gemma3n lora

Signed-off-by: NickLucche <[email protected]>

Author: NickLucche

docs/models/supported_models.md

@@ -350,7 +350,7 @@ th {
 | `GemmaForCausalLM` | Gemma | `google/gemma-2b`, `google/gemma-1.1-2b-it`, etc. | ✅︎ | ✅︎ | ✅︎ |
 | `Gemma2ForCausalLM` | Gemma 2 | `google/gemma-2-9b`, `google/gemma-2-27b`, etc. | ✅︎ | ✅︎ | ✅︎ |
 | `Gemma3ForCausalLM` | Gemma 3 | `google/gemma-3-1b-it`, etc. | ✅︎ | ✅︎ | ✅︎ |
-| `Gemma3nForCausalLM` | Gemma 3n | `google/gemma-3n-E2B-it`, `google/gemma-3n-E4B-it`, etc. | | | ✅︎ |
+| `Gemma3nForCausalLM` | Gemma 3n | `google/gemma-3n-E2B-it`, `google/gemma-3n-E4B-it`, etc. | ✅︎ | | ✅︎ |
 | `GlmForCausalLM` | GLM-4 | `zai-org/glm-4-9b-chat-hf`, etc. | ✅︎ | ✅︎ | ✅︎ |
 | `Glm4ForCausalLM` | GLM-4-0414 | `zai-org/GLM-4-32B-0414`, etc. | ✅︎ | ✅︎ | ✅︎ |
 | `Glm4MoeForCausalLM` | GLM-4.5 | `zai-org/GLM-4.5`, etc. | ✅︎ | ✅︎ | ✅︎ |
@@ -624,7 +624,7 @@ These models primarily accept the [`LLM.generate`](./generative_models.md#llmgen
 | `Florence2ForConditionalGeneration` | Florence-2 | T + I | `microsoft/Florence-2-base`, `microsoft/Florence-2-large`, etc. | | | |
 | `FuyuForCausalLM` | Fuyu | T + I | `adept/fuyu-8b`, etc. | | ✅︎ | ✅︎ |
 | `Gemma3ForConditionalGeneration` | Gemma 3 | T + I<sup>+</sup> | `google/gemma-3-4b-it`, `google/gemma-3-27b-it`, etc. | ✅︎ | ✅︎ | ⚠️ |
-| `Gemma3nForConditionalGeneration` | Gemma 3n | T + I + A | `google/gemma-3n-E2B-it`, `google/gemma-3n-E4B-it`, etc. | | | ✅︎ |
+| `Gemma3nForConditionalGeneration` | Gemma 3n | T + I + A | `google/gemma-3n-E2B-it`, `google/gemma-3n-E4B-it`, etc. | ✅︎ | | ✅︎ |
 | `GLM4VForCausalLM`<sup>^</sup> | GLM-4V | T + I | `zai-org/glm-4v-9b`, `zai-org/cogagent-9b-20241220`, etc. | ✅︎ | ✅︎ | ✅︎ |
 | `Glm4vForConditionalGeneration` | GLM-4.1V-Thinking | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.1V-9B-Thinking`, etc. | ✅︎ | ✅︎ | ✅︎ |
 | `Glm4vMoeForConditionalGeneration` | GLM-4.5V | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.5V`, etc. | ✅︎ | ✅︎ | ✅︎ |

vllm/model_executor/models/gemma3n_mm.py

@@ -5,14 +5,14 @@
 
 import torch
 from torch import nn
+
 from transformers import AutoModel, BatchFeature
 from transformers.models.gemma3n import (Gemma3nAudioConfig,
                                          Gemma3nAudioFeatureExtractor,
                                          Gemma3nConfig, Gemma3nProcessor,
                                          Gemma3nTextConfig,
                                          Gemma3nVisionConfig)
 from transformers.models.siglip import SiglipImageProcessorFast
-
 from vllm.config import VllmConfig
 from vllm.logger import init_logger
 from vllm.model_executor.layers.layernorm import RMSNorm
@@ -40,7 +40,7 @@
 from vllm.multimodal.profiling import BaseDummyInputsBuilder
 from vllm.sequence import IntermediateTensors
 
-from .interfaces import MultiModalEmbeddings, SupportsMultiModal
+from .interfaces import MultiModalEmbeddings, SupportsLoRA, SupportsMultiModal
 from .utils import (AutoWeightsLoader, WeightsMapper, flatten_bn,
                     init_vllm_registered_model, maybe_prefix,
                     merge_multimodal_embeddings)
@@ -410,7 +410,8 @@ def forward(
 @MULTIMODAL_REGISTRY.register_processor(Gemma3nMultiModalProcessor,
                                         info=Gemma3nProcessingInfo,
                                         dummy_inputs=Gemma3nDummyInputsBuilder)
-class Gemma3nForConditionalGeneration(nn.Module, SupportsMultiModal):
+class Gemma3nForConditionalGeneration(nn.Module, SupportsMultiModal,
+                                      SupportsLoRA):
     packed_modules_mapping = {
         "qkv_proj": [
             "q_proj",