← Search

Ana Klimovic

2 accepted papers

2025

Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs

ICML 2025poster

Recent advancements in Large Language Models (LLMs) have led to increasingly diverse requests, accompanied with varying resource (compute and memory) demands to serve them. However, this in turn degrades the cost-efficiency of LLM serving as common practices primarily rely on homogeneous GPU resourc…

Cited by 4SourcePDFScholar
2024

DéjàVu: KV-cache Streaming for Fast, Fault-tolerant Generative LLM Serving

ICML 2024poster

Distributed LLM serving is costly and often underutilizes hardware accelerators due to three key challenges: bubbles in pipeline-parallel deployments caused by the bimodal latency of prompt and token processing, GPU memory overprovisioning, and long recovery times in case of failures. DéjàVu address…

Cited by 29SourcePDFScholar