Skip to content

Paper 093 / Microsoft Research / University of Washington

Splitwise: Efficient generative LLM inference using phase splitting

Splitwise studies phase splitting for generative inference, placing compute-heavy prompt processing and memory-heavy token generation on hardware suited to each phase.

UPDATED 16 Jul 2026SOURCE-LED REVIEWRESEARCH REVIEW
01

Paper, researchers, and primary source

Inference, evaluation & serving / inference_systems

Splitwise studies phase splitting for generative inference, placing compute-heavy prompt processing and memory-heavy token generation on hardware suited to each phase.

CONTRIBUTION / 01

Contribution 1

Characterized distinct prefill and decode resource behavior.

CONTRIBUTION / 02

Contribution 2

Designed clusters that split inference phases across heterogeneous machines.

CONTRIBUTION / 03

Contribution 3

Evaluated cost, power, throughput, and latency tradeoffs under serving workloads.

02

Research context

inference_systems / 2023

Splitwise: Efficient generative LLM inference using phase splitting places splitwise inside the broader inference systems discussion at Microsoft Research / University of Washington, with phase splitting supplying a second analytical lens. Read together, the source records three advances: Characterized distinct prefill and decode resource behavior; Designed clusters that split inference phases across heterogeneous machines; and Evaluated cost, power, throughput, and latency tradeoffs under serving workloads. Keeping those moves together prevents heterogeneous hardware from being detached from its evidence. For an implementation review, the relevant consequence is that hardware specialization can improve efficiency but adds transfer latency, capacity-planning complexity, and sensitivity to workload mix.

03

Methods and evidence reading

1 cataloged method notes

METHOD / 01

Method 1

The experimental design in Splitwise: Efficient generative LLM inference using phase splitting tests characterized distinct prefill and decode resource behavior and designed clusters that split inference phases across heterogeneous machines against the paper's documented baselines, datasets, model variants, or systems workloads.

How to read the evidence

The evidentiary value of Splitwise: Efficient generative LLM inference using phase splitting comes from the relationship among its reported moves. Two entries define the method-level claim: Characterized distinct prefill and decode resource behavior; and Designed clusters that split inference phases across heterogeneous machines. The cataloged result is: Evaluated cost, power, throughput, and latency tradeoffs under serving workloads. On that basis, hardware specialization can improve efficiency but adds transfer latency, capacity-planning complexity, and sensitivity to workload mix. The catalog nevertheless records that evidence for splitwise in Splitwise: Efficient generative LLM inference using phase splitting covers reported models, software revisions, request shapes, numerical precision, comparison baselines, accelerator hardware, and service-level objectives; behavior beyond that documented envelope remains untested. Reproduction work should separate genuine splitwise transfer from behavior caused by a changed phase splitting setup. To retest Splitwise: Efficient generative LLM inference using phase splitting, hold the splitwise baseline visible while changing phase splitting, then log where Designed clusters that split inference phases across heterogeneous machines no longer predicts the reported outcome.

04

Findings in the source record

1 paper-specific findings

  1. The reported evidence in Splitwise: Efficient generative LLM inference using phase splitting supports evaluated cost, power, throughput, and latency tradeoffs under serving workloads.
05

Practical implication for AI builders

Microsoft Research / University of Washington / 2023

06

Proposed BrokenGPT application

Research blueprint / proposed status

INTEGRATION POINT / 01

Proposed route placement / splitwise

For a proposed BrokenGPT experiment based on Splitwise: Efficient generative LLM inference using phase splitting, compare split and unified clusters with the same model and trace, recording quality, both latency phases, energy, utilization, transfer overhead, and failover. Keep the splitwise path isolated, versioned, and attributable to this research record.

VALIDATION METRIC / 02

Proposed acceptance test / phase splitting

Validate the proposed splitwise route against the paper's reported outcome: Evaluated cost, power, throughput, and latency tradeoffs under serving workloads. Assess the proposed Splitwise: Efficient generative LLM inference using phase splitting route through time to first token, inter-token delay, memory headroom, and goodput, and treat phase splitting failures as their own splitwise decision input.

TRADEOFF / 03

Proposed decision boundary / heterogeneous hardware

Balance latency, throughput, and operational complexity before promoting the proposed heterogeneous hardware design. Because even if the reported result reproduces, authentication, safety checks, failure recovery, workload drift, networking overhead, and tokenization can reverse its product value and must be measured separately, adoption remains conditional on replay under BrokenGPT's selected model, runtime, and policy configuration.

07

Limitations, verification, and source

Boundaries recorded with the paper

Limitations

  • Evidence for splitwise in Splitwise: Efficient generative LLM inference using phase splitting covers reported models, software revisions, request shapes, numerical precision, comparison baselines, accelerator hardware, and service-level objectives; behavior beyond that documented envelope remains untested.
  • Even if the reported result reproduces, authentication, safety checks, failure recovery, workload drift, networking overhead, and tokenization can reverse its product value and must be measured separately.

PRIMARY SOURCES

  1. 01
    Splitwise: Efficient generative LLM inference using phase splitting

    Microsoft Research / University of Washington — Primary primary arXiv paper / 30 November 2023 / Pratyush Patel, Esha Choukse, Chaojie Zhang, and 4 more

Related research reviews

View all 100 credited research papers

STRAIGHT ANSWERS

Frequently asked questions

01What does Splitwise: Efficient generative LLM inference using phase splitting study?

Splitwise studies phase splitting for generative inference, placing compute-heavy prompt processing and memory-heavy token generation on hardware suited to each phase.

02Which methods does Splitwise: Efficient generative LLM inference using phase splitting use?

The experimental design in Splitwise: Efficient generative LLM inference using phase splitting tests characterized distinct prefill and decode resource behavior and designed clusters that split inference phases across heterogeneous machines against the paper's documented baselines, datasets, model variants, or systems workloads.

03What does Splitwise: Efficient generative LLM inference using phase splitting report?

The reported evidence in Splitwise: Efficient generative LLM inference using phase splitting supports evaluated cost, power, throughput, and latency tradeoffs under serving workloads.

04What is the proposed BrokenGPT application for Splitwise: Efficient generative LLM inference using phase splitting?

Proposed: compare split and unified clusters with the same model and trace, recording quality, both latency phases, energy, utilization, transfer overhead, and failover.

INFERENCE, EVALUATION & SERVING / PAPER 093

Continue after Splitwise: Efficient generative LLM inference using phase splitting

After Splitwise: Efficient generative LLM inference using phase splitting, browse the full index for adjacent inference_systems research and work from Microsoft Research / University of Washington.

Open the paper index