# P/D-Serve: Serving Disaggregated Large Language Model at Scale

arXiv: https://arxiv.org/abs/2408.08147 · HTML: https://mlsanity.com/paper/2408.08147/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 33 of its 45 references that are in the map.
- First posted on arXiv 15 Aug 2024.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification](https://mlsanity.com/paper/2305.09781/) (2023)
- [Prompt Cache: Modular Attention Reuse for Low-Latency Inference](https://mlsanity.com/paper/2311.04934/) (2023)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention](https://mlsanity.com/paper/2403.19708/) (2024)
- [Fast Distributed Inference Serving for Large Language Models](https://mlsanity.com/paper/2305.05920/) (2023)
- [Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads](https://mlsanity.com/paper/2401.11181/) (2024)
- [LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism](https://mlsanity.com/paper/2404.09526/) (2024)
- [ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition](https://mlsanity.com/paper/2402.15220/) (2024)
- [Fairness in Serving Large Language Models](https://mlsanity.com/paper/2401.00588/) (2023)
- [FlashDecoding++: Faster Large Language Model Inference on GPUs](https://mlsanity.com/paper/2311.01282/) (2023)
- [MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool](https://mlsanity.com/paper/2406.17565/) (2024)
- [PanGu-Sigma: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing](https://mlsanity.com/paper/2303.10845/) (2023)

## Built on by (most cited first, 27 of 27)

- [TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text](https://mlsanity.com/paper/2410.07590/) (2024)
- [BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching](https://mlsanity.com/paper/2412.03594/) (2024)
- [ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production](https://mlsanity.com/paper/2505.09999/) (2025)
- [ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments](https://mlsanity.com/paper/2502.09334/) (2025)
- [Efficiently Serving Large Multimodal Models Using EPD Disaggregation](https://mlsanity.com/paper/2501.05460/) (2024)
- [Taming the Titans: A Survey of Efficient LLM Inference Serving](https://mlsanity.com/paper/2504.19720/) (2025)
- [Seesaw: High-throughput LLM Inference via Model Re-sharding](https://mlsanity.com/paper/2503.06433/) (2025)
- [TokenFlow: Responsive LLM Text Streaming Serving under Request Burst via Preemptive Scheduling](https://mlsanity.com/paper/2510.02758/) (2025)
- [Beyond the Buzz: A Pragmatic Take on Inference Disaggregation](https://mlsanity.com/paper/2506.05508/) (2025)
- [LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure](https://mlsanity.com/paper/2602.23036/) (2026)
- [ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism](https://mlsanity.com/paper/2507.10069/) (2025)
- [EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference](https://mlsanity.com/paper/2410.12247/) (2024)
- [Arrow: Adaptive Scheduling Mechanisms for Disaggregated LLM Inference Architecture](https://mlsanity.com/paper/2505.11916/) (2025)
- [Sparser Block-Sparse Attention via Token Permutation](https://mlsanity.com/paper/2510.21270/) (2025)
- [ElasticMoE: An Efficient Auto Scaling Method for Mixture-of-Experts Models](https://mlsanity.com/paper/2510.02613/) (2025)
- [LAPS: A Length-Aware-Prefill LLM Serving System](https://mlsanity.com/paper/2601.11589/) (2026)
- [Disaggregated Prefill and Decoding Inference System for Large Language Model Serving on Multi-Vendor GPUs](https://mlsanity.com/paper/2509.17542/) (2025)
- [xLLM Technical Report](https://mlsanity.com/paper/2510.14686/) (2025)
- [P/D-Device: Disaggregated Large Language Model between Cloud and Devices](https://mlsanity.com/paper/2508.09035/) (2025)
- [RelayGR: Scaling Long-Sequence Generative Recommendation via Cross-Stage Relay-Race Inference](https://mlsanity.com/paper/2601.01712/) (2026)
- [Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels](https://mlsanity.com/paper/2412.18106/) (2024)
- [SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference](https://mlsanity.com/paper/2603.04716/) (2026)
- [OmniInfer: System-Wide Acceleration Techniques for Optimizing LLM Serving Throughput and Latency](https://mlsanity.com/paper/2511.22481/) (2025)
- [Tropical: Enhancing SLO Attainment in Disaggregated LLM Serving via SLO-Aware Multiplexing](https://mlsanity.com/paper/2606.16264/) (2026)
- [3DLS: A 3D Logic-Stacked Architecture for Disaggregated LLM Serving](https://mlsanity.com/paper/2607.01617/) (2026)
- [From Tensor Buffer to Distributed Memory Hierarchy: A Survey of KV Cache Management for LLM Serving](https://mlsanity.com/paper/2607.02574/) (2026)
- [FluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving](https://mlsanity.com/paper/2610.06917/) (2026)

## Abstract (arXiv)

Serving disaggregated large language models (LLMs) over tens of thousands of xPU devices (GPUs or NPUs) with reliable performance faces multiple challenges. 1) Ignoring the diversity (various prefixes and tidal requests), treating all the prompts in a mixed pool is inadequate. To facilitate the similarity per scenario and minimize the inner mismatch on P/D (prefill and decoding) processing, fine-grained organization is required, dynamically adjusting P/D ratios for better performance. 2) Due to inaccurate estimation on workload (queue status or maintained connections), the global scheduler easily incurs unnecessary timeouts in prefill. 3) Block-fixed device-to-device (D2D) KVCache transfer over cluster-level RDMA (remote direct memory access) fails to achieve desired D2D utilization as expected. To overcome previous problems, this paper proposes an end-to-end system P/D-Serve, complying with the paradigm of MLOps (machine learning operations), which models end-to-end (E2E) P/D performance and enables: 1) fine-grained P/D organization, mapping the service with RoCE (RDMA over converged ethernet) as needed, to facilitate similar processing and dynamic adjustments on P/D ratios; 2) on-demand forwarding upon rejections for idle prefill, decoupling the scheduler from regular inaccurate reports and local queues, to avoid timeouts in prefill; and 3) efficient KVCache transfer via optimized D2D access. P/D-Serve is implemented upon Ascend and MindSpore, has been deployed over tens of thousands of NPUs for more than eight months in commercial use, and further achieves 60%, 42% and 46% improvements on E2E throughput, time-to-first-token (TTFT) SLO (service level objective) and D2D transfer time. As the E2E system with optimizations, P/D-Serve achieves 6.7x increase on throughput, compared with aggregated LLMs.