salad_mcp vs Inference AIops

Manage GPU workloads on SaladCloud, including container groups and inference endpoints. Operate queues, jobs, logs, and quotas to run and monitor deployments. Check CPU/GPU availability to plan capacity and scale efficiently.

Governed GPU inference operations for vLLM and Ray Serve deployments, including latency root-cause analysis, scaling, and draining.

MCP Servers

Models

—

—

—

—

—

Python

—

MIT

—

—

76

0