Adrian Lizarraga 84d48b6ad6 [QNN EP] Add provider option to offload graph I/O quantization/dequantization to the CPU EP (#22436) ... ### Description Adds QNN provider option `offload_graph_io_quantization` to offload graph input quantization and graph output dequantization to the CPU EP. Option is disabled by default to maintain current behavior. ### Motivation and Context Offloading the handling of I/O quantization to the CPU EP significantly improves inference latency for many models.		2024-10-16 15:00:53 -07:00
..
onnxruntime/core	[QNN EP] Add provider option to offload graph I/O quantization/dequantization to the CPU EP (#22436)	2024-10-16 15:00:53 -07:00