fix: bake_adapter offset, plus a preflight and a discoverability hint

feat: adapters dial on the LoRA node, and bake_adapter.py

perf: measure the LoKr bypass path, and keep it staging per call

feat: support LoKr, LoHa and OFT LoRAs on quantized layers

fix: accept the transformer. LoRA key prefix

Sync docs and code: gallery, troubleshooting, cleanup pass

Fix LoRA stacking double-applying non-quantized layers

Sync nodes and scripts with the GitHub repo

Fix lowvram OOM, add backend diagnostics, support the base model

Upload svdquant_lora.py with huggingface_hub

Upload folder using huggingface_hub