v75 (S24/SM8650, soc 57): Qwen3.5-4B sharded-W8 decode bundle — Plane A greedy-correct, 3.8 tok/s (#2)

Add v79 W8 sharded bundle (QAIRT 2.45; device-validated S25 3/3 greedy-exact, 5.1 tok/s) (#1)

Upload v81/tokenizer.json with huggingface_hub

initial commit