The paper presents a method for distributing large language model inference across multiple Intel AI PCs by splitting the model into pipeline shards, each pre‑compiled into an OpenVINO graph. Three key techniques—beam_idx Gather to enable GPU optimizations, speculative decoding on stateful models, and interleaved micro‑batching—allow a two‑node Llama 3.1 8B INT4 pipeline to serve two users at 1.79× the throughput of a single‑node model, while a four‑node deployment can run a 70B model that no single PC can hold. The authors provide code, benchmark logs, and reproduction scripts on GitHub.
By Tate Berenbaum, Muthaiah Venkatachalam
arXiv:2605. 25645v2 Announce Type: replace-cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation.
By Jatin Kishnani, Mayank Goel, Amit Singh, Pulkit Agrawal, Sairanjan Mishra
arXiv:2606. 11257v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) pipelines are compute-intensive, combining embedding, retrieval, reranking, and large language model (LLM) generation.
By Zhiyuan Cheng, Longying Lai
KernelGenBench is a unified benchmark that evaluates large language models and agentic systems for generating efficient Triton kernels across diverse operator sources and hardware platforms. It covers 210 operators from PyTorch ATen, vLLM, and cuBLAS, and tests a 110‑operator subset on six different chips, consuming over 15 billion tokens in evaluation. The study finds that no single method dominates across all sources and platforms, with significant variations in correctness and performance depending on the operator source and hardware, and that agentic approaches require millions of tokens per successful operator.
By Peiyu Zang, Jian Tao, Jialing Zhang, Yichen Yuan, Wentao Zhang, Guang Liu, Yonghua Lin
arXiv:2606. 10493v1 Announce Type: cross Abstract: Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-concurrency workloads.
By Wenxin Wang, Yule Hou, Yu Ji, Peng Qu, Youhui Zhang
arXiv:2607. 29221v1 Announce Type: cross Abstract: We address the challenge of securely and efficiently outsourcing AI computations from a trusted but computationally weak client to an untrusted but powerful server, in the setting where the client holds both the input and the model, and the server must learn neither.
By James Hsin-yu Chiang, Sheila Zingg, Kari Kostiainen, Srdjan Capkun
arXiv:2606. 02963v1 Announce Type: new Abstract: Production inference increasingly targets a heterogeneous mix of accelerators.
By Taras Sereda, Burak Bartan, Ankita Nayak, Tom St. John, Natalie Serrino, Zain Asgar
arXiv:2606. 04023v1 Announce Type: cross Abstract: While large language models (LLMs) have been extensively evaluated on code generation tasks for general-purpose programming and GPU-accelerated environments (e.
By Jie Li, Wenzhao Wu, Junqi Hu, Qinrui Zheng, Bowen Wu, Juepeng Zheng, Yutong Lu, Haohuan Fu
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
arXiv:2608. 15127v1 Announce Type: cross Abstract: Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state.
By Chaokun Chang, Yukun Zhou, Kaihua Fu, Dakai An, Tianyu Feng, Hanfeng Lu, Sheng Yao, Pu Guo, Yinghao Yu, Yizhou Shan, Bo Li, Binhang Yuan, Wei Wang
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
The paper introduces QUILT, a new sparse‑attention execution mechanism that jointly processes neighboring queries to reuse shared key‑value (KV) entries, thereby reducing redundant memory traffic and computation. QUILT employs Shift‑and‑Compare Set Decomposition (SCSD) to convert irregular set operations into regular data‑parallel primitives and pipelines this with attention computation to hide overhead. The approach includes cascaded sharing across multiple granularities and a tile‑aware strategy that balances sharing with hardware utilization, achieving up to 55.1% lower kernel latency and 36.8% faster time‑to‑first‑token on LongBench benchmarks with negligible accuracy loss.
By Zhenduo Zhao, Qihui Zhou, Mingcong Song, Zhiyi Chen, Chuangguan Ye, Fengfan Hou, Zequn Gong, Jing Li, Hongjie Si, Guoping Long