Shuhe Accelerates AI Model Service Deployment with Knative
Talkat KubeCon + CloudNativeCon + Open Source Summit China 2023 · on Thursday, 2023-09-28· at 13:55· 2层 会议室 2 | 2F Room 2·
summary
Shows how Shuhe uses Knative on Kubernetes to run 500+ AI model services for financial workloads, cutting resource costs by ~60% and halving deployment time. Covers extending Knative Serving autoscaling to support concurrency-based precise scaling and predictive scaling, a walkthrough of deploying Stable Diffusion on Knative, and Shuhe’s operational best practices for model services.
AI-written summary · about
related talks
18mOpen Hybrid Cloud & AI Developer Experience
25mHow We Power the Largest AI Deployments on the Planet: Running Vir...
40mHow an AI driven approach reduces cloud cost and makes your Kubernetes infrastructure autonomous
05mKeynote: Intuit’s AI-Native Platform: Scaling to 8x Velocity for 8,000 Developers
15mKeynote: From Platforms to AI Factories. Has Kubernetes Solved It?
30mBuilding a Self-Service Platform for Stateful AI Agents
33mAI Model Distribution Challenges and Best Practices
29mNavigating Innovation with Open Hybrid Cloud and Openshift AI