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 14, 05:30 UTC
[Bugfix] Update import path for bc_linter_include (#24766)
Signed-off-by: Mohammad Miadh Angkad <mangkad.bsdsba2027@aim.edu>
Mohammad Miadh Angkad committed
Sep 18, 2025 at 04:33 UTC
883131544faf78f31f85a0350f74ea913ee6ef9c
1 file changed
+1
-1
vllm/v1/core/sched/output.py
+1
-1
@@ -6,7 +6,7 @@ from __future__ import annotations
6
from dataclasses import dataclass
7
from typing import TYPE_CHECKING, Optional
8
9
-from vllm import bc_linter_include
9
+from vllm._bc_linter import bc_linter_include
10
11
if TYPE_CHECKING:
12
import numpy as np