winskuo-quic 509cbcae6e [QNN EP] Support prelu fp16 (#20428) ... ### Description Originally, Prelu in QNN will fail when the input is fp16 and alpha is fp32. QNN requires alpha is fp16 when input is fp16. This can be resolved by casting alpha to fp16 and pass it to QNN. ### Motivation and Context Makes QNN Prelu support fp16 case. --------- Co-authored-by: Hector Li <hecli@microsoft.com>		2024-04-29 13:26:51 -07:00
..
contrib_ops	mlas nbit matmul requires packed_b (#20482)	2024-04-26 17:18:53 -07:00
core	[QNN EP] Support prelu fp16 (#20428)	2024-04-29 13:26:51 -07:00
python	[python] MinMax calibration per channel (#19285)	2024-04-26 12:40:49 -07:00
test	[QNN EP] Support prelu fp16 (#20428)	2024-04-29 13:26:51 -07:00
tool/etw
wasm	[js/web] rewrite backend resolve to allow multiple EPs (#19735)	2024-03-15 11:47:45 -07:00
__init__.py	[ORT 1.17.0 release] Bump up version to 1.18.0 (#19170)	2024-01-17 11:18:32 -08:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings