"Skip to main content\narXiv is now an independent nonprofit!\nLearn more\n×\nSearch\nSubmit\nDonate\nLog in\nComputer Science > Hardware Architecture\n[Submitted on 2 Jul 2026]\n3DLS: A 3D Logic-Stacked Architecture for Disaggregated LLM Serving\nJaehun Lee, In-Jun Jung, Joo-Young Kim\nLarge language model (LLM) serving increasingly combines prefill-decode (PD) disaggregation with tensor parallelism (TP) to support large models and long contexts. In conventional 2D/2.5D chiplet architectures, layer-wise prefill-to-decode KV-cache transfer decode-side TP collectives share the same lateral die-to-die (D2D) interconnect, creating mixed-traffic contention on the decode critical path. This contention increases communication latency, prolongs token generation intervals, and degrades end-to-end serving performance. We propose 3DLS, a logic-on-logic 3D-stacked chiplet architecture that separates traffic classes by routing KV-cache transfers through vertical interconnects while preserving decode-side TP collectives on the lateral D2D fabric. 3DLS achieves up to 1.49\n×\n throughput and 60.2\\% lower end-to-end (E2E) latency over the shared-fabric planar baseline, and still achieves up to 1.17\n×\n throughput and 31.4\\% lower E2E latency over a workload-aware priority-managed planar baseline. These results highlight that physical isolation is an important design principle for future chiplet-based PD-disaggregated LLM serving systems.\nComments:\tAccepted to IEEE Computer Architecture Letters (CAL), 2026\nSubjects:\tHardware Architecture (cs.AR)\nCite as:\tarXiv:2607.01617 [cs.AR]\n \t(or arXiv:2607.01617v1 [cs.AR] for this version)\n \t\nhttps://doi.org/10.48550/arXiv.2607.01617\nFocus to learn more\n\nRelated DOI:\t\nhttps://doi.org/10.1109/LCA.2026.3709108\nFocus to learn more\nSubmission history\nFrom: Jaehun Lee [view email]\n[v1] Thu, 2 Jul 2026 02:32:44 UTC (545 KB)\n\nAccess Paper:\nView PDF\nHTML (experimental)\nTeX Source\nview license\nCurrent browse context:\ncs.AR\n< prev | next >\n\nnew | recent | 2026-07\nChange to browse by:\ncs\n\nReferences & Citations\nNASA ADS\nGoogle Scholar\nSemantic Scholar\nExport BibTeX Citation\nBookmark\n \nBibliographic Tools\nBibliographic and Citation Tools\nBibliographic Explorer Toggle\nBibliographic Explorer (What is the Explorer?)\nConnected Papers Toggle\nConnected Papers (What is Connected Papers?)\nLitmaps Toggle\nLitmaps (What is Litmaps?)\nscite.ai Toggle\nscite Smart Citations (What are Smart Citations?)\nCode, Data, Media\nDemos\nRelated Papers\nAbout arXivLabs\nWhich authors of this paper are endorsers? | Disable MathJax (What is MathJax?)\nWe gratefully acknowledge support from our major funders, member institutions, and all contributors.\nAbout\n·\nHelp\n·\nContact\n·\nSubscribe\n·\nCopyright\n·\nPrivacy\n·\nAccessibility\n·\nOperational Status\n(opens in new tab)\nMajor funding support from"