[Feature] mm and thinking model support structred output

[kevincheng2]

1. mm and thinking model support structred output
2. offline Inference support structred output

[paddle-bot]

Thanks for your contribution!

[Copilot]

Pull Request Overview

This PR adds structured output support via guided decoding (reasoning parsers) for multi-modal and thinking models, including offline inference capabilities.

• Introduce a new --reasoning_parser CLI argument and propagate it through configuration to model runners.
• Extend the sampling and guided decoding pipeline: updated Sampler, guided backend interfaces, and skip-index logic.
• Enhance SamplingParams with GuidedDecodingParams and document offline inference usage for structured outputs.

Reviewed Changes

Copilot reviewed 18 out of 18 changed files in this pull request and generated 2 comments.

Show a summary per file

File	Description
fastdeploy/worker/worker_process.py	Add --reasoning_parser CLI arg and integrate it into FDConfig.
fastdeploy/worker/vl_gpu_model_runner.py	Initialize guided backend and reasoning parser; update guided decoding flow in the GPU model runner.
fastdeploy/model_executor/layers/sample/sampler.py	Enhance Sampler to support reasoning parsing and skip indices when masking tokens.
fastdeploy/engine/sampling_params.py	Introduce GuidedDecodingParams in SamplingParams for offline structured inference.
docs/features/structured_outputs.md	Add offline inference examples for structured output using GuidedDecodingParams.

Comments suppressed due to low confidence (3)

fastdeploy/worker/vl_gpu_model_runner.py:145

• The code checks for guided_json, guided_regex, guided_grammar, and structural_tag but does not handle guided_choice from GuidedDecodingParams. Add support for guided_choice to ensure all constraint types are honored.

        elif request.guided_grammar is not None:

fastdeploy/engine/engine.py:1049

• The code references self.cfg.reasoning_parser, but reasoning_parser is not defined on the engine config object. It should likely reference self.cfg.model_config.reasoning_parser.

            f" --reasoning_parser {self.cfg.reasoning_parser}")

fastdeploy/worker/vl_gpu_model_runner.py:152

• Using request.get(...) may not work if request is not a dict-like object. Consider using getattr(request, 'enable_thinking', True) to access the attribute safely.

            enable_thinking=request.get("enable_thinking", True),