-
Stefy Lanza (nextime / spora ) authoredQLoRA training reached VAE encode then failed: the ZImagePipeline loads the VAE in bf16, but the image tensor was fed as float32 -> conv2d "Input type (float) and bias type (BFloat16) should be the same". Feed the VAE its own weight dtype. Co-Authored-By:
Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01RdMufYvtTbtGDWsiZVoXce
ff6002d6
| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| admin | ||
| api | ||
| backends | ||
| broker | ||
| frontproxy | ||
| models | ||
| openai | ||
| pydantic | ||
| queue | ||
| tasks | ||
| __init__.py | ||
| cli.py | ||
| config.py | ||
| main.py | ||
| platform_paths.py | ||
| system_app.py |