feat: Enhance capability of engine caching and refitting

[zewenli98]

Description

TensorRT 10.14 will add an argument trt.SerializationFlag.INCLUDE_REFIT to allow refitted engines to keep refittable. Based on the capability, this PR enhances the existing engine caching and refitting features as follows:

1. To save hard disk space, engine caching will only save weight-stripped engines on disk regardless of compilation_settings.strip_engine_weights. Then, when users pull out the cached engine, it will be automatically refitted and kept refittable.
2. Compiled TRT modules can be refitted multiple times with refit_module_weights(). e.g.:

for _ in range(3):
    trt_gm = refit_module_weights(trt_gm, exp_program)

Type of change

• New feature (non-breaking change which adds functionality)

Checklist:

• My code follows the style guidelines of this project (You can use the linters)
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas and hacks
• I have made corresponding changes to the documentation
• I have added tests to verify my fix or my feature
• New and existing unit tests pass locally with my changes
• I have added the relevant labels to my PR in so that relevant reviewers are notified

[zewenli98]

TODO:

1. Consider if turning on engine caching by default.
2. Consider which arguments should be put into _SETTINGS_TO_BE_ENGINE_INVARIANT