xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-05 06:30:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Model] Fixed stream generator for gpt-oss + spec-decoding (#26027)

Browse Source 
Signed-off-by: Aleksandr Samarin <astrlrd@nebius.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Aleksandr Samarin 2025-10-03 15:43:41 +02:00 committed by yewentao256
parent d8b1f9ccc3
commit c40c0d9c82
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/entrypoints/openai/serving_chat.py
View File

@ -691,11 +691,13 @@ class OpenAIServingChat(OpenAIServing):
if self.use_harmony:
harmony_parser = harmony_parsers[i]
prev_recipient = harmony_parser.current_recipient
delta_text = ""
for token_id in output.token_ids:
harmony_parser.process(token_id)
delta_text += (harmony_parser.last_content_delta
or "")
cur_channel = harmony_parser.current_channel
cur_recipient = harmony_parser.current_recipient
delta_text = harmony_parser.last_content_delta or ""
else:
delta_text = output.text