M\'elange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity

arXiv:2404.14527v1 Announce Type: cross
Abstract: Large language models (LLMs) are increasingly integrated into many online services. However, a major challenge in deploying LLMs is their high cost, due primarily to the use of expensive GPU instances. To address this problem, we find that the significant heterogeneity of GPU types presents an opportunity to increase GPU cost efficiency and reduce deployment costs. The broad and growing market of GPUs creates a diverse option space with varying costs and hardware specifications. Within …

arxiv cost cs.dc cs.lg gpu language language model large language large language model type