Learning Semantics, Not Addresses: Runtime Neural Prefetching for Far Memory

• URL: http://arxiv.org/abs/2506.00384v2
• Date: Sun, 05 Oct 2025 21:29:28 GMT
• Title: Learning Semantics, Not Addresses: Runtime Neural Prefetching for Far Memory
• Abstract summary: We introduce FarSight, the first Linux-based far-memory system to leverage deep learning by decoupling application semantics from runtime memory layout.<n>Across four data-intensive workloads, FarSight delivers up to 3.6x higher performance than the state-of-the-art.
• Score: 5.122853300811336
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Memory prefetching has long boosted CPU caches and is increasingly vital for far-memory systems, where large portions of memory are offloaded to cheaper, remote tiers. While effective prefetching requires accurate prediction of future accesses, prior ML approaches have been limited to simulation or small-scale hardware. We introduce FarSight, the first Linux-based far-memory system to leverage deep learning by decoupling application semantics from runtime memory layout. This separation enables offline-trained models to predict access patterns over a compact ordinal vocabulary, which are resolved at runtime through lightweight mappings. Across four data-intensive workloads, FarSight delivers up to 3.6x higher performance than the state-of-the-art.

Related papers

• UniMem: Unifying Multimodal Memory and Control for Vision-Language-Action Models [8.70663346892131]
  We present UniMem, a framework that unifies high-level, multimodal memory and low-level control under one backbone.<n>We evaluate UniMem across five simulation and four hardware tasks targeting sequential and spatial memory.
  arXiv  Detail & Related papers  (2026-08-24T06:56:02Z)
• Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents [72.3752981234916]
  Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.<n>We present Memory as a Controlled Process (MemCon), a framework that models memory operations as a Markov Decision Process.<n>MemCon consistently outperforms multiple memory baselines by up to 15.2 points in task success while reducing token consumption by 5-20%.
  arXiv  Detail & Related papers  (2026-07-15T08:32:40Z)
• Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory [65.39827296429527]
  Scaling conditional memory offers a promising way to increase language-model capacity.<n>Existing methods such as Engram learn large memory tables from scratch during pre-training.<n>We propose Memory Grafting, a conditional memory scaling method that utilizes frozen hidden states from a grafting model as conditional n-gram memory.
  arXiv  Detail & Related papers  (2026-05-20T09:35:04Z)
• MemLoRA: Distilling Expert Adapters for On-Device Memory Systems [71.32550994522738]
  Memory-augmented Large Language Models (LLMs) have demonstrated remarkable consistency during dialogues.<n>MemLoRA is a novel memory system that integrates small Vision-Language Models.<n>VLM-integrated MemLoRA-V shows massive improvements in caption-based approaches.
  arXiv  Detail & Related papers  (2025-12-04T12:56:30Z)
• LightMem: Lightweight and Efficient Memory-Augmented Generation [72.21680105265824]
  We introduce a new memory system called LightMem, which strikes a balance between the performance and efficiency of memory systems.<n>Inspired by the Atkinson-Shiffrin model of human memory, LightMem organizes memory into three complementary stages.<n>Experiments on LongMemEval with GPT and Qwen backbones show that LightMem outperforms strong baselines in accuracy (up to 10.9% gains) while reducing token usage by up to 117x.
  arXiv  Detail & Related papers  (2025-10-21T17:58:17Z)
• Leveraging Lightweight Generators for Memory Efficient Continual Learning [0.01874930567916036]
  Catastrophic forgetting can be trivially alleviated by keeping all data from previous tasks in memory.<n>This paper aims to decrease required memory for memory-based continuous learning algorithms.
  arXiv  Detail & Related papers  (2025-06-24T14:59:52Z)
• MOM: Memory-Efficient Offloaded Mini-Sequence Inference for Long Context Language Models [72.61076288351201]
  We propose Memory-efficient Offloaded Mini-sequence Inference (MOM)<n>MOM partitions critical layers into smaller "mini-sequences" and integrates seamlessly with KV cache offloading.<n>On Meta-Llama-3.2-8B, MOM extends the maximum context length from 155k to 455k tokens on a single A100 80GB GPU.
  arXiv  Detail & Related papers  (2025-04-16T23:15:09Z)
• 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)
• MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models [58.3342517278868]
  This paper describes the design of Mixed-precision AutoRegressive LINear kernels. It shows that batchsizes up to 16-32 can be supported with close to maximum ($4times$) quantization speedup. MarLIN accomplishes this via a combination of techniques, such as asynchronous memory access, complex task scheduling and pipelining.
  arXiv  Detail & Related papers  (2024-08-21T16:10:41Z)
• Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model [51.83436609094658]
  We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs' spatial-temporal reasoning with 2D images as input. Our method uses a lightweight tracking model to identify primary object correspondences between frames in a video or across different image viewpoints. We demonstrate that this simple training-free approach brings substantial gains to GPT4-V/O consistently on four benchmarks.
  arXiv  Detail & Related papers  (2024-08-01T17:57:12Z)
• vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving [53.972175896814505]
  Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests.
  arXiv  Detail & Related papers  (2024-07-22T14:37:58Z)
• S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs [7.816840847892339]
  Speculative decoding (SD) has attracted a significant amount of research attention due to the substantial speedup it can achieve for LLM inference. We propose Skippy Simultaneous Speculative Decoding (or S3D), a cost-effective self-speculative SD method based on simultaneous multi-token decoding and mid-layer skipping. Our method has achieved one of the top performance-memory ratios while requiring minimal architecture changes and training data.
  arXiv  Detail & Related papers  (2024-05-30T17:54:35Z)
• vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention [8.20523619534105]
  PagedAttention is a popular approach for dynamic memory allocation in LLM serving systems.<n>We present vAttention -- an approach that mitigates fragmentation in physical memory while retaining the contiguity of KV cache in virtual memory.<n>Overall, vAttention is a simpler, portable, and performant alternative to PagedAttention.
  arXiv  Detail & Related papers  (2024-05-07T16:00:32Z)
• JORA: JAX Tensor-Parallel LoRA Library for Retrieval Augmented Fine-Tuning [16.86356520836045]
  We introduce a novel framework for PEFT-compatible fine-tuning of Llama-2 models, leveraging distributed training. Our framework uniquely utilizes JAX's just-in-time (JIT) compilation and tensor-sharding for efficient resource management. Our experiments show more than 12x improvement in runtime compared to Hugging Face/DeepSpeed implementation with four GPU while consuming less than half the VRAM per GPU.
  arXiv  Detail & Related papers  (2024-03-17T23:02:04Z)
• Online Adaptation of Language Models with a Memory of Amortized Contexts [82.02369596879817]
  Memory of Amortized Contexts (MAC) is an efficient and effective online adaptation framework for large language models. We show how MAC can be combined with and improve the performance of popular alternatives such as retrieval augmented generations.
  arXiv  Detail & Related papers  (2024-03-07T08:34:57Z)
• GLIMMER: generalized late-interaction memory reranker [29.434777627686692]
  Memory-augmentation is a powerful approach for incorporating external information into language models. Recent work introduced LUMEN, a memory-retrieval hybrid that partially pre-computes memory and updates memory representations on the fly with a smaller live encoder. We propose GLIMMER, which improves on this approach through 1) exploiting free access to the powerful memory representations by applying a shallow reranker on top of memory to drastically improve retrieval quality at low cost.
  arXiv  Detail & Related papers  (2023-06-17T01:54:25Z)
• Augmenting Language Models with Long-Term Memory [142.04940250657637]
  Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit. We propose a framework, Language Models Augmented with Long-Term Memory (LongMem), which enables LLMs to memorize long history.
  arXiv  Detail & Related papers  (2023-06-12T15:13:39Z)
• Optimizing Memory Mapping Using Deep Reinforcement Learning [29.48627805378257]
  This paper focuses on the memory mapping problem that occurs during compilation of machine learning programs. We introduce an approach for solving the memory mapping problem using Reinforcement Learning. We also introduce a Reinforcement Learning agent, mallocMuZero, and show that it is capable of playing this game to discover new and improved memory mapping solutions.
  arXiv  Detail & Related papers  (2023-05-11T11:55:16Z)
• 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)
• LaMemo: Language Modeling with Look-Ahead Memory [50.6248714811912]
  We propose Look-Ahead Memory (LaMemo) that enhances the recurrence memory by incrementally attending to the right-side tokens. LaMemo embraces bi-directional attention and segment recurrence with an additional overhead only linearly proportional to the memory length. Experiments on widely used language modeling benchmarks demonstrate its superiority over the baselines equipped with different types of memory.
  arXiv  Detail & Related papers  (2022-04-15T06:11:25Z)
• KML: Using Machine Learning to Improve Storage Systems [0.2810625954925814]
  Machine learning techniques promise to learn patterns, generalize from them, and enable optimal solutions. We develop a prototype KML architecture and apply it to two problems: optimal read and read-size values. Experiments show that KML consumes little OS resources, adds negligible latency, and yet can learn patterns that can improve I/O throughput by as much as 2.3x or 15x.
  arXiv  Detail & Related papers  (2021-11-22T21:59:50Z)
• Hierarchical Memory Matching Network for Video Object Segmentation [38.24999776705497]
  We propose two advanced memory read modules that enable us to perform memory in multiple scales while exploiting temporal smoothness. We first propose a guided memory matching module that replaces the non-local dense memory read, commonly adopted in previous memory-based methods. We introduce a hierarchical memory matching scheme and propose a top-k guided memory matching module in which memory read on a fine-scale is guided by that on a coarse-scale.
  arXiv  Detail & Related papers  (2021-09-23T14:36:43Z)

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.