# PipeSwift: Revisiting Pipeline Parallelism for Large-Scale Completion-Oriented Agentic LLM Serving

arXiv: https://arxiv.org/abs/2609.16491 · HTML: https://mlsanity.com/paper/2609.16491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Efficient reasoning and agent inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Placed in

- Efficient LLM inference and serving / [Efficient reasoning and agent inference](https://mlsanity.com/inference/efficient-reasoning-and-agent-inference/)

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

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving](https://mlsanity.com/paper/2407.00079/) (2024)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [Parrot: Efficient Serving of LLM-based Applications with Semantic Variable](https://mlsanity.com/paper/2405.19888/) (2024)
- [SpotServe: Serving Generative Large Language Models on Preemptible Instances](https://mlsanity.com/paper/2311.15566/) (2023)
- [Autellix: An Efficient Serving Engine for LLM Agents as General Programs](https://mlsanity.com/paper/2502.13965/) (2025)
- [KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows](https://mlsanity.com/paper/2507.07400/) (2025)
- [POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference](https://mlsanity.com/paper/2410.18038/) (2024)
- [Teola: Towards End-to-End Optimization of LLM-based Applications](https://mlsanity.com/paper/2407.00326/) (2024)
- [Prefill-Decode Aggregation or Disaggregation? Unifying Both for Goodput-Optimized LLM Serving](https://mlsanity.com/paper/2508.01989/) (2025)
- [FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism](https://mlsanity.com/paper/2412.01523/) (2024)
- [ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System](https://mlsanity.com/paper/2602.13692/) (2026)
- [DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference](https://mlsanity.com/paper/2602.21548/) (2026)
- [Pie: A Programmable Serving System for Emerging LLM Applications](https://mlsanity.com/paper/2510.24051/) (2025)
- [DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training](https://mlsanity.com/paper/2604.26256/) (2026)
- [Heddle: A Distributed Orchestration System for Agentic RL Rollout](https://mlsanity.com/paper/2603.28101/) (2026)
- [ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL](https://mlsanity.com/paper/2605.06534/) (2026)
- [KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving](https://mlsanity.com/paper/2605.13734/) (2026)

## Abstract (arXiv)

LLM agents execute long-horizon workflows where each model response determines the progress of subsequent tool interactions and environment transitions. Unlike chatbot serving, where TTFT and TPOT SLO constraints are critical, agentic workloads are completion-oriented and increasingly governed by job completion time (JCT). This shift challenges existing LLM serving designs optimized around token SLOs. Through a systematic exploration of scheduling and parallelism, we uncover a previously overlooked principle for agent serving: JCT is governed by the balance between prefill and decode efficiency. A prefill-prioritized scheduling policy achieves the best TTFT and the highest decode throughput, yet fails to attain the lowest JCT. This principle further reshapes the parallelism landscape: we show that pipeline parallelism (PP), long overlooked because it offers little decode-latency advantage, can reduce JCT by providing a more favorable balance between prefill and decode efficiency. Based on these insights, we build PipeSwift, an optimized open-source pipeline-parallel runtime integrated with a tailored micro-batch partitioning strategy co-designed with schedule considering the above trade-off, and pipeline-integrated multi-token prediction. Evaluated on real coding and web-search agent trajectories with two 360B+ MoE models on 64 H800 GPUs, PipeSwift reduces overall JCT by up to 1.45× over SGLang wide-EP, 2.33× over vLLM PP2, and 1.54× over today's state-of-the-art open-source PD-disaggregated deployment.