clika_runtime.graph

The graph as data.

A compiled or traced :class:ModelGraph answers nodes() with its :class:Node views: each carries an :class:OpCode, a name, its attributes as plain Python values, and the :class:Value views of the tensors it consumes and produces; bound_tensors() names the weights a traced module bound into the operator (constants() lists edge constants such as an ONNX initializer). find_nodes(op_code), node(name), constants() and is_finalized() complete the read surface, and a :class:Pattern (a graph of operator constraints) finds its occurrences through find_pattern as :class:Match entries::

graph = crt.io.OnnxModel.open("model.onnx").compile()
for node in graph.nodes():
    print(node.name, node.op_code, node.attributes)
(relu,) = graph.find_nodes(crt.graph.OpCode.Relu)
for match in graph.find_pattern(crt.graph.Pattern([OpCode.MatMul, OpCode.Relu])):
    matmul, relu = match

A view stays valid while its graph is alive and unchanged; holding one keeps the graph alive.

The graph also answers what shapes it admits and how fast it runs: shape_domains() reports one :class:ShapeDomain per input (each dimension :class:DimDomain Fixed, Range or Free), validate_shapes checks shapes against them, and bench times synthesized or given inputs into a :class:BenchReport::

domains = graph.shape_domains()
report = graph.bench([[8, 131]], crt.graph.BenchOptions(warmup=2, iterations=10))
print(report.p50_ms, report.throughput_items_per_s)
print(report.to_csv())

Name	Kind
BenchOptions	class
BenchReport	class
DimDomain	class
FeedFill	class
InputShape	class
Match	class
ModelGraph	class
Node	class
NodeKind	class
OpCode	class
Pattern	class
ShapeDomain	class
Value	class