Hermes: Algorithm-System Co-design for Efficient Retrieval-Augmented Generation At-Scale

N/A

Hermes: Algorithm-System Co-design for Efficient Retrieval-Augmented Generation At-Scale Michael Shen Muhammad Umar Kiwan Maeng Cornell University Cornell University Pennsylvania State University New York, NY, USA Ithaca, NY, USA University Park, PA, USA…

related reading

• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• Retrieval-Augmented Generation for Large Language Models: A Surveyarxiv.org
• Look Ma, No Bubbles! Designing a Low-Latency Megakernel for Llama-1B · Hazy Researchhazyresearch.stanford.edu
• The Big LLM Architecture Comparisonmagazine.sebastianraschka.com
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• [2603.23516] MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokensarxiv.org
• Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Modelsarxiv.org
• [2304.13343] Unleashing Infinite-Length Input Capacity for Large-scale Language Models with Self-Controlled Memory Systemarxiv.org
• [2605.15156] MeMo: Memory as a Modelarxiv.org
• Paged Attention from First Principles: A View Inside vLLM – Hamza's Bloghamzaelshafie.bearblog.dev
• 2025.acl-long.896.pdfaclanthology.org
• Towards Data Sciencetowardsdatascience.com