EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Fix Harmony reasoning parser for and auto-separation for gpt-oss models (#9190)

Browse Source 
Co-authored-by: Chang Su <chang.s.su@oracle.com>
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: zhaochenyang20 <zhaochenyang20@gmail.com>
Co-authored-by: minleminzui <2969413251@qq.com>
Co-authored-by: maocheng23 <maocheng@berkeley.edu>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
This commit is contained in:
Jonas
2025-08-26 00:26:26 +02:00
committed by GitHub
parent 24a8cee66d
commit a0a77d937b
8 changed files with 1676 additions and 551 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
python/sglang/srt/entrypoints/openai/serving_chat.py
View File

@@ -148,6 +148,16 @@ class OpenAIServingChat(OpenAIServingBase):
self, request: ChatCompletionRequest, is_multimodal: bool
) -> MessageProcessingResult:
"""Process chat messages and apply chat template"""
is_gpt_oss = (
hasattr(self.tokenizer_manager.model_config, "hf_config")
and hasattr(self.tokenizer_manager.model_config.hf_config, "model_type")
and self.tokenizer_manager.model_config.hf_config.model_type == "gpt_oss"
)
# GptOss model needs to keep special tokens for harmony parsing
if is_gpt_oss:
request.skip_special_tokens = False
tool_call_constraint = None
# Apply chat template and its stop strings