How vLLM serves many fine-tuned MoE and dense models with Multi-LoRA, including fused MoE LoRA kernels, Triton compiler fixes, Split-K and CTA swizzling optimizations, and SageMaker AI and Bedrock tuning.
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