EngineX-Iluvatar/enginex-vllm-bi100-qwen36
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

fix no reasoning token issue

Browse Source
This commit is contained in:
Lu Xinlong
2026-06-18 12:21:05 +08:00
parent 3b8a567e9e
commit 47a4d9e72a
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
qwen3_6_scripts/serving_chat.py
View File

@@ -560,9 +560,14 @@ class OpenAIServingChat(OpenAIServing):
# if the message delta is None (e.g. because it was a # if the message delta is None (e.g. because it was a
# "control token" for tool calls or the parser otherwise # "control token" for tool calls or the parser otherwise
# wasn't ready to send a token, then # wasn't ready to send a token, then
# get the next token without streaming a chunk # get the next token without streaming a chunk.
# However, if this is the finish token we must NOT skip —
# the finish block updates reasoning_token_counts, sets
# finish_reason_sent, and flushes the final usage chunk.
if delta_message is None: if delta_message is None:
if output.finish_reason is None:
continue continue
delta_message = DeltaMessage()
if output.finish_reason is None: if output.finish_reason is None:
# Send token-by-token response for each request.n # Send token-by-token response for each request.n