ECO-LLM jointly selects query processing, retrieval, and model components per query, cutting cost by 60% and latency up to 6x versus model routing in edge-cloud tests.
Packt Publishing Ltd, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Orchestration for Domain-specific Edge-Cloud Language Models
ECO-LLM jointly selects query processing, retrieval, and model components per query, cutting cost by 60% and latency up to 6x versus model routing in edge-cloud tests.