paper-with-me

Papers

The DMA Streaming Framework: Kernel-Level Buffer Orchestration for High-Performance AI Data Paths

2026-02-26 · Marco Graziano arxiv

AI transport libraries move bytes efficiently, but they commonly assume that buffers are already correctly allocated, placed, shared, registered, and safe under completion and teardown pressure. This paper presents dmaplane, a Linux kernel module that makes this missing layer explicit as buffer orchestration. dmaplane exposes a stable kernel UAPI via /dev/dmaplane and composes ring-based command channels, DMA buffer lifecycle management, dma-buf export for cross-device sharing, a kernel-space RDMA engine, NUMA-aware allocation and verification, credit-based flow control, low-overhead observability, and GPU memory integration via PCIe BAR pinning. We evaluate orchestration sensitivity with measurements of NUMA cross-node penalties at DRAM scale, completion-safe flow control under sustained RDMA load, and GPU BAR mapping tiers versus cudaMemcpy. We also demonstrate end-to-end disaggregated inference by transferring KV-cache chunks between two machines using RDMA WRITE WITH IMMEDIATE and reconstructing tensor views on the receiver. RDMA measurements use Soft-RoCE; we distinguish measured results from provider-independent properties by construction.

📄 PDF Abstract BibTeX arXiv:2603.10030

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

eBandit: Kernel-Driven Reinforcement Learning for Adaptive Video Streaming

2026-04-09 · Mahdi Alizadeh arxiv

User-space Adaptive Bitrate (ABR) algorithms cannot see the transport layer signals that matter most, such as minimum RTT and instantaneous delivery rate, and they respond to network changes only after damage has already…

Reinforcement Learning

Online Action Detection in Streaming Videos with Time Buffers

2020-10-06 · BoWen Zhang, Hao Chen, Meng Wang, Yuanjun Xiong

We formulate the problem of online temporal action detection in live streaming videos, acknowledging one important property of live streaming videos that there is normally a broadcast delay between the latest captured fr…

Action DetectionOnline Action Detection

Architecting AgentOS: From Token-Level Context to Emergent System-Level Intelligence

2026-02-24 · ChengYou Li, XiaoDong Liu, XiangBao Meng, XinYu Zhao arxiv

The paradigm of Large Language Models is undergoing a fundamental transition from static inference engines to dynamic autonomous cognitive systems.While current research primarily focuses on scaling context windows or op…

Prompt Engineering

ODEStream: A Buffer-Free Online Learning Framework with ODE-based Adaptor for Streaming Time Series Forecasting

2024-11-11 · Futoon M. Abushaqra, Hao Xue, Yongli Ren, Flora D. Salim

Addressing the challenges of irregularity and concept drift in streaming time series is crucial in real-world predictive modelling. Previous studies in time series continual learning often propose models that require buf…

Continual LearningTime SeriesTime Series Forecasting

An Autonomous Network Orchestration Framework Integrating Large Language Models with Continual Reinforcement Learning

2025-02-22 · Masoud Shokrnezhad, Tarik Taleb

6G networks aim to achieve global coverage, massive connectivity, and ultra-stringent requirements. Space-Air-Ground Integrated Networks (SAGINs) and Semantic Communication (SemCom) are essential for realizing these goal…

ARCContinual LearningContrastive LearningFew-Shot Learning+4