会员服务
ARCANE: Adaptive RISC-V Cache Architecture for Near-memory Extensions
Arxiv
0+阅读 · 4月3日
Comparative Analysis of Distributed Caching Algorithms: Performance Metrics and Implementation Considerations
Arxiv
0+阅读 · 4月3日
MERE: Hardware-Software Co-Design for Masking Cache Miss Latency in Embedded Processors
Arxiv
0+阅读 · 4月2日
Knowledge-Aware Iterative Retrieval for Multi-Agent Systems
Knowledge-Aware Iterative Retrieval for Multi-Agent Systems
Arxiv
0+阅读 · 4月1日
Mitigating Cache Noise in Test-Time Adaptation for Large Vision-Language Models
Arxiv
0+阅读 · 3月31日
Training-Free Exponential Context Extension via Cascading KV Cache
Arxiv
0+阅读 · 3月31日
SQuat: Subspace-orthogonal KV Cache Quantization
Arxiv
0+阅读 · 3月31日
FB$^+$-tree: A Memory-Optimized B$^+$-tree with Latch-Free Update
Arxiv
0+阅读 · 3月30日
AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference
Arxiv
0+阅读 · 3月31日
Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving
Arxiv
0+阅读 · 3月31日
A Unified Framework for Quantitative Cache Analysis
Arxiv
0+阅读 · 3月30日
EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices
Arxiv
0+阅读 · 3月28日
Spineless Traversal for Layout Invalidation
Arxiv
0+阅读 · 3月27日
WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM Inference
Arxiv
0+阅读 · 3月27日
FlooNoC: A 645 Gbps/link 0.15 pJ/B/hop Open-Source NoC with Wide Physical Links and End-to-End AXI4 Parallel Multi-Stream Support
Arxiv
0+阅读 · 3月27日
参考链接
微信扫码咨询专知VIP会员
Top