Category B: Binary Bundling

Embed ML models directly into Rust binaries for zero-dependency deployment.

Recipes

RecipeDescriptionStatus
Bundle Static ModelEmbed model with include_bytes!()Verified
Bundle Quantized ModelReduce model size with quantizationVerified
Bundle Encrypted ModelProtect model weightsVerified
Static Binary EmbeddingFull static linkingVerified
Q4 Quantization4-bit quantizationVerified
Signed ModelsCryptographic signingVerified
Lambda PackageAWS Lambda deploymentVerified

Learning Objectives

  • Embed models using include_bytes!() macro
  • Reduce binary size with quantization
  • Protect intellectual property with encryption
  • Create single-binary deployments

Toyota Way: Muda (Waste Elimination)

Bundling eliminates external dependencies, reducing deployment complexity and potential failure points.