2 Commits

Author	SHA1	Message	Date
Vijay Janapa Reddi	30026b1713	Clean up compression test function names ... - Removed redundant '_comprehensive' suffix from test function names: * test_compression_metrics_comprehensive → test_compression_metrics * test_magnitude_pruning_comprehensive → test_magnitude_pruning * test_quantization_comprehensive → test_quantization * test_distillation_comprehensive → test_distillation * test_structured_pruning_comprehensive → test_structured_pruning - Updated testing framework to recognize new compression test patterns - All tests still pass (6/6 inline + 8/8 integration = 14/14 total) - Other modules unaffected (tensor 4/4, activations 5/5 still pass) - Cleaner, more concise test function names	2025-07-14 09:53:37 -04:00
Vijay Janapa Reddi	fc7c00c2e2	Complete compression module with 6 compression techniques ... - Added CompressionMetrics for parameter counting and model size analysis - Implemented magnitude-based pruning with sparsity calculation - Added quantization for FP32→INT8 conversion with error tracking - Implemented knowledge distillation with temperature scaling - Added structured pruning with neuron removal - Created comprehensive comparison framework - All 6 tests passing (100% success rate) - Module follows TinyTorch educational patterns - Uses standard tito testing framework - Ready for integration testing	2025-07-14 09:44:04 -04:00