Use PPU to deploy the Qwen3.5 inference service in ACS
Using PPU in ACS to Deploy GLM-5 Inference Service
Use ACS to quickly deploy a Qwen3 inference service running on a PPU
Using GU8TF and PPU in ACS to Quickly Deploy QwQ-32B Inference Services
Use PPU to quickly deploy the DeepSeek V3/R1 inference service in ACS
Deploy Kubeflow Community Edition on ACS
ACS Serverless Pod Scenarios Use Cache to Accelerate CI Image Building
Development practices of ACS PPU user container images
In the PAI-PPU a key to pull up the Qwen3 inference service
Fast Deployment of DeepSeek-R1/V3 Inference Services on PPU
PAI-PPU best practices
Best practices for initializing permissions on the PAI platform
Run a CogVideo model on PAI
Evaluate the adaptability of CUDA operators
Self-developed collection communication library (ACCL-P) best practices