Related papers: Cost-Efficient LLM Serving in the Cloud: VM Select…

With the rapid expansion of cloud computing applications, optimizing resource allocation has become crucial for improving system performance and cost efficiency. This paper proposes an intelligent resource allocation algorithm that…

With the rapid advancement of large language models (LLMs), efficiently serving LLM inference under limited GPU resources has become a critical challenge. Recently, an increasing number of studies have explored applying serverless computing…

KV cache management is essential for efficient LLM inference. To maximize utilization, existing inference engines evict finished requests' KV cache if new requests are waiting. This policy breaks for agentic workloads, which interleave LLM…

Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because the key-value (KV) cache, an intermediate structure storing…

The Key-Value (KV) cache reading latency increases significantly with context lengths, hindering the efficiency of long-context LLM inference. To address this, previous works propose retaining a small fraction of KV cache based on token…

LLMs often struggle with memory-constrained deployment on consumer-grade hardware due to their massive parameter sizes. While existing solutions such as model compression and offloading improve deployment feasibility, they often suffer from…

The rise of Generative AI introduces a new class of HPC workloads that integrates lightweight LLMs with traditional high-throughput applications to accelerate scientific discovery. The current design of HPC clusters is inadequate to support…

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation. However, its memory footprint…

As Large Language Models (LLMs) scale to handle massive concurrent traffic, optimizing the infrastructure required for inference has become a primary challenge. To manage the high cost of GPU resources while ensuring strict service-level…

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve…

Long-context LLMs demand accurate inference at low latency, yet decoding becomes primarily constrained by KV cache as context grows. Prior pruning methods are largely context-agnostic: their token selection ignores step-wise relevance and…

As augmented large language models (LLMs) with external tools become increasingly popular in web applications, improving augmented LLM inference serving efficiency and optimizing service-level objectives (SLOs) are critical for enhancing…

Most Large Language Models (LLMs) are currently deployed in the cloud, with users relying on internet connectivity for access. However, this paradigm faces challenges such as network latency, privacy concerns, and bandwidth limits. Thus,…

The rise of million-token, agent-based applications has placed unprecedented demands on large language model (LLM) inference services. The long-running nature of these tasks increases their susceptibility to hardware and software faults,…

How to efficiently serve LLMs in practice has become exceptionally challenging due to their prohibitive memory and computation requirements. In this study, we investigate optimizing the KV cache, whose memory footprint poses a critical…

Serving large language models (LLMs) is important for cloud providers, and caching intermediate results (KV\$) after processing each request substantially improves serving throughput and latency. However, there is limited understanding of…

Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…

Running LLMs on end devices has garnered significant attention recently due to their advantages in privacy preservation. With the advent of lightweight LLM models and specially designed GPUs, on-device LLM inference has achieved the…

With the skyrocketing costs of GPUs and their virtual instances in the cloud, there is a significant desire to use CPUs for large language model (LLM) inference. KV cache update, often implemented as allocation, copying, and in-place…

Multimodal large language model (MLLM) inference splits into two phases with opposing hardware demands: vision encoding is compute-bound, while language generation is memory-bandwidth-bound. We show that under standard transformer KV…