[Frontend] User-provided uuids for medias in chat. (RFC #22044)

[huachenheli]

Summary:
This PR adds user-supplied uuids to the chat interface (#22044). Should only land after #23394 due to the changes needed in multimodal cache.

Test Plan:
pytest tests/entrypoints/test_chat_utils.py

e2e test:
HF_HUB_DISABLE_XET=1 CUDA_VISIBLE_DEVICES=2 pytest tests/entrypoints/openai/test_vision.py

python -m vllm.entrypoints.openai.api_server --model Qwen/Qwen2.5-VL-7B-Instruct --port 8001 --host 0.0.0.0 --dtype bfloat16 --limit-mm-per-prompt '{"video":1}'

chat_completion_from_url = client.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "video_url",
                    "video_url": {"url": video_url},
                    "uuid": "my_uuid_1234",
                },
                {
                    "type": "text",
                    "text": "Describe this video in detail",
                },
            ],
        }
    ],
    model=model,
)

Also manually verified provided UUIDs are correctly passed down to mm hasher.

Reviewers:

Subscribers:

Tasks:

Tags:

Purpose

Test Plan

Test Result

(Optional) Documentation Update

---

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, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

[DarkLight1337]

Are you working with @ywang96 on this? He has opened #23394

[huachenheli]

Are you working with @ywang96 on this? He has opened #23394

Yeah. I think this needs to rebased on top of that instead. I was originally thinking about tracking uuids as part of multi_modal_data but that would have compatibility issues.