arXiv subjects

Eiko Yoneki

Publications and source records attributed to Eiko Yoneki.

At least 19 recordsLinked to original sources

arXiv2026

Efficient Multi-round LLM Inference over Disaggregated Serving

With the rapid evolution of Large Language Models (LLMs), multi-round workflows, such as autonomous agents and iterative retrieval, have become increasingly prevalent. However, this raises hurdles for serving LLMs under prefill-decode (PD) disaggregation, a widely adopted paradigm that separates the compute-bound prefill phase and memory-bound decode phase onto individual resources. Specifically, existing systems overlook the interleaved prefill-decode workload pattern in multi-round inference, leading to sub-optimal handling of the incremental prefill workloads and model deployment for the two phases. In this work, we present AMPD, a brand new disaggregated serving framework for multi-round LLM inference. The core of AMPD is to coordinate the prefill workloads based on real-time workloads by adaptively determining where to carry out these workloads and how they are scheduled, in order to maximize service level objective (SLO) attainment. In addition, we tailor a planning algorithm for our scenario, facilitating the deduction of optimal resource allocation and parallel strategies for the two phases. Empirical results demonstrate that AMPD substantially improves SLO attainment compared to state-of-the-art baselines.

cs.DC↗

arXiv2026

OServe: Accelerating LLM Serving via Spatial-Temporal Workload Orchestration

Serving Large Language Models (LLMs) can benefit immensely from parallelizing both the model and input requests across multiple devices, but incoming workloads exhibit substantial spatial and temporal heterogeneity. Spatially, workloads comprise heterogeneous requests with varying compute and memory demands. Temporally, workload composition varies over time. Nevertheless, existing systems typically assume spatially uniform and temporally stable workloads, employing a homogeneous, static model deployment. This mismatch between the assumption and real-world spatial-temporal heterogeneity results in suboptimal performance. We present OServe, an LLM serving system with heterogeneous and flexible model deployment that addresses both spatial and temporal heterogeneity. First, OServe introduces a novel workload-aware scheduling algorithm that optimizes heterogeneous model deployments according to real-time workload characteristics. Second, OServe proposes an efficient workload-adaptive switching method that migrates model deployments in response to predicted workload changes. Experiments on real-world traces show that OServe improves performance by up to 2$\times$ (average: 1.5$\times$) compared to state-of-the-art serving systems.

cs.DC↗

arXiv2026

BOute: Cost-Efficient LLM Serving with Heterogeneous LLMs and GPUs via Multi-Objective Bayesian Optimization

The rapid growth of large language model (LLM) deployments has made cost-efficient serving systems essential. Recent efforts to enhance system cost-efficiency adopt two main perspectives: (i) An algorithmic perspective that exploits heterogeneous model capabilities to route simpler queries to lower-cost models and complex queries to higher-cost models (i.e., heterogeneous query routing); and (ii) a systems perspective that utilizes heterogeneous GPU resources as cost-effective alternatives to homogeneous high-end GPUs (i.e., heterogeneous model deployment). However, algorithm-system co-design for cost-efficient LLM serving necessitates sophisticated management: (i) Determining optimal query routing strategies under latency and quality requirements, (ii) configuring model deployment across heterogeneous GPUs with appropriate resource allocation and parallelism strategies, and (iii) co-optimizing routing and deployment decisions to maximize overall system performance. To address these challenges, we present BOute, a quality-aware scheduling system that jointly exploits heterogeneous model and GPU capabilities for cost-efficient LLM serving. BOute employs a multi-objective Bayesian optimization (MOBO) framework to co-optimize the routing strategy and model deployment, thereby maximizing the cost-efficiency of the serving system while guaranteeing response quality. Evaluation results demonstrate that BOute outperforms state-of-the-art LLM serving systems by up to 157% and 59% on average under identical cost budgets and quality requirements, or reducing serving costs by 15%-61% (38% on average) while maintaining the same performance targets, validating its effectiveness in achieving cost-efficient LLM serving.

cs.DC↗

arXiv2025

ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments

Recent developments in large language models (LLMs) have demonstrated their remarkable proficiency in a range of tasks. Compared to in-house homogeneous GPU clusters, deploying LLMs in cloud environments with diverse types of GPUs is crucial for addressing the GPU shortage problem and being more cost-effective. However, the diversity of network environments and various GPU types on the cloud bring difficulties to achieving high-performance serving. In this work, we propose ThunderServe, a high-performance and cost-efficient LLM serving system for heterogeneous cloud environments. We introduce a novel scheduling algorithm, which optimizes the deployment plan of LLM serving to accommodate the heterogeneous resource and network bandwidth conditions in cloud environments. Furthermore, we propose a lightweight re-scheduling mechanism, designed to adapt to fluctuating online conditions (e.g., node failures, workload shifts) without the need for costly restarts of ongoing services. Empirical results in both heterogeneous cloud and homogeneous in-house environments reveal that ThunderServe delivers up to a 2.1$\times$ and on average a $1.7\times$ increase in throughput and achieves up to a 2.5$\times$ and on average a $1.5\times$ reduction in latency deadlines compared with state-of-the-art systems given the same price budget, suggesting opting for cloud services provides a more cost-efficient solution.

cs.DC↗

arXiv2025

Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs

The scaling law for large language models (LLMs) depicts that the path towards machine intelligence necessitates training at large scale. Thus, companies continuously build large-scale GPU clusters, and launch training jobs that span over thousands of computing nodes. However, LLM pre-training presents unique challenges due to its complex communication patterns, where GPUs exchange data in sparse yet high-volume bursts within specific groups. Inefficient resource scheduling exacerbates bandwidth contention, leading to suboptimal training performance. This paper presents Arnold, a scheduling system summarizing our experience to effectively align LLM communication patterns with data center topology at scale. An in-depth characteristic study is performed to identify the impact of physical network topology to LLM pre-training jobs. Based on the insights, we develop a scheduling algorithm to effectively align communication patterns with the physical network topology in modern data centers. Through simulation experiments, we show the effectiveness of our algorithm in reducing the maximum spread of communication groups by up to $1.67$x. In production training, our scheduling system improves the end-to-end performance by $10.6\%$ when training with more than $9600$ GPUs, a significant improvement for our training pipeline.

cs.DC↗

arXiv2025

AutoIndexer: A Reinforcement Learning-Enhanced Index Advisor Towards Scaling Workloads

Efficiently selecting indexes is fundamental to database performance optimization, particularly for systems handling large-scale analytical workloads. While deep reinforcement learning (DRL) has shown promise in automating index selection through its ability to learn from experience, few works address how these RL-based index advisors can adapt to scaling workloads due to exponentially growing action spaces and heavy trial and error. To address these challenges, we introduce AutoIndexer, a framework that combines workload compression, query optimization, and specialized RL models to scale index selection effectively. By operating on compressed workloads, AutoIndexer substantially lowers search complexity without sacrificing much index quality. Extensive evaluations show that it reduces end-to-end query execution time by up to 95% versus non-indexed baselines. On average, it outperforms state-of-the-art RL-based index advisors by approximately 20% in workload cost savings while cutting tuning time by over 50%. These results affirm AutoIndexer's practicality for large and diverse workloads.

cs.DB↗

arXiv2025

Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs

Recent advancements in Large Language Models (LLMs) have led to increasingly diverse requests, accompanied with varying resource (compute and memory) demands to serve them. However, this in turn degrades the cost-efficiency of LLM serving as common practices primarily rely on homogeneous GPU resources. In response to this problem, this work conducts a thorough study about serving LLMs over heterogeneous GPU resources on cloud platforms. The rationale is that different GPU types exhibit distinct compute and memory characteristics, aligning well with the divergent resource demands of diverse requests. Particularly, through comprehensive benchmarking, we discover that the cost-efficiency of LLM serving can be substantially optimized by meticulously determining GPU composition, deployment configurations, and workload assignments. Subsequently, we design a scheduling algorithm via mixed-integer linear programming, aiming at deducing the most cost-efficient serving plan under the constraints of price budget and real-time GPU availability. Remarkably, our approach effectively outperforms homogeneous and heterogeneous baselines under a wide array of scenarios, covering diverse workload traces, varying GPU availablilities, and multi-model serving. This casts new light on more accessible and efficient LLM serving over heterogeneous cloud resources.

cs.DC↗

arXiv2025

Navigating in High-Dimensional Search Space: A Hierarchical Bayesian Optimization Approach

Optimizing black-box functions in high-dimensional search spaces has been known to be challenging for traditional Bayesian Optimization (BO). In this paper, we introduce HiBO, a novel hierarchical algorithm integrating global-level search space partitioning information into the acquisition strategy of a local BO-based optimizer. HiBO employs a search-tree-based global-level navigator to adaptively split the search space into partitions with different sampling potential. The local optimizer then utilizes this global-level information to guide its acquisition strategy towards most promising regions within the search space. A comprehensive set of evaluations demonstrates that HiBO outperforms state-of-the-art methods in high-dimensional synthetic benchmarks and presents significant practical effectiveness in the real-world task of tuning configurations of database management systems (DBMSs).

cs.LG↗

arXiv2025

A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning Enhanced Approach

Learned Index Structures (LIS) have significantly advanced data management by leveraging machine learning models to optimize data indexing. However, designing these structures often involves critical trade-offs, making it challenging for both designers and end-users to find an optimal balance tailored to specific workloads and scenarios. While some indexes offer adjustable parameters that demand intensive manual tuning, others rely on fixed configurations based on heuristic auto-tuners or expert knowledge, which may not consistently deliver optimal performance. This paper introduces LITune, a novel framework for end-to-end automatic tuning of Learned Index Structures. LITune employs an adaptive training pipeline equipped with a tailor-made Deep Reinforcement Learning (DRL) approach to ensure stable and efficient tuning. To accommodate long-term dynamics arising from online tuning, we further enhance LITune with an on-the-fly updating mechanism termed the O2 system. These innovations allow LITune to effectively capture state transitions in online tuning scenarios and dynamically adjust to changing data distributions and workloads, marking a significant improvement over other tuning methods. Our experimental results demonstrate that LITune achieves up to a 98% reduction in runtime and a 17-fold increase in throughput compared to default parameter settings given a selected Learned Index instance. These findings highlight LITune's effectiveness and its potential to facilitate broader adoption of LIS in real-world applications.

cs.DB↗

arXiv2025

CuAsmRL: Optimizing GPU SASS Schedules via Deep Reinforcement Learning

Large language models (LLMs) are remarked by their substantial computational requirements. To mitigate the cost, researchers develop specialized CUDA kernels, which often fuse several tensor operations to maximize the utilization of GPUs as much as possible. However, those specialized kernels may still leave performance on the table as CUDA assembly experts show that manual optimization of GPU SASS schedules can lead to better performance, and trial-and-error is largely employed to manually find the best GPU SASS schedules. In this work, we employ an automatic approach to optimize GPU SASS schedules, which thus can be integrated into existing compiler frameworks. The key to automatic optimization is training an RL agent to mimic how human experts perform manual scheduling. To this end, we formulate an assembly game, where RL agents can play to find the best GPU SASS schedules. The assembly game starts from a \textit{-O3} optimized SASS schedule, and the RL agents can iteratively apply actions to mutate the current schedules. Positive rewards are generated if the mutated schedules get higher throughput by executing on GPUs. Experiments show that CuAsmRL can further improve the performance of existing specialized CUDA kernels transparently by up to $26\%$, and on average $9\%$. Moreover, it is used as a tool to reveal potential optimization moves learned automatically.

cs.AR↗

arXiv2024

Optimizing Tensor Computation Graphs with Equality Saturation and Monte Carlo Tree Search

The real-world effectiveness of deep neural networks often depends on their latency, thereby necessitating optimization techniques that can reduce a model's inference time while preserving its performance. One popular approach is to sequentially rewrite the input computation graph into an equivalent but faster one by replacing individual subgraphs. This approach gives rise to the so-called phase-ordering problem in which the application of one rewrite rule can eliminate the possibility to apply an even better one later on. Recent work has shown that equality saturation, a technique from compiler optimization, can mitigate this issue by first building an intermediate representation (IR) that efficiently stores multiple optimized versions of the input program before extracting the best solution in a second step. In practice, however, memory constraints prevent the IR from capturing all optimized versions and thus reintroduce the phase-ordering problem in the construction phase. In this paper, we present a tensor graph rewriting approach that uses Monte Carlo tree search to build superior IRs by identifying the most promising rewrite rules. We also introduce a novel extraction algorithm that can provide fast and accurate runtime estimates of tensor programs represented in an IR. Our approach improves the inference speedup of neural networks by up to 11% compared to existing methods.

cs.LG↗

arXiv2024

Learned Graph Rewriting with Equality Saturation: A New Paradigm in Relational Query Rewrite and Beyond

Query rewrite systems perform graph substitutions using rewrite rules to generate optimal SQL query plans. Rewriting logical and physical relational query plans is proven to be an NP-hard sequential decision-making problem with a search space exponential in the number of rewrite rules. In this paper, we address the query rewrite problem by interleaving Equality Saturation and Graph Reinforcement Learning (RL). The proposed system, Aurora, rewrites relational queries by guiding Equality Saturation, a method from compiler literature to perform non-destructive graph rewriting, with a novel RL agent that embeds both the spatial structure of the query graph as well as the temporal dimension associated with the sequential construction of query plans. Our results show Graph Reinforcement Learning for non-destructive graph rewriting yields SQL plans orders of magnitude faster than existing equality saturation solvers, while also achieving competitive results against mainstream query optimisers.

cs.DB↗

arXiv2024

IA2: Leveraging Instance-Aware Index Advisor with Reinforcement Learning for Diverse Workloads

This study introduces the Instance-Aware Index Advisor (IA2), a novel deep reinforcement learning (DRL)-based approach for optimizing index selection in databases facing large action spaces of potential candidates. IA2 introduces the Twin Delayed Deep Deterministic Policy Gradient - Temporal Difference State-Wise Action Refinery (TD3-TD-SWAR) model, enabling efficient index selection by understanding workload-index dependencies and employing adaptive action masking. This method includes a comprehensive workload model, enhancing its ability to adapt to unseen workloads and ensuring robust performance across diverse database environments. Evaluation on benchmarks such as TPC-H reveals IA2's suggested indexes' performance in enhancing runtime, securing a 40% reduction in runtime for complex TPC-H workloads compared to scenarios without indexes, and delivering a 20% improvement over existing state-of-the-art DRL-based index advisors.

cs.DB↗

arXiv2024

SIP: Autotuning GPU Native Schedules via Stochastic Instruction Perturbation

Large language models (LLMs) have become a significant workload since their appearance. However, they are also computationally expensive as they have billions of parameters and are trained with massive amounts of data. Thus, recent works have developed dedicated CUDA kernels for LLM training and inference instead of relying on compilergenerated ones, so that hardware resources are as fully utilized as possible. In this work, we explore the possibility of GPU native instruction optimization to further push the CUDA kernels to extreme performance. Contrary to prior works, we adopt an automatic optimization approach by defining a search space of possible GPU native instruction schedules, and then we apply stochastic search to perform optimization. Experiments show that SIP can further improve CUDA kernel throughput by automatically discovering better GPU native instruction schedules and the optimized schedules are tested by 10 million test samples.

cs.AR↗

arXiv2023

X-RLflow: Graph Reinforcement Learning for Neural Network Subgraphs Transformation

Tensor graph superoptimisation systems perform a sequence of subgraph substitution to neural networks, to find the optimal computation graph structure. Such a graph transformation process naturally falls into the framework of sequential decision-making, and existing systems typically employ a greedy search approach, which cannot explore the whole search space as it cannot tolerate a temporary loss of performance. In this paper, we address the tensor graph superoptimisation problem by exploring an alternative search approach, reinforcement learning (RL). Our proposed approach, X-RLflow, can learn to perform neural network dataflow graph rewriting, which substitutes a subgraph one at a time. X-RLflow is based on a model-free RL agent that uses a graph neural network (GNN) to encode the target computation graph and outputs a transformed computation graph iteratively. We show that our approach can outperform state-of-the-art superoptimisation systems over a range of deep learning models and achieve by up to 40% on those that are based on transformer-style architectures.

cs.LG↗

arXiv2023

MCTS-GEB: Monte Carlo Tree Search is a Good E-graph Builder

Rewrite systems [6, 10, 12] have been widely employing equality saturation [9], which is an optimisation methodology that uses a saturated e-graph to represent all possible sequences of rewrite simultaneously, and then extracts the optimal one. As such, optimal results can be achieved by avoiding the phase-ordering problem. However, we observe that when the e-graph is not saturated, it cannot represent all possible rewrite opportunities and therefore the phase-ordering problem is re-introduced during the construction phase of the e-graph. To address this problem, we propose MCTS-GEB, a domain-general rewrite system that applies reinforcement learning (RL) to e-graph construction. At its core, MCTS-GEB uses a Monte Carlo Tree Search (MCTS) [3] to efficiently plan for the optimal e-graph construction, and therefore it can effectively eliminate the phase-ordering problem at the construction phase and achieve better performance within a reasonable time. Evaluation in two different domains shows MCTS-GEB can outperform the state-of-the-art rewrite systems by up to 49x, while the optimisation can generally take less than an hour, indicating MCTS-GEB is a promising building block for the future generation of rewrite systems.

cs.AI↗

arXiv2023

Guided Graph Generation: Evaluation of Graph Generators in Terms of Network Statistics, and a New Algorithm

We consider the problem of graph generation guided by network statistics, i.e., the generation of graphs which have given values of various numerical measures that characterize networks, such as the clustering coefficient and the number of cycles of given lengths. Algorithms for the generation of synthetic graphs are often based on graph growth models, i.e., rules of adding (and sometimes removing) nodes and edges to a graph that mimic the processes present in real-world networks. While such graph generators are desirable from a theoretical point of view, they are often only able to reproduce a narrow set of properties of real-world networks, resulting in graphs with otherwise unrealistic properties. In this article, we instead evaluate common graph generation algorithms at the task of reproducing the numerical statistics of real-world networks, such as the clustering coefficient, the degree assortativity, and the connectivity. We also propose an iterative algorithm, the Guided Graph Generator, based on a greedy-like procedure that recovers realistic values over a large number of commonly used graph statistics, while at the same time allowing an efficient implementation based on incremental updating of only a small number of subgraph counts. We show that the proposed algorithm outperforms previous graph generation algorithms in terms of the error in the reconstructed graphs for a large number of graph statistics such as the clustering coefficient, the assortativity, the mean node distance, and also evaluate the algorithm in terms of precision, speed of convergence and scalability, and compare it to previous graph generators and models. We also show that the proposed algorithm generates graphs with realistic degree distributions, graph spectra, clustering coefficient distributions, and distance distributions.

cs.SI↗

arXiv2022

RLFlow: Optimising Neural Network Subgraph Transformation with World Models

Training deep learning models takes an extremely long execution time and consumes large amounts of computing resources. At the same time, recent research proposed systems and compilers that are expected to decrease deep learning models runtime. An effective optimisation methodology in data processing is desirable, and the reduction of compute requirements of deep learning models is the focus of extensive research. In this paper, we address the neural network sub-graph transformation by exploring reinforcement learning (RL) agents to achieve performance improvement. Our proposed approach RLFlow can learn to perform neural network subgraph transformations, without the need for expertly designed heuristics to achieve a high level of performance. Recent work has aimed at applying RL to computer systems with some success, especially using model-free RL techniques. Model-based reinforcement learning methods have seen an increased focus in research as they can be used to learn the transition dynamics of the environment; this can be leveraged to train an agent using a hallucinogenic environment such as World Model (WM), thereby increasing sample efficiency compared to model-free approaches. WM uses variational auto-encoders and it builds a model of the system and allows exploring the model in an inexpensive way. In RLFlow, we propose a design for a model-based agent with WM which learns to optimise the architecture of neural networks by performing a sequence of sub-graph transformations to reduce model runtime. We show that our approach can match the state-of-the-art performance on common convolutional networks and outperforms by up to 5% those based on transformer-style architectures

cs.LG↗