M2 — Numeric kernels

Definition of done (PLAN.md §5): Regime A fused subtree kernels, regime B fused per-front kernels (Cholesky first, LDLᵀ/LU hooks), regime C vendor bindings in all four extensions with KA tiled fallbacks, assembly/extend-add kernels. Unit tests against the CPU reference on every backend; per-bin micro-benchmarks deciding where vendor batched calls replace regime B.

Generated by Claude Code