Patrice Vignola 49512e558a [DML EP] Add I/O binding and If operator (#16859) ... Being able to leverage I/O binding for DML and registering `If` for the DML EP allows us to avoid copying the past/present key/values back and forth between the CPU and the GPU after every token. This gives us a 25% performance increase for Dolly V2 with 128 tokens on an RTX 4090.		2023-07-31 19:45:59 -07:00
..
contrib_ops	[JS/Web] Added Gelu contrib operator support to JSEP (#16909)	2023-07-31 09:18:58 -07:00
core	[DML EP] Add I/O binding and If operator (#16859)	2023-07-31 19:45:59 -07:00
python	[DML EP] Add I/O binding and If operator (#16859)	2023-07-31 19:45:59 -07:00
test	Extend saving models optimized by inference session (#16912)	2023-07-31 16:39:35 -07:00
tool/etw
wasm	[js/web] enable ONNX Runtime Web error messages in JS (#16335)	2023-06-15 09:45:41 -07:00
__init__.py	ExecutionProvider API refactor - move allocator from EP level to SessionState level and indexed by OrtDevice (#15833)	2023-06-19 17:44:45 -07:00
ReformatSource.ps1
ReformatSourcePython.bat
VSCodeCoverage.runsettings