[Model] Enable LoRA support for PaliGemma (#31656)

Signed-off-by: 赵策 <alcor@mac.mynetworksettings.com>
Signed-off-by: Alcor <alcor_zhao@outlook.com>
Co-authored-by: 赵策 <alcor@mac.mynetworksettings.com>

docs/models/supported_models.md

@@ -716,7 +716,7 @@ These models primarily accept the [`LLM.generate`](./generative_models.md#llmgen
 | `Ovis` | Ovis2, Ovis1.6 | T + I<sup>+</sup> | `AIDC-AI/Ovis2-1B`, `AIDC-AI/Ovis1.6-Llama3.2-3B`, etc. | | ✅︎ |
 | `Ovis2_5` | Ovis2.5 | T + I<sup>+</sup> + V | `AIDC-AI/Ovis2.5-9B`, etc. | | |
 | `PaddleOCRVLForConditionalGeneration` | Paddle-OCR | T + I<sup>+</sup> | `PaddlePaddle/PaddleOCR-VL`, etc. | | |
-| `PaliGemmaForConditionalGeneration` | 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. | | ✅︎ |
+| `PaliGemmaForConditionalGeneration` | 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. | ✅︎ | ✅︎ |
 | `Phi3VForCausalLM` | Phi-3-Vision, Phi-3.5-Vision | T + I<sup>E+</sup> | `microsoft/Phi-3-vision-128k-instruct`, `microsoft/Phi-3.5-vision-instruct`, etc. | | ✅︎ |
 | `Phi4MMForCausalLM` | Phi-4-multimodal | T + I<sup>+</sup> / T + A<sup>+</sup> / I<sup>+</sup> + A<sup>+</sup> | `microsoft/Phi-4-multimodal-instruct`, etc. | ✅︎ | ✅︎ |
 | `PixtralForConditionalGeneration` | Ministral 3 (Mistral format), Mistral 3 (Mistral format), Mistral Large 3 (Mistral format), Pixtral (Mistral format) | T + I<sup>+</sup> | `mistralai/Ministral-3-3B-Instruct-2512`, `mistralai/Mistral-Small-3.1-24B-Instruct-2503`, `mistralai/Mistral-Large-3-675B-Instruct-2512` `mistralai/Pixtral-12B-2409` etc. | | ✅︎ |

vllm/model_executor/models/paligemma.py

@@ -35,7 +35,13 @@ from vllm.multimodal.profiling import BaseDummyInputsBuilder
 from vllm.sequence import IntermediateTensors
 from vllm.utils.tensor_schema import TensorSchema, TensorShape
 
-from .interfaces import MultiModalEmbeddings, SupportsMultiModal, SupportsPP
+from .interfaces import (
+    MultiModalEmbeddings,
+    SupportsLoRA,
+    SupportsMultiModal,
+    SupportsPP,
+)
+from .module_mapping import MultiModelKeys
 from .siglip import SiglipVisionModel
 from .utils import (
     AutoWeightsLoader,
@@ -250,7 +256,9 @@ class PaliGemmaMultiModalProcessor(BaseMultiModalProcessor[PaliGemmaProcessingIn
     info=PaliGemmaProcessingInfo,
     dummy_inputs=PaliGemmaDummyInputsBuilder,
 )
-class PaliGemmaForConditionalGeneration(nn.Module, SupportsMultiModal, SupportsPP):
+class PaliGemmaForConditionalGeneration(
+    nn.Module, SupportsLoRA, SupportsMultiModal, SupportsPP
+):
     packed_modules_mapping = {
         "qkv_proj": [
             "q_proj",
@@ -406,3 +414,16 @@ class PaliGemmaForConditionalGeneration(nn.Module, SupportsMultiModal, SupportsP
     def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]) -> set[str]:
         loader = AutoWeightsLoader(self)
         return loader.load_weights(weights, mapper=self.hf_to_vllm_mapper)
+
+    def get_mm_mapping(self) -> MultiModelKeys:
+        return MultiModelKeys.from_string_field(
+            language_model="language_model",
+            connector="multi_modal_projector",
+            tower_model="vision_tower",
+        )
+
+    def get_num_mm_encoder_tokens(self, num_image_tokens: int) -> int:
+        return num_image_tokens
+
+    def get_num_mm_connector_tokens(self, num_vision_tokens: int) -> int:
+        return num_vision_tokens