Lines Matching defs:output

83  * The information would include the shape and type of input and output required for the inference.
87  * for the output. APIs are provided to enable quantization through rte_ml_io_quantize() and
89  * and output buffers holding data for multiple batches.
92  * size of quantized and de-quantized multi-batch input and output buffers.
416 /** ML operation's input and output buffer representation as scatter gather list
459 	struct rte_ml_buff_seg **output;
460 	/**< Array of buffer segments to hold the inference output data.
532  * and this is likely to signify that other processed operations remain in the devices output queue.
760  *   A pointer to a file for output.
870  * Input and output data types. ML models can operate on reduced precision
915 	 * Same applies to output.
927 	 * Same applies to output.
934  * Input and output data information structure
936  * Specifies the type and shape of input and output data.
1521  * Dequantize output data.
1531  *   Address of quantized output data
1533  *   Address of dequantized output data