainable models but introduce substantial communication overheads and CPU workloads.<n>We propose AutoHete, an automatic and efficient heterogeneous training system compatible with both single- GPU and multi- GPU environments.
  arXiv  Detail & Related papers  (2025-02-27T14:46:22Z)
• Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels [12.77187564450236]
  We introduce XY-Serve, a versatile, Ascend native, end-to-end production large language model (LLM) serving system.<n>The core idea is an abstraction mechanism that smooths out the workload variability by decomposing computations into fine-grained meta primitives.<n>For GEMM, we introduce a virtual padding scheme that adapts to dynamic shape changes while using highly efficient GEMM primitives with assorted fixed tile sizes.
  arXiv  Detail & Related papers  (2024-12-24T02:27:44Z)
• DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution [114.61347672265076]
  Development of MLLMs for real-world robots is challenging due to the typically limited computation and memory capacities available on robotic platforms. We propose a Dynamic Early-Exit Framework for Robotic Vision-Language-Action Model (DeeR) that automatically adjusts the size of the activated MLLM. DeeR demonstrates significant reductions in computational costs of LLM by 5.2-6.5x and GPU memory of LLM by 2-6x without compromising performance.
  arXiv  Detail & Related papers  (2024-11-04T18:26:08Z)
• LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale [17.00936774784349]
  There is a lack of simulation infrastructure capable of accurately modeling versatile hardware-software behaviors in large language model (LLM) serving systems. This paper aims to develop an effective simulation tool, called LLMServingSim, to support future research in LLM serving systems.
  arXiv  Detail & Related papers  (2024-08-10T09:26:15Z)
• In Situ Framework for Coupling Simulation and Machine Learning with Application to CFD [51.04126395480625]
  Recent years have seen many successful applications of machine learning (ML) to facilitate fluid dynamic computations. As simulations grow, generating new training datasets for traditional offline learning creates I/O and storage bottlenecks. This work offers a solution by simplifying this coupling and enabling in situ training and inference on heterogeneous clusters.
  arXiv  Detail & Related papers  (2023-06-22T14:07:54Z)

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.