diff options
| author | skal <pascal.massimino@gmail.com> | 2026-02-12 12:11:53 +0100 |
|---|---|---|
| committer | skal <pascal.massimino@gmail.com> | 2026-02-12 12:11:53 +0100 |
| commit | eaf0bd855306e70ca03f2d6579b4d6551aff6482 (patch) | |
| tree | 62316af1143db1e59e1ad62e70b9844e324cda55 /validation_results/epoch_55_output.png | |
| parent | e8344bc84ec0f571e5c5aafffe7c914abe226bd6 (diff) | |
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)
Diffstat (limited to 'validation_results/epoch_55_output.png')
0 files changed, 0 insertions, 0 deletions