Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.39631

Kirin: Cloud-native WebAssembly Service Orchestration

Joshua Bauer·Sebastian Werner·Maria C. Borges
View original source ↗Read source document ↗Export metadata ↓

Abstract

Modern cloud computing infrastructure relies heavily on virtualization to provide workload isolation and resource efficiency. While containers have become the dominant deployment primitive due to their fast orchestration compared to traditional virtual machines, they still introduce non-trivial overhead. WebAssembly (Wasm) has emerged as an alternative isolation technology, offering a lightweight execution model. Because of compatibility limitations, WebAssembly has mainly been applied to Function-as-a-Service (FaaS) and Edge Computing scenarios, where it has attracted growing research interest. However, recent advances in the WebAssembly ecosystem have significantly matured the technology, raising the question of whether it can serve as a viable replacement for containers in cloud-native workloads. In this paper, we present Kirin, an orchestrator for cloud-native WebAssembly services. It supports core orchestration responsibilities, including resource scheduling, lifecycle management, scaling, and request routing. We evaluate Kirin against container-based deployments for several service workloads and demonstrate promising results, particularly in service lifecycle management. Simultaneously, we confirm known limitations in CPU-intensive workloads. However, for typical service workloads, Kirin demonstrates competitive performance, suggesting that WebAssembly is a viable candidate for broader adoption as a cloud-native deployment technology.

Explore related subjects

cs.DC

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Joshua Bauer, Sebastian Werner, Maria C. Borges. 2026-09-30. Kirin: Cloud-native WebAssembly Service Orchestration. https://arxiv.org/abs/2609.39631

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Deterministic Self-Stabilizing BFS Construction in Constant Space

In this paper, we resolve a long-standing question in self-stabilization by demonstrating that it is indeed possible to construct a spanning tree in a semi-uniform network using constant memory per node. We introduce a self-stabilizing synchronous algorithm that builds a breadth-first search (BFS) spanning tree with only $O(1)$ bits of memory per node, converging in $2^ε$ time units, where $ε$ denotes the eccentricity of the distinguish node. Crucially, our approach operates without any prior knowledge of global network parameters such as maximum degree, diameter, or total node count. In contrast to traditional self-stabilizing methods, such as pointer-to-neighbor communication or distance-to-root computation, that are unsuitable under strict memory constraints, our solution employs an innovative constant-space token dissemination mechanism. This mechanism effectively eliminates cycles and rectifies deviations in the BFS structure, ensuring both correctness and memory efficiency. The proposed algorithm not only meets the stringent requirements of memory-constrained distributed systems but also opens new avenues for research in self-stabilizing protocols under severe resource limitations.

cs.DC↗
arXiv2026

Space Filling Curves is All You Need: Communication-Avoiding Matrix Multiplication Made Simple

General Matrix Multiplication (GEMM) is the cornerstone of HPC workloads and Deep Learning. State-of-the-art (SOTA) vendor libraries tune tensor layouts, parallelization schemes and cache blocking to minimize data movement across the memory hierarchy and maximize throughput. However, optimal settings for these parameters depend on the target platform and matrix shapes, making exhaustive tuning infeasible. In this work, we address this cumbersome scheduling search and tuning using space-filling curves (SFC). We partition the matrix multiplication using advancements in SFC, and obtain platform-oblivious and shape-oblivious matrix multiplication schemes with a high degree of data locality. We extend the SFC-based work partitioning to implement Communication-Avoiding (CA) algorithms with replication techniques in a seamless fashion. The resulting SFC-CA GEMM achieves provable asymptotic communication optimality for both square and rectangular matrix regimes. Across four x86 and Arm platforms, SFC-CA GEMM outperforms vendor libraries by up to 5.5$\times$ per shape and 1.8$\times$ in weighted harmonic mean (WHM) throughput. Last, we show the impact of our work on two real-world applications by leveraging our SFC-CA GEMM as a compute backend: i) prefill of LLM inference with speedups up to 1.85$\times$ over SOTA inference runtimes, and ii) distributed-memory matrix multiplication with speedups up to 2.3$\times$ over the SOTA distributed-memory GEMM framework with vendor-optimized compute backend.

cs.DC↗
arXiv2026

MoEless: Efficient MoE LLM Serving with Serverless Experts

Large Language Models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale efficiently under stringent resource constraints. However, MoE's sparse activation causes severe expert load imbalance, where a few experts become stragglers while others remain underutilized, leading to inflated inference latency and cost. Existing solutions assume static, serverful model deployments, limiting expert elasticity and often incurring costly expert swapping or degraded output quality. We present MoEless, an efficient serverless MoE serving framework that mitigates expert load imbalance via elastic expert execution. MoEless leverages lightweight, layer-aware predictors to estimate incoming expert load distributions and proactively identify stragglers. We design optimized scaling and placement strategies to improve function locality, GPU utilization, and cross-expert load balance. MoEless is prototyped on top of Megatron-LM and deployed on an eight-GPU testbed. Experiments with open-source MoE models and real-world workloads show that MoEless reduces inference latency by 43% and inference cost by 84% compared to state-of-the-art solutions.

cs.DC↗