Related papers: Mooncake: A KVCache-centric Disaggregated Architec…

The rising global prevalence of diabetes necessitates early detection to prevent severe complications. While AI-powered prediction applications offer a promising solution, they require a responsive and scalable back-end architecture to…

Modern data-intensive applications face memory latency challenges exacerbated by disaggregated memory systems. Recent work shows that coroutines are promising in effectively interleaving tasks and hiding memory latency, but they struggle to…

Existing large language model (LLM) serving systems typically employ Prefill-Decode disaggregated architecture to prevent computational interference between the prefill and decode phases. However, in real-world LLM serving scenarios,…

The Key-Value (KV) cache, which stores intermediate attention computations (Key and Value pairs) to avoid redundant calculations, is a fundamental mechanism for accelerating Large Language Model (LLM) inference. However, this efficiency…

Disaggregated inference has become an essential framework that separates the prefill (P) and decode (D) stages in large language model inference to improve throughput. However, the KV cache transfer faces significant delays between prefill…

Advances in hybrid bonding and packaging have driven growing interest in 3D DRAM-stacked accelerators with higher memory bandwidth and capacity. As LLMs scale to hundreds of billions or trillions of parameters, distributed inference across…

Low-latency online services have strict Service Level Objectives (SLOs) that require datacenter systems to support high throughput at microsecond-scale tail latency. Dataplane operating systems have been designed to scale up multi-core…

One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption of the Key-Value (KV) cache. Existing approaches, such as quantization, have demonstrated promising…

Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute and memory intensive, where a single request can require…

Owing to the huge success of generative artificial intelligence (AI), large language models (LLMs) have emerged as a core subclass, underpinning applications such as question answering, text generation, and code completion. While…

The deployment and scaling of large language models (LLMs) have become critical as they permeate various applications, demanding high-throughput and low-latency serving systems. Existing frameworks struggle to balance these requirements,…

Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with…

This paper presents Block, a distributed scheduling framework designed to optimize load balancing and auto-provisioning across instances in large language model serving frameworks by leveraging contextual information from incoming requests.…

Distributed prefix caching accelerates long-context LLM serving by reusing KV cache entries for common context prefixes. However, KV cache fetches can become a bottleneck when network bandwidth is limited. Compression mitigates the…

The demand for smartness in embedded systems has been mounting up drastically in the past few years. Embedded system today must address the fundamental challenges introduced by cloud computing and artificial intelligence. KubeEdge [1] is an…

When compared to blocking concurrency, non-blocking concurrency can provide higher performance in parallel shared-memory contexts, especially in high contention scenarios. This paper proposes FLeeC, an application-level cache system based…

The rapid adoption of machine learning (ML) has underscored the importance of serving ML models with high throughput and resource efficiency. Traditional approaches to managing increasing query demands have predominantly focused on hardware…

Serving large language models (LLMs) to millions of users requires efficient resource allocation and parallelism strategies. It is a labor intensive trial-and-error process to find such a strategy. We present BestServe, a novel framework…

Data centers capable of running large language models (LLMs) are spread across the globe. Some have high end GPUs for running the most advanced models (100B+ parameters), and others are only suitable for smaller models (1B parameters). The…

As cloud computing and microservice architectures become increasingly prevalent, API rate limiting has emerged as a critical mechanism for ensuring system stability and service quality. Traditional rate limiting algorithms, such as token…