Proud to be a Silver Sponsor of @KubeCon_ #CloudNativeCon China 2026! 🎉 We've been proud to be part of this amazing community over the years. Excited to bring multiple DaoCloud sessions to KubeCon China 2026 and share our insights with you all. See you there!

Here is an AI-Era technical evolution event in Jakarta which #DaoCloud was participated in. We explored virtualization alternatives and #AI infrastructure platform for improved compute efficiency. Highly engaging discussions. Excited for more collaboration ahead!

vLLM v0.20.1 is now available. During this release cycle, DaoCloud collaborated deeply with community partners to deliver over 10 stability fixes and performance optimizations for DeepSeek V4, helping DeepSeek V4 run more stably and faster on vLLM. @vllm_project

Three core AI inference cluster challenges: GPU topology, scheduling, cost validation. 🎤DaoCloud's Weizhou Lan presents topology discovery for Kueue scheduling, using Kwok virtual nodes for cost-free validation to boost GPU and cluster efficiency.

Growing AI workloads such as LLMs make cache-aware scheduling and routing critical to GPU efficiency. 🎤Kay Yan (DaoCloud) collaborates with Red Hat & IBM to resolve K8s KV-Cache fragmentation, sharing high-performance LLM inference best practices.