Merge branch 'main' into add_ci_for_mtk_backend

Author: neuropilot-captain

.ci/scripts/build_llama_android.sh

@@ -42,6 +42,7 @@ build_llama_runner() {
     popd
     ANDROID_ABI=arm64-v8a
     cmake -DBUCK2="${BUCK2}" \
+    -DBUILD_TESTING=OFF \
     -DCMAKE_TOOLCHAIN_FILE="$ANDROID_NDK"/build/cmake/android.toolchain.cmake  \
     -DANDROID_ABI="${ANDROID_ABI}" \
     -DCMAKE_INSTALL_PREFIX=cmake-android-out \

.ci/scripts/test_llama.sh

@@ -169,6 +169,7 @@ cmake_build_llama_runner() {
     popd
     dir="examples/models/llama"
     retry cmake \
+        -DBUILD_TESTING=OFF \
         -DCMAKE_INSTALL_PREFIX=cmake-out \
         -DCMAKE_BUILD_TYPE="$CMAKE_BUILD_TYPE" \
         -Bcmake-out/${dir} \

.ci/scripts/test_llama_torchao_lowbit.sh

@@ -40,6 +40,7 @@ cmake --build cmake-out -j16 --target install --config Release
 
 # Install llama runner with torchao
 cmake -DPYTHON_EXECUTABLE=python \
+    -DBUILD_TESTING=OFF \
     -DCMAKE_BUILD_TYPE=Release \
     -DEXECUTORCH_BUILD_KERNELS_CUSTOM=ON \
     -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON \

.ci/scripts/test_llava.sh

@@ -64,9 +64,10 @@ cmake_install_executorch_libraries_for_android() {
 
 
 LLAVA_COMMON_CMAKE_ARGS="                        \
+        -DBUILD_TESTING=OFF                      \
         -DPYTHON_EXECUTABLE="$PYTHON_EXECUTABLE" \
         -DCMAKE_INSTALL_PREFIX=${BUILD_DIR}      \
-        -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}         \
+        -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}   \
         -DEXECUTORCH_BUILD_KERNELS_CUSTOM=ON     \
         -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON  \
         -DEXECUTORCH_BUILD_XNNPACK=ON"

.github/workflows/trunk.yml

@@ -262,7 +262,7 @@ jobs:
         output=$(ls -la ${elf})
         arr=($output)
         size=${arr[4]}
-        threshold="102400" # 100KiB
+        threshold="103068" # ~100KiB
         echo "size: $size, threshold: $threshold"
         if [[ "$size" -le "$threshold" ]]; then
           echo "Success $size <= $threshold"

CMakeLists.txt

@@ -75,9 +75,13 @@ if(NOT PYTHON_EXECUTABLE)
 endif()
 announce_configured_options(PYTHON_EXECUTABLE)
 
+if(NOT BUCK2)
+  resolve_buck2()
+endif()
+announce_configured_options(BUCK2)
+
 announce_configured_options(CMAKE_CXX_COMPILER_ID)
 announce_configured_options(CMAKE_TOOLCHAIN_FILE)
-announce_configured_options(BUCK2)
 
 load_build_preset()
 include(${PROJECT_SOURCE_DIR}/tools/cmake/preset/default.cmake)
@@ -290,9 +294,6 @@ set(_common_include_directories
 #
 
 if(NOT EXECUTORCH_SRCS_FILE)
-  # Find or download buck2 binary.
-  resolve_buck2()
-
   # A file wasn't provided. Run a script to extract the source lists from the
   # buck2 build system and write them to a file we can include.
   #

backends/arm/_passes/annotate_channels_last_dim_order_pass.py

@@ -35,7 +35,10 @@
 def _transpose_impl(*args, **kwargs):
     # Validate length of dim_order array
     dim = args[1]
-    assert len(dim) in (4, 5)
+    if len(dim) != 4 and len(dim) != 5:
+        raise ValueError(
+            f"Dim order length must be either 4 or 5, got {len(dim)}: {dim}"
+        )
     # Pass-through in edge-IR
     return args[0]
 

backends/arm/_passes/convert_split_to_slice.py

@@ -41,9 +41,14 @@ def call(self, graph_module: torch.fx.GraphModule):
             dim = split_node.args[2] if len(split_node.args) > 2 else 0
             dim = (dim + rank) % rank
 
-            assert (
-                sum(split_lengths) == shape[dim]
-            ), "Given split lengths don't sum up to the size of the dimension."
+            # Validate that split lengths cover the entire dimension
+            length_sum = sum(split_lengths)
+            dim_size = shape[dim]
+            if length_sum != dim_size:
+                raise ValueError(
+                    f"Split sizes {split_lengths} sum to {length_sum}, "
+                    f"but dimension {dim} has size {dim_size}"
+                )
 
             # Convert split argument 'split_lengths' to slice arguments start and end.
             starts = [0] * len(split_lengths)

backends/arm/_passes/fold_qdq_with_annotated_qparams_pass.py

@@ -120,7 +120,9 @@ def fold_and_annotate_arg(
         if input_qparams is not None:
             node.meta["input_qparams"][i] = input_qparams
             for n in nodes_to_remove:
-                assert n.target == dq_op
+                if n.target != dq_op:
+                    raise RuntimeError(f"Expected {dq_op} dq_op, got {n.target}")
+
                 n.replace_all_uses_with(n.args[0])  # type: ignore[arg-type]
                 graph_module.graph.erase_node(n)
 
@@ -136,14 +138,16 @@ def call(self, graph_module: GraphModule) -> PassResult:
                 continue
 
             # Make sure we haven't already set qparams meta information on the node
-            assert "input_qparams" not in n.meta, (
-                f'Unexpected key "input_qparams" found in meta for node {n}. '
-                "input_qparams should not have been set at this point"
-            )
-            assert "output_qparams" not in n.meta, (
-                f'Unexpected key "output_qparams" found in meta for node {n}. '
-                "output_qparams should not have been set at this point"
-            )
+            if "input_qparams" in n.meta:
+                raise RuntimeError(
+                    f'Unexpected key "input_qparams" found in meta for node {n}. '
+                    "input_qparams should not have been set at this point"
+                )
+            if "output_qparams" in n.meta:
+                raise RuntimeError(
+                    f'Unexpected key "output_qparams" found in meta for node {n}. '
+                    "output_qparams should not have been set at this point"
+                )
 
             # for the inputs and outputs search the graph for quantization info and
             # store the information in a dict with order of the _tensor_ inputs as key,

backends/arm/_passes/insert_table_ops.py

@@ -240,8 +240,17 @@ def call(self, graph_module: GraphModule) -> PassResult:
                     args=(node.args[0],),
                 )
                 output_node = table_node
-                assert len(input_qparams) == 1
-                assert len(output_qparams) == 1
+                # Expect exactly one quantization parameter for input and output
+                if len(input_qparams) != 1:
+                    raise ValueError(
+                        f"InsertTableOpsPass expected exactly one input quantization parameter, "
+                        f"got {len(input_qparams)} for node {node.name}"
+                    )
+                if len(output_qparams) != 1:
+                    raise ValueError(
+                        f"InsertTableOpsPass expected exactly one output quantization parameter, "
+                        f"got {len(output_qparams)} for node {node.name}"
+                    )
 
                 # Generate table buffer and how much to lshift the table output.
                 buffer, lshift = self.generate_table_values(