mirror of
https://github.com/MLSysBook/TinyTorch.git
synced 2026-05-06 07:27:30 -05:00
64fb1ae730
Critical fixes to resolve module import issues: 1. Module 01 (tensor_dev.py): - Wrapped all test calls in if __name__ == '__main__': guards - Tests no longer execute during import - Clean imports now work: from tensor_dev import Tensor 2. Module 08 (dataloader_dev.py): - REMOVED redefined Tensor class (was breaking dependency chain) - Now imports real Tensor from Module 01 - DataLoader uses actual Tensor with full gradient support Impact: - Modules properly build on previous work (no isolated implementations) - Clean dependency chain: each module imports from previous modules - No test execution during imports = fast, clean module loading This resolves the root cause where DataLoader had to redefine Tensor because importing tensor_dev.py would execute all test code.