[Doc] docs: fix note formatting for pooling models (#47701)

Signed-off-by: Sungjae Lee <33976427+llsj14@users.noreply.github.com>
Signed-off-by: Sungjae Lee <sung-jae.lee@navercorp.com>
This commit is contained in:
Sungjae Lee
2026-07-06 09:01:10 +00:00
committed by GitHub
parent 736f1a5907
commit 3d7f357ebf
+2 -3
View File
@@ -2,8 +2,7 @@
!!! note
We currently support pooling models primarily for convenience. This is not guaranteed to provide any performance
improvements over using Hugging Face Transformers or Sentence Transformers directly.
improvements over using Hugging Face Transformers or Sentence Transformers directly.
We plan to optimize pooling models in vLLM. Please comment on <https://github.com/vllm-project/vllm/issues/21796> if you have any suggestions!
## What are pooling models?
@@ -63,7 +62,7 @@ please refer to [IO Processor Plugins](../../design/io_processor_plugins.md).
!!! note
Within classification tasks, there is a specialized subcategory: Cross-encoder (aka reranker) models. These models
are a subset of classification models that accept two prompts as input and output num_labels equal to 1.
are a subset of classification models that accept two prompts as input and output num_labels equal to 1.
### Pooling Types