Related papers: KunServe: Parameter-centric Memory Management for …

Inference on large-language models (LLMs) is constrained by GPU memory capacity. A sudden increase in the number of inference requests to a cloud-hosted LLM can deplete GPU memory, leading to contention between multiple prompts for limited…

Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM…

In LLM serving, reusing the KV cache of prompts across requests is critical for reducing TTFT and serving costs. Cache-affinity scheduling, which co-locates requests with the same prompt prefix to maximize KV cache reuse, often conflicts…

LLM inference must meet strict latency SLOs (e.g., 100 ms P99 time-between-tokens) while maximizing goodput. Yet, real-world variability in prompt and response lengths skews compute-intensive prefill and memory-bound decode phases, making…

Large Language Models (LLMs) are increasingly being deployed in applications such as chatbots, code editors, and conversational agents. A key feature of LLMs is their ability to engage in multi-turn interactions with humans or external…

LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to improve throughput, they still rely on unified scheduling…

The architectural shift to prefill/decode (PD) disaggregation in LLM serving improves resource utilization but struggles with the bursty nature of modern workloads. Existing autoscaling policies, often retrofitted from monolithic systems…

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…

Generative recommendation (GR) offers superior modeling capabilities but suffers from prohibitive inference costs due to the repeated encoding of long user histories. While cross-request Key-Value (KV) cache reuse presents a significant…

The advent of the Attention mechanism and Transformer architecture enables contextually natural text generation and compresses the burden of processing entire source information into singular vectors. Based on these two main ideas, model…

Meeting stringent Time-To-First-Token (TTFT) requirements is crucial for LLM applications. To improve efficiency, modern LLM serving systems adopt disaggregated architectures with diverse parallelisms, introducing complex multi-stage…

An effective way to improve energy efficiency is to throttle hardware resources to meet a certain performance target, specified as a QoS constraint, associated with all applications running on a multicore system. Prior art has proposed…

The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct scheduling challenges. Unlike traditional deployments where…

Existing work only effective on a given number of GPUs, often neglecting the complexities involved in manually determining the specific types and quantities of GPUs needed, which can be a significant burden for developers. To address this…

The rapid growth of generative AI and its integration into everyday workflows have significantly increased the demand for large language model (LLM) inference services. While proprietary models remain popular, recent advancements in…

We investigate the feasibility of using Multimodal Large Language Models (MLLMs) for real-time online episodic memory question answering. While cloud offloading is common, it raises privacy and latency concerns for wearable assistants,…

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…

As Large Language Models (LLMs) gain traction, their reliance on power-hungry GPUs places ever-increasing energy demands, raising environmental and monetary concerns. Inference dominates LLM workloads, presenting a critical challenge for…

Multi-agent LLM systems on edge devices need to hand off latent context efficiently, but the practical choices today are expensive re-prefill or full-precision KV transfer. We study QKVShare, a framework for quantized KV-cache handoff…

Multi-task learning (MTL) improves generalization and data efficiency by jointly learning related tasks through shared representations. In the widely used hard-parameter-sharing setting, a shared backbone is combined with task-specific…