[GPU] remove _execute_empty_input and fix some code style

[zhoutianzi666]

Motivation

去掉 self._execute_empty_input()，统一模型调用入口！

Modifications

Usage or Command

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[bot]]

Thanks for your contribution!

[Wanglongzhi2001]

请问下为什么要删掉_empty_input_forward呢？EP 需要这个逻辑，删掉的话能跑通吗？

[zhoutianzi666]

请问下为什么要删掉_empty_input_forward呢？EP 需要这个逻辑，删掉的话能跑通吗？

1. 减少代码量，保证模型forward入口只有1处，方便支持TBO处理corner case
2. 空跑的时候确保可以进入cuda graph，减少单条query时延

[Wanglongzhi2001]

请问下为什么要删掉_empty_input_forward呢？EP 需要这个逻辑，删掉的话能跑通吗？

1. 减少代码量，保证模型forward入口只有1处，方便支持TBO处理corner case
2. 空跑的时候确保可以进入cuda graph，减少单条query时延

唔，可以再解释下么～，现在空跑已经是可以进入 cudagraph 的了， EP 下现在把空跑删掉的话，假设EP8只有一张卡有收到数据的话，在 dispatch 的时候其他卡没有进入空跑的话还怎么进行all2all的 dispatch 和 combine 通信呢？

[gongshaotian]

请问下为什么要删掉_empty_input_forward呢？EP 需要这个逻辑，删掉的话能跑通吗？

1. 减少代码量，保证模型forward入口只有1处，方便支持TBO处理corner case
2. 空跑的时候确保可以进入cuda graph，减少单条query时延

唔，可以再解释下么～，现在空跑已经是可以进入 cudagraph 的了， EP 下现在把空跑删掉的话，假设EP8只有一张卡有收到数据的话，在 dispatch 的时候其他卡没有进入空跑的话还怎么进行all2all的 dispatch 和 combine 通信呢？

”空跑已经是可以进入 cudagraph 的了“ 这个指的是 model.forward 已经支持空跑了，还是 empty_input_forward 能进 cuda graph 了

[Wanglongzhi2001]

请问下为什么要删掉_empty_input_forward呢？EP 需要这个逻辑，删掉的话能跑通吗？

1. 减少代码量，保证模型forward入口只有1处，方便支持TBO处理corner case
2. 空跑的时候确保可以进入cuda graph，减少单条query时延

唔，可以再解释下么～，现在空跑已经是可以进入 cudagraph 的了， EP 下现在把空跑删掉的话，假设EP8只有一张卡有收到数据的话，在 dispatch 的时候其他卡没有进入空跑的话还怎么进行all2all的 dispatch 和 combine 通信呢？

”空跑已经是可以进入 cudagraph 的了“ 这个指的是 model.forward 已经支持空跑了，还是 empty_input_forward 能进 cuda graph 了

抱歉，我说的不大对，应该是空跑和 cudagraph 不冲突，EP 在现在空跑逻辑下也能进 cudagraph

[codecov-commenter]

Codecov Report

:x: Patch coverage is 66.66667% with 5 lines in your changes missing coverage. Please review. :warning: Please upload report for BASE (develop@5bcf79d). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
fastdeploy/worker/gpu_model_runner.py	66.66%	2 Missing and 2 partials :warning:
fastdeploy/model_executor/models/ernie4_5_moe.py	66.66%	0 Missing and 1 partial :warning:

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5067   +/-   ##
==========================================
  Coverage           ?   57.69%           
==========================================
  Files              ?      317           
  Lines              ?    38441           
  Branches           ?     5763           
==========================================
  Hits               ?    22177           
  Misses             ?    14489           
  Partials           ?     1775           

Flag	Coverage Δ
diff	57.69% <66.66%> (?)

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

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

:rocket: New features to boost your workflow:

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