Serving GenAI Workloads At Scale With LitServe
41 min

Serving GenAI Workloads At Scale With LitServe

MLOps World - MLOps World & Generative AI World 2024
Aniket Maurya
lit-serve pytorch-lightning api-serving dynamic-batching genai ai llm python autoscaling rag openai-api docker
SIG Autoscaling Updates and Feature Highlights
35 min

SIG Autoscaling Updates and Feature Highlights

KubeCon + CloudNativeCon - KubeCon + CloudNativeCon Europe 2023
Chen Wang Michele Orlandi Piotr Betkier Jayant Jain Guy Templeton
kubernetes autoscaling cluster-autoscaler horizontal-pod-autoscaler vertical-pod-autoscaler multi-dimensional-pod-autoscaler balancer-api kubernetes-1-24 kubernetes-1-27 cloud-native debugging resource-management
Cloud Computing’s First Economic Recession? Let’s Talk Platform Efficiency
37 min

Cloud Computing’s First Economic Recession? Let’s Talk Platform Efficiency

KubeCon + CloudNativeCon - KubeCon + CloudNativeCon Europe 2023
Aparna Subramanian Todd Ekenstam Phillip Wittrock Nagarajan Chinnakaveti Thulasiraman
cloud-computing platform-efficiency cost-optimization kubernetes autoscaling finops cloud-costs design culture observability ci-cd
Autoscaling Elastic Kubernetes Infrastructure for Stateful Applications Using Proxyless gRPC and Istio
31 min

Autoscaling Elastic Kubernetes Infrastructure for Stateful Applications Using Proxyless gRPC and Istio

KubeCon + CloudNativeCon - KubeCon + CloudNativeCon Europe 2023
Sanjay Pujare Costin Manolache
kubernetes autoscaling stateful-applications grpc proxyless-grpc istio service-mesh load-balancing session-affinity api-gateway gke
Autoscaling Can Be Reliable: Running Cluster Autoscaler in Prod
25 min

Autoscaling Can Be Reliable: Running Cluster Autoscaler in Prod

KubeCon + CloudNativeCon - KubeCon + CloudNativeCon Europe 2023
Maciej Pytel
kubernetes cluster-autoscaler autoscaling monitoring debugging cloud-provider gke vm nodes pods
Container Is the New VM: The Paradigm Change No One Explained to You
27 min

Container Is the New VM: The Paradigm Change No One Explained to You

KubeCon + CloudNativeCon - KubeCon + CloudNativeCon Europe 2023
Marga Manterola Rodrigo Campos Catelin
containers kubernetes vms cloud-native deployment ingress autoscaling network-policies security docker yaml
Unlocking the Potential of KEDA: New Features and Best Practices
35 min

Unlocking the Potential of KEDA: New Features and Best Practices

KubeCon + CloudNativeCon - KubeCon + CloudNativeCon Europe 2023
Jorge Turrado Ferrero Zbynek Roubalik
keda kubernetes autoscaling event-driven-architecture serverless hpa operator scaling-to-zero cloud-native devops ci-cd
Supercharging Pipeline Efficiency with ML Performance Prediction
26 min

Supercharging Pipeline Efficiency with ML Performance Prediction

PyCon - PyCon US 2023
Boaz Wiesner Keren Meron
python celery kubernetes machine-learning pipeline-optimization data-pipelines performance-prediction autoscaling cloud-cost-optimization aws-spot-instances svms data-processing