Skip to content

GitLab

Unverified Commit 9ca710e5 authored by Roger Wang's avatar Roger Wang Committed by GitHub
Browse files

[CI][V1] Fix passing `tokenizer` as kwarg to `validate_guidance_grammar` (#16117) 


Signed-off-by: default avatarRoger Wang <ywang@roblox.com>
parent eb07c8cb
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 2 deletions
vllm/v1/structured_output/backend_guidance.py
View file @ 9ca710e5
...@@ -163,7 +163,6 @@ def validate_guidance_grammar( ...@@ -163,7 +163,6 @@ def validate_guidance_grammar(
tokenizer: Optional[llguidance.LLTokenizer] = None) -> None: tokenizer: Optional[llguidance.LLTokenizer] = None) -> None:
tp, grm = get_structured_output_key(sampling_params) tp, grm = get_structured_output_key(sampling_params)
guidance_grm = serialize_guidance_grammar(tp, grm) guidance_grm = serialize_guidance_grammar(tp, grm)
err = llguidance.LLMatcher.validate_grammar(guidance_grm, err = llguidance.LLMatcher.validate_grammar(guidance_grm, tokenizer)
tokenizer=tokenizer)
if err: if err:
raise ValueError(f"Grammar error: {err}") raise ValueError(f"Grammar error: {err}")
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment