Best practices
- Build a Qwen3-32B model inference service with ACS GPU computing power
- Build a QwQ-32B model inference service using ACS GPU computing power
- Build a DeepSeek distilled model inference service using ACS GPU computing power
- Deploy a DeepSeek-R1 model inference service with ACS GPU
- Use ACS GPU computing power to build a distributed DeepSeek full-performance inference service
- Build a Dify AI Q&A assistant on ACS
- Enable web search for a self-hosted DeepSeek service
- Use BestEffort pods to run Spark applications
- KubeVela best practices
- Tekton best practices
- Best practices for GitOps with Argo CD
- Use Fluid to accelerate data access
- Use GitLab Runner to build a CI/CD environment in an ACS cluster
- Accelerate Wan2.1 video generation with DeepGPU
- Best practices for deploying MoE models with PD separation and EP optimization on ACS
- Quickly build AI agents in an ACS cluster using AgentScope
- Use OSS Connector for AI/ML to improve model deployment efficiency
- Best practices for using Perf with ACS