3 papers
cs.DC2026
ShuntServe: Cost-Efficient LLM Serving on Heterogeneous Spot GPU Clusters
Seungwoo Jeong, Moohyun Song, Juhyun Park +1
As large language model (LLM) services become widely adopted, the cost of GPU resources for serving these models in cloud environments has emerged as a critical concern. Spot insta…
cs.DC2026
Ding-Dong Ditch: Peeking Into Spot Instance Availability
Kyumin Kim, Moohyun Song, Taeyoon Kim +1
Spot instances offer significant cost savings of up to 90% over on-demand prices, making them an attractive resource for large-scale computing workloads. However, understanding the…
cs.DC2026
SpotVista: Availability-Aware Recommendation System for Reliable and Cost-Efficient Multi-Node Spot Instances
Taeyoon Kim, Kyumin Kim, Kyunghwan Kim +4
Cloud vendors offer discounted spot instances to maximize surplus resource utilization, but these instances are subject to the risk of sudden interruption. Traditional pricing data…