Webinar
Introducing Milvus 2.6: Scalable AI at Lower Costs with James Luan, VP of Engineering at Zilliz
Join the Webinar
Loading...
About this webinar
Join James Luan, VP of Engineering at Zilliz, for an exclusive deep dive into the latest release of the open-source vector database Milvus 2.6. Built for AI workloads at scale, Milvus 2.6 introduces major architectural improvements that dramatically reduce storage, compute, and operational costs—without compromising on performance.
You'll learn
- New Features for All Users: How tiered storage, vector quantization, and a diskless WAL (with Woodpecker) can cut infrastructure costs by up to 10X—ideal for scaling AI workloads affordably.
- For Existing Users: How Milvus 2.6 simplifies your operations with new features like CDC + BulkInsert for easier data replication and native package support that streamlines installation and upgrades (no more manual dependencies or setup headaches!).
- How Milvus 2.6 boosts developer productivity with built-in tools for ingestion, advanced search, analytics, and reranking—making it easier than ever to iterate and deploy your AI applications.
- What's next on the Milvus roadmap: Insights into future enhancements and how they’ll further streamline your workflows.
Whether you're just starting with vector search, building GenAI applications, or managing multimodal data, Milvus 2.6 offers significant advantages that can scale with your needs.
Meet the Speaker
Join the session for live Q&A with the speaker
James Luan
VP of Engineering at Zilliz
James Luan is the VP of Engineering at Zilliz. With a master's degree in computer engineering from Cornell University, he has extensive experience as a Database Engineer at Oracle, Hedvig, and Alibaba Cloud. James played a crucial role in developing HBase, Alibaba Cloud's open-source database, and Lindorm, a self-developed NoSQL database. He is also a respected member of the Technical Advisory Committee of LF AI & Data Foundation, contributing his expertise to shaping the future of AI and data technologies.