Organizations and individuals running multiple custom AI models, especially recent Mixture of Experts (MoE) model families, can face the challenge of paying for idle GPU capacity when the…
Efficiently serve dozens of fine-tuned models with vLLM on Amazon SageMaker AI and Amazon Bedrock
calendar_today
February 26, 2026
person
Danielle Maddix Robinson, Florian Saupe, George Novack, Haipeng Li, Mani Kumar Adari, Xiang Song, Yu Gong (AWS AI Team)
domain
vllm