arXiv:2606. 07362v1 Announce Type: new Abstract: As scalable inference services become popular, the cold start latency of an inference engine becomes important.
arXiv:2607. 09172v1 Announce Type: cross Abstract: Large Language Models are reshaping how software is developed and maintained.
arXiv:2609.08307v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as backends for intelligent web services, but serving them across the edge continuum requires bala...
AgentPerfBench is a new benchmarking suite designed to evaluate the inference performance of agentic large language models (LLMs) that handle multi‑turn, tool‑using, and context‑expanding tasks. It builds on real traces from agentic benchmarks such as SWE‑Bench and TerminalBench, and generates synthetic profiles that reflect realistic input/output lengths and turn counts. The suite also provides kernel‑level Nsight Compute traces and a multi‑dimensional roofline model to identify hardware bottlenecks and quantify the gap between traditional chat benchmarks and agentic workloads.
arXiv:2607. 20806v1 Announce Type: new Abstract: Lightweight large language models (LLMs) are increasingly being deployed locally on personal computers and are expected to play a growing role in resource-constrained edge and mobile environments.
arXiv:2607. 28848v1 Announce Type: cross Abstract: LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak.
HoliBench is a modular benchmarking and deployment toolkit that jointly measures accuracy, latency, and energy for foundation models across a wide range of devices, from single-board computers to GPU servers. It provides a platform abstraction layer that calibrates cross-device measurements and supports multiple model modalities, inference engines, and quantization levels. Using HoliBench, the authors evaluated 20 models on 7 device types, revealing tradeoffs such as limited latency gains from quantization on low‑precision hardware and diminishing accuracy returns relative to energy consumption, while also showing that single-model profiles can predict multi-model pipeline performance within a few percent.
arXiv:2609.12551v2 Announce Type: replace-cross Abstract: AI is beginning to make substantive contributions to LLM inference optimization. Existing AI optimizations are predominantly profiling-based....
arXiv:2604.05012v2 Announce Type: replace-cross Abstract: Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value...
arXiv:2606. 28565v1 Announce Type: cross Abstract: As large language models (LLMs) move into production serving, practitioners must rapidly evaluate inference performance across diverse hardware, models, and serving parameters to meet cost and latency targets.
Edge LLM deployment is shaped by more than model size and precision: inference backend, hardware platform, memory traffic, and power management all affect latency and efficiency. We present Hydra, a c...
arXiv:2609.23130v1 Announce Type: new Abstract: Large language model (LLM) inference is evolving from an engine-local optimization problem into a distributed control problem involving reusable state,...
The paper argues that AI deployment performance depends on interactions among compression, compiler transformations, and serving policies rather than just model architecture. It introduces a three‑layer taxonomy—model‑level techniques, compiler transformations, and system policies—and frames deployment as a constrained multi‑objective optimization problem over accuracy, latency, throughput, memory footprint, and energy. The authors propose an evidence protocol for comparable benchmarking and synthesize data from edge and data‑center platforms to show that cross‑layer interactions drive deployment outcomes, concluding with a constraint‑aware selection procedure and open research problems.