# TinyTorch Module Metadata # Essential system information for CLI tools and build systems name: "11_kernels" title: "Kernels - Hardware-Aware Optimization" description: "Custom operations, performance optimization, and hardware-aware computing for ML systems" # Dependencies - Used by CLI for module ordering and prerequisites dependencies: prerequisites: [ "00_setup", "01_tensor", "02_activations", "03_layers", "04_networks", "05_cnn", "06_dataloader", "07_autograd", "08_optimizers", "09_training", "10_compression" ] enables: ["12_benchmarking", "13_mlops"] # Package Export - What gets built into tinytorch package exports_to: "tinytorch.core.kernels" # File Structure - What files exist in this module files: dev_file: "kernels_dev.py" readme: "README.md" tests: "inline" # Educational Metadata difficulty: "⭐⭐⭐⭐" time_estimate: "8-10 hours" # Components - What's implemented in this module components: - "matmul_custom" - "relu_custom" - "conv2d_custom" - "matmul_vectorized" - "matmul_cache_optimized" - "matmul_parallel" - "quantized_matmul" - "sparse_matmul" - "pruned_conv2d" - "KernelProfiler" - "PerformanceBenchmark" - "HardwareProfiler"