apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 09:07:10 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[fix] fix completion stream api output_tokens not in usage (#3588)

Browse Source
This commit is contained in:
李泳桦
2025-08-25 18:31:57 +08:00
committed by GitHub
parent 4e369c7fa7
commit b1f8f1aa07
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fastdeploy/entrypoints/openai/serving_completion.py
View File

@@ -413,6 +413,7 @@ class OpenAIServingCompletion:
usage=UsageInfo( usage=UsageInfo(
prompt_tokens=len(prompt_batched_token_ids[idx]), prompt_tokens=len(prompt_batched_token_ids[idx]),
completion_tokens=output_tokens[idx], completion_tokens=output_tokens[idx],
total_tokens=len(prompt_batched_token_ids[idx]) + output_tokens[idx],
), ),
) )
yield f"data: {usage_chunk.model_dump_json(exclude_unset=True)}\n\n" yield f"data: {usage_chunk.model_dump_json(exclude_unset=True)}\n\n"