nn/utils.h

Neural-network schema helpers, including onnx_light::getConvPoolStrides() and onnx_light::AttentionPropagateElemTypeFromInputToOutput().

Declares shared neural-network operator helpers.

This header provides utility APIs used by NN operator schemas, including Conv/Pool stride extraction, Attention type propagation, and function-body construction helpers.

namespace onnx_light

Alias that makes onnx-light headers compatible with code that references ONNX_LIGHT_NAMESPACE (the macro used in the standard onnx package).

Set to ONNX_LIGHT_NAMESPACE so both names resolve to the same namespace.

Symbol-visibility attribute for the public onnx-light C++ API.

Defined as empty because onnx-light does not require explicit __declspec(dllexport) or __attribute__((visibility("default"))) annotations — visibility is controlled at the shared-library level. The macro is provided so that vendored ONNX headers that decorate their declarations with ONNX_API compile without modification.

Namespace alias so that ONNX C++ code (and consumers such as onnxruntime) that refers to the literal onnx namespace — rather than the ONNX_NAMESPACE macro — resolves to the onnx-light namespace. The standard onnx package lives in namespace onnx; onnx-light uses onnx_light (via ONNX_LIGHT_NAMESPACE), so this alias keeps onnx-light a true drop-in. It is only introduced when the onnx-light namespace differs from onnx.

Functions

std::vector<int64_t> getConvPoolStrides(InferenceContext &ctx, size_t n_input_dims)

Reads and validates the ‘strides’ attribute for Conv/Pool shape inference. Returns the attribute value or a default value if the attribute is not present.

void AttentionPropagateElemTypeFromInputToOutput(InferenceContext &ctx)

Implements shape and type propagation for Attention (23-).

bool AttentionAppendFunctionCausalMask(const FunctionBodyBuildContext &ctx, FunctionBuilder &builder, bool padding)

Implements CausalMask for Attention.