Sync the node pack: compile-friendly kernel op, faster conversion, honest int8 numbers

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

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

docs: list the base rank-256 actaware checkpoint; bench gains a base mode

Sync docs and code: gallery, troubleshooting, cleanup pass

Add activation-aware low-rank objective (--act-stats) + Test 4 benchmark

Measure LoRA fidelity properly: branch rank matters under a LoRA

Sync nodes and scripts with the GitHub repo