method · first seen 5 Oct 2026
prefill-decode disaggregation
Also: 1P-1D, PD disaggregation, disaggregated serving, disaggregated prefill and decode serving
Separating prefill and decode stages of LLM inference onto distinct hardware workers to improve serving efficiency.
Mentions per week
PapersCodeDiscussion
Rank 184 on 3 Nov 2026 · 10 mentions in 28 days · 10 independent groups · papers · first seen 4 weeks ago · acceleration +0.69
Earliest sources
- Evaluating Inference Compute for Generative AI: A Framework for Enterprise WorkloadsPapers · 5 Oct 2026 · Abbas Raza Ali, Muhammad Ajmal Siddiqui, Moona Zahid
- Compositional Performance Modeling of LLM Inference Clusters with Hierarchical KV CachingPapers · 11 Oct 2026 · Ruiyang Ma, Sheng Qi, DaiKang Kuang, Teng Ma, Guojie Luo
- Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement LearningPapers · 12 Oct 2026 · Chiheng Lou, Xiangwei Deng, Bangjun Xiao, Xiaodong Ji, Yikai Zhao, Xin Jin, Hail…
- HAWK: Heterogeneity-Aware KV Cache Transfer for Efficient GPU-NPU Phase-Disaggregated LLM InferencePapers · 21 Oct 2026 · Junhyeok Park, Jungeun Yoon, Kyungmin Kim, Hunsoon Lee, Shinyoung Ahn, Kangho Ki…
- InferSlice: A Reference Architecture for SLO-driven LLM Inference over a Telco Wide-Area NetworkPapers · 23 Oct 2026 · Juan Parra-Ullauri, Anthony Chiu, Hari Madhukumar, Zhaozhou Wu, Anderson Bravalh…
- LLMs in Cloud: A Discussion on Architecture, Orchestration, and InferencePapers · 24 Oct 2026 · Jannatun Noor, Athar Noor Mohammad Rafee, Md. Sadman Haque, Sreezon Das Gupta, A…
Latest sources
- Callo: Serving Cache-Miss Requests with Speculative Decoding on Invalidated KV under Prefill-Decode DisaggregationPapers · 13 Nov 2026 · Jianjun Ou, Matthew Lentz
- VelServe: Taming Decode Jitters in LLM Inference with Tail-Calibrated SchedulingPapers · 13 Nov 2026 · Ishaan Datta, Alind Khare, Koushik Kumar Dey, Ratnesh Jamidar, Anand Kumar Singh
- Evolving Infra: Agent-Adaptive LLM Serving at ScalePapers · 9 Nov 2026 · Hao Kang, Weili Xu, Ziyang Li, Zheng Du, Hanchen Li, Tian Xia, Song Bian, Tushar…
- ReKV: Overlapping Quantized KV Transfer and Suffix RecomputationPapers · 5 Nov 2026 · Guangjian Dong
- HELIX: HEterogeneous LLM Inference with FleXible and Fine-Grained PartitioningPapers · 4 Nov 2026 · Victoria Clerico, William Simon, Corey Liam Lammie, Orhun Görkem, Athanasios Va…
- What Sets the Serving Speed of Looped Language Models? Measurements and Optimizations Graded by ExactnessPapers · 3 Nov 2026 · Dezhen Lu, Runguo Li, Zixiang Ni, Yuchen Tang, Xingquan Kong, Jiaxing Yang, Jiar…
- ROCm InferaSim: Cut LLM Serving Trial Costs and Deploy the Best ConfigurationPapers · 2 Nov 2026 · Anshu Raina, Yao Fu, Zhang Jiejing, Peyman Razaghi, Shiksha Patel, Ravi Gupta, D…
- When Cache Pressure Becomes a Trap: Metastability in Agent ServingPapers · 2 Nov 2026 · Chengzhi Lu, Boxi Zhou, Yanying Lin, Dmitrii Ustiugov
- DolphinRouting: Cluster-Level Binary Routing for Disaggregated LLM Inference ServingPapers · 29 Oct 2026 · Yishuo Yuan, Shaoyu Yang, Chunrong Fang
- ConfluxServe: Reconciling Resource Utilization and Parallelism Efficiency across Prefill and Decode in LLM ServingPapers · 27 Oct 2026 · Wenhao Chen, Hong Zhang
- LLMs in Cloud: A Discussion on Architecture, Orchestration, and InferencePapers · 24 Oct 2026 · Jannatun Noor, Athar Noor Mohammad Rafee, Md. Sadman Haque, Sreezon Das Gupta, A…
- InferSlice: A Reference Architecture for SLO-driven LLM Inference over a Telco Wide-Area NetworkPapers · 23 Oct 2026 · Juan Parra-Ullauri, Anthony Chiu, Hari Madhukumar, Zhaozhou Wu, Anderson Bravalh…