EY
Eiko Yoneki
cs.LGcs.AIcs.DBcs.DCstat.MLcs.ARcs.IRcs.NIcs.PLcs.SI
On Valency
published · living versionsW_ajdq8vfr·v1 · currentpublished
Introducing Cluster Efficiency to LLM Serving: Pooling Economical Accelerators over Fast Interconnects
with Youhe Jiang, Pavle Glušac, Binhang Yuan
1 version
Preprints & journals
31 papers in the corpus · 2010–2026Efficient Multi-round LLM Inference over Disaggregated Serving2602.14516v2 · Wenhao He, Youhe Jiang, Penghao Zhao et al.2026 · 0 citationsarXiv
OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration2602.12151v2 · Youhe Jiang, Fangcheng Fu, Taiyi Wang et al.2026 · 0 citationsarXiv
BOute: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimization2602.10729v1 · Youhe Jiang, Fangcheng Fu, Eiko Yoneki2026 · 0 citationsarXiv
Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs2509.15940v1 · Guoliang He, Youhe Jiang, Wencong Xiao et al.2025 · 2 citationsarXiv
AutoIndexer: A Reinforcement Learning-Enhanced Index Advisor Towards Scaling Workloads2507.23084v1 · Taiyi Wang, Eiko Yoneki2025 · 0 citationsarXiv
ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments2502.09334v2 · Youhe Jiang, Fangcheng Fu, Xiaozhe Yao et al.2025 · 0 citationsarXiv
A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning Enhanced Approach2502.05001v2 · Taiyi Wang, Liang Liang, Guang Yang et al.2025 · 3 citationsarXiv
Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs2502.00722v2 · Youhe Jiang, Fangcheng Fu, Xiaozhe Yao et al.2025 · 0 citationsarXiv
CuAsmRL: Optimizing GPU SASS Schedules via Deep Reinforcement Learning2501.08071v1 · Guoliang He, Eiko Yoneki2025 · 7 citationsarXiv
Navigating in High-Dimensional Search Space: A Hierarchical Bayesian Optimization Approach2410.23148v6 · Wenxuan Li, Taiyi Wang, Eiko Yoneki2024 · 1 citationarXiv
Optimizing Tensor Computation Graphs with Equality Saturation and Monte Carlo Tree Search2410.05534v1 · Jakob Hartmann, Guoliang He, Eiko Yoneki2024 · 7 citationsarXiv
Learned Graph Rewriting with Equality Saturation: A New Paradigm in Relational Query Rewrite and Beyond2407.12794v1 · George-Octavian Barbulescu, Taiyi Wang, Zak Singh et al.2024 · 0 citationsarXiv
IA2: Leveraging Instance-Aware Index Advisor with Reinforcement Learning for Diverse Workloads2404.05777v2 · Taiyi Wang, Eiko Yoneki2024 · 3 citationsarXiv
SIP: Autotuning GPU Native Schedules via Stochastic Instruction Perturbation2403.16863v1 · Guoliang He, Eiko Yoneki2024 · 0 citationsarXiv
X-RLflow: Graph Reinforcement Learning for Neural Network Subgraphs Transformation2304.14698v1 · Guoliang He, Sean Parker, Eiko Yoneki2023 · 2 citationsarXiv
MCTS-GEB: Monte Carlo Tree Search is a Good E-graph Builder2303.04651v3 · Guoliang He, Zak Singh, Eiko Yoneki2023 · 7 citationsarXiv
Guided Graph Generation: Evaluation of Graph Generators in Terms of Network Statistics, and a New Algorithm2303.00635v1 · J'erome Kunegis, Jun Sun, Eiko Yoneki2023 · 0 citationsarXiv
RLFlow: Optimising Neural Network Subgraph Transformation with World Models2205.01435v2 · Sean Parker, Sami Alabed, Eiko Yoneki2022 · 0 citationsarXiv
BoGraph: Structured Bayesian Optimization From Logs for Expensive Systems with Many Parameters2112.08774v2 · Sami Alabed, Eiko Yoneki2021 · 2 citationsarXiv
GDDR: GNN-based Data-Driven Routing2104.09919v1 · Oliver Hope, Eiko Yoneki2021 · 33 citationsarXiv
High-Dimensional Bayesian Optimization with Multi-Task Learning for RocksDB2103.16267v2 · Sami Alabed, Eiko Yoneki2021 · 16 citations{The 1st Workshop on Machine Learning and Systems (EuroMLSys'21), April 26, 2021, Online, United Kingdom}
The Future is Big Graphs! A Community View on Graph Processing Systems2012.06171v1 · Sherif Sakr, Angela Bonifati, Hannes Voigt et al.2020 · 159 citationsarXiv
Learning Index Selection with Structured Action Spaces1909.07440v1 · Jeremy Welborn, Michael Schaarschmidt, Eiko Yoneki2019 · 7 citationsarXiv
Wield: Systematic Reinforcement Learning With Progressive Randomization1909.06844v1 · Michael Schaarschmidt, Kai Fricke, Eiko Yoneki2019 · 0 citationsarXiv
Cloud Futurology1902.03656v1 · Blesson Varghese, Philipp Leitner, Suprio Ray et al.2019 · 0 citationsarXiv
RLgraph: Modular Computation Graphs for Deep Reinforcement Learning1810.09028v2 · Michael Schaarschmidt, Sven Mika, Kai Fricke et al.2018 · 13 citationsarXiv
LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations1808.07903v1 · Michael Schaarschmidt, Alexander Kuhnle, Ben Ellis et al.2018 · 36 citationsarXiv
Tuning the Scheduling of Distributed Stochastic Gradient Descent with Bayesian Optimization1612.00383v1 · Valentin Dalibard, Michael Schaarschmidt, Eiko Yoneki2016 · 0 citationsarXiv
Learning Runtime Parameters in Computer Systems with Delayed Experience Injection1610.09903v1 · Michael Schaarschmidt, Felix Gessert, Valentin Dalibard et al.2016 · 8 citationsarXiv
Web Data Knowledge Extraction1603.07534v1 · Juan M. Tirado, Ovidiu Serban, Qiang Guo et al.2016 · 4 citationsarXiv
European routes to reinventing Internet technology.20336112 · Crowcroft, Jon, Yoneki, Eiko2010 · 0 citationsNature. 2010;464(7288):486
Career total: 191 works. 31 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.