Sebastian Raschka
4e61dc4224
Fix d_out code comment in bonus materials (#715)
|
4 luni în urmă | |
|---|---|---|
| .. | ||
| README.md | 1 an în urmă | |
| mha-implementations.ipynb | 4 luni în urmă | |
README.md
More Efficient Multi-Head Attention Implementations
- mha-implementations.ipynb contains and compares different implementations of multi-head attention
Summary
The figures below summarize the performance benchmarks (lower is better).
Forward pass only
Forward and backward pass
Forward and backward pass after compilation
