- Enable #![feature(portable_simd)] and #![feature(specialization)] (Nightly).
- Implement DeinterleaveSupported trait to provide specialized SIMD paths.
- Add SIMD-accelerated deinterleaving for f32, u8, i8, and i16 using a 8-lane configuration.
- Introduce deinterleave_scalar_logic for the base case and tail processing.
- Use a macro to reduce duplication across SIMD-supported types.
- Add comprehensive unit tests covering odd sample counts and multiple types.
- Add a Criterion benchmark to track deinterleaving performance (reaching ~1 Gelem/s).
- Update documentation in AGENTS.md and agent_docs/ to reflect the new performance pattern.

…e gate

- Implement SIMD-accelerated scaled conversion for u8 -> f32 (3x speedup).
- Add 'simd' feature gate to Cargo.toml to allow stable Rust compilation.
- Refactor Deinterleave and TypeConverter to use conditional compilation for SIMD.
- Add TypeConvertSupported trait for specialized type conversions.
- Add Criterion benchmark for type converters.
- Update SIMD.md with roadmap and established patterns.

- Implement FreqShiftSupported trait with specialized SIMD path for Complex32.
- Achieve ~4.4x speedup on complex rotation compared to naive scalar loop.
- Use vectorized complex multiplications with periodic NCO re-sync (every 1024 samples) to maintain numerical precision.
- Add Criterion benchmark for FreqShift.
- Update SIMD.md with performance results.

- Address clippy::clone_on_copy warning by dereferencing NCO.

- Switch from specialization to min_specialization for better stability.
- Add #[allow(incomplete_features)] to src/lib.rs to satisfy clippy in CI/CD.