모델 경량화 및 Kubernetes 도입을 통한 서빙 비용 최적화와 15GB→300MB 용량 절감
Serving AI Models: Balancing Cost and Performance
Serving AI Models: Balancing Cost and Performance
Deploying Hugging Face Models with BentoML: DeepFloyd IF in Action
Faster TensorFlow models in Hugging Face Transformers