paper-with-me

홈 › Papers

Adaptive Orchestration for Large-Scale Inference on Heterogeneous Accelerator Systems Balancing Cost, Performance, and Resilience

2025-03-25 · Yahav Biran, Imry Kissos

The surge in generative AI workloads has created a need for scalable inference systems that can flexibly harness both GPUs and specialized accelerators while containing operational costs. This paper proposes a hardware-agnostic control loop that adaptively allocates requests across heterogeneous accelerators based on real-time cost and capacity signals. The approach sustains low latency and high throughput by dynamically shifting between cost-optimized and capacity-optimized modes, ensuring the most efficient use of expensive compute resources under fluctuating availability. Evaluated using the Stable Diffusion model, the framework consistently meets latency targets, automatically redirects traffic during capacity shortfalls, and capitalizes on lower-cost accelerators when possible. These results highlight how a feedback-driven deployment strategy, spanning the entire software and hardware stack, can help organizations efficiently scale generative AI workloads while maintaining resilience in the face of limited accelerator capacity.

📄 PDF Abstract BibTeX arXiv:2503.20074

Code (1)

aws-samples/scalable-hw-agnostic-inference 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Adaptive Orchestration for Inference of Large Foundation Models at the Edge

2025-03-19 · Fernando Koch, Aladin Djuhera, Alecio Binotto

Large Foundation Models (LFMs), including multi-modal and generative AI models, promise to unlock new capabilities for next-generation Edge AI applications. However, performing inference with LFMs in resource-constrained…

Edge-computing

Learning to Orchestrate Agents under Uncertainty

2026-05-26 · Mary Chriselda Antony Oliver, Lan Jiang, Aaron Bundi Anampiu, Elaf Almahmoud 외 arxiv

Adaptive orchestration of heterogeneous agents requires making sequential delegation decisions under uncertain and evolving agent behaviour, e.g., coordinating specialised AI models with varying reliability, cost, and re…

A-IO: Adaptive Inference Orchestration for Memory-Bound NPUs

2026-04-10 · Chen Zhang, Yan Ding, Haotian Wang, Chubo Liu 외 arxiv

During the deployment of Large Language Models (LLMs), the autoregressive decoding phase on heterogeneous NPU platforms (e.g., Ascend 910B) faces severe memory-bound challenges. This study reveals the ``Model Scaling Par…

Multi-Agent Coordination Adaptation via Structure-Guided Orchestration

2026-05-25 · Haoran Li, Shulun Chen, Shaoyuan Sun, Hanchen Wang arxiv

As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically ado…

Joint Partitioning and Placement of Foundation Models for Real-Time Edge AI

2025-11-30 · Aladin Djuhera, Fernando Koch, Alecio Binotto arxiv

Inference over large-scale foundation models within heterogeneous edge environments necessitates a fundamentally reconfigurable orchestration substrate. Static partitioning of model layers presumes temporal stability acr…