AIvailable: A Software-Defined Architecture for LLM-as-a-Service on Heterogeneous and Legacy GPUs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Antunes, Pedro, Ortigoso, Ana Rita, Vieira, Gabriel, Fuentes, Daniel, Frazão, Luís, Costa, Nuno, Pereira, António
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914158845362176
author Antunes, Pedro
Ortigoso, Ana Rita
Vieira, Gabriel
Fuentes, Daniel
Frazão, Luís
Costa, Nuno
Pereira, António
author_facet Antunes, Pedro
Ortigoso, Ana Rita
Vieira, Gabriel
Fuentes, Daniel
Frazão, Luís
Costa, Nuno
Pereira, António
contents The rise of Large Language Models (LLM) has increased the need for scalable, high-performance inference systems, yet most existing frameworks assume homogeneous, resource-rich hardware, often unrealistic in academic, or resource-constrained settings. We introduce AIvailable, a low-cost, highly available LLM-as-a-Service (LLMaaS) platform, that uses a software-defined approach for running LLMs across heterogeneous and legacy GPU nodes, including NVIDIA and AMD devices, with a focus on fully utilizing each node's VRAM. AIvailable operates as a fully GPU-accelerated inference without CPU fallbacks, featuring a unified client interface that allows seamless interaction with all deployed LLMs through a single logical unit. The architecture comprises four main components: the Client Interface for user access, the Service Frontend for secure request routing and load balancing, the SDAI Controller for orchestration, deployment, and monitoring, and the Service Backend of heterogeneous GPU nodes executing workloads. By abstracting GPU-specific details and providing dynamic, VRAM-aware allocation and reallocation of models, AIvailable ensures efficient use of resources and resilience against failures or workload fluctuations. Targeting academic labs, private companies, and other constrained organizations, it supports diverse open LLMs helping democratize generative AI through the repurposing of legacy GPUs.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11621
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AIvailable: A Software-Defined Architecture for LLM-as-a-Service on Heterogeneous and Legacy GPUs
Antunes, Pedro
Ortigoso, Ana Rita
Vieira, Gabriel
Fuentes, Daniel
Frazão, Luís
Costa, Nuno
Pereira, António
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Networking and Internet Architecture
I.2.7
The rise of Large Language Models (LLM) has increased the need for scalable, high-performance inference systems, yet most existing frameworks assume homogeneous, resource-rich hardware, often unrealistic in academic, or resource-constrained settings. We introduce AIvailable, a low-cost, highly available LLM-as-a-Service (LLMaaS) platform, that uses a software-defined approach for running LLMs across heterogeneous and legacy GPU nodes, including NVIDIA and AMD devices, with a focus on fully utilizing each node's VRAM. AIvailable operates as a fully GPU-accelerated inference without CPU fallbacks, featuring a unified client interface that allows seamless interaction with all deployed LLMs through a single logical unit. The architecture comprises four main components: the Client Interface for user access, the Service Frontend for secure request routing and load balancing, the SDAI Controller for orchestration, deployment, and monitoring, and the Service Backend of heterogeneous GPU nodes executing workloads. By abstracting GPU-specific details and providing dynamic, VRAM-aware allocation and reallocation of models, AIvailable ensures efficient use of resources and resilience against failures or workload fluctuations. Targeting academic labs, private companies, and other constrained organizations, it supports diverse open LLMs helping democratize generative AI through the repurposing of legacy GPUs.
title AIvailable: A Software-Defined Architecture for LLM-as-a-Service on Heterogeneous and Legacy GPUs
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Networking and Internet Architecture
I.2.7
url https://arxiv.org/abs/2511.11621