JANGH Metal kernels (legacy JANGTQ2 format) in vmlx_engine/jangh/kernels.py adapt Apple MLX
quantized matrix-vector, matrix-matrix, and Steel/NAX kernel layouts.
Copyright 2023-2024 Apple Inc. Distributed under the MIT license.
Source: https://github.com/ml-explore/mlx/tree/v0.32.2/mlx/backend/metal/kernels
Changes: odd-cubic codebook weight decoding, per-row scales, expert routing,
fused gate/up and router-weighted down projections, integer extent clamping,
and a sorted weighted prefill epilogue preserving the MLX col_reduce_small
BF16 reduction order (reduction/reduce_col.h and reduction/ops.h).
MLX headers are loaded from the installed MLX package at runtime.
