MCPcopy Create free account
hub / github.com/pytorch/executorch / annotate

Method annotate

backends/qualcomm/quantizer/annotators/htp_rules.py:110–111  ·  view source on GitHub ↗
(node: Node, quantization_config: QuantizationConfig)

Source from the content-addressed store, hash-verified

108class Add(GeneralOpDef):
109 @staticmethod
110 def annotate(node: Node, quantization_config: QuantizationConfig) -> None:
111 annotate_binary(node, quantization_config)
112
113
114@register_annotator([torch.ops.aten.amax.default], QnnConstants.OpReduceMax.op_name)

Callers

nothing calls this directly

Calls 1

annotate_binaryFunction · 0.90

Tested by

no test coverage detected