Skip to content

[Bugfix] Fix vLLM startup to avoid a hard dependency on Outlines #20875

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[Bugfix] Fix vLLM startup to avoid a hard dependency on Outlines #20875

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions vllm/v1/structured_output/backend_outlines.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,6 @@
import torch
from regex import escape as regex_escape

from vllm.model_executor.guided_decoding.outlines_logits_processors import (
OutlinesVocabulary, get_cache, get_vocabulary)
from vllm.sampling_params import SamplingParams
from vllm.utils import LazyLoader
from vllm.v1.structured_output.backend_types import (StructuredOutputBackend,
Expand All @@ -24,6 +22,8 @@
if TYPE_CHECKING:
import outlines_core as oc
import outlines_core.json_schema as json_schema
from vllm.model_executor.guided_decoding.outlines_logits_processors import (
OutlinesVocabulary, get_cache, get_vocabulary)
else:
oc = LazyLoader("oc", globals(), "outlines_core")
json_schema = LazyLoader("json_schema", globals(),
Expand Down
Loading