SGLang adds UnifiedRadixCache external cache

SemiAnalysis @SemiAnalysis_Originally posted 2026.09.23

Open original on X

MI355X IS UP TO 1.7X BETTER 💰️PERF PER DOLLAR 💰️THAN DGX B300. The AMD Mainland China UMBP team co-designed, in collaboration with Alibaba & the @sgl_project community, a new feature in SGLang that removes the duplicated KVCache contained between local L2 DRAM & distributed L3 DRAM, allowing for up to 2x more KVCache to be stored in DRAM. This feature is called UnifiedRadixCache external cache. But importantly, this marks the trend of AMD increasingly being first-class co-designed for new features in widely used top production engines like SGLang.