# POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference

arXiv: https://arxiv.org/abs/2410.18038 · HTML: https://mlsanity.com/paper/2410.18038/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 68 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Builds on (most cited first, 28 of 28)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mlsanity.com/paper/2312.12456/) (2023)
- [SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills](https://mlsanity.com/paper/2308.16369/) (2023)
- [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)
- [Vidur: A Large-Scale Simulation Framework For LLM Inference](https://mlsanity.com/paper/2405.05465/) (2024)
- [LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism](https://mlsanity.com/paper/2404.09526/) (2024)
- [DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency](https://mlsanity.com/paper/2408.00741/) (2024)
- [DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference](https://mlsanity.com/paper/2401.08671/) (2024)
- [vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention](https://mlsanity.com/paper/2405.04437/) (2024)
- [NanoFlow: Towards Optimal Large Language Model Serving Throughput](https://mlsanity.com/paper/2408.12757/) (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)
- [FLUX: Fast Software-based Communication Overlap On GPUs Through Kernel Fusion](https://mlsanity.com/paper/2406.06858/) (2024)
- [Breaking the Computation and Communication Abstraction Barrier in Distributed Machine Learning Workloads](https://mlsanity.com/paper/2105.05720/) (2021)
- [Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference](https://mlsanity.com/paper/2303.06182/) (2023)
- [Stream-K: Work-centric Parallel Decomposition for Dense Matrix-Matrix Multiplication on the GPU](https://mlsanity.com/paper/2301.03598/) (2023)
- [Automatic Horizontal Fusion for GPU Kernels](https://mlsanity.com/paper/2007.01277/) (2020)
- [Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers](https://mlsanity.com/paper/2405.10480/) (2024)
- [A Framework for Fine-Grained Synchronization of Dependent GPU Kernels](https://mlsanity.com/paper/2305.13450/) (2023)

## Built on by (most cited first, 30 of 47)

- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving](https://mlsanity.com/paper/2502.00937/) (2025)
- [Throughput-Optimal Scheduling Algorithms for LLM Inference and AI Agents](https://mlsanity.com/paper/2504.07347/) (2025)
- [LLM-42: Enabling Determinism in LLM Inference with Verified Speculation](https://mlsanity.com/paper/2601.17768/) (2026)
- [Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving](https://mlsanity.com/paper/2507.06608/) (2025)
- [KunServe: Parameter-centric Memory Management for Efficient Memory Overloading Handling in LLM Serving](https://mlsanity.com/paper/2412.18169/) (2024)
- [Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective](https://mlsanity.com/paper/2603.16104/) (2026)
- [DynaServe: Unified and Elastic Execution for Dynamic Disaggregated LLM Serving](https://mlsanity.com/paper/2504.09285/) (2025)
- [Optimal Scheduling Algorithms for LLM Inference: Theory and Practice](https://mlsanity.com/paper/2508.01002/) (2025)
- [TokenLake: A Unified Segment-level Prefix Cache Pool for Fine-grained Elastic Long-Context LLM Serving](https://mlsanity.com/paper/2508.17219/) (2025)
- [Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference](https://mlsanity.com/paper/2508.19559/) (2025)
- [DuoServe-MoE: Dual-Phase Expert Prefetch and Caching for LLM Inference QoS Assurance](https://mlsanity.com/paper/2509.07379/) (2025)
- [Efficient MoE Serving in the Memory-Bound Regime: Balance Activated Experts, Not Tokens](https://mlsanity.com/paper/2512.09277/) (2025)
- [From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill](https://mlsanity.com/paper/2510.08055/) (2025)
- [DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU Multiplexing](https://mlsanity.com/paper/2511.04791/) (2025)
- [DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training](https://mlsanity.com/paper/2601.21824/) (2026)
- [PyGraph: Robust Compiler Support for CUDA Graphs in PyTorch](https://mlsanity.com/paper/2503.19779/) (2025)
- [QUOKA: Query-Oriented KV Selection For Efficient LLM Prefill](https://mlsanity.com/paper/2602.08722/) (2026)
- [Bole: Efficient Tree Speculation for Hybrid-Attention Language Models](https://mlsanity.com/paper/2608.01651/) (2026)
- [AGFT: An Adaptive GPU Frequency Tuner for Real-Time LLM Inference Optimization](https://mlsanity.com/paper/2508.01744/) (2025)
- [Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided Scheduling](https://mlsanity.com/paper/2508.03611/) (2025)
- [P/D-Device: Disaggregated Large Language Model between Cloud and Devices](https://mlsanity.com/paper/2508.09035/) (2025)
- [Simple is Better: Multiplication May Be All You Need for LLM Request Scheduling](https://mlsanity.com/paper/2603.15202/) (2026)
- [Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving](https://mlsanity.com/paper/2607.02043/) (2026)
- [SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling](https://mlsanity.com/paper/2607.08565/) (2026)
- [SmartGen: Seamless Disaggregated LLM Inference with Selective KV Cache Transfer](https://mlsanity.com/paper/2607.28150/) (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)
- [PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models](https://mlsanity.com/paper/2602.11530/) (2026)
- [HyFunc: Accelerating LLM-based Function Calls for Agentic AI through Hybrid-Model Cascade and Dynamic Templating](https://mlsanity.com/paper/2602.13665/) (2026)
- [Parallelization Strategies for Dense LLM Deployment: Navigating Through Application-Specific Tradeoffs and Bottlenecks](https://mlsanity.com/paper/2603.05692/) (2026)

## Abstract (arXiv)

Each request in LLM inference goes through two phases: compute-bound prefill and memory-bandwidth-bound decode. To improve GPU utilization, recent systems use hybrid batching that combines the prefill and decode phases of different requests into the same batch. This approach optimizes linear operations but remains inefficient for attention computation because existing attention kernels specialize execution independently for the prefill and decode phases. In this paper, we present POD-Attention - the first GPU kernel that efficiently computes attention for hybrid batches. POD-Attention aims to maximize the utilization of both compute and memory bandwidth by carefully allocating the GPU's resources such that prefill and decode operations happen concurrently on the same multiprocessor. POD-Attention speeds up attention computation by up to 59% (mean 28%), enabling higher throughput and lower latency LLM inference compared to the use of independently optimized prefill and decode attention kernels.