salad_mcp vs rai

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.

CPU-only LLM inference engine in pure Rust — 4-bit quantized models, hand-written AVX2 kernels, speculative decoding, and a local HTTP/MCP server. No GPU, no Python runtime.

MCP Servers

MCP Servers

—

—

—

—

Rust

—

Apache-2.0

—

—

16

0

0