[BugFix] Fix redundant prompt_logprobs in the second chunk of streaming response when return_token_ids is enabled for v1/completions and fix trace file name (#5829)

* fix prompt logprobs bug

* fix trace file name

---------

Co-authored-by: qwes5s5 <root@yq01-sys-rpm26xc1knu.yq01.baidu.com>
This commit is contained in:
qwes5s5
2026-01-06 14:11:43 +08:00
committed by GitHub
parent ca574119e5
commit b3ca7f041a
2 changed files with 4 additions and 2 deletions
@@ -546,7 +546,9 @@ class OpenAIServingCompletion:
reasoning_content="",
arrival_time=arrival_time,
logprobs=logprobs_res,
prompt_logprobs=clamp_prompt_logprobs(prompt_logprobs_res),
prompt_logprobs=(
clamp_prompt_logprobs(prompt_logprobs_res) if not request.return_token_ids else None
),
draft_logprobs=draft_logprobs_res,
speculate_metrics=output_speculate_metrics,
)