[Model][LoRA] Enable LoRA support for ModernBertModel (#57148)

Signed-off-by: linitra24 <renshuang.zhou@daocloud.io>

docs/models/pooling_models/embed.md

@@ -47,7 +47,7 @@ You can compute pairwise similarity scores to build a similarity matrix using th
 | `JinaEmbeddingsV5Model`<sup>C</sup> | Qwen3-decoder or EuroBERT-encoder backbone with task-specific LoRA adapters | `jinaai/jina-embeddings-v5-text-small`, `jinaai/jina-embeddings-v5-text-nano` (see note) | ✅︎ | ✅︎ |
 | `LlamaBidirectionalModel`<sup>C</sup> | Llama-based with bidirectional attention | `nvidia/llama-nemotron-embed-1b-v2`, etc. | ✅︎ | ✅︎ |
 | `LlamaModel`<sup>C</sup>, `LlamaForCausalLM`<sup>C</sup>, `MistralModel`<sup>C</sup>, etc. | Llama-based | `intfloat/e5-mistral-7b-instruct`, etc. | ✅︎ | ✅︎ |
-| `ModernBertModel` | ModernBERT-based | `Alibaba-NLP/gte-modernbert-base`, etc. | | |
+| `ModernBertModel` | ModernBERT-based | `Alibaba-NLP/gte-modernbert-base`, etc. | ✅︎ | |
 | `NomicBertModel` | Nomic BERT | `nomic-ai/nomic-embed-text-v1`, `nomic-ai/nomic-embed-text-v2-moe`, `Snowflake/snowflake-arctic-embed-m-long`, etc. | | |
 | `Qwen2Model`<sup>C</sup>, `Qwen2ForCausalLM`<sup>C</sup> | Qwen2-based | `ssmits/Qwen2-7B-Instruct-embed-base` (see note), `Alibaba-NLP/gte-Qwen2-7B-instruct` (see note), etc. | ✅︎ | ✅︎ |
 | `Qwen3Model`<sup>C</sup>, `Qwen3ForCausalLM`<sup>C</sup> | Qwen3-based | `Qwen/Qwen3-Embedding-0.6B`, etc. | ✅︎ | ✅︎ |

vllm/model_executor/models/modernbert.py

@@ -32,7 +32,7 @@ from vllm.model_executor.layers.vocab_parallel_embedding import VocabParallelEmb
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader
 from vllm.sequence import IntermediateTensors
 
-from .interfaces import SupportsCrossEncoding
+from .interfaces import SupportsCrossEncoding, SupportsLoRA
 from .interfaces_base import attn_type, default_pooling_type
 from .utils import AutoWeightsLoader, WeightsMapper, maybe_prefix
 
@@ -262,7 +262,7 @@ class ModernBertEncoderLayer(nn.Module):
 
 @support_torch_compile
 @default_pooling_type(seq_pooling_type="CLS")
-class ModernBertModel(nn.Module):
+class ModernBertModel(nn.Module, SupportsLoRA):
     hf_to_vllm_mapper = WeightsMapper(
         orig_to_new_prefix={
             "model.layers.": "encoder_layer.layers.",
@@ -271,6 +271,11 @@ class ModernBertModel(nn.Module):
         }
     )
 
+    packed_modules_mapping = {
+        "Wqkv": ["Wqkv"],
+        "Wi": ["Wi"],
+    }
+
     def __init__(
         self,
         vllm_config: VllmConfig,