Bump torchao to 03ca489dc and nightly wheel to dev20260729

backends/arm/test/models/test_llama.py

@@ -229,6 +229,11 @@ def test_llama_tosa_INT():
         pipeline.run()
 
 
+@pytest.mark.xfail(
+    reason="index_put into a preserved fp32 mutable buffer (torchao pytorch/ao#4466) is "
+    "not delegatable by the INT backend, so the KV-cache round-trip forms a partition "
+    "dependency cycle. Same root cause as the xfailed static-cache tests: MLETORCH-1971."
+)
 def test_llama_tosa_INT_static():
     llama_model, llama_inputs, _ = TestLlama().prepare_model_hf_static()
     if llama_model is None or llama_inputs is None:

install_requirements.py

@@ -16,7 +16,7 @@
 # This will be dynamically set based on CUDA availability and CUDA backend enabled/disabled.
 TORCH_URL_BASE = "https://download.pytorch.org/whl/test"
 TORCHAO_URL_BASE = "https://download.pytorch.org/whl/nightly"
-TORCHAO_NIGHTLY_VERSION = "0.18.0.dev20260715"
+TORCHAO_NIGHTLY_VERSION = "0.18.0.dev20260729"
 
 # Since ExecuTorch often uses main-branch features of pytorch, only the nightly
 # pip versions will have the required features.