apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Benchmark]支持Completions接口 (#5700)

Browse Source 
* benchmark工具支持受限解码场景指定response_format

* Update backend_request_func.py

output.success判断兼容思考内容超长截断时回复内容为空的情况

* Update benchmark_serving.py

更新benchmark_metrics

* 支持Completions接口

* 支持Completions接口

* 支持Completions接口

* [Benchmark]支持Completions接口

* [Benchmark]支持Completions接口

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
This commit is contained in:
ophilia-lee
2025-12-23 19:46:23 +08:00
committed by GitHub
parent 04c30521dd
commit 99258e19c8
5 changed files with 17 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
benchmarks/backend_request_func.py
View File

@@ -273,7 +273,8 @@ async def async_request_eb_openai_chat_completions(
# 新增metrics统计，计算首token过滤空包
output.metrics = metrics_summary(metrics_list, token_timestamps[1:])
if output.generated_text.strip() == "":
# 兼容思考内容超长截断的情况，此时回复内容为空
if output.generated_text.strip() == "" and output.reasoning_content.strip() == "":
output.success = False
output.reasoning_tokens = output.output_tokens
output.error = "No generated text found!"