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] Fix lazy imports involving outlines_core (#27158)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
22quinn committed
Oct 18, 2025 at 19:35 UTC
191eed0bb981912712d4a5ccc9544749af7ab3f4
2 files changed
+4
vllm/v1/structured_output/backend_outlines.py
+2
@@ -1,6 +1,8 @@
1
# SPDX-License-Identifier: Apache-2.0
2
# SPDX-FileCopyrightText: Copyright 2025-present the Outlines developers
3
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
4
+from __future__ import annotations
5
+
6
import ast
7
import importlib
8
import json
vllm/v1/structured_output/utils.py
+2
@@ -1,5 +1,7 @@
1
# SPDX-License-Identifier: Apache-2.0
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
+from __future__ import annotations
4
+
5
import hashlib
6
import importlib.metadata
7
import os