[Feat] add diffusion pipeline profiler and progress bar support to FluxKontextPipeline et.al

[RuixiangMa]

Purpose

Add diffusion pipeline profiler and progress bar support to FluxKontextPipeline, Flux2Pipeline, HunyuanVideo15Pipeline, and HunyuanVideo15I2VPipeline

Test Plan

Test Result

INFO 04-05 14:40:13 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] FluxKontextPipeline.text_encoder.forward took 0.005479s
INFO 04-05 14:40:13 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] FluxKontextPipeline.text_encoder.forward took 0.005396s
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:25<00:00,  1.95it/s]
INFO 04-05 14:40:40 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] FluxKontextPipeline.vae.decode took 0.153891s
INFO 04-05 14:40:40 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] FluxKontextPipeline.forward took 35.915194s
INFO 04-05 14:40:40 [diffusion_model_runner.py:212] Peak GPU memory (this request): 21.99 GB reserved, 19.79 GB allocated, 2.20 GB pool overhead (10.0%)
INFO 04-05 14:40:40 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] FluxKontextPipeline.vae.decode took 0.155134s
INFO 04-05 14:40:40 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] FluxKontextPipeline.forward took 35.916372s

INFO 04-05 14:35:37 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] HunyuanVideo15Pipeline.text_encoder.forward took 0.113588s
INFO 04-05 14:35:37 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] HunyuanVideo15Pipeline.text_encoder.forward took 0.115647s
INFO 04-05 14:35:37 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] HunyuanVideo15Pipeline.text_encoder.forward took 0.111926s
  0%|                                                                                                                                                                                                                                                    | 0/50 [00:00<?, ?it/s]
INFO 04-05 14:35:37 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] HunyuanVideo15Pipeline.text_encoder.forward took 0.113859s
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:32<00:00,  1.52it/s]
INFO 04-05 14:36:12 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] HunyuanVideo15Pipeline.vae.decode took 1.732654s
INFO 04-05 14:36:12 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] HunyuanVideo15Pipeline.forward took 40.605841s
INFO 04-05 14:36:12 [diffusion_model_runner.py:212] Peak GPU memory (this request): 22.62 GB reserved, 21.74 GB allocated, 0.88 GB pool overhead (3.9%)
INFO 04-05 14:36:12 [diffusion_engine.py:119] Generation completed successfully.
INFO 04-05 14:36:12 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] HunyuanVideo15Pipeline.vae.decode took 1.815525s
INFO 04-05 14:36:12 [diffusion_pipeline_profiler.py:31] [DiffusionPipelineProfiler] HunyuanVideo15Pipeline.forward took 40.688484s

---

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan. Please provide the test scripts & test commands. Please state the reasons if your codes don't require additional test scripts. For test file guidelines, please check the test style doc
• The test results. Please paste the results comparison before and after, or the e2e results.
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model. Please run mkdocs serve to sync the documentation editions to ./docs.
• (Optional) Release notes update. If your change is user-facing, please update the release notes draft.

BEFORE SUBMITTING, PLEASE READ https://github.com/vllm-project/vllm-omni/blob/main/CONTRIBUTING.md (anything written below this line will be removed by GitHub Actions)

[gcanlin]

Could you help add ProgressBarMixin for these models, specifically for Hunyuan video?

[RuixiangMa]

Could you help add ProgressBarMixin for these models, specifically for Hunyuan video?

Done 😊