Streamlining AI Deployments
8 min

Streamlining AI Deployments

MLOps World - MLOps World & Generative AI World 2024
Vasilis Vagias
ai llm mlops deployment optimization inference compiler pytorch docker gpu api
The State and Future of Cloud-Native Model Serving
40 min

The State and Future of Cloud-Native Model Serving

KubeCon + CloudNativeCon - KubeCon + CloudNativeCon Europe 2023
Dan Sun Theofilos Papapanagiotou
mlops cloud-native kubernetes model-serving kserve cncf knative istio serverless scalability observability inference
Efficient Access to Shared GPU Resources: Mechanisms and Use Cases
35 min

Efficient Access to Shared GPU Resources: Mechanisms and Use Cases

KubeCon + CloudNativeCon - KubeCon + CloudNativeCon Europe 2023
Diogo Guerra Diana Gaponcic
gpu-scheduling kubernetes nvidia-mig time-slicing resource-management high-energy-physics machine-learning inference ci-cd benchmarking