相关论文: Learned Best-Effort LLM Serving

With the widespread adoption of 5G and Internet of Things (IoT) technologies, the low latency provided by edge computing has great importance for real-time processing. However, managing numerous simultaneous service requests poses a…

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…

The recent advances in LLMs bring a strong demand for efficient system support to improve overall serving efficiency. As LLM inference scales towards multiple GPUs and even multiple compute nodes, various coordination patterns, such as…

Test-time training (TTT) adapts an LLM during generation by reading and updating request-owned state, such as fast weights, low-rank deltas, or streaming learner state. This breaks batched LLM serving, which assumes shared static weights:…

We propose a novel adaptive transfer learning framework, learning to transfer learn (L2TL), to improve performance on a target dataset by careful extraction of the related information from a source dataset. Our framework considers…

Large-scale online ride-sharing platforms have substantially transformed our lives by reallocating transportation resources to alleviate traffic congestion and promote transportation efficiency. An efficient fleet management strategy not…

Recent advances in large language model (LLM) reasoning have shown that sophisticated behaviors such as planning and self-reflection can emerge through reinforcement learning (RL). However, despite these successes, RL in its current form…

A practical large language model (LLM) service may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across requests. However, the long system prompt causes…

Real-world autonomous decision-making systems, from robots to recommendation engines, must operate in environments that change over time. While deep reinforcement learning (RL) has shown an impressive ability to learn optimal policies in…

Effective network slicing requires an infrastructure/network provider to deal with the uncertain demand and real-time dynamics of network resource requests. Another challenge is the combinatorial optimization of numerous resources, e.g.,…

Distributed prefix caching has become a core technique for efficient LLM serving. However, for long-context requests with high cache hit ratios, retrieving reusable KVCache blocks from remote servers has emerged as a new performance…

Large Language Model (LLM) agents can leverage multiple turns and tools to solve complex tasks, with prompt-based approaches achieving strong performance. This work demonstrates that Reinforcement Learning (RL) can push capabilities…

Network Utility Maximization (NUM) studies the problems of allocating traffic rates to network users in order to maximize the users' total utility subject to network resource constraints. In this paper, we propose a new NUM framework,…

This paper introduces SLOs-Serve, a system designed for serving multi-stage large language model (LLM) requests with application- and stage-specific service level objectives (SLOs). The key idea behind SLOs-Serve is to customize the…

Large Language Models (LLMs) such as GPT-4 and Llama3 can already comprehend complex commands and process diverse tasks. This advancement facilitates their application in controlling drones and robots for various tasks. However, existing…

We consider a meal delivery service fulfilling dynamic customer requests given a set of couriers over the course of a day. A courier's duty is to pick-up an order from a restaurant and deliver it to a customer. We model this service as a…

Generative recommendation (GR) models possess greater scaling power compared to traditional deep learning recommendation models (DLRMs), yet they also impose a tremendous increase in computational burden. Measured in FLOPs, a typical GR…

Various congestion control protocols have been designed to achieve high performance in different network environments. Modern online learning solutions that delegate the congestion control actions to a machine cannot properly converge in…

In this paper, we study the peak-aware energy scheduling problem using the competitive framework with machine learning prediction. With the uncertainty of energy demand as the fundamental challenge, the goal is to schedule the energy output…

Serving Large Language Models (LLMs) can benefit immensely from parallelizing both the model and input requests across multiple devices, but incoming workloads exhibit substantial spatial and temporal heterogeneity. Spatially, workloads…