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.
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 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Beyond the Buzz: A Pragmatic Take on Inference Disaggregation
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.