The paper introduces Rotary GPU, an exploratory execution approach demonstrating that large Mixture-of-Experts models can be run locally on consumer GPUs with limited VRAM, achieving usable decode thr…

This paper identifies suboptimalities in default GPU-first scheduling for AI tool workloads and proposes an agentic scheduler that adaptively assigns tools to GPU or CPU based on runtime factors.

This paper proposes a decentralized, confidential computing platform using Intel TDX, ITA, and NVIDIA CC for secure and affordable AI workloads.

RAMSES is a new HPC system that integrates hardware-based memory encryption and state-of-the-art file encryption to deliver high performance and robust security.

This paper proposes an HPC-aware methodology for Knowledge Distillation (KD) that decouples teacher and student partitioning efficiently, achieving up to 67% higher samples-per-second than the widely…

Researchers used a large language model to generate checkpoint/restart code for MPI applications, achieving comparable efficiency to human-engineered solutions.

The paper presents Dyserve, a workflow-aware serving layer for agentic AI applications that compiles per-node model and verifier choices into an integer linear program, allowing for efficient model se…

The paper presents CHASE, an application-driven framework that explores physically feasible Cross-layer Heterogeneous System architectures for executing workloads with diverse requirements.

The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.

The paper proposes Arbiter-K, a Governance-First execution architecture that treats LLMs as probabilistic units encapsulated by a deterministic kernel, significantly improving the security and reliabi…

The paper presents the Quantum Resource Management Interface (QRMI) as a standardized, vendor-agnostic middleware layer for integrating quantum resources into high-performance computing environments,…

HighTide is an evolving, AI-assisted, open-source benchmark suite for VLSI design, providing a comprehensive and scalable platform for hardware development.

The paper introduces PRISM, an evaluation framework for assessing POSIX storage systems for AI research workloads, and compares Lustre and NFS based systems.

The paper proposes a taxonomy of 20 hardware-level governance mechanisms for AI compute, finding that the most critical mechanisms needed for international treaty verification are currently the least…

The paper argues that distributed training algorithms allow developers to evade compute governance regulations by using decentralized hardware, necessitating new detection methods like chip tracking a…

BiJuTy is a user-friendly solution for executing complex big data processing workflows on high-performance computing systems within the Jupyter ecosystem.

This paper systematically analyzes security risks in cloud-hosted, tool-enabled AI agents, concluding that most risks stem from over-privileged tools and capability-intent mismatches rather than novel…

The elasticAI.explorer is an extensible, unified Python framework that simplifies hardware-aware Neural Architecture Search (NAS) by decoupling search space definition from model implementation and de…

The paper proposes a fine-grained approach to overlap expert compute with the second all-to-all communication in Mixture-of-Experts (MoE) models, improving distributed MoE execution efficiency on mult…