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

• URL: http://arxiv.org/abs/2601.09985v1
• Date: Thu, 15 Jan 2026 01:59:29 GMT
• Title: FaTRQ: Tiered Residual Quantization for LLM Vector Search in Far-Memory-Aware ANNS Systems
• Authors: Tianqi Zhang, Flavio Ponzina, Tajana Rosing,
• Abstract summary: FaTRQ is a far-memory-aware refinement system that eliminates the need to fetch full vectors from storage.<n>A custom accelerator is deployed in a CXL Type-2 device to perform low-latency refinement locally.<n>Together, FaTRQ improves the storage efficiency by 2.4$times$ and improves the throughput by up to 9$ times$ than SOTA GPU ANNS system.
• Score: 16.221654013698963
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Approximate Nearest-Neighbor Search (ANNS) is a key technique in retrieval-augmented generation (RAG), enabling rapid identification of the most relevant high-dimensional embeddings from massive vector databases. Modern ANNS engines accelerate this process using prebuilt indexes and store compressed vector-quantized representations in fast memory. However, they still rely on a costly second-pass refinement stage that reads full-precision vectors from slower storage like SSDs. For modern text and multimodal embeddings, these reads now dominate the latency of the entire query. We propose FaTRQ, a far-memory-aware refinement system using tiered memory that eliminates the need to fetch full vectors from storage. It introduces a progressive distance estimator that refines coarse scores using compact residuals streamed from far memory. Refinement stops early once a candidate is provably outside the top-k. To support this, we propose tiered residual quantization, which encodes residuals as ternary values stored efficiently in far memory. A custom accelerator is deployed in a CXL Type-2 device to perform low-latency refinement locally. Together, FaTRQ improves the storage efficiency by 2.4$\times$ and improves the throughput by up to 9$ \times$ than SOTA GPU ANNS system.

Related papers

• Hippocampus: An Efficient and Scalable Memory Module for Agentic AI [4.508092142808317]
  Hippocampus is an agentic memory management system that uses compact binary signatures for semantic search.<n>Its core is a Dynamic Wavelet Matrix (DWM) that compresses and co-indexes both streams to support ultra-fast search.<n>Our evaluation shows that Hippocampus reduces end-to-end retrieval latency by up to 31$times$.
  arXiv  Detail & Related papers  (2026-02-14T04:25:20Z)
• Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction [72.27673320976933]
  Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding.<n>Current caching techniques accelerate decoding by storing full-layer states, yet impose substantial memory usage.<n>We propose Sparse-dLLM, the first training-free framework integrating dynamic cache eviction with sparse attention.
  arXiv  Detail & Related papers  (2025-08-04T16:14:03Z)
• FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge [60.000984252907195]
  Auto-regressive (AR) models have recently shown promise in visual generation tasks due to their superior sampling efficiency.<n>Video generation requires a substantially larger number of tokens to produce coherent temporal frames, resulting in significant overhead during the decoding phase.<n>We propose the textbfFastCar framework to accelerate the decode phase for the AR video generation by exploring the temporal redundancy.
  arXiv  Detail & Related papers  (2025-05-17T05:00:39Z)
• A Universal Framework for Compressing Embeddings in CTR Prediction [68.27582084015044]
  We introduce a Model-agnostic Embedding Compression (MEC) framework that compresses embedding tables by quantizing pre-trained embeddings.<n>Our approach consists of two stages: first, we apply popularity-weighted regularization to balance code distribution between high- and low-frequency features.<n> Experiments on three datasets reveal that our method reduces memory usage by over 50x while maintaining or improving recommendation performance.
  arXiv  Detail & Related papers  (2025-02-21T10:12:34Z)
• QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache [67.84112700032007]
  Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings.<n>In these scenarios, the Key-Value ( KV) cache is the primary bottleneck in terms of both GPU memory and latency.<n>We propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration.
  arXiv  Detail & Related papers  (2025-02-05T20:43:48Z)
• On Storage Neural Network Augmented Approximate Nearest Neighbor Search [1.3654846342364308]
  It is necessary to search for the most similar vectors to a given query vector from the data stored in storage devices, not from that in memory.<n>In this paper, we propose a method to predict the correct clusters by means of a neural network.<n>Compared to state-of-the-art SPANN and an exhaustive method using k-means clustering and linear search, the proposed method achieves 90% recall on SIFT1M with 80% and 58% less data fetched from storage, respectively.
  arXiv  Detail & Related papers  (2025-01-23T06:56:18Z)
• Accelerating Retrieval-Augmented Generation [15.179354005559338]
  Retrieval-Augmented Generation (RAG) involves augmenting large language models with information retrieved from an external knowledge source, such as the web.<n>IKS is a type-2 CXL device that implements a scale-out near-memory acceleration architecture with a novel cache-coherent interface between the host CPU and near-memory accelerators.
  arXiv  Detail & Related papers  (2024-12-14T06:47:56Z)
• RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval [24.472784635757016]
  RetrievalAttention is a training-free approach to both accelerate attention computation and reduce GPU memory consumption.<n>We show that RetrievalAttention achieves near full attention accuracy while only requiring access to 1--3% of the data.
  arXiv  Detail & Related papers  (2024-09-16T17:59:52Z)
• Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference [23.633481089469836]
  Auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance.<n>We propose a novel parallel prompt decoding that requires only $0.0002$% trainable parameters, enabling efficient training on a single A100-40GB GPU in just 16 hours.<n>Our approach demonstrates up to 2.49$times$ speedup and maintains a minimal memory overhead of just $0.0004$%.
  arXiv  Detail & Related papers  (2024-05-28T22:19:30Z)
• AiSAQ: All-in-Storage ANNS with Product Quantization for DRAM-free Information Retrieval [1.099532646524593]
  We propose All-in-Storage ANNS with Product Quantization (AiSAQ), which offloads compressed vectors to the SSD index.<n>Our method achieves $sim$10 MB memory usage in query search with billion-scale datasets without critical latency degradation.
  arXiv  Detail & Related papers  (2024-04-09T04:20:27Z)
• HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference [68.59839755875252]
  HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47times$ on a single TPUv5e device.
  arXiv  Detail & Related papers  (2024-02-14T18:04:36Z)
• NumS: Scalable Array Programming for the Cloud [82.827921577004]
  We present NumS, an array programming library which optimize NumPy-like expressions on task-based distributed systems. This is achieved through a novel scheduler called Load Simulated Hierarchical Scheduling (LSHS) We show that LSHS enhances performance on Ray by decreasing network load by a factor of 2x, requiring 4x less memory, and reducing execution time by 10x on the logistic regression problem.
  arXiv  Detail & Related papers  (2022-06-28T20:13:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.