Adrian Lizarraga b47e1e64d7 [QNN EP] Make offloading graph input/output quantization (to CPU) the default (#23368) ... ### Description Makes the QNN provider option `offload_graph_io_quantization` enabled by default. It was previously disabled by default. ### Motivation and Context Enabling this option significantly decreases inference latency for many models.		2025-02-04 11:42:46 -08:00
..
common	remove log spam from cpuinfo (#23548)	2025-01-31 18:16:24 -08:00
dll	fix webgpu delay load test (#23157)	2024-12-20 13:37:12 -08:00
dlpack
eager
flatbuffers
framework	Fix the issue that the new generated EP context model not able to find external data (#23537)	2025-01-29 22:01:13 -08:00
graph	Update BiasGelu fusion and related ops (#23518)	2025-01-30 22:53:59 -08:00
mickey
mlas	[ARM CPU] hgemm optimized for gqa (#23107)	2025-01-24 15:25:24 -08:00
optimizer	Update BiasGelu fusion and related ops (#23518)	2025-01-30 22:53:59 -08:00
platform	[QNN EP] Make QNN EP a shared library (#23120)	2025-01-22 12:11:00 -08:00
providers	[QNN EP] Make offloading graph input/output quantization (to CPU) the default (#23368)	2025-02-04 11:42:46 -08:00
quantization
session	[onnxruntime/build] Add new flag enable_generic_interface to build primary EPs by default (#23342)	2025-01-28 15:24:09 -08:00
util	Address CodeQL security issues on comparison of different types (#23276)	2025-01-07 17:30:44 -08:00