Story
arxiv_cs_lg ยท Nov 19, 2026 ยท paper
Source brief
TideCache: Efficient Hybrid LLM Serving with Transparent Cache Management and Layer-Wise Streaming
arxiv.orgNov 19, 2026
original source linked
In brief
Hybrid architectures have become mainstream among open-weight language models. Their global-attention and bounded-state layers maintain heterogeneous caches whose demands vary with context length and concurrency. We p...
Feed lens
agenteval