Qualcomm AI Engine Direct - Add MHA2SHA pass

Summary:
- Integrated mha into sha pass and implemented it in qnn_preprocess
- Refactored mha in static llama
  - Added support for masked softmax
  - Included spin quant r3 support
  - Combined the n_heads key-value cache into a single cache for each
    layer to decrease the number of inputs and outputs, which enhances
performance.
- Deprecated ShiftPointer kv updater mode
  - Since each layer now has its own kv cache, the v cache no longer
    benefits from ShiftPointer, which previously avoided copying the new
v cache to the input v cache. To prevent user confusion, ShiftPointer
mode has been deprecated
- Applied the correct input template for smollm2 135m
- Corrected the quantization annotation for reshape
- Remove outdated code from CanonicalizeConv

Author: shewu-quic

backends/qualcomm/_passes/__init__.py

@@ -11,6 +11,7 @@
 from .canonicalize_conv import CanonicalizeConv
 from .convert_bmm_to_matmul import ConvertBmmToMatmul
 from .convert_linear_to_conv2d import ConvertLinearToConv2d
+from .convert_mha_to_sha import ConvertMhaToSha
 from .convert_square_to_pow import ConvertSquareToPow
 from .decompose_any import DecomposeAny
 from .decompose_binary_alpha import DecomposeBinaryAlpha
@@ -55,6 +56,7 @@
     CanonicalizeConv,
     ConvertBmmToMatmul,
     ConvertLinearToConv2d,
+    ConvertMhaToSha,
     ConvertSquareToPow,
     DecomposeAny,
     DecomposeBinaryAlpha,

backends/qualcomm/_passes/canonicalize_conv.py

@@ -9,7 +9,6 @@
 import torch
 
 from executorch.backends.qualcomm.builders.utils import get_parameter, set_parameter
-from executorch.backends.qualcomm.utils.constants import QCOM_REQUANTIZE
 from executorch.exir.pass_base import ExportPass, PassResult
 from torch._guards import detect_fake_mode
 
@@ -197,14 +196,6 @@ def call(self, graph_module: torch.fx.GraphModule):
                             )
                             squeeze_node.meta = copy_meta(node.meta)
 
-                            if QCOM_REQUANTIZE in input_node.meta:
-                                input_node.meta.pop(QCOM_REQUANTIZE)
-                            if QCOM_REQUANTIZE in node.meta:
-                                squeeze_node.meta[QCOM_REQUANTIZE] = node.meta[
-                                    QCOM_REQUANTIZE
-                                ]
-                                conv2d_node.meta.pop(QCOM_REQUANTIZE, None)
-
                 for user in node.users.copy():
                     user.replace_input_with(node, squeeze_node)