Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.
Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 39 tools.
Inference AIops · v0.8.0 (latest)
by AIops-tools
75
Step 1: Install
Run this MCP server locally
Run this MCP server locally and expose it via stdio so your MCP client can connect.
Run via PyPI
inference-aiops@0.8.0Run command
uvx inference-aiops==0.8.0Step 2: Connect
Connect in your MCP client
After you're running this MCP server locally, connect it to your MCP client using the configuration examples below.
Loading MCP clients…