Max (CPU)

• Domain: ai.onnx

• Device: CPU

• Kernel: onnx_light_cpu::Max

• Supported types: FLOAT, DOUBLE, FLOAT16, INT8, INT16, INT32, INT64, UINT8, UINT16, UINT32, UINT64

• Opset bounds: since opset 13

Operator support

The standard ONNX schema and any standard shape inference come from onnx-light. No additional shape, peak-memory, fusion-pattern, or gradient implementation is registered by onnx-light-cpu for this operator.