vllm-project/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-12-06 06:53:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Missing tokens in return_token_ids when tool parsers is enabled in streaming mode (#29074)

Browse Source 
Signed-off-by: Peng-YM <1048217874pengym@gmail.com>
This commit is contained in:
Peng-YM
2025-12-05 03:09:39 +08:00
committed by GitHub
parent 1119f6e47a
commit 48a5fff66e
1 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
vllm/entrypoints/openai/serving_chat.py
View File

@@ -1072,10 +1072,15 @@ class OpenAIServingChat(OpenAIServing):
# wasn't ready to send a token, then
# get the next token without streaming a chunk
if delta_message is None:
if output.finish_reason is None:
# NOTE: If return_token_ids is enabled, we still need to
# send a chunk with token_ids even if delta_message is None
# to ensure all tokens are included in the response
if (
output.finish_reason is None
and not request.return_token_ids
):
continue
else:
delta_message = DeltaMessage()
delta_message = DeltaMessage()
# Log streaming delta if output logging is enabled
if self.enable_log_outputs and self.request_logger: