GAR routes LLM inference requests via constrained multi-objective optimization to cut per-request CO2 emissions while respecting accuracy floors and p95 latency SLOs.
Cargo: A framework for confidence-aware routing of llm queries.arXiv preprint arXiv:2509.14899
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GAR: Carbon-Aware Routing for LLM Inference via Constrained Optimization
GAR routes LLM inference requests via constrained multi-objective optimization to cut per-request CO2 emissions while respecting accuracy floors and p95 latency SLOs.