add --use_kv_cache to image-to-text pipeline

[KimBioInfoStudio]

What does this PR do?

• add --use_kv_cahe to image-to-text pipeline
• add two new models to supported list
• replace hard code prompt with transformers.prcessor

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[KimBioInfoStudio]

llava-hf/llama3-llava-next-8b-hf

[KimBioInfoStudio]

llava-hf/llava-v1.6-34b-hf

[KimBioInfoStudio]

@yafshar should me split this pr into 3 small one to speed up the merge process?

1. kv-cache
2. Processor
3. Profiling

[yafshar]

@yafshar should me split this pr into 3 small one to speed up the merge process?

1. kv-cache

2. Processor

3. Profiling

No need to do that. If you need time to workout profiling, then remove it for now. The rest are working nicely. My comments above were just suggestions

[yafshar]

LGTM!

@regisss please check this PR.

[github-actions]

The code quality check failed, please run make style.

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[KimBioInfoStudio]

@yafshar @libinta the failed cases not related on this pr