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
[CI] Fix pre commit issue (#20782)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Wentao Ye committed
Jul 10, 2025 at 15:48 UTC
299252ea8243db5c783fbaa4162d611ad10cf2f4
1 file changed
+2
-2
vllm/entrypoints/openai/serving_score.py
+2
-2
@@ -216,8 +216,8 @@ class ServingScores(OpenAIServing):
216
# cross_encoder models defaults to using pad_token.
217
tokenized_prompts = await asyncio.gather(*(
218
tokenize_async(
219
- text=t1, # type: ignore[arg-type]
220
- text_pair=t2, # type: ignore[arg-type]
219
+ text=t1, # type: ignore[arg-type]
220
+ text_pair=t2, # type: ignore[arg-type]
221
**tokenization_kwargs) for t1, t2 in input_pairs))
222
else:
223
# `llm as reranker` models defaults to not using pad_token.