biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Core][V0] Add guidance backend for structured output (#14589)

Browse Source 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Loc Huynh <lohuynh@microsoft.com>
Co-authored-by: Michal Moskal <michal@moskal.me>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
This commit is contained in:
Russell Bryant
2025-03-20 00:33:51 -04:00
committed by GitHub
parent b88be22165
commit 1f16b7fe74
8 changed files with 167 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/model_executor/test_guided_processors.py
View File

@@ -16,7 +16,9 @@ from vllm.model_executor.guided_decoding.outlines_logits_processors import (
from vllm.sampling_params import GuidedDecodingParams
MODEL_NAME = 'HuggingFaceH4/zephyr-7b-beta'
GUIDED_DECODING_BACKENDS = ["outlines", "lm-format-enforcer", "xgrammar"]
GUIDED_DECODING_BACKENDS = [
"outlines", "lm-format-enforcer", "xgrammar", "guidance"
]
GUIDED_DECODING_BACKENDS_WITH_REASONING_SUPPORT = ["outlines", "xgrammar"]
REASONING_MODEL_NAME = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"