[TRTLLM-11403][feat] VisualGen Cache-DiT + unified cache accelerator

[o-stoner]

@coderabbitai summary

Description

Initial unified cache accelerator and Cache-DiT implementation for the Wan and FLUX models.

Test Coverage

PR Checklist

Please review the following before submitting your PR:

• PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

• PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

• Test cases are provided for new code paths (see test instructions)

• Any new dependencies have been scanned for license and vulnerabilities

• CODEOWNERS updated if ownership changes

• Documentation updated as needed

• Update tava architecture diagram if there is a significant design change in PR.

• The reviewers assigned automatically/manually are appropriate for the PR.

• Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

[o-stoner]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #40364 [ run ] triggered by Bot. Commit: eeddeaa Link to invocation

[tensorrt-cicd]

PR_Github #40364 [ run ] completed with state FAILURE. Commit: eeddeaa
/LLM/main/L0_MergeRequest_PR pipeline #31466 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation