[TRT EP] Fix trt context memory sharing

[toothache]

Description

Fixed a TRT context memory sharing bug where the context memory was assigned to a unique_ptr that was immediately destructed upon leaving scope.

Motivation and Context

The bug seems to be introduced by a refactor work: #15833 :

[toothache]

@yf711 @chilo-ms , may I get a review for this change? Thanks!

[tianleiwu]

/azp run Linux QNN CI Pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows x64 QNN CI Pipeline

[azure-pipelines]

Azure Pipelines successfully started running 5 pipeline(s).

[chilo-ms]

/azp run Linux QNN CI Pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline, Windows GPU Doc Gen CI Pipeline, Windows x64 QNN CI Pipeline

[azure-pipelines]

Azure Pipelines successfully started running 5 pipeline(s).

[jywu-msft]

@chilo-ms can you help double check if this same issue is there on NV RTX EP?

[chilo-ms]

@chilo-ms can you help double check if this same issue is there on NV RTX EP?

@ankan-ban @ishwar-raut1 @gedoensmax @gaugarg-nv
Please see this TRT context memory sharing bug and fix in TRT EP.
Even though NV RTX EP for now doesn't expose TRT context memory sharing option, you might need the fix later.