onnxruntime/onnxruntime
simonjub c969237321
[TRT EP] Fix ProviderOptions functions (#17567)
### Description
When trying to use the TRT EP option trt_extra_plugin_lib_paths I
noticed that my custom op library was not being loaded by the EP. After
some digging I found that code was missing to update this option when
UpdateTensorRTProviderOptions() is used to set it.

At the same time I noticed that char arrays were allocated in that
function and wondered where they are de-allocated. When I found it was
done in ReleaseTensorRTProviderOptions(), I noticed that a few
de-allocations were missing.

### Motivation and Context
This PR fixes the problems described above.
2023-09-17 12:19:32 -07:00
..
contrib_ops Refactoring of attention cuda kernel: move prepare qkv and concat_past_to_present (#17559) 2023-09-15 10:57:29 -07:00
core [TRT EP] Fix ProviderOptions functions (#17567) 2023-09-17 12:19:32 -07:00
python [TensorRT EP] Fallback to CUDA EP if it's explicitly assigned (#17535) 2023-09-15 15:16:11 -07:00
test Update optimize_pipeline for SDXL (#17536) 2023-09-15 10:17:20 -07:00
tool/etw
wasm [js/web] add sessionOptions.freeDimensionOverrides (#17488) 2023-09-13 09:17:34 -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