Inference Infrastructure & ServingZheng et al.
SGLang paper
SGLang paper — RadixAttention
Why it matters
Automatically reuses the prefix KV cache through a radix tree
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2312.07104Added in Week 35, 2026 · See that week