Copertina

Scheduling the Unschedulable: Taming Black-Box LLM Inference at Scale

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yuan, Renzhong, Zeng, Yijun, Gao, Xiaosong, Yu, Linxi, Liao, Haochun, Wang, Han
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Distributed, Parallel, and Cluster Computing Operating Systems Performance C.2.4; D.4.4; I.2.11
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Designing Scalable Rate Limiting Systems: Algorithms, Architecture, and Distributed Solutions
di: Guan, Bo
Pubblicazione: (2026)

How Machine Learning-Data Driven Replication Strategies Enhance Fault Tolerance in Large-Scale Distributed Systems
di: Murimi, Almond Kiruthu
Pubblicazione: (2025)

Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly
di: Woisetschläger, Herbert, et al.
Pubblicazione: (2023)

Impact of Network Topology on Byzantine Resilience in Decentralized Federated Learning
di: Bhattacharya, Siddhartha, et al.
Pubblicazione: (2024)

AMP4EC: Adaptive Model Partitioning Framework for Efficient Deep Learning Inference in Edge Computing Environments
di: Zhang, Guilin, et al.
Pubblicazione: (2025)

Complex Event Processing in the Edge: A Combined Optimization Approach for Data and Code Placement
di: Uyanık, Halit, et al.
Pubblicazione: (2026)

Accelerating Geo-distributed Machine Learning with Network-Aware Adaptive Tree and Auxiliary Route
di: Li, Zonghang, et al.
Pubblicazione: (2024)

HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation
di: Nguyen, Thinh, et al.
Pubblicazione: (2025)

How Can We Train Deep Learning Models Across Clouds and Continents? An Experimental Study
di: Erben, Alexander, et al.
Pubblicazione: (2023)

SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters
di: Guo, Dongxin, et al.
Pubblicazione: (2026)

Shattering the Ephemeral Storage Cost Barrier for Data-Intensive Serverless Workflows
di: Ustiugov, Dmitrii, et al.
Pubblicazione: (2023)

TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications
di: Bian, Zhuohang, et al.
Pubblicazione: (2025)

FLEdge: Benchmarking Federated Machine Learning Applications in Edge Computing Systems
di: Woisetschläger, Herbert, et al.
Pubblicazione: (2023)

Libra: Unleashing GPU Heterogeneity for High-Performance Sparse Matrix Multiplication
di: Shi, Jinliang, et al.
Pubblicazione: (2025)

zScore: A Universal Decentralised Reputation System for the Blockchain Economy
di: Udupi, Himanshu, et al.
Pubblicazione: (2025)

Opportunistic Scheduling for Optimal Spot Instance Savings in the Cloud
di: Bhuyan, Neelkamal, et al.
Pubblicazione: (2026)

Shipwright: Proving liveness of distributed systems with Byzantine participants
di: Leung, Derek, et al.
Pubblicazione: (2025)

Federated Learning Model Aggregation in Heterogenous Aerial and Space Networks
di: Dong, Fan, et al.
Pubblicazione: (2023)

Adaptive GPU Resource Allocation for Multi-Agent Collaborative Reasoning in Serverless Environments
di: Zhang, Guilin, et al.
Pubblicazione: (2025)

Dodoor: Efficient Randomized Decentralized Scheduling with Load Caching for Heterogeneous Tasks and Clusters
di: Da, Wei, et al.
Pubblicazione: (2025)

TAGC: Optimizing Gradient Communication in Distributed Transformer Training
di: Polyakov, Igor, et al.
Pubblicazione: (2025)

Chameleon: Adaptive Caching and Scheduling for Many-Adapter LLM Inference Environments
di: Iliakopoulou, Nikoleta, et al.
Pubblicazione: (2024)

FCDP: Fully Cached Data Parallel for Communication-Avoiding Large-Scale Training
di: Park, Gyeongseo, et al.
Pubblicazione: (2026)

Trident: Adaptive Scheduling for Heterogeneous Multimodal Data Pipelines
di: Pan, Ding, et al.
Pubblicazione: (2026)

Token Coherence: Adapting MESI Cache Protocols to Minimize Synchronization Overhead in Multi-Agent LLM Systems
di: Parakhin, Vladyslav
Pubblicazione: (2026)

Next-Generation Event-Driven Architectures: Performance, Scalability, and Intelligent Orchestration Across Messaging Frameworks
di: Arafat, Jahidul, et al.
Pubblicazione: (2025)

Laminar: A Probe-First Scheduling Paradigm with Deterministic Runtime Survival
di: Chu, Zhengyan
Pubblicazione: (2026)

Rank-Aware Resource Scheduling for Tightly-Coupled MPI Workloads on Kubernetes
di: Xie, Tianfang
Pubblicazione: (2026)

dpBento: Benchmarking DPUs for Data Processing
di: Hu, Jiasheng, et al.
Pubblicazione: (2025)

Reexamining Paradigms of End-to-End Data Movement
di: Fang, Chin, et al.
Pubblicazione: (2025)

Serverless Cold Starts and Where to Find Them
di: Joosen, Artjom, et al.
Pubblicazione: (2024)

Bridging Generalization Gap of Heterogeneous Federated Clients Using Generative Models
di: Niu, Ziru, et al.
Pubblicazione: (2025)

Towards Building Private LLMs: Exploring Multi-Node Expert Parallelism on Apple Silicon for Mixture-of-Experts Large Language Model
di: Chen, Mu-Chi, et al.
Pubblicazione: (2025)

DDS: DPU-optimized Disaggregated Storage [Extended Report]
di: Zhang, Qizhen, et al.
Pubblicazione: (2024)

OPTIMUMP2P: Fast and Reliable Gossiping in P2P Networks
di: Nicolaou, Nicolas, et al.
Pubblicazione: (2025)

Verifying In-Network Computing Systems for Design Risks
di: Bai, Tianyu, et al.
Pubblicazione: (2026)

Studying the Effect of Schedule Preemption on Dynamic Task Graph Scheduling
di: Khodabandehlou, Mohammadali, et al.
Pubblicazione: (2026)

EWSJF: An Adaptive Scheduler with Hybrid Partitioning for Mixed-Workload LLM Inference
di: Sidik, Bronislav, et al.
Pubblicazione: (2026)

Exploiting Spot Instances for Time-Critical Cloud Workloads Using Optimal Randomized Strategies
di: Bhuyan, Neelkamal, et al.
Pubblicazione: (2026)

nvidia-pcm: A D-Bus-Driven Platform Configuration Manager for OpenBMC Environments
di: Singh, Harinder
Pubblicazione: (2026)