Add shimmy - Python-free Rust inference server

[Michael-A-Kuykendall]

Adds shimmy to the Interface & Pipeline & AutoML section.

Project Details:

• Repository: https://github.com/Michael-A-Kuykendall/shimmy
• Crate: https://crates.io/crates/shimmy
• Stars: 2,918 ⭐
• Description: Python-free Rust inference server — OpenAI-API compatible

Key ML Features:

• OpenAI-compatible API for seamless integration
• GGUF + SafeTensors format support
• Hot model swapping for dynamic serving
• Auto-discovery of available models
• Single binary deployment (no Python dependencies)
• GPU acceleration support
• LLaMA, ChatML, and various model architectures

Why this belongs in Awesome Rust ML:

• Pure Rust implementation for ML inference serving
• Production-ready inference server with significant adoption
• Fills important gap for OpenAI-compatible Rust inference solutions
• Zero-dependency deployment suitable for ML production environments
• Active development with regular feature additions

Placement: Added alphabetically to Interface & Pipeline & AutoML section alongside other inference servers like orkhon, wonnx, and tract.

Following contribution guidelines: "Please just update the README.md"