Attention--Feed-Forward Network (FFN) Disaggregation (AFD) is emerging as a promising architecture for serving Mixture-of-Experts (MoE) language models. While existing AFD systems improve the efficiency of disaggregated execution, they leave a deployment question unanswered: under the same model, workload, time-per-output-token (TPOT) service-level objective (SLO), hardware budget, hardware catalog, and runtime capabilities, does AFD provide higher throughput than the best collocated deployment?
arXiv:2601. 21351v4 Announce Type: replace-cross Abstract: Attentio-FFN disaggregation (AFD) is an emerging architecture for LLM decoding that separates state-heavy, KV-cache-dominated Attention computation from stateless, compute-intensive FFN computation, connected by per-step communication.
By Chendong Song, Meixuan Wang, Hang Zhou, Hong Liang, Yuan Lyu, Zixi Chen, Yuwei Fan, Zijie Zhou
arXiv:2609.14237v1 Announce Type: cross
Abstract: LLM serving systems increasingly disaggregate inference into finer-grained stages, with recent approaches separating attention from FFN or MoE execut...
By Zikun Li, Yixuan Mei, Shiqi Pan, Zixuan Chen, Xiaowen Zhang, Mengdi Wu, Shuhuai Lin, Yutong Yang, Zhihao Zhang, Xupeng Miao, Rashmi Vinayak, Zhihao Jia
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.
By Tejinder Singh, John Pflueger, Jeebak Mitra, Robert Lincourt, Mitchell Markow, Bhavesh A. Patel
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.
By Inesh Chakrabarti, Zejun Xiong, Pragya Sharma, Mani Srivastava
arXiv:2605. 21312v2 Announce Type: replace-cross Abstract: Modern LLM serving is no longer homogeneous or monolithic.
By Yicheng Feng, Xin Tan, Yangtao Deng, Yimin Jiang, Yibo Zhu, Hong Xu
arXiv:2606. 15004v1 Announce Type: cross Abstract: Deploying neural networks on low-power microcontrollers (MCUs) requires selecting model architectures under tight memory, latency, and energy constraints.
By Joseph Q. Zales, Pragya Sharma, Mani Srivastava
arXiv:2607. 05876v1 Announce Type: cross Abstract: LLM serving optimization typically benchmarks many configurations and reaches for heavy profilers when latency targets are missed.
By Yihua Liu
arXiv:2504. 17584v2 Announce Type: replace-cross Abstract: Attention-FC Disaggregated (AFD) LLM inference systems offload memory-bound Attention operations to memory-rich accelerators (e.
By Qingyuan Liu, Liyan Chen, Haocheng Wang, Yanning Yang, Dong Du, Zhigang Mao, Naifeng Jing, Yubin Xia, Haibo Chen
arXiv:2608. 26418v1 Announce Type: cross Abstract: Modern AI workloads and the hardware that runs them evolve on different timescales: architectural definition precedes volume silicon by years, while target workloads shift in months.
By Architect Labs
arXiv:2607. 24434v1 Announce Type: cross Abstract: Large Mixture-of-Experts (MoE) language models are attractive for end-device deployment because only a small subset of experts is active per token, but their routed expert weights often exceed accelerator memory.
By Dengke Han
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