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 15, 02:15 UTC
[Bugfix] fix define of RerankDocument (#20877)
Signed-off-by: liuchenlong <liuchenlong@xiaohongshu.com> Co-authored-by: liuchenlong <liuchenlong@xiaohongshu.com>
Liuchenlong committed
Jul 13, 2025 at 22:32 UTC
211b6a611328ba472576cd8db2deea0ec05d9a83
1 file changed
+3
-2
vllm/entrypoints/openai/protocol.py
+3
-2
@@ -30,7 +30,8 @@ from typing_extensions import TypeAlias
30
from vllm import envs
31
from vllm.entrypoints.chat_utils import (ChatCompletionMessageParam,
32
random_tool_call_id)
33
-from vllm.entrypoints.score_utils import ScoreMultiModalParam
33
+from vllm.entrypoints.score_utils import (ScoreContentPartParam,
34
+ ScoreMultiModalParam)
35
from vllm.logger import init_logger
36
from vllm.pooling_params import PoolingParams
37
from vllm.sampling_params import (BeamSearchParams, GuidedDecodingParams,
@@ -1354,7 +1355,7 @@ class RerankRequest(OpenAIBaseModel):
1355
1356
class RerankDocument(BaseModel):
1357
text: Optional[str] = None
1357
- multi_modal: Optional[ScoreMultiModalParam] = None
1358
+ multi_modal: Optional[ScoreContentPartParam] = None
1359
1360
1361
class RerankResult(BaseModel):