Commit History
-
Replace dependency, add quantizer support, fix safetensors export, improve error handling, update UI docs
Kyle Pearsonb89e643
-
Add dynamic dtype selection for `get_device_info()` with CUDA/CPU checks, update config logic
Kyle Pearsondf6e003 -
Remove deprecated MPS backend support, eliminate torch.mps availability checks
Kyle Pearson8d08093 -
Add zero-gpu support, enhance model export with quantization/gpu acceleration helpers, optimize inference pipeline with vae fixes, modernize pipeline loading with unified decorators, implement gpu decorator infrastructure.
Kyle Pearson3631a8e -
cleaned up code
Kyle Pearson570384a -
Remove Python cache files and update .gitignore
Kyle Pearson +1: Qwen-Coder- Delete all __pycache__/*.pyc files from src/ and src/ui/ - Add .huggingface/ to .gitignore to prevent committing cached tokens - Update .gitignore with new patterns Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>459ac47 -
Add cancel button, validate cache files, detect cache hits, update peft dependency, fix race conditions, enhance feedback, improve interrupt handling.
Kyle Pearsonb1e7bdb -
updated
Kyle Pearson8cdb001 -
Update Gradio to 6.9.0, add cached file checks in LoRA loading, fix unloading errors, optimize download cancellation, improve device/dtype handling, update optimum dependency.
Kyle Pearson60d66bd -
code
Kyle Pearson6a07ce1