Related papers: FLYING SERVING: On-the-Fly Parallelism Switching f…

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a…

Generative recommendation (GR) models possess greater scaling power compared to traditional deep learning recommendation models (DLRMs), yet they also impose a tremendous increase in computational burden. Measured in FLOPs, a typical GR…

KV cache restoration has emerged as a dominant bottleneck in serving long-context LLM workloads, including multi-turn conversations, retrieval-augmented generation, and agentic pipelines. Existing approaches treat restoration as a…

Large Language Models (LLMs) such as GPT-4 and Llama3 can already comprehend complex commands and process diverse tasks. This advancement facilitates their application in controlling drones and robots for various tasks. However, existing…

Latent variable models have accumulated a considerable amount of interest from the industry and academia for their versatility in a wide range of applications. A large amount of effort has been made to develop systems that is able to extend…

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…

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…

Tensor program tuning is a non-convex objective optimization problem, to which search-based approaches have proven to be effective. At the core of the search-based approaches lies the design of the cost model. Though deep learning-based…

As data-intensive applications grow, batch processing in limited-resource environments faces scalability and resource management challenges. Serverless computing offers a flexible alternative, enabling dynamic resource allocation and…

Large-scale models rely heavily on 3D parallelism for distributed training, which utilizes tensor parallelism (TP) as the intra-operator parallelism to partition model states across GPUs. However, TP introduces significant communication…

Advances in Large Language Models (LLMs) have led to a surge of LLM-powered applications. These applications have diverse token-generation latency requirements. As a result, simply classifying workloads as latency-sensitive (LS) or…

How can we effectively handle queries for on-device large language models (LLMs) with varying runtime constraints, such as latency and accuracy? Multi-scale quantization addresses this challenge by enabling memory-efficient runtime model…

Large language models (LLMs) have been widely deployed for online generative services, where numerous LLM instances jointly handle workloads with fluctuating request arrival rates and variable request lengths. To efficiently execute…

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…

Large language models (LLMs) have demonstrated remarkable performance, and organizations are racing to serve LLMs of varying sizes as endpoints for use-cases like chat, programming and search. However, efficiently serving multiple LLMs…

Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, existing large language models face increasing computational and…

The paper introduces PDSP-Bench, a novel benchmarking system designed for a systematic understanding of performance of parallel stream processing in a distributed environment. Such an understanding is essential for determining how Stream…

A parallel server system is a stochastic processing network with applications in manufacturing, supply chain, ride-hailing, call centers, etc. Heterogeneous customers arrive in the system, and only a subset of servers can serve any customer…

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…

The rapid advancement of Large Language Models (LLMs) has driven the need for more efficient serving strategies. In this context, efficiency refers to the proportion of requests that meet their Service Level Objectives (SLOs), particularly…