Implement caching on LTX and WAN video models

[vladmandic]

CacheConfig is used to enable FasterCache and PyramidAttentionBroadcast
CacheConfig is present in Hunyuan, Mochi, Latte, Allegro, Cog transformer modules
but its not present in WAN or LTX transformer modules:

• WanTransformer3DModel
• LTXVideoTransformer3DModel

ask is to enable caching functionality for WAN and LTX models.

cc @a-r-r-o-w

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

[a-r-r-o-w]

Worked on in #11180