Related papers: Serving Hybrid LLM Loads with SLO Guarantees Using…

Serving long-context LLMs is challenging because request lengths and batch composition vary during token generation, causing the memory footprint to fluctuate significantly at runtime. Offloading KV caches to host memory limits effective…

Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly…

Applications in emerging domains such as XR are being built as compound inference systems, where multiple ML models are composed in the form of a task graph to service each request. Serving these compound systems efficiently raises two…

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…

Serving large language models (LLMs) efficiently remains challenging due to the high memory and latency overhead of key-value (KV) cache access during autoregressive decoding. We present \textbf{TinyServe}, a lightweight and extensible…

The integration of Large Language Models (LLMs) into applications ranging from interactive chatbots to multi-agent systems has introduced a wide spectrum of service-level objectives (SLOs) for responsiveness. These include latency-sensitive…

Large language models (LLMs) deployed on edge servers are increasingly used in latency-sensitive applications such as personalized assistants, recommendation, and content moderation. However, the non-stationary nature of user data…

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…

In this paper, we consider a mixed-prompt scenario for a large language model (LLM) inference serving system that supports diverse applications with both short prompts and long prompts and heterogeneous SLOs for iteration time. To improve…

The attention layer, a core component of Transformer-based LLMs, brings out inefficiencies in current GPU systems due to its low operational intensity and the substantial memory requirements of KV caches. We propose a High-bandwidth…

Large language models (LLMs) have facilitated a wide range of applications with distinct service-level objectives (SLOs), from latency-sensitive online tasks like interactive chatbots to throughput-oriented offline workloads like data…

Large language models (LLMs) with different architectures and sizes have been developed. Serving each LLM with dedicated GPUs leads to resource waste and service inefficiency due to the varying demand of LLM requests. A common practice is…

The widespread adoption of Large Language Models (LLMs) has exponentially increased the demand for efficient serving systems. With growing requests and context lengths, key-value (KV)-related operations, including attention computation and…

Modern LLM serving systems must sustain high throughput while meeting strict latency SLOs across two distinct inference phases: compute-intensive prefill and memory-bound decode phases. Existing approaches either (1) aggregate both phases…

Large language models (LLMs) are increasingly deployed as AI agents that operate in short reasoning-action loops, interleaving model computation with external calls. Unlike traditional chat applications, these agentic workloads require…

Large language models (LLMs) have become increasingly popular in various areas, traditional business gradually shifting from rule-based systems to LLM-based solutions. However, the inference of LLMs is resource-intensive or…

Large Language Model (LLM) inference is rapidly becoming a core datacenter service, yet current serving stacks keep the host CPU on the critical path for orchestration and token-level control. This makes LLM performance sensitive to CPU…

This paper introduces LLMServingSim2.0, a system simulator designed for exploring heterogeneous hardware in large-scale LLM serving systems. LLMServingSim2.0 addresses two key limitations of its predecessor: (1) integrating hardware models…

Large Language Models (LLMs) are wildly popular today and it is important to serve them efficiently. Existing LLM serving systems are stateless across requests. Consequently, when LLMs are used in the common setting of multi-turn…

Tensor parallelism (TP) enables large language models (LLMs) to scale inference efficiently across multiple GPUs, but its tight coupling makes systems fragile: a single GPU failure can halt execution, trigger costly KVCache recomputation,…