ci: Support BF16 data type in TensorRT backend

[pskiran1]

What does the PR do?

• Added new L0_trt_bf16_dtype job to test BF16 datatype for TensorRT backend.
• Updated model generation script to generate BF16 datatype TensorRT models.

Note: BF16 datatype data type is supported for GPU with CC 8.0 and above only.

Checklist

• PR title reflects the change and is of format <commit_type>: <Title>
• Changes are described in the pull request.
• Related issues are referenced.
• Populated github labels field
• Added test plan and verified test passes.
• Verified that the PR passes existing CI.
• Verified copyright is correct on all changed files.
• Added succinct git squash message before merging ref.
• All template sections are filled out.
• Optional: Additional screenshots for behavior/output changes with before/after.

Commit Type:

Check the conventional commit type
box here and add the label to the github PR.

• build
• ci
• docs
• feat
• fix
• perf
• refactor
• revert
• style
• test

Related PRs:

triton-inference-server/tensorrt_backend#90

Where should the reviewer start?

Test plan:

• CI Pipeline ID: 15487143

Caveats:

Background

https://docs.nvidia.com/deeplearning/tensorrt/support-matrix/index.html#hardware-precision-matrix

Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)

• closes GitHub issue: #xxx