[benchmark] update tools

[ZhangYulongg]

Motivation

截断case也记录usage

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]

Thanks for your contribution!

[EmmonsCurse]

/skip-ci all

[EmmonsCurse]

LGTM～ Skip check for Benchmark.

[PaddlePaddle-bot]

🤖 AI Code Review | 2026-04-20 17:46:36

📋 Review 摘要

PR 概述：在流式请求截断场景下，补充记录 usage 信息（output_tokens、prompt_tokens、prompt_len）
变更范围：benchmarks/backend_request_func.py
影响面 Tag：[Benchmark]

📝 PR 规范检查

PR 标题 Tag 大小写不规范，且标题描述过于笼统，建议修改：

标题建议（可直接复制）：

• [Benchmark] Record usage info for truncated streaming cases

描述模板（可直接复制）：

Motivation

当流式请求被截断时，usage 信息（completion_tokens、prompt_tokens、prompt_len）未被记录，导致 benchmark 统计数据不完整。

Modifications

在 async_request_eb_openai_chat_completions 函数中，流式循环结束后增加对最后一个 chunk 的 usage 字段读取，确保截断场景下也能正确记录 token 用量。

问题

未发现阻塞性问题。

总体评价

变更逻辑正确，在流式循环退出后从最后一个 chunk 中补充读取 usage 信息，与循环内 elif 分支（第 416-423 行）的已有逻辑保持一致，且使用了更安全的 .get() 访问方式。代码改动范围小、风险低。