The paper evaluates a learned request‑routing policy for disaggregated large‑language‑model serving, where compute‑heavy prefill and memory‑heavy decode stages run on separate GPU pools. Using a discrete‑event simulator and real NVIDIA A40 GPUs, the calibrated router—leveraging prompt length, predicted output length, KV‑cache pressure, and SLO class—outperforms round‑robin, least‑loaded, and length‑based heuristics, achieving the highest mean goodput (0.864) and lowest variance across three mixed, bursty arrival traces. Hardware calibration proves critical, providing a 4.5‑point goodput boost and roughly 40 % of the tail‑latency advantage, and the learned router can match round‑robin performance with one fewer GPU in certain scenarios.
By Srikanta Datta Tumkur, Jay Iyer, Mehar Simhadri, Sai Pavan Kumar, Sai Kapil Kumar, Ramesh Nampelly
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
arXiv:2606. 00946v1 Announce Type: cross Abstract: Efficiently serving large language model (LLM) inference tasks is crucial both for user-perceived latency such as time-to-first-token (TTFT) and for GPU utilization.
By Gangmuk Lim, Wanyu Zhao, Brighten Godfrey, Jiaxin Shan, Le Xu, Liguang Xie
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...
By Maysam Khatib, Moysis Symeonides, Demetris Trihinas, George Pallis, Marios D. Dikaiakos
PrefixBench-H100 is a reproducible benchmark that evaluates how reusing prompt prefixes affects LLM serving performance on NVIDIA H100 GPUs. It tests two popular runtimes (vLLM and TensorRT-LLM) across varied workloads, measuring metrics such as time-to-first-token, latency, throughput, cache hits, and GPU memory usage. The study identifies when prefix reuse significantly reduces first‑token latency and when cache pressure diminishes those gains, noting that cache effectiveness is largely unaffected by concurrency or output length, while differences arise mainly in scheduling.
By Omkar Shewale, Deepak Kumar, Divakar Kumar Yadav
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.
By Xiteng Yao, Taeho Kim, Hengzhi Pei, Xinle Liu, Kyle Ulrich, Leonard Lausen, Ashish Khetan, Xiang Song, George Karypis, Martin Herbordt
arXiv:2607. 19353v1 Announce Type: new Abstract: Confidential computing is becoming a practical deployment requirement for AI inference workloads that process sensitive inputs or protect proprietary model assets.
By Wei Wang, Abdul Hyee Waqas, Burns Smith
arXiv:2609.38090v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-...
By Sanjali Yadav, Bahar Asgari
The paper argues that for large‑context autoregressive language‑model inference, memory bandwidth—specifically the Key‑Value (KV) cache—becomes the limiting resource rather than arithmetic throughput. It analytically derives how arithmetic intensity decays with context length for NVIDIA H100, NVIDIA B200, and AMD MI300X, identifies crossover points where KV traffic overtakes weight traffic, and evaluates representative techniques across five compression domains. The study finds a three‑regime behavior: below the crossover, weight traffic dominates and KV compression offers little benefit; beyond it, KV traffic dominates and compression methods trade quality for bandwidth, with paging and prefix sharing being lossless but capacity‑limited, while quantization and eviction directly reduce bandwidth at the cost of accuracy.
whyItMatters":"The work provides a unified analytical framework and a standardized protocol that enable consistent comparison of KV‑compression techniques across hardware and workloads, guiding practitioners in selecting appropriate methods for long‑context inference."
By Tejinder Singh
The paper investigates how a single SM utilization metric can misrepresent the true workload of large language model (LLM) inference on Nvidia Hopper GPUs. By profiling vLLM with FlashAttention‑3 and cuBLASLt on an H100 NVL across various phases (cold prefill, warm prefill, and decode) and varying sequence length and batch size, the authors replace the single utilization figure with eight detailed counter‑validated views. These views, tied to specific Nsight Compute counters or formulas, reveal how factors such as fragment fill, occupancy limits, stall signatures, wave quantization, and kernel selection create utilization gaps across four production models and six per‑layer kernel roles.
By Mohammad Siavashi, Gerald Q. Maguire Jr., Dejan Kostic, Marco Chiesa
Masked diffusion language models (dLLMs) promise faster text generation by denoising multiple tokens simultaneously, yet their real‑world serving behavior has been largely unexamined. Using LLaDA‑8B‑Instruct on a single NVIDIA H200 GPU, the study finds that request difficulty is discretized into 11 step‑count levels, short‑budget benchmarks underestimate serving variance, and only 24% of single‑request time is GPU computation, with batching mainly reducing CPU dispatch overhead. The authors also demonstrate that output quality remains stable across batch sizes and propose a batch‑timeout rule for synchronized batching under Poisson arrivals.
By Farhana Amin, Sabiha Afroz, Mona Moghadampanah, Dimitrios S. Nikolopoulos
arXiv:2608. 15383v1 Announce Type: new Abstract: Sparse mixture-of-experts (MoE) language models reduce arithmetic by activating only a small subset of experts per token, yet deployment still requires storing and moving the full expert bank.
By Amjad Saab