What's Inside Milvus 1.0?
Apr 29, 2021milvus

Summary
This post introduces Milvus v1.0, detailing its core features and optimizations. It covers CPU/GPU distributions, vector entity structure with integer IDs, partitioning for search acceleration, and enhancements to index algorithms (IVF, FLAT, IVF_SQ8H). Performance optimizations for search (nq < threads, request combining) and index building are highlighted. It also mentions distance metrics, logging configuration, the Mishards distributed solution, Prometheus integration for monitoring, and metadata management (SQLite/MySQL).
More from the AI Data Storage Engine trail
- Milvus Snapshots: Point-in-Time Collection Views Without Copying Data
- Announcing Milvus 3.0: Lake-Native Vector Search and a More Powerful Retrieval Engine
- How to Recover Milvus Data After etcd Corruption Without a Backup
- Open Tag: An Open-Source Claude Tag for Claude Code and Codex
- How Force Merge Compaction Nearly Doubled Milvus Search QPS