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.
ASFL: Adaptive Semi- asynchronous Federated Learning for Balancing Model Accuracy and Total Latency in Mobile Edge Networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.DC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Extends Flower framework with FedSaSync semi-asynchronous strategy, claiming reduced idle time versus synchronous baselines in heterogeneous settings.
citing papers explorer
-
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.
-
Semi-asynchronous Federated Learning in Flower: Framework Extension and Performance Assessment
Extends Flower framework with FedSaSync semi-asynchronous strategy, claiming reduced idle time versus synchronous baselines in heterogeneous settings.