[Optimization] The pre- and post-processing pipeline do not perform dict conversion

[kxz2002]

Motivation

The online pipeline currently converts requests into dictionaries, which are then transformed into final requests. The post-processing pipeline converts returned results into dictionaries for processing before returning them. To align with the offline pipeline's processing approach, dictionary conversion will no longer be performed.

💡 If this PR is a Cherry Pick, the PR title needs to follow the format by adding the [Cherry-Pick] label at the very beginning and appending the original PR ID at the end. For example, [Cherry-Pick][CI] Add check trigger and logic(#5191)

💡 如若此PR是Cherry Pick，PR标题需遵循格式，在最开始加上[Cherry-Pick]标签，以及最后面加上原PR ID，例如[Cherry-Pick][CI] Add check trigger and logic(#5191)

Modifications

Modified the chat/completion interface, the completion interface, and the pre- and post-processing chains associated with PoolingRequest. Replaced all dictionary usage within these chains with Request object usage. Similar modifications were made to the post-processing chain.

Usage or Command

No change in user command.

Accuracy Tests

No need.

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!

[codecov-commenter]

Codecov Report

❌ Patch coverage is 73.31461% with 190 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@23d488c). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/engine/request.py	65.38%	22 Missing and 5 partials ⚠️
fastdeploy/entrypoints/openai/serving_chat.py	66.25%	18 Missing and 9 partials ⚠️
fastdeploy/input/text_processor.py	70.88%	17 Missing and 6 partials ⚠️
fastdeploy/entrypoints/engine_client.py	60.78%	10 Missing and 10 partials ⚠️
...astdeploy/entrypoints/openai/serving_completion.py	74.66%	13 Missing and 6 partials ⚠️
...put/ernie4_5_vl_processor/ernie4_5_vl_processor.py	68.18%	6 Missing and 8 partials ⚠️
fastdeploy/engine/async_llm.py	71.79%	6 Missing and 5 partials ⚠️
...eploy/input/qwen_vl_processor/qwen_vl_processor.py	70.58%	5 Missing and 5 partials ⚠️
...stdeploy/entrypoints/openai/response_processors.py	72.72%	6 Missing and 3 partials ⚠️
fastdeploy/input/ernie4_5_processor.py	88.57%	4 Missing and 4 partials ⚠️
... and 7 more

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5494   +/-   ##
==========================================
  Coverage           ?   65.51%           
==========================================
  Files              ?      330           
  Lines              ?    41896           
  Branches           ?     6417           
==========================================
  Hits               ?    27449           
  Misses             ?    12425           
  Partials           ?     2022           

Flag	Coverage Δ
GPU	65.51% <73.31%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.