Picture for Andreas Kosmas Kakolyris

Andreas Kosmas Kakolyris

SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving

Add code
Aug 05, 2024
Figure 1 for SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving
Figure 2 for SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving
Figure 3 for SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving
Figure 4 for SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving
Viaarxiv icon