TODO: 8-bit weight quantization for 2× size reduction

- Add QAT (quantization-aware training) notes
- Requires training with fake quantization
- Target: ~1.6 KB weights (vs 3.2 KB f16)
- Shader unpacking needs adaptation (4× u8 per u32)

1 files changed, 2 insertions, 0 deletions

diff --git a/training/export_cnn_v2_weights.py b/training/export_cnn_v2_weights.py
index e3d1724..723f572 100755
--- a/training/export_cnn_v2_weights.py
+++ b/training/export_cnn_v2_weights.py
@@ -94,6 +94,8 @@ def export_weights_binary(checkpoint_path, output_path):
     weight_offset += len(layer2_flat)
 
     # Convert to f16
+    # TODO: Use 8-bit quantization for 2× size reduction
+    # Requires quantization-aware training (QAT) to maintain accuracy
     all_weights_f16 = np.array(all_weights, dtype=np.float16)
 
     # Pack f16 pairs into u32 for storage buffer