Related papers: WWW.Serve: Interconnecting Global LLM Services thr…
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…
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 model (LLM) serving is becoming an increasingly important workload for cloud providers. Based on performance SLO requirements, LLM inference requests can be divided into (a) interactive requests that have tight SLOs in the…
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…
Production LLM serving must simultaneously deliver high throughput, low latency, and sufficient context capacity under non-stationary traffic and mixed request requirements. Data parallelism (DP) maximizes throughput by running independent…
The rapid rise of large language models (LLMs) in text streaming services has introduced significant cost and Quality of Experience (QoE) challenges in serving millions of daily requests, especially in meeting Time-To-First-Token (TTFT) and…
The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models behave across large-scale, multi-GPU systems. In this paper,…
User experience is a critical factor Large Language Model (LLM) serving systems must consider, where service level objectives (SLOs) considering the experience of individual requests and system level metrics (SLMs) considering the overall…
The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-sized models and infrequent requests. While existing serverless solutions follow exclusive GPU allocation, we take a step back to explore…
Serving Large Language Models (LLMs) is a GPU-intensive task where traditional autoscalers fall short, particularly for modern Prefill-Decode (P/D) disaggregated architectures. This architectural shift, while powerful, introduces…
The increasing demand for Large Language Models (LLMs) across various applications has led to a significant shift in the design of deep learning serving systems. Deploying LLMs, particularly in multi-tenant environments, poses substantial…
We consider a large-scale parallel-server system, where each server independently adjusts its processing speed in a decentralized manner. The objective is to minimize the overall cost, which comprises the average cost of maintaining the…
Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling richer interactions with text, images, and videos. These heterogeneous workloads introduce additional inference stages, such as vision…
Dramatic increases in the capabilities of neural network models in recent years are driven by scaling model size, training data, and corresponding computational resources. To develop the exceedingly large networks required in modern…
Recently, there has been an extensive research effort in building efficient large language model (LLM) inference serving systems. These efforts not only include innovations in the algorithm and software domains but also constitute…
Large language models have gained widespread popularity for their ability to process natural language inputs and generate insights derived from their training data, nearing the qualities of true artificial intelligence. This advancement has…
Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adaptability. To address these challenges, we introduce…
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…
As Large Language Models (LLMs) become increasingly accessible to end users, an ever-growing number of inference requests are initiated from edge devices and computed on centralized GPU clusters. However, the resulting exponential growth in…
Deploying Large Language Model (LLM) services at the edge benefits latency-sensitive and privacy-aware applications. However, the stateless nature of LLMs makes managing user context (e.g., sessions, preferences) across geo-distributed edge…