Bump torch-ao pin (pytorch#16824)

To include
pytorch/ao#3642

cc @freddan80 @per @zingo @oscarandersson8218 @digantdesai

Signed-off-by: Erik Lundell <erik.lundell@arm.com>

Author: Erik-Lundell

backends/arm/requirements-arm-models-test.txt

@@ -1,6 +1,6 @@
-# Copyright 2025 Arm Limited and/or its affiliates.
+# Copyright 2025-2026 Arm Limited and/or its affiliates.
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
 
-diffusers[torch] == 0.33.1
+diffusers[torch] @ git+https://github.com/huggingface/diffusers.git@a7cb14efbe4b255f4c8721c91a04f0ef40f4a05a

backends/cortex_m/test/ops/test_add.py

@@ -1,4 +1,4 @@
-# Copyright 2025 Arm Limited and/or its affiliates.
+# Copyright 2025-2026 Arm Limited and/or its affiliates.
 #
 # This source code is licensed under the BSD-style license found in the
 # LICENSE file in the root directory of this source tree.
@@ -153,10 +153,7 @@ class CortexMAlphaAdd(ModelAlpha):
 
 
 xfails_implementation = {
-    "alpha": (
-        "Expecting kwargs for aten op IR to be empty - alpha arg not supported.",
-        AssertionError,
-    ),
+    "alpha": "Expecting kwargs for aten op IR to be empty - alpha arg not supported.",
 }
 xfails_dialect = xfails_implementation | {
     # Cortex-M quantizer will not quantize additions that require broadcasting

requirements-examples.txt

@@ -3,5 +3,5 @@
 datasets == 3.6.0 # 4.0.0 deprecates trust_remote_code and load scripts. For now pin to 3.6.0
 timm == 1.0.7
 torchsr == 1.0.4
-torchtune >= 0.6.1
+torchtune @ git+https://github.com/pytorch/torchtune.git@44271b570af36cfda8ee20a4479d2652770378c0
 transformers == 5.0.0rc1