加载中...
Implementing an AI Personal Assistant using NanoBot and OpenIM
Using the dify subworkflow
Deploying Step3-VL-10B using vLLM multi-GPU inference
Running the Funasr-Nano-2512 model locally
Using NLLB to implement language translation
Using FastText to implement language identification
Use HAProxy to load balance CMPP Socket persistent connections
Use One-API as an AI agent
Use FastAPI MCP on Mac