Fold DyT affine maps into following convolutions (pytorch#21953) (pytorch#21953)

Summary:

Companion to FoldDyTAlphaIntoLUTPass. FoldDyTAffineIntoConvPass removes
the per-channel gamma Mul and beta Add after the DyT TABLE by folding
their exact integer-affine map into the following convolution weights
and bias.

The pass evaluates the materialized 256-entry TABLE path and rewrites
only when the map is provably exact. It fails closed on nonlinear or
saturating maps, unsupported layouts or constants, mismatched
quantization metadata, and ambiguous layout provenance. Padded
convolutions retain beta when its boundary contribution cannot be
represented by one bias.

Coverage includes non-uniform gamma/beta, unpadded depthwise
convolutions, output-zero-point equality, unused-constant cleanup, and
exact-one-permute layout provenance. This revision contains only the
public pass implementation, tests, and package export; pass registration
is intentionally outside this public change.

Reviewed By: rascani

Differential Revision: D116573000

Author: cgreenberg

backends/arm/_passes/__init__.py

@@ -116,6 +116,7 @@
 from .deduplicate_get_attr_pass import DeduplicateGetAttrPass  # noqa
 from .ensure_unique_output_nodes_pass import EnsureUniqueOutputNodesPass  # noqa
 from .exir_to_tosa_pass import ExirToTosaPass  # noqa
+from .fold_dyt_affine_into_conv_pass import FoldDyTAffineIntoConvPass  # noqa
 from .fold_dyt_alpha_into_lut_pass import FoldDyTAlphaIntoLUTPass  # noqa
 from .fold_qdq_with_annotated_qparams_pass import (  # noqa
     FoldAndAnnotateQParamsPass,