SVF scheduling algorithm achieves a competitive ratio of 3 for LLM serving and integrates into vLLM to reduce average and tail latency.
GreenLLM: SLO-aware dynamic frequency scaling for energy-efficient LLM serving
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
AI inference can be relocated across geographies to access lower-cost or lower-carbon electricity when latency budgets are relaxed, with the energy-latency frontier quantifying marginal benefits and new metrics tracking returns on latency tolerance.
Festina reduces energy consumption by up to 56% for serverless LLM inference on shared GPUs while keeping TTFT/TBT SLO attainment within 2% of four state-of-the-art baselines.
citing papers explorer
-
Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice
SVF scheduling algorithm achieves a competitive ratio of 3 for LLM serving and integrates into vLLM to reduce average and tail latency.
-
AI Inference as Relocatable Electricity Demand: A Latency-Constrained Energy-Geography Framework
AI inference can be relocated across geographies to access lower-cost or lower-carbon electricity when latency budgets are relaxed, with the energy-latency frontier quantifying marginal benefits and new metrics tracking returns on latency tolerance.
-
Energy-Aware Scheduling for Serverless LLM Serving on Shared GPUs
Festina reduces energy consumption by up to 56% for serverless LLM inference on shared GPUs while keeping TTFT/TBT SLO attainment within 2% of four state-of-the-art baselines.