WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving

• URL: http://arxiv.org/abs/2512.09472v1
• Date: Wed, 10 Dec 2025 09:47:40 GMT
• Title: WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving
• Authors: Chiheng Lou, Sheng Qi, Rui Kang, Yong Zhang, Chen Sun, Pengcheng Wang, Bingyang Liu, Xuanzhe Liu, Xin Jin,
• Abstract summary: Existing multi-LLM serving systems optimize GPU utilization at the cost of worse inference performance.<n>We propose universal GPU workers to enable one-for-many GPU prewarming that loads models with knowledge of future workloads.<n>WarmServe improves TTFT by up to 50.8$times$ compared to the state-of-the-art autoscaling-based system.
• Score: 17.92164698813269
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying multiple models within shared GPU clusters is promising for improving resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems optimize GPU utilization at the cost of worse inference performance, especially time-to-first-token (TTFT). We identify the root cause of such compromise as their unawareness of future workload characteristics. In contrast, recent analysis on real-world traces has shown the high periodicity and long-term predictability of LLM serving workloads. We propose universal GPU workers to enable one-for-many GPU prewarming that loads models with knowledge of future workloads. Based on universal GPU workers, we design and build WarmServe, a multi-LLM serving system that (1) mitigates cluster-wide prewarming interference by adopting an evict-aware model placement strategy, (2) prepares universal GPU workers in advance by proactive prewarming, and (3) manages GPU memory with a zero-overhead memory switching mechanism. Evaluation under real-world datasets shows that WarmServe improves TTFT by up to 50.8$\times$ compared to the state-of-the-art autoscaling-based system, while being capable of serving up to 2.5$\times$ more requests compared to the GPU-sharing system.

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)
• Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs [61.953548065938385]
  We introduce the ''Three Taxes'' (Bulk Synchronous, Inter- Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework.<n>We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution.<n>We observe a 10-20% speedup in end-to-end latency over BSP-based approaches.
  arXiv  Detail & Related papers  (2025-11-04T01:15:44Z)
• Scalable GPU-Based Integrity Verification for Large Machine Learning Models [4.301162531343759]
  We present a security framework that strengthens distributed machine learning by standardizing integrity protections across CPU and GPU platforms.<n>Our approach co-locates integrity verification directly with large ML model execution on GPU accelerators.<n>We provide a hardware-agnostic foundation that enterprise teams can deploy regardless of their underlying CPU and GPU infrastructures.
  arXiv  Detail & Related papers  (2025-10-27T23:45:21Z)
• CARMA: Collocation-Aware Resource Manager [5.998463702026698]
  Collocating multiple deep learning (DL) training tasks on the same GPU can improve utilization but introduces two key risks.<n>We present CARMA, a task-level, collocation-aware resource management system for the server-scale.
  arXiv  Detail & Related papers  (2025-08-26T14:29:34Z)
• Minute-Long Videos with Dual Parallelisms [57.22737565366549]
  Diffusion Transformer (DiT)-based video diffusion models generate high-quality videos at scale but incur prohibitive processing latency and memory costs for long videos.<n>We propose a novel distributed inference strategy, termed DualParal.<n>Instead of generating an entire video on a single GPU, we parallelize both temporal frames and model layers across GPUs.
  arXiv  Detail & Related papers  (2025-05-27T11:55:22Z)
• MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs [55.95879347182669]
  MoE architecture is renowned for its ability to increase model capacity without a proportional increase in inference cost. MoE-Lightning introduces a novel CPU-GPU-I/O pipelining schedule, CGOPipe, with paged weights to achieve high resource utilization. MoE-Lightning can achieve up to 10.3x higher throughput than state-of-the-art offloading-enabled LLM inference systems for Mixtral 8x7B on a single T4 GPU (16GB)
  arXiv  Detail & Related papers  (2024-11-18T01:06:12Z)
• Deep Optimizer States: Towards Scalable Training of Transformer Models Using Interleaved Offloading [2.8231000588510757]
  Transformers and large language models(LLMs) have seen rapid adoption in all domains. Training of transformers is very expensive and often hits a memory wall'' We propose a novel technique to split the LLM into subgroups, whose update phase is scheduled on either the CPU or the GPU.
  arXiv  Detail & Related papers  (2024-10-26T00:43:59Z)
• 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)
• A Frequency-aware Software Cache for Large Recommendation System Embeddings [11.873521953539361]
  Deep learning recommendation models (DLRMs) have been widely applied in Internet companies. We propose a GPU-based software cache approaches to dynamically manage the embedding table in the CPU and GPU memory space. Our proposed software cache is efficient in training entire DLRMs on GPU in a synchronized update manner.
  arXiv  Detail & Related papers  (2022-08-08T12:08:05Z)
• PARIS and ELSA: An Elastic Scheduling Algorithm for Reconfigurable Multi-GPU Inference Servers [0.9854614058492648]
  NVIDIA's Ampere GPU architecture provides features to "reconfigure" one large, monolithic GPU into multiple smaller "GPU partitions" In this paper, we study this emerging GPU architecture with reconfigurability to develop a high-performance multi-GPU ML inference server.
  arXiv  Detail & Related papers  (2022-02-27T23:30:55Z)
• Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers [65.60007071024629]
  We show that Adaptive SGD outperforms four state-of-the-art solutions in time-to-accuracy. We show experimentally that Adaptive SGD outperforms four state-of-the-art solutions in time-to-accuracy.
  arXiv  Detail & Related papers  (2021-10-13T20:58:15Z)

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.