Lightning Talk: How to Build a Serverless AIGC Platform on Kubernetes Using AIGC-Gateway
Lightningat KubeCon + CloudNativeCon + Open Source Summit China 2023 · on Wednesday, 2023-09-27· at 15:10· 3层 302会议室| 3F Room 302·
summary
AIGC-Gateway is an open-source project from Alibaba Cloud and XingZhe AI for building private, serverless AIGC platforms on Kubernetes. The talk covers using AIGC-Gateway to improve GPU utilization via GPU pooling, manage multiple AIGC engine types and versions, and provide user registration/login, tenant-level resource isolation, and resource access authentication, plus problems and solutions XingZhe AI encountered when implementing a serverless platform with it.
AI-written summary · about
related talks
45mRun, Secure, and Govern Your AI Traffic with an AI Gateway for Multi-LLM
05m⚡ Lightning Talk: Mastering Prefill-Decode-Disaggregated Architecture: Solutions and Best Practices in Alibaba Cloud
09mSponsored Keynote: Hand Meet Glove: Why Kubernetes Will Become the Platform of Choice for Agentic Architectures
15mKeynote: From Platforms to AI Factories. Has Kubernetes Solved It?
33mBuild Serverless with K8s, Kata Containers and Bare Mental Cloud...
05mContainerization Beyond CPUs – A Kubernetes-based Serverless Pl...
44mServerless Kubernetes Boosts AI Business
32mBuilding a Serverless GenAI Platform