Adrian Lizarraga eae7b705ac [Quant tool] Fix quantized bias's scale dtype to properly handle fp16 bias inputs (#20340) ... ### Description - Fix quantization tool bug that did not correctly set a quantized bias's scale data type to fp16 if the original bias was fp16. - Enabled fp16 ConvTranspose quantization unit tests that were disabled. ### Motivation and Context Python quantization tests for fp16 ConvTranspose were originally disabled due to a shape inference bug. It turns out that we also have a bug in our quantizer that does not properly handle fp16 bias inputs. Fixing the bug allows us to re-enable these tests with the latest version of ONNX.		2024-04-17 10:24:28 -07:00
..
contrib_ops	Add Gemma Rotary Embedding (#20267)	2024-04-16 15:31:56 -07:00
core	Enable provider option to let user provider the profiling file path (#20285)	2024-04-17 09:42:40 -07:00
python	[Quant tool] Fix quantized bias's scale dtype to properly handle fp16 bias inputs (#20340)	2024-04-17 10:24:28 -07:00
test	[Quant tool] Fix quantized bias's scale dtype to properly handle fp16 bias inputs (#20340)	2024-04-17 10:24:28 -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
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings