apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Feature] add prompt_tokens and completion_tokens (#3504)
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source
This commit is contained in:
memoryCoderC
2025-08-21 10:23:27 +08:00
committed by GitHub
parent 30b3f2dc07
commit 31f639f10b
3 changed files with 16 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/entrypoints/openai/serving_completion.py
+4
View File
@@ -343,6 +343,7 @@ class OpenAIServingCompletion:
text="",
prompt_token_ids=list(prompt_batched_token_ids[idx]),
text_after_process=text_after_process_list[idx],
prompt_tokens=text_after_process_list[idx],
completion_token_ids=None,
)
],
@@ -393,6 +394,7 @@ class OpenAIServingCompletion:
completion_token_ids=output.get("token_ids") if request.return_token_ids else None,
tool_calls=None,
raw_prediction=output.get("raw_prediction") if request.return_token_ids else None,
completion_tokens=output.get("raw_prediction") if request.return_token_ids else None,
reasoning_content=output.get("reasoning_content"),
arrival_time=arrival_time,
logprobs=logprobs_res,
@@ -511,7 +513,9 @@ class OpenAIServingCompletion:
prompt_token_ids=prompt_token_ids if request.return_token_ids else None,
completion_token_ids=completion_token_ids if request.return_token_ids else None,
raw_prediction=output.get("raw_prediction") if request.return_token_ids else None,
completion_tokens=output.get("raw_prediction") if request.return_token_ids else None,
text_after_process=text_after_process_list[idx] if request.return_token_ids else None,
prompt_tokens=text_after_process_list[idx] if request.return_token_ids else None,
reasoning_content=output.get("reasoning_content"),
tool_calls=output.get("tool_call"),
logprobs=aggregated_logprobs,