apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-15 05:01:00 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[fix] fix output tokens count in streaming completion api (#3507)

Browse Source
This commit is contained in:
李泳桦
2025-08-21 18:19:13 +08:00
committed by GitHub
parent e4f0b755b4
commit 8bea4b1e25
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -407,7 +407,6 @@ class OpenAIServingCompletion:
delta_message.tool_calls = delta_message_output.tool_calls
choices.append(delta_message)
output_tokens[idx] += 1
if res["finished"]:
choices[-1].finish_reason = self.calc_finish_reason(