paper-with-me

홈 › Papers

Cost-Efficient LLM Serving in the Cloud: VM Selection with KV Cache Offloading

2025-04-16 · Kihyun Kim, Jinwoo Kim, Hyunsun Chung, Myung-Hoon Cha, Hong-Yeon Kim, Youngjae Kim

LLM inference is essential for applications like text summarization, translation, and data analysis, but the high cost of GPU instances from Cloud Service Providers (CSPs) like AWS is a major burden. This paper proposes InferSave, a cost-efficient VM selection framework for cloud based LLM inference. InferSave optimizes KV cache offloading based on Service Level Objectives (SLOs) and workload charac teristics, estimating GPU memory needs, and recommending cost-effective VM instances. Additionally, the Compute Time Calibration Function (CTCF) improves instance selection accuracy by adjusting for discrepancies between theoretical and actual GPU performance. Experiments on AWS GPU instances show that selecting lower-cost instances without KV cache offloading improves cost efficiency by up to 73.7% for online workloads, while KV cache offloading saves up to 20.19% for offline workloads.

📄 PDF Abstract BibTeX arXiv:2504.11816

Code (1)

lass-lab/InferSave 공식 구현

Tasks

GPUText Summarization

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

HERALD: High-Throughput Block Diffusion LLM Serving via CPU-GPU Cooperative KV Cache Retrieval

2026-06-19 · Omin Kwon, Doyeon Kim, Jongseok Park, Seung Yul Lee 외 arxiv

Diffusion LLMs (dLLMs) improve GPU utilization over autoregressive decoding by generating multiple tokens per forward pass, but their KV cache still grows linearly with context, limiting throughput at long contexts. KV c…

10Cache: Heterogeneous Resource-Aware Tensor Caching and Migration for LLM Training

2025-11-18 · Sabiha Afroz, Redwan Ibne Seraj Khan, Hadeel Albahar, Jingoo Han 외 arxiv

Training large language models (LLMs) in the cloud faces growing memory bottlenecks due to the limited capacity and high cost of GPUs. While GPU memory offloading to CPU and NVMe has made large-scale training more feasib…

Speech Understanding on Tiny Devices with A Learning Cache

2023-11-30 · Afsara Benazir, Zhiming Xu, Felix Xiaozhu Lin

This paper addresses spoken language understanding (SLU) on microcontroller-like embedded devices, integrating on-device execution with cloud offloading in a novel fashion. We leverage temporal locality in the speech inp…

speech-recognitionSpeech RecognitionSpoken Language Understanding

Improving Image-recognition Edge Caches with a Generative Adversarial Network

2022-02-11 · Guilherme B. Souza, Roberto G. Pacheco, Rodrigo S. Couto

Image recognition is an essential task in several mobile applications. For instance, a smartphone can process a landmark photo to gather more information about its location. If the device does not have enough computation…

Generative Adversarial Network

OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration

2026-01-05 · Xinyue Ma, Heelim Hong, Taegeon Um, Jongseop Lee 외 arxiv

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…