Systems & Networks · Computer Science & AI
Performance
The newest papers in Performance that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
158 papers, from 4 September 2026 to 5 November 2026: 158 arXiv preprints.
Get the few papers worth your time in Performance every morning.
Follow Performance and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 7
Total Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows
Every node in a multi-agent large language model (LLM) workflow retrieves context from memory and injects it into its prompt, where those injected tokens are billed as input tokens at the same…Measured Joules, Learned Routes: Learning to Route for Energy-Efficient LLM Serving
Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajectories extend.From Inference Engine to Inference Control Plane: Connecting vLLM, llm-d, and the Evolution of Efficient Distributed LLM Serving
Large language model (LLM) inference is evolving from an engine-local optimization problem into a distributed control problem involving reusable state, phase placement, heterogeneous accelerators…Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale
Embedding-based retrieval on user-generated content at the trillion-document scale exposes a sharp conflict between two production demands: deep, expressive personalization for queries with rich…Cross-Platform vs Native Mobile Development: An Empirical Study of Software Quality Trade-offs
Cross-platform mobile frameworks promise code reuse, shorter delivery cycles, and lower implementation effort, but their trade-offs relative to native development remain difficult to assess…The Weight Is Over - Interactive Diffusion on Consumer GPUs
On-device inference is booming, but the momentum is almost all in language models.PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving
Repeated prompt prefixes are increasingly common in LLM serving workloads, appearing in system prompts, templated retrieval-augmented generation pipelines, agent frameworks, and multi-turn…Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation
Autoregressive image generation has emerged as a paradigm for multimodal AI systems due to its compatibility with transformer-based LLM serving infrastructures.The Life of a Token: from Words to Bits on the Wire
Large Language Models (LLMs) transform vast collections of unstructured text into semantic patterns used for language generation and reasoning tasks.Not All AI Agents Are Equal: Characterizing Resource and Performance Dynamics
LLM-based AI agents process user requests through iterative reasoning and tool execution, often involving the invocation of remote LLM APIs with local tool containers.Efficiently Distributed Federated Learning
Federated Learning (FL) is experiencing a substantial research interest, with many frameworks being developed to allow practitioners to build federations easily and quickly.Accelerating Sharded Data Parallelism at Scale with Federated Learning
The symbiotic scaling of artificial intelligence models and high-performance computing systems continually creates algorithmic challenges in their convergence.Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses.FlashVector: Agent for Hierarchical Model Serving Stack Optimization
Model serving is one of the largest cost drivers in production recommender systems.JustFit: Just-in-Time State Management for Local LLM Serving
Local agents need memory for model execution and working history.FAME: An FPGA-Based Platform for Approximate Multipliers Evaluation with Pattern-Guided DNN Retraining
Approximate multipliers can reduce hardware area and energy consumption in Deep Neural Network (DNN) inference; however, they introduce computational errors.GGUF-Metadata Prediction of Single-Sequence llama.cpp Throughput Across Three Systems
We predict single-sequence model throughput from GGUF metadata using roofline-shaped predictors with quantization-specific scale factors fitted on reference models.Shared KV Caching for Replicated 27B Inference: Correctness Failures and Performance Boundaries
Shared host-memory caching can avoid repeated prefill when a request moves between inference replicas.Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
External cache transfers can succeed while a hybrid language model resumes from an inconsistent state.Turkish MMLU Pro: Traceable Option Augmentation and Its Validity Limits in Turkish Multiple-Choice Evaluation
Adding answer options can lower multiple-choice scores without improving assessment validity.