Links to Elastic Algorithm Service (EAS) use case tutorials.
Deploy large language models (LLMs)
Deploy Mixture-of-Experts (MoE) models with expert parallelism and PD separation
Deploy an MLLM application in EAS
Deploy ComfyUI for video generation
Deploy Stable Diffusion web UI
Manually deploy a Stable Diffusion WebUI service
Deploy a LoRA SD model using Kohya_ss in EAS
Virtual try-on solution based on PAI products
LLM RAG chatbot
Best practices for integrating RAG with web search
Best practices for integrating RAG with an OpenAI-compatible interface
Build a RAG chatbot with EAS and Elasticsearch
Build a RAG chatbot with EAS and Milvus
Build a RAG chatbot with EAS and OpenSearch
Build a RAG chatbot with EAS and ApsaraDB RDS for PostgreSQL
Build a security-enhanced RAG application with an encrypted knowledge base
Best practices for accessing dedicated gateway across VPCs
Deploy models using the EAS Python SDK
Best practices for deploying Proxima on EAS
Best practices for PAI-EAS Spot
Enable tracing for LLM applications in EAS
Secure and encrypted inference service