会员服务
FMCache: File-System Metadata Caching in Programmable Switches
Arxiv
0+阅读 · 10月9日
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
Arxiv
0+阅读 · 10月9日
Systematic Assessment of Cache Timing Vulnerabilities on RISC-V Processors
Arxiv
0+阅读 · 10月9日
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
Arxiv
0+阅读 · 10月9日
LLM meets ML: Data-efficient Anomaly Detection on Unstable Logs
Arxiv
0+阅读 · 10月9日
Artificial Hippocampus Networks for Efficient Long-Context Modeling
Arxiv
0+阅读 · 10月8日
VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
Arxiv
0+阅读 · 10月7日
On Enhancing Delay SLAs in TCP Networks through Joint Routing and Transport Assistant Deployment
Arxiv
0+阅读 · 10月7日
PATCHEDSERVE: A Patch Management Framework for SLO-Optimized Hybrid Resolution Diffusion Serving
Arxiv
0+阅读 · 10月5日
Detecting and Preventing Latent Risk Accumulation in High-Performance Software Systems
Arxiv
0+阅读 · 10月4日
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
Arxiv
0+阅读 · 10月3日
NetCAS: Dynamic Cache and Backend Device Management in Networked Environments
Arxiv
0+阅读 · 9月25日
Cache-to-Cache: Direct Semantic Communication Between Large Language Models
Arxiv
0+阅读 · 10月3日
KAIROS: Unified Training for Universal Non-Autoregressive Time Series Forecasting
KAIROS: Unified Training for Universal Non-Autoregressive Time Series Forecasting
Arxiv
0+阅读 · 10月3日
KAIROS: Unified Training for Universal Non-Autoregressive Time Series Forecasting
KAIROS: Unified Training for Universal Non-Autoregressive Time Series Forecasting
Arxiv
0+阅读 · 10月2日
参考链接
微信扫码咨询专知VIP会员
Top