A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 07:15 UTC
[Cleanup][v1]:remote guided-decoding-backend for example (#19059)
Signed-off-by: calvin chen <120380290@qq.com>
Calvin Chen committed
Jun 4, 2025 at 12:23 UTC
8d646c2e53d3d840a3442bdd00845a6b57eb666f
1 file changed
-1
examples/online_serving/openai_chat_completion_structured_outputs.py
-1
@@ -139,7 +139,6 @@ def extra_backend_options_completion(client: OpenAI, model: str):
139
extra_body={
140
"guided_regex": r"\w+@\w+\.com\n",
141
"stop": ["\n"],
142
- "guided_decoding_backend": "xgrammar",
142
"guided_decoding_disable_fallback": True,
143
},
144
)