From 3147586ebdb36ceae653e9dceec8cf9922fe2c28 Mon Sep 17 00:00:00 2001 From: Benjamin Chislett Date: Mon, 7 Apr 2025 18:15:43 -0400 Subject: [PATCH] [Bugfix] Fix guidance backend for Qwen models (#16210) Signed-off-by: Benjamin Chislett --- vllm/v1/structured_output/backend_guidance.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/vllm/v1/structured_output/backend_guidance.py b/vllm/v1/structured_output/backend_guidance.py index ec7e6271..9150a285 100644 --- a/vllm/v1/structured_output/backend_guidance.py +++ b/vllm/v1/structured_output/backend_guidance.py @@ -46,7 +46,8 @@ class GuidanceBackend(StructuredOutputBackend): in vllm_config.decoding_config.guided_decoding_backend) tokenizer = tokenizer_group.get_lora_tokenizer(None) - self.ll_tokenizer = llguidance_hf.from_tokenizer(tokenizer, None) + self.ll_tokenizer = llguidance_hf.from_tokenizer( + tokenizer, self.vocab_size) def compile_grammar(self, request_type: StructuredOutputOptions, grammar_spec: str) -> StructuredOutputGrammar: