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

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

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

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

add base activation statistics (8 prompts, BF16 raw, 2.6M tokens/layer)

add base rank256 activation-aware checkpoint

fix: keep sage off attention shorter than one K/V block

fix: accept the transformer. LoRA key prefix

fix: keep sage-attention off float attention masks

Sync docs and code: gallery, troubleshooting, cleanup pass

Sync docs and code: gallery, troubleshooting, cleanup pass

Move checkpoints into checkpoints/ and checkpoints/legacy/

Add calibration/krea2_act_stats.safetensors

Add Krea2-Turbo-SVDQuant-W4A4-rank256-actaware.safetensors

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

Measure LoRA fidelity properly: branch rank matters under a LoRA

Fix LoRA stacking double-applying non-quantized layers

Tidy: sync README, rename cmp2_* to compare_* (matches GitHub)

Add Krea2-Turbo-SVDQuant-W4A4-rank16-norefine.safetensors

Add Krea2-Turbo-SVDQuant-W4A4-rank128-norefine.safetensors

Add Krea2-Turbo-SVDQuant-W4A4-rank16-norefine.safetensors

Add Krea2-Turbo-SVDQuant-W4A4-rank256-norefine.safetensors

Add Krea2-Turbo-SVDQuant-W4A4-rank256-norefine.safetensors

Add Krea2-Turbo-SVDQuant-W4A4-rank256.safetensors

Add Krea2-Turbo-SVDQuant-W4A4-rank256.safetensors

Delete speedtest3.bin with huggingface_hub

speed test 3, will delete

Delete speedtest2.bin with huggingface_hub

speed test 2, will delete

Delete speedtest.bin with huggingface_hub

speed test, will delete

Upload BENCHMARKS.md with huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload README.md with huggingface_hub

Upload BENCHMARKS.md with huggingface_hub

Republish Krea2-Turbo-SVDQuant-W4A4-rank128.safetensors built with refinement

Republish Krea2-Turbo-SVDQuant-W4A4-rank16.safetensors built with refinement

Republish Krea2-Turbo-SVDQuant-W4A4-rank64.safetensors built with refinement

Sync nodes and scripts with the GitHub repo

Update README.md

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

Upload svdquant_w4a4.py with huggingface_hub

Upload README.md with huggingface_hub

Upload quantize_krea2.py with huggingface_hub

Upload svdquant_w4a4.py with huggingface_hub

Upload quantize_krea2.py with huggingface_hub

Upload svdquant_w4a4.py with huggingface_hub