Pith. sign in

DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serv- ing

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.DC 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Beyond the Buzz: A Pragmatic Take on Inference Disaggregation

cs.DC · 2025-06-05 · conditional · novelty 5.0

Disaggregated serving (separate prefill and decode GPU pools) expands the throughput-interactivity Pareto frontier mainly for prefill-heavy workloads and models larger than about 10B parameters, provided the prefill-to-decode GPU ratio is tuned dynamically.

citing papers explorer

Showing 1 of 1 citing paper.

  • Beyond the Buzz: A Pragmatic Take on Inference Disaggregation cs.DC · 2025-06-05 · conditional · none · ref 5

    Disaggregated serving (separate prefill and decode GPU pools) expands the throughput-interactivity Pareto frontier mainly for prefill-heavy workloads and models larger than about 10B parameters, provided the prefill-to-decode GPU ratio is tuned dynamically.