Related papers: FATE: Future-State-Aware Scheduling for Heterogene…

Performance-, power-, and energy-aware scheduling techniques play an essential role in optimally utilizing processing elements (PEs) of heterogeneous systems. List schedulers, a class of low-complexity static schedulers, have commonly been…

Climate change stands as one of the most pressing global challenges of the twenty-first century, with far-reaching consequences such as rising sea levels, melting glaciers, and increasingly extreme weather patterns. Accurate forecasting is…

With the emergence of heterogeneous hardware paving the way for the post-Moore era, it is of high importance to adapt the runtime scheduling to the platform's heterogeneity. To enhance adaptive and responsive scheduling, we introduce a…

Coflow is a recently proposed networking abstraction to help improve the communication performance of data-parallel computing jobs. In multi-stage jobs, each job consists of multiple coflows and is represented by a Directed Acyclic Graph…

Beyond training-time optimization, scaling test-time computation has emerged as a key paradigm to extend the reasoning capabilities of Large Language Models (LLMs). However, most existing methods adopt a rigid Planning-before-Trial (PbT)…

Large Language Models have revolutionized natural language processing, yet serving them efficiently in data centers remains challenging due to mixed workloads comprising latency-sensitive (LS) and best-effort (BE) jobs. Existing inference…

We present Interfaze, a system that treats modern LLM applications as a problem of building and acting over context, not just picking the right monolithic model. Instead of a single transformer, we combine (i) a stack of heterogeneous DNNs…

Autoware is an autonomous driving system implemented on Robot Operation System (ROS) 2, where an end-to-end timing guarantee is crucial to ensure safety. However, existing ROS 2 cause-effect chain models for analyzing end-to-end latency…

LLM serving is increasingly dominated by decode attention, which is a memory-bound operation due to massive KV cache loading from global memory. Meanwhile, real-world workloads exhibit substantial, hierarchical shared prefixes across…

Non-uniform performance and power consumption across the processing elements (PEs) of heterogeneous SoCs increase the computation complexity of the task scheduling problem compared to homogeneous architectures. Latency of a software-based…

Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substantial operating costs and severe availability risks.…

We present a federated, asynchronous, memory-limited algorithm for online task scheduling across large-scale networks of hundreds of workers. This is achieved through recent advancements in federated edge computing that unlocks the ability…

ROS 2 has become a dominant middleware for robotic systems, where perception, estimation, planning, and control pipelines are structured as directed acyclic graphs of callbacks executed under a shared executor. However, default ROS 2…

Most multi-agent systems rely exclusively on autoregressive language models (ARMs) that are based on sequential generation. Although effective for fluent text, ARMs limit global reasoning and plan revision. On the other hand, Discrete…

Compared to former mobile networks, Long Term Evolution (LTE) offers higher transfer speeds, significantly lower latencies and a widespread availability, qualifying LTE for a wide range of different applications and services in the field of…

Large Foundation Models (LFMs), including multi-modal and generative models, promise to unlock new capabilities for next-generation Edge AI applications. However, performing inference with LFMs in resource-constrained and heterogeneous edge…

As demand for Large Language Models (LLMs) and AI agents grows rapidly, optimizing systems for efficient LLM inference becomes critical. While significant efforts have targeted system-level engineering, little has been explored from a…

Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binary relational graphs. However, fixed graph structures cannot capture the varying…

Efficient scheduling of directed acyclic graphs (DAGs) in heterogeneous environments is challenging due to resource capacities and dependencies. In practice, the need for adaptability across environments with varying resource pools and task…

Fraud detection and anti-money-laundering (AML) compliance are high-value domains for large language models (LLMs), but their serving requirements differ sharply from generic chat workloads. Compliance prompts are often prefix-heavy,…