The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures

Power capping is the standard GPU energy lever in LLM serving, and it appears to work: throughput drops, power readings fall, and energy budgets are met. We show the appearance is illusory for the phase that dominates production serving: autoregressive decode. Across four attention paradigms -- GQA, MLA, Gated DeltaNet, and Mamba2 -- on NVIDIA H200, decode draws only 137--300\,W on a 700\,W GPU; no cap ever triggers, because memory-bound decode saturates HBM bandwidth rather than compute and leaves power headroom untouched. Firmware-initiated clock throttling compounds the illusion: these deviations can corrupt any throughput measurement that attributes them to the cap. SM clock locking dissolves both confounds. By targeting the lever that is actually on the critical path, clock locking Pareto-dominates power capping universally, recovering up to 32\% of decode energy at minimal throughput loss. We identify three architecture-dependent DVFS behavioural classes and characterise a common energy pattern across novel attention replacements: a heavy prefill cost recouped by efficient decode, eventually halving total request energy relative to GQA at production batch sizes.

Safety and accuracy follow different scaling laws in clinical large language models

Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation that higher accuracy implies safer behavior. This assumption is incomplete in medicine, where a few confident, high-risk, or evidence-contradicting errors can matter more than average benchmark performance. We introduce SaFE-Scale, a framework for measuring how clinical LLM safety changes across model scale, evidence quality, retrieval strategy, context exposure, and inference-time compute. To instantiate this framework, we introduce RadSaFE-200, a Radiology Safety-Focused Evaluation benchmark of 200 multiple-choice questions with clinician-defined clean evidence, conflict evidence, and option-level labels for high-risk error, unsafe answer, and evidence contradiction. We evaluated 34 locally deployed LLMs across six deployment conditions: closed-book prompting (zero-shot), clean evidence, conflict evidence, standard RAG, agentic RAG, and max-context prompting. Clean evidence produced the strongest improvement, increasing mean accuracy from 73.5% to 94.1%, while reducing high-risk error from 12.0% to 2.6%, contradiction from 12.7% to 2.3%, and dangerous overconfidence from 8.0% to 1.6%. Standard RAG and agentic RAG did not reproduce this safety profile: agentic RAG improved accuracy over standard RAG and reduced contradiction, but high-risk error and dangerous overconfidence remained elevated. Max-context prompting increased latency without closing the safety gap, and additional inference-time compute produced only limited gains. Worst-case analysis showed that clinically consequential errors concentrated in a small subset of questions. Clinical LLM safety is therefore not a passive consequence of scaling, but a deployment property shaped by evidence quality, retrieval design, context construction, and collective failure behavior.

SteuerLLM: Local specialized large language model for German tax law analysis

Large language models (LLMs) demonstrate strong general reasoning and language understanding, yet their performance degrades in domains governed by strict formal rules, precise terminology, and legally binding structure. Tax law exemplifies these challenges, as correct answers require exact statutory citation, structured legal argumentation, and numerical accuracy under rigid grading schemes. We algorithmically generate SteuerEx, the first open benchmark derived from authentic German university tax law examinations. SteuerEx comprises 115 expert-validated examination questions spanning six core tax law domains and multiple academic levels, and employs a statement-level, partial-credit evaluation framework that closely mirrors real examination practice. We further present SteuerLLM, a domain-adapted LLM for German tax law trained on a large-scale synthetic dataset generated from authentic examination material using a controlled retrieval-augmented pipeline. SteuerLLM (28B parameters) consistently outperforms general-purpose instruction-tuned models of comparable size and, in several cases, substantially larger systems, demonstrating that domain-specific data and architectural adaptation are more decisive than parameter scale for performance on realistic legal reasoning tasks. All benchmark data, training datasets, model weights, and evaluation code are released openly to support reproducible research in domain-specific legal artificial intelligence. A web-based demo of SteuerLLM is available at https://steuerllm.i5.ai.fau.de.

Agentic large language models improve retrieval-based radiology question answering

Clinical decision-making in radiology increasingly benefits from artificial intelligence (AI), particularly through large language models (LLMs). However, traditional retrieval-augmented generation (RAG) systems for radiology question answering (QA) typically rely on single-step retrieval, limiting their ability to handle complex clinical reasoning tasks. Here we propose an agentic RAG framework enabling LLMs to autonomously decompose radiology questions, iteratively retrieve targeted clinical evidence from Radiopaedia, and dynamically synthesize evidence-based responses. We evaluated 24 LLMs spanning diverse architectures, parameter scales (0.5B to >670B), and training paradigms (general-purpose, reasoning-optimized, clinically fine-tuned), using 104 expert-curated radiology questions from previously established RSNA-RadioQA and ExtendedQA datasets. Agentic retrieval significantly improved mean diagnostic accuracy over zero-shot prompting (73% vs. 64%; P<0.001) and conventional online RAG (73% vs. 68%; P<0.001). The greatest gains occurred in mid-sized models (e.g., Mistral Large improved from 72% to 81%) and small-scale models (e.g., Qwen 2.5-7B improved from 55% to 71%), while very large models (>200B parameters) demonstrated minimal changes (<2% improvement). Additionally, agentic retrieval reduced hallucinations (mean 9.4%) and retrieved clinically relevant context in 46% of cases, substantially aiding factual grounding. Even clinically fine-tuned models exhibited meaningful improvements (e.g., MedGemma-27B improved from 71% to 81%), indicating complementary roles of retrieval and fine-tuning. These results highlight the potential of agentic frameworks to enhance factuality and diagnostic accuracy in radiology QA, particularly among mid-sized LLMs, warranting future studies to validate their clinical utility.

Exploring Techniques for the Analysis of Spontaneous Asynchronicity in MPI-Parallel Applications

This paper studies the utility of using data analytics and machine learning techniques for identifying, classifying, and characterizing the dynamics of large-scale parallel (MPI) programs. To this end, we run microbenchmarks and realistic proxy applications with the regular compute-communicate structure on two different supercomputing platforms and choose the per-process performance and MPI time per time step as relevant observables. Using principal component analysis, clustering techniques, correlation functions, and a new "phase space plot," we show how desynchronization patterns (or lack thereof) can be readily identified from a data set that is much smaller than a full MPI trace. Our methods also lead the way towards a more general classification of parallel program dynamics.

$K$-way $p$-spectral clustering on Grassmann manifolds

Spectral methods have gained a lot of recent attention due to the simplicity of their implementation and their solid mathematical background. We revisit spectral graph clustering, and reformulate in the $p$-norm the continuous problem of minimizing the graph Laplacian Rayleigh quotient. The value of $p \in (1,2]$ is reduced, promoting sparser solution vectors that correspond to optimal clusters as $p$ approaches one. The computation of multiple $p$-eigenvectors of the graph $p$-Laplacian, a nonlinear generalization of the standard graph Laplacian, is achieved by the minimization of our objective function on the Grassmann manifold, hence ensuring the enforcement of the orthogonality constraint between them. Our approach attempts to bridge the fields of graph clustering and nonlinear numerical optimization, and employs a robust algorithm to obtain clusters of high quality. The benefits of the suggested method are demonstrated in a plethora of artificial and real-world graphs. Our results are compared against standard spectral clustering methods and the current state-of-the-art algorithm for clustering using the graph $p$-Laplacian variant.

Performance Engineering for a Medical Imaging Application on the Intel Xeon Phi Accelerator

We examine the Xeon Phi, which is based on Intel's Many Integrated Cores architecture, for its suitability to run the FDK algorithm--the most commonly used algorithm to perform the 3D image reconstruction in cone-beam computed tomography. We study the challenges of efficiently parallelizing the application and means to enable sensible data sharing between threads despite the lack of a shared last level cache. Apart from parallelization, SIMD vectorization is critical for good performance on the Xeon Phi; we perform various micro-benchmarks to investigate the platform's new set of vector instructions and put a special emphasis on the newly introduced vector gather capability. We refine a previous performance model for the application and adapt it for the Xeon Phi to validate the performance of our optimized hand-written assembly implementation, as well as the performance of several different auto-vectorization approaches.