Imagen de Portada

FaTRQ: Tiered Residual Quantization for LLM Vector Search in Far-Memory-Aware ANNS Systems

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Tianqi, Ponzina, Flavio, Rosing, Tajana
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Hardware Architecture Information Retrieval
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SpANNS: Optimizing Approximate Nearest Neighbor Search for Sparse Vectors Using Near Memory Processing
por: Zhang, Tianqi, et al.
Publicado: (2026)

FedUHD: Unsupervised Federated Learning using Hyperdimensional Computing
por: Lee, You Hak, et al.
Publicado: (2025)

CHIME: Chiplet-based Heterogeneous Near-Memory Acceleration for Edge Multimodal LLM Inference
por: Chen, Yanru, et al.
Publicado: (2025)

Fast-OverlaPIM: A Fast Overlap-driven Mapping Framework for Processing In-Memory Neural Network Acceleration
por: Wang, Xuan, et al.
Publicado: (2024)

RAG-Enhanced Kernel-Based Heuristic Synthesis (RKHS): A Structured Methodology Using Large Language Models for Hardware Design
por: Ahir, Shiva, et al.
Publicado: (2026)

Efficient Open Modification Spectral Library Searching in High-Dimensional Space with Multi-Level-Cell Memory
por: Fan, Keming, et al.
Publicado: (2024)

SpecPCM: A Low-power PCM-based In-Memory Computing Accelerator for Full-stack Mass Spectrometry Analysis
por: Fan, Keming, et al.
Publicado: (2024)

HAVEN: High-Bandwidth Flash Augmented Vector Engine for Large-Scale Approximate Nearest-Neighbor Search Acceleration
por: Hsu, Po-Kai, et al.
Publicado: (2026)

Enhancing Scalability in Recommender Systems through Lottery Ticket Hypothesis and Knowledge Distillation-based Neural Network Pruning
por: R, Rajaram, et al.
Publicado: (2024)

GEN-Graph: Heterogeneous PIM Accelerator for General Computational Patterns in Graph-based Dynamic Programming
por: Chen, Yanru, et al.
Publicado: (2026)

GenDRAM:Hardware-Software Co-Design of General Platform in DRAM
por: Lu, Tsung-Han, et al.
Publicado: (2026)

Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving
por: Pan, Yue, et al.
Publicado: (2025)

Pushing the Performance Envelope of DNN-based Recommendation Systems Inference on GPUs
por: Jain, Rishabh, et al.
Publicado: (2024)

PIFS-Rec: Process-In-Fabric-Switch for Large-Scale Recommendation System Inferences
por: Huo, Pingyi, et al.
Publicado: (2024)

PIM-FW: Hardware-Software Co-Design of All-pairs Shortest Paths in DRAM
por: Lu, Tsung-Han, et al.
Publicado: (2025)

UpANNS: Enhancing Billion-Scale ANNS Efficiency with Real-World PIM Architecture
por: Chen, Sitian, et al.
Publicado: (2024)

Hybrid SLC-MLC RRAM Mixed-Signal Processing-in-Memory Architecture for Transformer Acceleration via Gradient Redistribution
por: Song, Chang Eun, et al.
Publicado: (2025)

D2S-FLOW: Automated Parameter Extraction from Datasheets for SPICE Model Generation Using Large Language Models
por: Chen, Hong Cai, et al.
Publicado: (2025)

EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture
por: Duan, Bowen, et al.
Publicado: (2026)

Proxima: Near-storage Acceleration for Graph-based Approximate Nearest Neighbor Search in 3D NAND
por: Xu, Weihong, et al.
Publicado: (2023)

FSL-HDnn: A 5.7 TOPS/W End-to-end Few-shot Learning Classifier Accelerator with Feature Extraction and Hyperdimensional Computing
por: Yang, Haichao, et al.
Publicado: (2024)

Clo-HDnn: A 4.66 TFLOPS/W and 3.78 TOPS/W Continual On-Device Learning Accelerator with Energy-efficient Hyperdimensional Computing via Progressive Search
por: Song, Chang Eun, et al.
Publicado: (2025)

Histogram-Equalized Quantization for logic-gated Residual Neural Networks
por: Nguyen, Van Thien, et al.
Publicado: (2025)

FPGA-based Emulation and Device-Side Management for CXL-based Memory Tiering Systems
por: Chen, Yiqi, et al.
Publicado: (2025)

HDDB: Efficient In-Storage SQL Database Search Using Hyperdimensional Computing on Ferroelectric NAND Flash
por: Zhao, Quanling, et al.
Publicado: (2025)

FLARE: One-Shot PE-Level Fault Localization in Systolic Arrays via Algebraic Test Vectors
por: Venkatasubramanian, Logashree, et al.
Publicado: (2026)

NeoMem: Hardware/Software Co-Design for CXL-Native Memory Tiering
por: Zhou, Zhe, et al.
Publicado: (2024)

Digital Signal Processing from Classical Coherent Systems to Continuous-Variable QKD: A Review of Cross-Domain Techniques, Applications, and Challenges
por: de Sousa, Davi Juvêncio Gomes, et al.
Publicado: (2025)

Architectural and System Implications of CXL-enabled Tiered Memory
por: Yang, Yujie, et al.
Publicado: (2025)

Asynchronous Memory Access Unit: Exploiting Massive Parallelism for Far Memory Access
por: Wang, Luming, et al.
Publicado: (2024)

RapidOMS: FPGA-based Open Modification Spectral Library Searching with HD Computing
por: Pinge, Sumukh, et al.
Publicado: (2024)

Accelerating Recommendation System Training by Leveraging Popular Choices
por: Adnan, Muhammad, et al.
Publicado: (2021)

KLLM: Fast LLM Inference with K-Means Quantization
por: Wu, Xueying, et al.
Publicado: (2025)

Binary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
por: Zhou, Wenyong, et al.
Publicado: (2025)

HTM-EAR: Importance-Preserving Tiered Memory with Hybrid Routing under Saturation
por: Singh, Shubham Kumar
Publicado: (2026)

Reimagining Memory Access for LLM Inference: Compression-Aware Memory Controller Design
por: Xie, Rui, et al.
Publicado: (2025)

FeNOMS: Enhancing Open Modification Spectral Library Search with In-Storage Processing on Ferroelectric NAND (FeNAND) Flash
por: Pinge, Sumukh, et al.
Publicado: (2025)

SigmaQuant: Hardware-Aware Heterogeneous Quantization Method for Edge DNN Inference
por: Liu, Qunyou, et al.
Publicado: (2026)

Exploring Quantization and Mapping Synergy in Hardware-Aware Deep Neural Network Accelerators
por: Klhufek, Jan, et al.
Publicado: (2024)

HASS: Hardware-Aware Sparsity Search for Dataflow DNN Accelerator
por: Yu, Zhewen, et al.
Publicado: (2024)