arXiv:2604. 26963v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators.
arXiv:2609.17193v1 Announce Type: new Abstract: Large language model (LLM)-powered agentic AI services increasingly demand low-latency inference, motivating the deployment of LLMs across distributed...
arXiv:2607. 03876v1 Announce Type: new Abstract: With the rise of small quantized GGUF-based language models and their increasing use for on-device inference tasks, we have seen the growing need for an approach capable of reliably delivering these models at scale even under severe memory bandwidth constraints such as those imposed by pure CPU implementations.
DART-FL is a multitask federated learning framework designed for edge devices that must balance online inference and model training under limited resources. It dynamically allocates resources between inference and training based on current inference backlog and service capacity, then distributes remaining training capacity among tasks using a queue‑aware scheduler that adjusts loss weights. Experiments on image classification datasets with synthetic and real workloads show that DART‑FL adapts to bursty inference demand, improving accuracy for high‑demand tasks while preserving overall multitask performance.
arXiv:2607. 24787v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models expand foundation model capacity through conditional expert activation, but their full expert pools remain difficult to deploy under limited accelerator memory.
arXiv:2606. 24340v1 Announce Type: new Abstract: In recent years, the Internet of Things (IoT) paradigm has been shifting toward batteryless, energy-harvesting architectures.
arXiv:2606. 01162v1 Announce Type: new Abstract: Workflow scheduling in cloud computing demands the intelligent allocation of dynamically arriving, graph-structured workflows with varying deadlines onto ever-changing virtual machine resources.
Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program execution. Serving these workloads requires scheduling, KV-cache management, and routing policies that use program-level context, including turn dependencies, tool-induced gaps, and reusable KV state.
COPE (Composable Offloading Policy Emulator) is a system that predicts the best mixture‑of‑experts (MoE) offloading policy for a given model‑platform configuration before runtime integration. It uses a Policy Matrix to separate expert residency and execution strategy, and a Virtual Heterogeneous Machine to profile combined‑operator schedules and estimate performance from offline routing traces. Compared to baselines, COPE improves fastest‑policy selection accuracy by 24‑100 % and reduces prediction error by 1.7‑6.8×, cutting policy‑specific implementation effort by up to 74 %.
arXiv:2608. 06025v1 Announce Type: new Abstract: In simulation-in-the-loop decision-making systems, reinforcement learning (RL) inference is often constrained by simulator-side execution overhead, where workloads are highly dynamic and sensitive to runtime thread configurations.
arXiv:2602. 18109v3 Announce Type: replace Abstract: Real-time schedulers must reason about tight deadlines under strict compute budgets.
arXiv:2606. 09613v1 Announce Type: cross Abstract: Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program execution.