gen-cards: regenerate Use-it block

Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure); gated token-for-token vs fp32 oracle

gen-cards: regenerate Use-it block

gen-cards: add Use-it markers

remove GatherMM int8hu — superseded by gather_qmm sym8 (2.1x, same quality)

Qwen3.6: sym8 gather_qmm bundle (2.1x faster, clean int8)

Qwen3.6: gather_qmm kernel card (2.1x, clean)

Add root config.json (Hub download-stats query file + framework pointer)

Upload README.md with huggingface_hub

Upload folder using huggingface_hub

Upload LICENSE with huggingface_hub

Upload README.md with huggingface_hub

initial commit