[NVBUG: 5619158] Enforce high precision model dtype for diffusion trt

[ajrasane]

What does this PR do?

Type of change:
Minor code change

Overview:

• Select the high precision dtype directly based on model type - FP16 for Stable Diffusion models, BF16 for Flux

Testing

python diffusion_trt.py --model flux-dev --benchmark

Before your PR is "Ready for review"

• Make sure you read and follow Contributor guidelines and your commits are signed.
• Is this change backward compatible?: No (No option to specify dtype while loading pipeline)
• Did you write any new necessary tests?: No
• Did you add or update any necessary documentation?: Yes
• Did you update Changelog?: Yes

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 73.52%. Comparing base (5adb9ba) to head (80a128d).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #526   +/-   ##
=======================================
  Coverage   73.52%   73.52%           
=======================================
  Files         181      181           
  Lines       18207    18207           
=======================================
  Hits        13387    13387           
  Misses       4820     4820           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[cjluo-nv]

can we just use the dtype from the model or this has to be setup like the hardcoded way?

[ajrasane]

We have hardcoded the dtype in create_pipeline_from() function, so we will have to use this in the hardcoded way.

[jingyu-ml]

LGTM