Mixture-of-Experts (MoE) models scale large language models through conditional computation, but inference becomes memory-bound once expert weights exceed the capacity of GPU memory. In this case, weights must be offloaded to external memory, and fetching them incurs costly and repeated transfers. We address this by adopting CXL-attached near-data processing (CXL-NDP) as the offloading tier to execute cold experts in place, converting expensive parameter movement into cheaper activation movement. Unlike prior GPU-NDP systems that are largely context-agnostic and reactive, we develop a context-aware MoE system that uses prefill-stage activation statistics to guide decoding-stage expert placement, dynamically pins hot experts in GPU-side HBM, and maps the remainder to CXL-NDP. To meet NDP's limited compute throughput, we introduce context-aware mixed-precision quantization that allocates per-expert bitwidths (1-4 bit) based on prefill stage. The resulting MoE inference system overlaps GPU and NDP execution while minimizing cross-device movement. The evaluation on the GPU-NDP system shows that our approach achieves up to an 8.7-fold decoding throughput improvement over the state-of-the-art method, while incurring only a 0.13% average accuracy drop.

Migrating a set of software variants into a software product line (SPL) is an expensive and potentially challenging endeavor. Indeed, SPL engineering can significantly impact a company's development process and often requires changes to established developer practices. The work presented in this paper stems from a collaboration with a Small and Medium-sized Enterprise (SME) that decided to migrate its existing code base into an SPL. In this study, we conducted an in-depth evaluation of the company's current development processes and practices, as well as the anticipated benefits and risks associated with the migration. Key stakeholders involved in software development participated in this evaluation to provide insight into their perceptions of the migration and their potential resistance to change. This paper describes the design of the interviews conducted with these stakeholders and presents an analysis of the results. Among the qualitative findings, we observed that all participants, regardless of their role in the development process, identified benefits of the migration relevant to their own activities. Furthermore, our results suggest that an effective risk mitigation strategy involves keeping stakeholders informed and engaged throughout the process, preserving as many good practices as possible, and actively involving them in the migration to ensure a smooth transition and minimize potential challenges.

Out-of-tree kernel patches are essential for adapting the Linux kernel to new hardware or enabling specific functionalities. Maintaining and updating these patches across different kernel versions demands significant effort from experienced engineers. Large language models (LLMs) have shown remarkable progress across various domains, suggesting their potential for automating out-of-tree kernel patch migration. However, our findings reveal that LLMs, while promising, struggle with incomplete code context understanding and inaccurate migration point identification. In this work, we propose MigGPT, a framework that employs a novel code fingerprint structure to retain code snippet information and incorporates three meticulously designed modules to improve the migration accuracy and efficiency of out-of-tree kernel patches. Furthermore, we establish a robust benchmark using real-world out-of-tree kernel patch projects to evaluate LLM capabilities. Evaluations show that MigGPT significantly outperforms the direct application of vanilla LLMs, achieving an average completion rate of 74.07 for migration tasks.

The paper presents a multi-resource load balancing strategy which can be utilised within an agent-based system. This approach can assist system designers in their attempts to optimise the structure for complex enterprise architectures. In this system, the social behaviour of the agent and its adaptation abilities are applied to determine an optimal setup for a given configuration. All the methods have been developed to allow the agent's self-assessment. The proposed agent system has been implemented and the experiment results are presented here.

Linux kernel evolution breaks drivers through API/ABI changes, semantic shifts, and security-hardening updates. We introduce DRIVEBENCH, an executable corpus of kernel$\rightarrow$driver co-evolution cases, and AUTODRIVER, a closed-loop, LLM-driven system for automating driver maintenance. The system integrates prompt engineering, multi-agent collaboration, static analysis, and iterative validation to ensure that generated patches are not only syntactically correct but also functionally and semantically consistent with kernel conventions. The corpus spans v5.10-v6.10 with 235 validated cases drawn from 612 candidates. In evaluation across 55 cases, AUTODRIVER achieves 56.4% compilation success; QEMU-based boot verification indicates that compiled patches preserve driver initialization in most instances. By releasing DRIVEBENCH and tooling, we enable reproducible research and a practical route to continuous, safe co-evolution of drivers with the Linux kernel.

UK's sweeping asylum law changes: How will they impact refugees? Shabana Mahmood, the United Kingdom's home secretary, has said the country's asylum system is "not working" and is placing "intense strain on communities" ahead of proposals for major government reforms that would end refugees' automatic right to settle permanently in the UK. Speaking to the BBC on Sunday, Mahmood said undocumented migration is "tearing the country apart". First, they would end the automatic path to settled status for refugees after five years. And second, they would remove state benefits from those who have the right to work and can support themselves.

A 40,000 kilograms Humpback Whale gracefully swims through the ocean, accompanied by two playful Bottlenose Dolphins. For a fleeting moment, the dolphins join the whale's majestic northern migration, sharing its journey through the vast blue expanse of the sea. Breakthroughs, discoveries, and DIY tips sent every weekday. Humpback whales can travel up to 5,000 miles on migrations. During these long-distance journeys, the majestic sea creatures can even give birth .

Hongyu Zhu, Tina Samizadeh, Rute C. Sofia fortiss - research Institute of the Free State of Bavaria associated with the Technical University of Munich (TUM) Abstract--Autonomous Mobile Robots (AMRs) increasingly adopt containerized micro-services across the Edge-Cloud continuum. While Kubernetes is the de-facto orchestrator for such systems, its assumptions--stable networks, homogeneous resources, and ample compute capacity do not fully hold in mobile, resource-constrained robotic environments. The paper describes a case-study on smart-manufacturing AMR and performs an initial comparison between CODECO orchestration and standard Kubernetes using a controlled Kubernetes-in-Docker (KinD) environment. Metrics include pod deployment and deletion times, CPU and memory usage, and inter-pod data rates. The observed results indicate that CODECO offers reduced CPU consumption and more stable communication patterns, at the cost of modest memory overhead ( 10-15%) and slightly increased pod lifecycle latency due to secure overlay initialization. Kubernetes provides declarative configuration, automated scaling, and robust availability mechanisms that make it highly effective in cloud data-centers. However, its design assumptions, namely, the existence of relatively stable networks, abundant compute resources, and largely static infrastructure, do not fully hold in Edge-Edge and Edge-Cloud environments. In such settings, resources can be constrained and heterogeneous.

The development of smart systems (i.e., systems enhanced with AI components) has thrived thanks to the rapid advancements in neural networks (NNs). A wide range of libraries and frameworks have consequently emerged to support NN design and implementation. The choice depends on factors such as available functionalities, ease of use, documentation and community support. After adopting a given NN framework, organizations might later choose to switch to another if performance declines, requirements evolve, or new features are introduced. Unfortunately, migrating NN implementations across libraries is challenging due to the lack of migration approaches specifically tailored for NNs. This leads to increased time and effort to modernize NNs, as manual updates are necessary to avoid relying on outdated implementations and ensure compatibility with new features. In this paper, we propose an approach to automatically migrate neural network code across deep learning frameworks. Our method makes use of a pivot NN model to create an abstraction of the NN prior to migration. We validate our approach using two popular NN frameworks, namely PyTorch and TensorFlow. We also discuss the challenges of migrating code between the two frameworks and how they were approached in our method. Experimental evaluation on five NNs shows that our approach successfully migrates their code and produces NNs that are functionally equivalent to the originals. Artefacts from our work are available online.

Modern software programs are built on stacks that are often undergoing changes that introduce updates and improvements, but may also break any project that depends upon them. In this paper we explore the use of Large Language Models (LLMs) for code migration, specifically the problem of maintaining compatibility with a dependency as it undergoes major and minor semantic version changes. We demonstrate, using metrics such as test coverage and change comparisons, that contexts containing diffs can significantly improve performance against out of the box LLMs and, in some cases, perform better than using code. We provide a dataset to assist in further development of this problem area, as well as an open-source Python package, AIMigrate, that can be used to assist with migrating code bases. In a real-world migration of TYPHOIDSIM between STARSIM versions, AIMigrate correctly identified 65% of required changes in a single run, increasing to 80% with multiple runs, with 47% of changes generated perfectly.