TAPER regulates LLM branch parallelism by admitting extra branches opportunistically when predicted externality fits slack, delivering 1.48-1.77x higher goodput than eager or fixed-cap baselines on Qwen3-32B while keeping over 95% SLO attainment.
Retrieval-Augmented Generation (RAG) Dataset 12000
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.DC 1years
2026 1verdicts
UNVERDICTED 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Regulating Branch Parallelism in LLM Serving
TAPER regulates LLM branch parallelism by admitting extra branches opportunistically when predicted externality fits slack, delivering 1.48-1.77x higher goodput than eager or fixed-cap baselines on Qwen3-32B while keeping over 95% SLO attainment.