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
[Minor] Fix type (#22347)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Woosuk Kwon committed
Aug 6, 2025 at 02:22 UTC
9edd1db02bc6dce6da503503a373657f3466a78b
1 file changed
+2
-2
vllm/entrypoints/harmony_utils.py
+2
-2
@@ -1,7 +1,7 @@
1
# SPDX-License-Identifier: Apache-2.0
2
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
3
import datetime
4
-from collections.abc import Iterable
4
+from collections.abc import Iterable, Sequence
5
from typing import Literal, Optional
6
7
from openai.types.responses.tool import Tool
@@ -120,7 +120,7 @@ def parse_output_into_messages(token_ids: Iterable[int]) -> StreamableParser:
120
121
122
def parse_chat_output(
123
- token_ids: list[int]) -> tuple[Optional[str], Optional[str], bool]:
123
+ token_ids: Sequence[int]) -> tuple[Optional[str], Optional[str], bool]:
124
parser = parse_output_into_messages(token_ids)
125
output_msgs = parser.messages
126
if len(output_msgs) == 0: