arXiv:2609.05760v1 Announce Type: cross
Abstract: We present RAGMark, a modular benchmarking framework for advanced Retrieval-Augmented Generation (RAG) systems targeting small-scale multi-GPU enviro...
By Zlatan Feric, Amir Taherin, Bin Ren, Yanzhi Wang, Jennifer Dy, David Kaeli
arXiv:2603. 29002v3 Announce Type: replace-cross Abstract: Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex reasoning.
By Zifan He, Rui Ma, Yizhou Sun, Jason Cong
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
arXiv:2609.21281v1 Announce Type: cross
Abstract: Embedding-based retrieval on user-generated content at the trillion-document scale exposes a sharp conflict between two production demands: deep, exp...
By Hao Fu, Jichao Sun, Baiting Zhu, Qiaoling Liu, Yan Shi, Cheng Lu, Liu Liu, Yubo Wang, Xin Yao, Xiangyu Niu, Xu Dong, Wenhan Lyu, Chiyao Shen, Yinjie Huang, Minglei Chen, Shuai Ding, Li Fan, Xiao Kong
arXiv:2602. 22647v2 Announce Type: replace-cross Abstract: Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation.
By Zhengyang Su, Isay Katsman, Yueqi Wang, Ruining He, Lukasz Heldt, Raghunandan Keshavan, Shao-Chuan Wang, Xinyang Yi, Mingyan Gao, Onkar Dalal, Lichan Hong, Ed Chi, Ningren Han
STAPLE is a method that integrates static sparse memory into pretrained language models by adding token‑indexed embeddings as a residual pathway while preserving the original feed‑forward network. On the OLMo‑2 1B and 7B models, STAPLE outperforms dense training and other static sparse baselines, improving benchmark scores by up to 4.27 points and achieving faster decoding with less GPU memory and energy usage. The approach demonstrates that large pretrained models can be expanded efficiently without costly sparse pretraining from scratch.
By Ranajoy Sadhukhan, Euijin Hong, Sheng Cao, Zechun Liu, Shuowei Jin, Sha Li, Changlong Yu, Xin Liu, Qin Lu, Zhenyu Shi, Priyanka Nigam, Beidi Chen
arXiv:2411. 16102v2 Announce Type: replace Abstract: Offline batch inference, which leverages the flexibility of request batching to achieve higher throughput and lower costs, is becoming more popular for latency-insensitive applications.
By Yilong Zhao, Shuo Yang, Kan Zhu, Lianmin Zheng, Baris Kasikci, Yang Zhou, Jiarong Xing, Ion Stoica
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
arXiv:2607. 20475v1 Announce Type: new Abstract: Sampling in LLM inference comprises a combinatorial set of logit processing, token selection, and verification operations for speculative decoding.
By Pragaash Ponnusamy, Shivam Sahni, Jue Wang, Tri Dao
Adaptive DHiSparse extends the HiSparse framework by enabling speculative decoding over a hierarchical sparse key‑value (KV) store and dynamically adapting memory residency to load. It protects the essential working set, retains extra history when GPU memory is available, and retrieves the remainder via exact fused retrieval, integrating draft‑model techniques such as DSpark and DFlash2. In benchmarks, it achieves up to 1.85× higher output rates than resident serving while reducing host fetches dramatically under low load.
By Naji Alazhar, Wassel Alazhar
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
GroupKV is a lightweight hierarchical KV cache management system designed for long‑context diffusion large language model (dLLM) inference. It partitions the context into contiguous groups and uses coarse‑to‑fine sparse selection, cross‑layer consistency for predictive prefetching, and a staleness correction mechanism to keep the cache coherent amid dynamic KV updates. The approach also incorporates streaming prefill to lower peak memory usage, achieving up to 48× longer serviceable context, 3.73× faster inference in offload‑based settings, and competitive task accuracy.
By Jinhao Wang, Zhexin Hu, Kangjie Zhou, Xin Zhou, Fangfang Liu