paper-with-me

홈 › Papers

Prompt-Aware Scheduling for Efficient Text-to-Image Inferencing System

2025-01-29 · Shubham Agarwal, Saud Iqbal, Subrata Mitra

Traditional ML models utilize controlled approximations during high loads, employing faster, but less accurate models in a process called accuracy scaling. However, this method is less effective for generative text-to-image models due to their sensitivity to input prompts and performance degradation caused by large model loading overheads. This work introduces a novel text-to-image inference system that optimally matches prompts across multiple instances of the same model operating at various approximation levels to deliver high-quality images under high loads and fixed budgets.

📄 PDF Abstract BibTeX arXiv:2502.06798

Code (0)

등록된 구현이 없습니다.

Tasks

SchedulingSensitivity

Similar Papers 제목 키워드 기반

LLM-Upgraded Graph Reinforcement Learning for Carbon-Aware Job Scheduling in Smart Manufacturing

2025-12-06 · Zhiying Yang, Fang Liu, Wei Zhang, Xin Lou 외 arxiv

This paper presents \textsc{Luca}, a \underline{l}arge language model (LLM)-\underline{u}pgraded graph reinforcement learning framework for \underline{c}arbon-\underline{a}ware flexible job shop scheduling. \textsc{Luca}…

Reinforcement LearningGraph Neural Network

Adaptively Robust LLM Inference Optimization under Prediction Uncertainty

2025-08-20 · Zixi Chen, Yinyu Ye, Zijie Zhou arxiv

We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-tra…

Implicit In-Context Learning: Evidence from Artificial Language Experiments

2025-03-31 · Xiaomeng Ma, Qihui Xu

Humans acquire language through implicit learning, absorbing complex patterns without explicit awareness. While LLMs demonstrate impressive linguistic capabilities, it remains unclear whether they exhibit human-like patt…

In-Context Learning

Semantic Scheduling for LLM Inference

2025-06-13 · Wenyue Hua, Dujian Ding, Yile Gu, Yujie Ren 외

Conventional operating system scheduling algorithms are largely content-ignorant, making decisions based on factors such as latency or fairness without considering the actual intents or semantics of processes. Consequent…

FairnessManagementScheduling

Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees

2026-04-13 · Xiaoyu Ma, Yiwen Li, Haoyue Liu, Zhichao Wang 외 arxiv

Automatic prompt optimization (APO) hinges on the quality of its evaluation signal, yet scoring every prompt candidate on the full training set is prohibitively expensive. Existing methods either fix a single evaluation …