Related papers: Don't Stop Me Now: Embedding Based Scheduling for …

In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to…

We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes…

Large language models (LLMs) have revolutionized the field of AI, demonstrating unprecedented capacity across various tasks. However, the inference process for LLMs comes with significant computational costs. In this paper, we propose an…

Augmented Large Language Models (LLMs) enhance the capabilities of standalone LLMs by integrating external data sources through API calls. In interactive LLM applications, efficient scheduling is crucial for maintaining low request…

Queueing systems present many opportunities for applying machine-learning predictions, such as estimated service times, to improve system performance. This integration raises numerous open questions about how predictions can be effectively…

It is well known that size-based scheduling policies, which take into account job size (i.e., the time it takes to run them), can perform very desirably in terms of both response time and fairness. Unfortunately, the requirement of knowing…

Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…

We propose ELIS, a serving system for Large Language Models (LLMs) featuring an Iterative Shortest Remaining Time First (ISRTF) scheduler designed to efficiently manage inference tasks with the shortest remaining tokens. Current LLM serving…

Conventional operating system scheduling algorithms are largely content-ignorant, making decisions based on factors such as latency or fairness without considering the actual intents or semantics of processes. Consequently, these algorithms…

The job shop scheduling problem (JSSP) remains a significant hurdle in optimizing production processes. This challenge involves efficiently allocating jobs to a limited number of machines while minimizing factors like total processing time…

Large Language Models (LLMs) have transformed code auto-completion by generating context-aware suggestions. Yet, deciding when to present these suggestions remains underexplored, often leading to interruptions or wasted inference calls. We…

The efficient deployment of large language models (LLMs) in online settings requires optimizing inference performance under stringent latency constraints, particularly the time-to-first-token (TTFT) and time-per-output-token (TPOT). This…

The scaling of transformer-based Large Language Models (LLMs) has significantly expanded their context lengths, enabling applications where inputs exceed 100K tokens. Our analysis of a recent Azure LLM inference trace reveals a highly…

With the growing use of Large Language Model (LLM)-based tools like ChatGPT, Perplexity, and Gemini across industries, there is a rising need for efficient LLM inference systems. These systems handle requests with a unique two-phase…

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we…

As large language models (LLMs) have shown great success in many tasks, they are used in various applications. While a lot of works have focused on the efficiency of single-LLM application (e.g., offloading, request scheduling, parallelism…

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…

Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent characteristics: prompt segmentation (e.g., system instructions, retrieved passages, tool…

The growing demand for large language models (LLMs) requires serving systems to handle many concurrent requests with diverse service level objectives (SLOs). This exacerbates head-of-line (HoL) blocking during the compute-intensive prefill…

Shortest Remaining Processing Time (SRPT) is a well known preemptive scheduling algorithm for uniprocessor and multiprocessor systems. SRPT finds applications in the emerging areas such as scheduling of client's requests that are submitted…