Fairness in Serving Large Language Models

• URL: http://arxiv.org/abs/2401.00588v2
• Date: Wed, 5 Jun 2024 06:43:16 GMT
• Title: Fairness in Serving Large Language Models
• Authors: Ying Sheng, Shiyi Cao, Dacheng Li, Banghua Zhu, Zhuohan Li, Danyang Zhuo, Joseph E. Gonzalez, Ion Stoica,
• Abstract summary: 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.
• Score: 45.81800239353461
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-demand LLM inference services (e.g., ChatGPT and BARD) support a wide range of requests from short chat conversations to long document reading. To ensure that all client requests are processed fairly, most major LLM inference services have request rate limits, to ensure that no client can dominate the request queue. However, this rudimentary notion of fairness also results in under-utilization of the resources and poor client experience when there is spare capacity. While there is a rich literature on fair scheduling, serving LLMs presents new challenges due to their unpredictable request lengths and their unique batching characteristics on parallel accelerators. This paper introduces the definition of LLM serving fairness based on a cost function that accounts for the number of input and output tokens processed. To achieve fairness in serving, we propose a novel scheduling algorithm, the Virtual Token Counter (VTC), a fair scheduler based on the continuous batching mechanism. We prove a 2x tight upper bound on the service difference between two backlogged clients, adhering to the requirement of work-conserving. Through extensive experiments, we demonstrate the superior performance of VTC in ensuring fairness, especially in contrast to other baseline methods, which exhibit shortcomings under various conditions. The reproducible code is available at https://github.com/Ying1123/VTC-artifact

Related papers

• Inference Optimal VLMs Need Only One Visual Token but Larger Models [54.01228554126122]
  Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks. VLMs are often constrained by high latency during inference due to substantial compute required to process the large number of input tokens. We take some initial steps towards building approaches tailored for high token compression settings.
  arXiv  Detail & Related papers  (2024-11-05T18:54:21Z)
• 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)
• SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization [8.121663525764294]
  Large language models (LLMs) play a crucial role in our daily lives due to their ability to understand and generate human-like text. In this report, we design a collaborative inference architecture between a server and its clients to alleviate the throughput limit. We show in the experiments that we are able to efficiently distribute the workload allowing for roughly 1/3 reduction in the server workload.
  arXiv  Detail & Related papers  (2024-10-14T17:38:41Z)
• Efficient LLM Scheduling by Learning to Rank [19.33941579312897]
  We show that it is possible to predict the relative ranks of output lengths in a batch of requests, using learning to rank. We develop a novel scheduler for LLM inference and serving that can approximate the shortest-job-first (SJF) schedule better than existing approaches.
  arXiv  Detail & Related papers  (2024-08-28T13:35:54Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches [52.02764371205856]
  Long context capability is a crucial competency for large language models (LLMs) This work provides a taxonomy of current methods and evaluating 10+ state-of-the-art approaches across seven categories of long context tasks.
  arXiv  Detail & Related papers  (2024-07-01T17:59:47Z)
• A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems [67.52782366565658]
  State-of-the-art recommender systems (RSs) depend on categorical features, which ecoded by embedding vectors, resulting in excessively large embedding tables. Despite the prosperity of lightweight embedding-based RSs, a wide diversity is seen in evaluation protocols. This study investigates various LERS' performance, efficiency, and cross-task transferability via a thorough benchmarking process.
  arXiv  Detail & Related papers  (2024-06-25T07:45:00Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• Scaling Laws for Discriminative Classification in Large Language Models [5.56747083508457]
  We present a system that allows us to use an LLM to augment our customer support advocates by re-framing the language modeling task as a discriminative classification task. We present the result of both offline and online experiments where we observed offline gains and statistically significant online lifts for our experimental system. We close by discussing the space of trade-offs with respect to model size, latency, and accuracy as well as and suggesting future applications to explore.
  arXiv  Detail & Related papers  (2024-05-24T17:58:38Z)

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.