Tempo: Application-aware LLM Serving with Mixed SLO Requirements

• URL: http://arxiv.org/abs/2504.20068v1
• Date: Thu, 24 Apr 2025 05:55:21 GMT
• Title: Tempo: Application-aware LLM Serving with Mixed SLO Requirements
• Authors: Wei Zhang, Zhiyu Wu, Yi Mu, Banruo Liu, Myungjin Lee, Fan Lai,
• Abstract summary: We introduce Tempo, a scheduler designed to maximize service gain across diverse LLM workloads.<n>Our evaluation shows that Tempo improves end-to-end service gain by up to 8.3$times$ achieves and up to 10.3$times$ SLO goodput compared to state-of-the-art designs.
• Score: 7.290735867969561
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The integration of Large Language Models (LLMs) into diverse applications, ranging from interactive chatbots and cloud AIOps to intelligent agents, has introduced a wide spectrum of Service Level Objectives (SLOs) for responsiveness. These workloads include latency-sensitive requests focused on per-token latency in streaming chat, throughput-intensive requests that require rapid full responses to invoke tools, and collective requests with dynamic dependencies arising from self-reflection or agent-based reasoning. This workload diversity, amplified by unpredictable request information such as response lengths and runtime dependencies, makes existing schedulers inadequate even within their design envelopes. In this paper, we define service gain as the useful service delivered by completing requests. We observe that as SLO directly reflects the actual performance needs of requests, completing a request much faster than its SLO (e.g., deadline) yields limited additional service gain. Based on this insight, we introduce Tempo, the first systematic SLO-aware scheduler designed to maximize service gain across diverse LLM workloads. Tempo allocates just enough serving bandwidth to meet each SLO, maximizing residual capacity for others best-effort workloads. Instead of assuming request information or none at all, it adopts a hybrid scheduling strategy: using quantile-based response upper bounds and dependency-graph matching for conservative initial estimates, prioritizing requests by service gain density, and refining decisions online as generation progresses. Our evaluation across diverse workloads, including chat, reasoning, and agentic pipelines, shows that Tempo improves end-to-end service gain by up to 8.3$\times$ and achieves up to 10.3$\times$ SLO goodput compared to state-of-the-art designs

Related papers

• Efficient LLM Serving on Hybrid Real-time and Best-effort Requests [0.6291443816903801]
  BROS is a hybrid Language Models (LLMs) serving system that aims to collocate RT/BE requests, meeting RT requests' latency requirements while maintaining BE requests' throughput. It significantly reduces the latency of RT requests (up to 74.20%), improving their fine-grained service level objectives (SLOs) attainments (up to 36.38x), with negligible throughput reduction for BE requests.
  arXiv  Detail & Related papers  (2025-04-13T14:16:57Z)
• Autellix: An Efficient Serving Engine for LLM Agents as General Programs [59.673243129044465]
  Large language model (LLM) applications are evolving beyond simple chatbots into dynamic, general-purpose agentic programs.<n>Existing LLM serving systems ignore dependencies between programs and calls, missing significant opportunities for optimization.<n>We introduce Autellix, an LLM serving system that treats programs as first-class citizens to minimize their end-to-end latencies.
  arXiv  Detail & Related papers  (2025-02-19T18:59:30Z)
• MixLLM: Dynamic Routing in Mixed Large Language Models [57.309520357563215]
  Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency.<n>We develop MixLLM, a dynamic contextual-bandit-based routing system for query-LLM assignment.
  arXiv  Detail & Related papers  (2025-02-09T02:26:15Z)
• HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location [3.348953136575379]
  HyGen is an interference-aware LLM serving system that enables efficient co-location of online and offline workloads.<n>Our evaluation on production workloads shows that HyGen achieves up to 3.87x overall throughput and 5.84x offline throughput gains.
  arXiv  Detail & Related papers  (2025-01-15T16:32:27Z)
• Hierarchical Autoscaling for Large Language Model Serving with Chiron [2.767894999702707]
  Large language model (LLM) serving is becoming an increasingly important workload for cloud providers.<n>Previous autoscalers for LLM serving do not consider request SLOs leading to unnecessary scaling and resource under-utilization.<n>We introduce Chiron, an autoscaler that uses the idea of hierarchical backpressure estimated using queue size, utilization, and SLOs.
  arXiv  Detail & Related papers  (2025-01-14T12:57:40Z)
• ALISE: Accelerating Large Language Model Serving with Speculative Scheduling [7.367068885621016]
  Large Language Models (LLMs) represent a revolutionary advancement in the contemporary landscape of artificial general intelligence (AGI) In this paper, we propose a new efficient LLM inference serving framework, named ALISE. We show that ALISE improves the throughput of inference serving by up to 1.8x and 2.1x under the same latency constraint on the Alpaca and ShareGPT datasets, respectively.
  arXiv  Detail & Related papers  (2024-10-31T00:58:11Z)
• Queue management for slo-oriented large language model serving [3.0134961904579094]
  We propose QLM, a queue management system for large language model (LLM) serving.<n>QLM maintains batch and interactive requests across different models and SLOs in a request queue.<n>It uses a Request Waiting Time (RWT) Estimator that estimates the waiting times for requests in the request queue.
  arXiv  Detail & Related papers  (2024-06-05T21:17:34Z)
• RelayAttention for Efficient Large Language Model Serving with Long System Prompts [59.50256661158862]
  This paper aims to improve the efficiency of LLM services that involve long system prompts. handling these system prompts requires heavily redundant memory accesses in existing causal attention algorithms. We propose RelayAttention, an attention algorithm that allows reading hidden states from DRAM exactly once for a batch of input tokens.
  arXiv  Detail & Related papers  (2024-02-22T18:58:28Z)
• Fairness in Serving Large Language Models [45.81800239353461]
  This paper introduces the definition of serving fairness based on a cost function that accounts for the number of input and output tokens processed. We propose a novel scheduling algorithm, the Virtual Counter Token (VTC), a fair difference between two backlogged clients. We prove a 2x tight upper bound on the service scheduler, adhering to the requirement of work-conserving.
  arXiv  Detail & Related papers  (2023-12-31T21:15:54Z)
• Client Orchestration and Cost-Efficient Joint Optimization for NOMA-Enabled Hierarchical Federated Learning [55.49099125128281]
  We propose a non-orthogonal multiple access (NOMA) enabled HFL system under semi-synchronous cloud model aggregation. We show that the proposed scheme outperforms the considered benchmarks regarding HFL performance improvement and total cost reduction.
  arXiv  Detail & Related papers  (2023-11-03T13:34:44Z)
• Cache & Distil: Optimising API Calls to Large Language Models [82.32065572907125]
  Large-scale deployment of generative AI tools often depends on costly API calls to a Large Language Model (LLM) to fulfil user queries. To curtail the frequency of these calls, one can employ a smaller language model -- a student. This student gradually gains proficiency in independently handling an increasing number of user requests.
  arXiv  Detail & Related papers  (2023-10-20T15:01:55Z)
• Optimization of Image Transmission in a Cooperative Semantic Communication Networks [68.2233384648671]
  A semantic communication framework for image transmission is developed. Servers cooperatively transmit images to a set of users utilizing semantic communication techniques. A multimodal metric is proposed to measure the correlation between the extracted semantic information and the original image.
  arXiv  Detail & Related papers  (2023-01-01T15:59:13Z)

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.