Related papers: LLM-Driven Intent-Based Privacy-Aware Orchestratio…

While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches…

This paper presents ServerlessLLM, a distributed system designed to support low-latency serverless inference for Large Language Models (LLMs). By harnessing the substantial near-GPU storage and memory capacities of inference servers,…

Sizing a GPU fleet for LLM inference is harder than it looks. The obvious questions -- how many GPUs, which type, where to split a two-pool fleet -- have no closed-form answers. They depend on the full token-length distribution, the routing…

Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive…

In recent years, the rapid advancement of deep neural networks (DNNs) has revolutionized artificial intelligence, enabling models with unprecedented capabilities in understanding, generating, and processing complex data. These powerful…

The ever-increasing computation and energy demand for LLM and AI agents call for holistic and efficient optimization of LLM serving systems. In practice, heterogeneous GPU clusters can be deployed in a geographically distributed manner,…

Large Language Models (LLMs) increasingly require processing long text sequences, but GPU memory limitations force difficult trade-offs between memory capacity and bandwidth. While HBM-based acceleration offers high bandwidth, its capacity…

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…

Monitoring unstructured streams increasingly requires persistent, semantics-aware computation, yet today's LLM frameworks remain stateless and one-shot, limiting their usefulness for long-running analytics. We introduce Continuous Prompts…

To meet strict Service-Level Objectives (SLOs),contemporary Large Language Models (LLMs) decouple the prefill and decoding stages and place them on separate GPUs to mitigate the distinct bottlenecks inherent to each phase. However, the…

Since the increasing popularity of large language model (LLM) backend systems, it is common and necessary to deploy stable serverless serving of LLM on multi-GPU clusters with autoscaling. However, there exist challenges because the…

Large Language Models (LLMs) built on transformer architectures have transformed natural language processing, achieving remarkable performance across diverse applications. While distributed inference frameworks enable practical deployment…

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM…

Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data. However, edge devices often struggle with limited computing power, memory, and bandwidth, requiring collaboration across…

Serverless computing has emerged as a compelling solution for cloud-based model inference. However, as modern large language models (LLMs) continue to grow in size, existing serverless platforms often face substantial model startup…

This paper presents LMStream, which ensures bounded latency while maximizing the throughput on the GPU-enabled micro-batch streaming systems. The main ideas behind LMStream's design can be summarized as two novel mechanisms: (1) dynamic…

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality).…

The scaling law for large language models (LLMs) depicts that the path towards machine intelligence necessitates training at large scale. Thus, companies continuously build large-scale GPU clusters, and launch training jobs that span over…

Large Language Models (LLMs) have significantly advanced artificial intelligence by optimizing traditional Natural Language Processing (NLP) workflows, facilitating their integration into various systems. Many such NLP systems, including…

To usher in the next round of client AI innovation, there is an urgent need to enable efficient, lossless inference of high-accuracy large language models (LLMs) and vision language models (VLMs), jointly referred to as xLMs, on client…