Image de couverture de livre

Swarm: Co-Activation Aware KVCache Offloading Across Multiple SSDs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Tuowei, Chu, Liyun, Fan, Ruwen, Ren, Ju
Format:	Preprint
Publié:	2026
Sujets:	Performance
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking
par: Wang, Tuowei, et autres
Publié: (2024)

Mosaic: Cross-Modal Clustering for Efficient Video Understanding
par: Wang, Tuowei, et autres
Publié: (2026)

A Zoned Storage Optimized Flash Cache on ZNS SSDs
par: Yang, Chongzhuo, et autres
Publié: (2024)

Matryoshka: Optimization of Dynamic Diverse Quantum Chemistry Systems via Elastic Parallelism Transformation
par: Wang, Tuowei, et autres
Publié: (2024)

A Microbenchmark Framework for Performance Evaluation of OpenMP Target Offloading
par: Atif, Mohammad, et autres
Publié: (2025)

A Pilot Study on Tunable Precision Emulation via Automatic BLAS Offloading
par: Liu, Hang, et autres
Publié: (2025)

Swarms on Stage: Swarm Simulations for Dance Performance
par: Bisig, Daniel, et autres
Publié: (2009)

Dissecting the NVIDIA Hopper Architecture through Microbenchmarking and Multiple Level Analysis
par: Luo, Weile, et autres
Publié: (2025)

High Performance Matrix Multiplication
par: Davis, Ethan
Publié: (2025)

Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage
par: Yuan, Ziqi, et autres
Publié: (2025)

GROOT: General-Purpose Automatic Parameter Tuning Across Layers, Domains, and Use Cases
par: Krahn, Robert, et autres
Publié: (2025)

SparseInfer: Training-free Prediction of Activation Sparsity for Fast LLM Inference
par: Shin, Jiho, et autres
Publié: (2024)

Offloading and Quality Control for AI Generated Content Services in 6G Mobile Edge Computing Networks
par: Wang, Yitong, et autres
Publié: (2023)

Size-Aware Dispatching to Fluid Queues
par: Xie, Runhan, et autres
Publié: (2025)

Waltz: Temperature-Aware Cooperative Compression for High-Performance Compression-Based CSDs
par: Yu, Dingcui, et autres
Publié: (2025)

GreedySnake: Accelerating SSD-Offloaded LLM Training with Efficient Scheduling and Optimizer Step Overlapping
par: Yin, Yishu, et autres
Publié: (2025)

Spatiotemporal Non-Uniformity-Aware Online Task Scheduling in Collaborative Edge Computing for Industrial Internet of Things
par: Li, Yang, et autres
Publié: (2025)

CARINA: Carbon-Aware Execution of Recurrent Industrial Analytics
par: Farooq, Muhammad Umar
Publié: (2026)

Heavy-Traffic Optimal Size- and State-Aware Dispatching
par: Xie, Runhan, et autres
Publié: (2023)

Latency and Privacy-Aware Resource Allocation in Vehicular Edge Computing
par: Ahmadvand, Hossein, et autres
Publié: (2025)

Leveraging LLMs for Structured Information Extraction and Analysis from Cloud Incident Reports (Work In Progress Paper)
par: Chu, Xiaoyu, et autres
Publié: (2026)

cuTeSpMM: Accelerating Sparse-Dense Matrix Multiplication using GPU Tensor Cores
par: Xiang, Lizhi, et autres
Publié: (2025)

AI Application Benchmarking: Power-Aware Performance Analysis for Vision and Language Models
par: Mayr, Martin, et autres
Publié: (2026)

GreenLLM: SLO-Aware Dynamic Frequency Scaling for Energy-Efficient LLM Serving
par: Liu, Qunyou, et autres
Publié: (2025)

ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
par: Fan, Ruibo, et autres
Publié: (2026)

Attributing the System's Overall Effect to its Components
par: Wang, Chenxi, et autres
Publié: (2026)

Achieving Consistent and Comparable CPU Evaluation
par: Wang, Chenxi, et autres
Publié: (2024)

Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks
par: Gardner, Jason, et autres
Publié: (2025)

DUAL-BLADE: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference
par: Jeong, Bodon, et autres
Publié: (2026)

Do LLMs Have Visualization Literacy? An Evaluation on Modified Visualizations to Test Generalization in Data Interpretation
par: Hong, Jiayi, et autres
Publié: (2025)

MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference
par: Chu, Kexin, et autres
Publié: (2026)

Beyond Tokens: Semantic-Aware Speculative Decoding for Efficient Inference by Probing Internal States
par: Dong, Ximing, et autres
Publié: (2026)

SSDTrain: An Activation Offloading Framework to SSDs for Faster Large Language Model Training
par: Wu, Kun, et autres
Publié: (2024)

Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity
par: Song, Zichen, et autres
Publié: (2024)

Machine Learning-Guided Memory Optimization for DLRM Inference on Tiered Memory
par: Ren, Jie, et autres
Publié: (2025)

Towards a Higher Roofline for Matrix-Vector Multiplication in Matrix-Free HOSFEM
par: Cao, Zijian, et autres
Publié: (2025)

An Analytical Cost Model for Fast Evaluation of Multiple Compute-Engine CNN Accelerators
par: Qararyah, Fareed, et autres
Publié: (2025)

Asymptotically Optimal Scheduling of Multiple Parallelizable Job Classes
par: Berg, Benjamin, et autres
Publié: (2024)

Adaptive Cache Pollution Control for Large Language Model Inference Workloads Using Temporal CNN-Based Prediction and Priority-Aware Replacement
par: Liu, Songze, et autres
Publié: (2025)

Approximation Algorithms for Minimizing Congestion in Demand-Aware Networks
par: Dai, Wenkai, et autres
Publié: (2024)