🧠 Memory Management - DiToast · Scour

KV Cache Offloading for Context-Intensive Tasks 🏗Computer Architecture

arxiv.org·10h

ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache 🏗Computer Architecture

arxiv.org·1d

CIDER: Boosting Memory-Disaggregated Key-Value Stores with Pessimistic Synchronization 🏗Computer Architecture

arxiv.org·4d

Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving 🔐Cryptography

arxiv.org·10h

Top-K Retrieval with Fixed-Size Linear-Attention Completion: Backbone- and KV-Format-Preserving Attention for KV-Cache Read Reduction 🎲Probabilistic Programming

arxiv.org·2d

FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving 🎲Probabilistic Programming

arxiv.org·4d

MIPT-SSM: Scaling Language Models with $O(1)$ Inference Cache via Phase Transitions 🎲Probabilistic Programming

arxiv.org·10h

AudioKV: KV Cache Eviction in Efficient Large Audio Language Models 🏗Computer Architecture

arxiv.org·1d

Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory 📊Information Theory

arxiv.org·10h

TRAPTI: Time-Resolved Analysis for SRAM Banking and Power Gating Optimization in Embedded Transformer Inference 🏗Computer Architecture

arxiv.org·1d

A Synthesis Method of Safe Rust Code Based on Pushdown Colored Petri Nets 🦀Rust

arxiv.org·4d

StructKV: Preserving the Structural Skeleton for Scalable Long-Context Inference 🎲Probabilistic Programming

arxiv.org·1d

Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion 🎲Probabilistic Programming

arxiv.org·2d

Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation 🏗Computer Architecture

arxiv.org·4d

DualDiffusion: A Speculative Decoding Strategy for Masked Diffusion Models 🎲Probabilistic Programming

arxiv.org·2d

Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use 🔐Cryptography

arxiv.org·2d

PG-MDP: Profile-Guided Memory Dependence Prediction for Area-Constrained Cores 🏗Computer Architecture

arxiv.org·10h

Lightweight LLM Agent Memory with Small Language Models 🎲Probabilistic Programming

arxiv.org·10h

Fast Heterogeneous Serving: Scalable Mixed-Scale LLM Allocation for SLO-Constrained Inference 🎲Probabilistic Programming

arxiv.org·10h

MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought 🎲Probabilistic Programming

arxiv.org·10h

Loading more...