Vijay Janapa Reddi e384e8827c fix(module-02): Rewrite Softmax to use Tensor operations ...

- Preserve computation graph by using Tensor arithmetic (x - x_max, exp / sum)
- No more .data extraction that breaks gradient flow
- Numerically stable with max subtraction before exp

Required for transformer attention softmax gradient flow

2025-10-27 20:29:35 -04:00

..

activations_dev.ipynb

…

activations_dev.py

…