Guardado en:
Detalles Bibliográficos
Autores principales: Malleni, Sai Sindhur, Sevilla, Raúl, Vasilevskii, Aleksei, Lema, José Castillo, Bauer, André
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.04900
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914322847891456
author Malleni, Sai Sindhur
Sevilla, Raúl
Vasilevskii, Aleksei
Lema, José Castillo
Bauer, André
author_facet Malleni, Sai Sindhur
Sevilla, Raúl
Vasilevskii, Aleksei
Lema, José Castillo
Bauer, André
contents As Generative AI (GenAI), particularly inference, rapidly emerges as a dominant workload category, the Kubernetes ecosystem is proactively evolving to natively support its unique demands. This industry paper demonstrates how emerging Kubernetes-native projects can be combined to deliver the benefits of container orchestration, such as scalability and resource efficiency, to complex AI workflows. We implement and evaluate an illustrative, multi-stage use case consisting of automatic speech recognition and summarization. First, we address batch inference by using Kueue to manage jobs that transcribe audio files with Whisper models and Dynamic Accelerator Slicer (DAS) to increase parallel job execution. Second, we address a discrete online inference scenario by feeding the transcripts to a Large Language Model for summarization hosted using llm-d, a novel solution utilizing the recent developments around the Kubernetes Gateway API Inference Extension (GAIE) for optimized routing of inference requests. Our findings illustrate that these complementary components (Kueue, DAS, and GAIE) form a cohesive, high-performance platform, proving Kubernetes' capability to serve as a unified foundation for demanding GenAI workloads: Kueue reduced total makespan by up to 15%; DAS shortened mean job completion time by 36\%; and GAIE working in conjunction with llm-d improved tail Time to First Token latency by up to 90% even under high loads.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04900
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evaluating Kubernetes Performance for GenAI Inference: From Automatic Speech Recognition to LLM Summarization
Malleni, Sai Sindhur
Sevilla, Raúl
Vasilevskii, Aleksei
Lema, José Castillo
Bauer, André
Emerging Technologies
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
As Generative AI (GenAI), particularly inference, rapidly emerges as a dominant workload category, the Kubernetes ecosystem is proactively evolving to natively support its unique demands. This industry paper demonstrates how emerging Kubernetes-native projects can be combined to deliver the benefits of container orchestration, such as scalability and resource efficiency, to complex AI workflows. We implement and evaluate an illustrative, multi-stage use case consisting of automatic speech recognition and summarization. First, we address batch inference by using Kueue to manage jobs that transcribe audio files with Whisper models and Dynamic Accelerator Slicer (DAS) to increase parallel job execution. Second, we address a discrete online inference scenario by feeding the transcripts to a Large Language Model for summarization hosted using llm-d, a novel solution utilizing the recent developments around the Kubernetes Gateway API Inference Extension (GAIE) for optimized routing of inference requests. Our findings illustrate that these complementary components (Kueue, DAS, and GAIE) form a cohesive, high-performance platform, proving Kubernetes' capability to serve as a unified foundation for demanding GenAI workloads: Kueue reduced total makespan by up to 15%; DAS shortened mean job completion time by 36\%; and GAIE working in conjunction with llm-d improved tail Time to First Token latency by up to 90% even under high loads.
title Evaluating Kubernetes Performance for GenAI Inference: From Automatic Speech Recognition to LLM Summarization
topic Emerging Technologies
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2602.04900