The paper proposes a simple technique of chunking workloads into smaller parts that alternate between compute-intensive and memory-bound operations to smooth power and temperature spikes in GPU systems. By doing so, it prevents throttling, leading to faster wall-clock times and lower total energy consumption. Experiments on a DGX Spark show up to 2% performance and energy gains, while similar benefits, though smaller, are observed on multi‑GPU servers.
By Erik Schultheis, Maximilian Kleinegger, Dan Alistarh
arXiv:2501.10375v3 Announce Type: replace-cross
Abstract: Mixture-of-Experts (MoE) models, though highly effective for various machine learning tasks, face significant deployment challenges on memory...
By Yujie Zhang, Shivam Aggarwal, Tulika Mitra
arXiv:2603. 16428v2 Announce Type: replace-cross Abstract: Fine-tuning Large Language Models (LLMs) has become essential for domain adaptation, but its memory-intensive property exceeds the capabilities of most GPUs.
By Ruijia Yang, Zeyi Wen
arXiv:2606. 17104v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in latency- and cost-sensitive settings, inference efficiency has become a central systems challenge.
By Shun Usami, Venkatram Vishwanath, E. Wes Bethel
arXiv:2606. 00735v1 Announce Type: cross Abstract: In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent stragglers under synchronized execution, where the slowest GPU determines layer latency.
By Seokjin Go, Marko Scrbak, Ephrem Wu, Srilatha Manne, Divya Mahajan
arXiv:2602. 24044v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently.
By Ferran Agullo, Joan Oliveras, Chen Wang, Alberto Gutierrez-Torre, Olivier Tardieu, Alaa Youssef, Jordi Torres, Josep Ll. Berral
arXiv:2608. 10506v1 Announce Type: cross Abstract: Accurate pre-deployment estimation of CNN inference cost--energy, latency, and peak memory--is increasingly critical as models are deployed on resource-constrained GPU platforms.
By Linh Nguyen, Zhixin Pan
Accurate pre-deployment estimation of CNN inference cost--energy, latency, and peak memory--is increasingly critical as models are deployed on resource-constrained GPU platforms. Existing approaches rely on FLOPs, latency measurements, or single-device profiling as energy proxies, overlooking the non-linear interactions between architectural design and hardware load.
The paper systematically studies decode‑phase energy consumption of open‑source large language models using different attention architectures—Multi‑Head Attention (MHA), Grouped Query Attention (GQA), and GQA with Sliding Window Attention (SWA). It evaluates four models across varying context lengths, batch sizes, and generation workloads, measuring GPU energy via NVIDIA counters. Findings show that the attention mechanism is the main driver of how energy scales with context length, with MHA models growing steeply, GQA models growing less, and GQA+SWA remaining nearly constant; model size mainly sets absolute energy use, while batching can cut energy per token and latency by up to 87%.
By Molka Chkir, Syed Muhammad Danish, Jos H\"oll, Arghavan Asad
Large Language Model (LLM) inference workloads are a rapidly growing contributor to data center energy consumption. Optimizing these deployments requires matching specific LLMs to the most efficient GPUs, but operators currently lack the tools to do so without exhaustively profiling each combination.
The paper introduces the Power Flexibility Index (PFI) to measure how large language model (LLM) training performance changes when GPU power is reduced. Using 131 training runs on H200 and H100 GPUs, the study finds that LLM jobs have significant but variable power elasticity and identifies telemetry signals that can predict PFI during runtime. The authors demonstrate that allocating power based on PFI maximizes overall token throughput, recovering about 1.5k tokens/s per job under a 30% power reduction, which represents 63% of the gap between equal-weight and perfect-information allocations.
By Philip Colangelo, Charles Dawson, Shayan Sengupta, Ayse Coskun, Varun Sivaram
arXiv:2608.28044v1 Announce Type: cross
Abstract: Large language model (LLM) inference serving is priced by tokens, but GPU energy is consumed over inference windows. This accounting mismatch makes t...
By Prabhu Vellaisamy, Vanessa Lam, Shawn Blanton, John Paul Shen