{"ID":5675083,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-05T01:57:11.175896696Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01617","arxiv_id":"2607.01617","title":"3DLS: A 3D Logic-Stacked Architecture for Disaggregated LLM Serving","abstract":"Large 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$\\times$ throughput and 60.2\\% lower end-to-end (E2E) latency over the shared-fabric planar baseline, and still achieves up to 1.17$\\times$ 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.","short_abstract":"Large 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 (...","url_abs":"https://arxiv.org/abs/2607.01617","url_pdf":"https://arxiv.org/pdf/2607.01617v1","authors":"[\"Jaehun Lee\",\"In-Jun Jung\",\"Joo-Young Kim\"]","published":"2026-07-02T02:32:44Z","proceeding":"cs.AR","tasks":"[\"cs.AR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}