9c2107e8d3
The Lightricks/LTX-2.3-fp8 checkpoints store float8 weights with per-tensor weight_scale and input_scale companions (verified from the file headers: 1496 F8_E4M3 tensors, 2924 scale tensors). A plain dtype cast would silently corrupt every quantized layer, so the 2.3 assembly now detects the companions and raises with a pointer to the GGUF quants, which offer comparable fidelity through the supported path. Dequantizing the scaled fp8 layout is a possible follow-up. |
||
|---|---|---|
| .. | ||
| data_recipe | ||
| export | ||
| inference | ||
| rag | ||
| training | ||
| __init__.py | ||
| _torchao_stub.py | ||
| import_guards.py | ||
| tool_healing.py | ||