Dragonfly V2.4.0 - Intro, Updates, Data Distribution in AI Infrastructure - Wenbo Qi & Chenyu Zhang
About this talk
This talk covers Dragonfly V2.4.0, presented by Wenbo Qi and Chenyu Zhang from Ant Group. The speakers introduce Dragonfly, a solution designed for efficient, stable, and secure file distribution and image acceleration using peer-to-peer technology within cloud-native architectures. They highlight key updates in the latest version, including enhancements in security and new functionalities aimed at improving model distribution. The session includes demonstrations of how Dragonfly preheats and distributes AI models, which are packaged as OCI Artifacts, to read-only volumes in Kubernetes, facilitating faster deployments. Additionally, the speakers discuss P2P-based state snapshot and restore capabilities relevant to AI agent scenarios.
More from this event
See all 436 talks →
Best of KubeCon + CloudNativeCon Amsterdam 2026
2:17
The Quiet Work of Forever: Sustaining Open Source Communities - O. Hope Amaechi-Okorie, JSON Schema
26:24
Evolving KServe: The Unified Model Inference Platform for Both Predictive and... F. Spolti & J. Lee
32:40
Preventing S3 Cost Storms: Applying Cortex’s Efficiency Lessons to I/O-Heav... A. Fishman-Lichterman
5:32