diff --git a/docs/source/models/supported_models.md b/docs/source/models/supported_models.md
index 1fde1761672e..c9140bd06e89 100644
--- a/docs/source/models/supported_models.md
+++ b/docs/source/models/supported_models.md
@@ -847,7 +847,7 @@ See [this page](#generative-models) for more information on how to use generativ
   * ✅︎
   * ✅︎
 - * `PaliGemmaForConditionalGeneration`
-  * PaliGemma (see note), PaliGemma 2 (see note)
+  * PaliGemma ⚠️, PaliGemma 2 ⚠️
   * T + I<sup>E</sup>
   * `google/paligemma-3b-pt-224`, `google/paligemma-3b-mix-224`, `google/paligemma2-3b-ft-docci-448`, etc.
   *
@@ -917,6 +917,12 @@ See [this page](#generative-models) for more information on how to use generativ
 <sup>E</sup> Pre-computed embeddings can be inputted for this modality.  
 <sup>+</sup> Multiple items can be inputted per text prompt for this modality.
 
+:::{warning}
+vLLM does not currently support PrefixLM attention mask, so our PaliGemma implementation uses regular causal attention, which causes the model output to be unstable.
+
+We may deprecate this model series in a future release.
+:::
+
 :::{note}
 `h2oai/h2ovl-mississippi-2b` will be available in V1 once we support backends other than FlashAttention.
 :::
@@ -930,10 +936,6 @@ The official `openbmb/MiniCPM-V-2` doesn't work yet, so we need to use a fork (`
 For more details, please see: <gh-pr:4087#issuecomment-2250397630>
 :::
 
-:::{note}
-Currently the PaliGemma model series is implemented without PrefixLM attention mask. This model series may be deprecated in a future release.
-:::
-
 :::{note}
 To use Qwen2.5-VL series models, you have to install Hugging Face Transformers library from source via `pip install git+https://github.com/huggingface/transformers`.
 :::