[2310.09949] Chameleon: a heterogeneous and disaggregated accelerator system for retrieval-augmented language models

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

View PDF HTML (experimental) Abstract:A Retrieval-Augmented Language Model (RALM) combines a large language model (LLM) with a vector database to retrieve context-specific knowledge during text generation. This strategy facilitates impressive generation quality even with smaller models, thus reducing computational demands by orders of magnitude. To serve RALMs efficiently and flexibly, we propose Chameleon, a heterogeneous accelerator system integrating both LLM and vector search accelerators in a disaggregated architecture. The heterogeneity ensures efficient serving for both inference and…

saved by

• Pavel

related reading

• [2312.15159] Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inferencearxiv.org
• [2403.00579] NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencingarxiv.org
• AttentionLego: An Open-Source Building Block For Spatially-Scalable Large Language Model Accelerator With Processing-In-Memory Technologyarxiv.org
• FTRANS: Energy-Efficient Acceleration of Transformers using FPGAarxiv.org
• [2403.06664] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real Systemarxiv.org
• [2209.10797] DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generationarxiv.org
• Recursive Language Models | Alex L. Zhangalexzhang13.github.io
• [2512.11949] Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitorsarxiv.org
• HeteroLLM: Accelerating Large Language Model Inference on Mobile SoCs with Heterogeneous AI Acceleratorsarxiv.org
• Large Language Diffusion Modelsarxiv.org
• TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answeringarxiv.org
• Retrieval-Augmented Generation for Large Language Models: A Surveyarxiv.org