MEASURED maskmod tests PASS after torch-universal refresh (YAML preserved)

MEASURED maskmod retest PASS after torch-universal create_dense_mask refresh

MEASURED maskmod retest PASS after torch-universal create_dense_mask refresh

MEASURED operational plate: formula-tax / I1-I8 / get_kernel (YAML preserved)

MEASURED laptop-Blackwell bench + operational honesty (not LoRA; Λ=Conjecture 1)

MEASURED laptop-Blackwell bench + operational honesty (not LoRA; Λ=Conjecture 1)

Add torch-universal variant for kernels 0.16 get_kernel (build.toml universal=true; no model conversion)

recut GPU ROADMAP to UNAVAILABLE (no cubin this session); CPU import-LIVE stays

stamp import-LIVE: Kernel Hub get_kernel 1e2ebef selfcheck vs SDPA (2026-08-28 2:28pm ET)

Add Kernel Hub build/torch-universal + torch-cpu for get_kernel (szl-maskmod, version 1)

initial commit