biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Fix duplicate words in comments (#36713)

Browse Source 
Signed-off-by: Hongbin10 <jdmjdm1998@163.com>
This commit is contained in:
Hongbin Guo
2026-03-11 12:28:31 +08:00
committed by GitHub
parent 5f77ef15ae
commit 4bf533623b
6 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/transformers/pooling.py
View File

@@ -57,7 +57,7 @@ class SequenceClassificationMixin(SupportsCrossEncoding, VllmModelForPooling):
pooler_config = vllm_config.model_config.pooler_config
assert pooler_config is not None
# Certain information about the the model and classifier can only be
# Certain information about the model and classifier can only be
# inferred from the `ForSequenceClassification` class. Therefore, we
# instantiate it on the "meta" device to avoid allocating GPU memory.
with torch.device("meta"):