[Feature] support reward api

[xiaolei373]

Motivation

支持reward接口，给指定的内容打分

Modifications

Usage or Command

本 PR 增加了一个多模态 chat/reward 接口请求示例。

示例请求如下：

curl --location 'http://xxxx/v1/chat/reward' \
--header 'Content-Type: application/json' \
--data '{
  "model": "",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://xxx/a.png"
          }
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "图里有几个人"
        }
      ]
    }
  ],
  "user": "user-123",
  "chat_template": null,
  "chat_template_kwargs": {
    "custom_var": "value"
  },
  "mm_processor_kwargs": {
    "image_size": 224
  }
}'

Accuracy Tests

Checklist

• Add at least a tag in the PR title.
  • Tag list: [[FDConfig],[APIServer],[Engine], [Scheduler], [PD Disaggregation], [Executor], [Graph Optimization], [Speculative Decoding], [RL], [Models], [Quantization], [Loader], [OP], [KVCache], [DataProcessor], [BugFix], [Docs], [CI], [Optimization], [Feature], [Benchmark], [Others], [XPU], [HPU], [GCU], [DCU], [Iluvatar], [Metax]]
  • You can add new tags based on the PR content, but the semantics must be clear.
• Format your code, run pre-commit before commit.
• Add unit tests. Please write the reason in this PR if no unit tests.
• Provide accuracy results.
• If the current PR is submitting to the release branch, make sure the PR has been submitted to the develop branch, then cherry-pick it to the release branch with the [Cherry-Pick] PR tag.

[paddle-bot]

Thanks for your contribution!

[lizexu123]

delete

[lizexu123]

这里reward哪里用到了吗？

[lizexu123]

改成英文注释

[lizexu123]

同上