diff --git a/src/liger_kernel/transformers/model/qwen2_5_vl.py b/src/liger_kernel/transformers/model/qwen2_5_vl.py
index a3271f53..41214d8c 100644
--- a/src/liger_kernel/transformers/model/qwen2_5_vl.py
+++ b/src/liger_kernel/transformers/model/qwen2_5_vl.py
@@ -5,12 +5,13 @@ from typing import Union
 
 import torch
 
-from torch.nn import CrossEntropyLoss
 from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLCausalLMOutputWithPast
+from transformers.utils import can_return_tuple
 
 from liger_kernel.transformers.model.loss_utils import LigerForCausalLMLoss
 
 
+@can_return_tuple
 def lce_forward(
     self,
     input_ids: torch.LongTensor = None,
@@ -34,14 +35,22 @@ def lce_forward(
     **kwargs,
 ) -> Union[Tuple, Qwen2_5_VLCausalLMOutputWithPast]:
     r"""
-    Copy paste Qwen2_5_VL's forward but replace torch cross entropy with liger fused linear cross entropy
-    Args:
-        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
-            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
-            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
-            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
-
-    Returns:
+    labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
+        Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
+        config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
+        (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
+    pixel_values_videos (`torch.FloatTensor` of shape `(seq_length, num_channels * temporal_size * image_size * image_size)):
+        The tensors corresponding to the input videos. Pixel values can be obtained using
+        [`AutoImageProcessor`]. See [`Qwen2_5_VLImageProcessor.__call__`] for details. [`Qwen2_5_VLProcessor`] uses
+        [`Qwen2_5_VLImageProcessor`] for processing videos.
+    image_grid_thw (`torch.LongTensor` of shape `(num_images, 3)`, *optional*):
+        The temporal, height and width of feature shape of each image in LLM.
+    video_grid_thw (`torch.LongTensor` of shape `(num_videos, 3)`, *optional*):
+        The temporal, height and width of feature shape of each video in LLM.
+    rope_deltas (`torch.LongTensor` of shape `(batch_size, )`, *optional*):
+        The rope index difference between sequence length and multimodal rope.
+    second_per_grid_ts (`torch.Tensor` of shape `(num_videos)`, *optional*):
+        The time interval (in seconds) for each grid along the temporal dimension in the 3D position IDs.
 
     Example:
 
@@ -73,78 +82,20 @@ def lce_forward(
     >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
     "The image shows a street scene with a red stop sign in the foreground. In the background, there is a large red gate with Chinese characters ..."
     ```"""
+
     output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
     output_hidden_states = (
         output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
     )
     return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
-    if inputs_embeds is None:
-        inputs_embeds = self.model.embed_tokens(input_ids)
-        if pixel_values is not None:
-            pixel_values = pixel_values.type(self.visual.dtype)
-            image_embeds = self.visual(pixel_values, grid_thw=image_grid_thw)
-            n_image_tokens = (input_ids == self.config.image_token_id).sum().item()
-            n_image_features = image_embeds.shape[0]
-            if n_image_tokens != n_image_features:
-                raise ValueError(
-                    f"Image features and image tokens do not match: tokens: {n_image_tokens}, features {n_image_features}"
-                )
-
-            mask = input_ids == self.config.image_token_id
-            mask_unsqueezed = mask.unsqueeze(-1)
-            mask_expanded = mask_unsqueezed.expand_as(inputs_embeds)
-            image_mask = mask_expanded.to(inputs_embeds.device)
-
-            image_embeds = image_embeds.to(inputs_embeds.device, inputs_embeds.dtype)
-            inputs_embeds = inputs_embeds.masked_scatter(image_mask, image_embeds)
-
-        if pixel_values_videos is not None:
-            pixel_values_videos = pixel_values_videos.type(self.visual.dtype)
-            video_embeds = self.visual(pixel_values_videos, grid_thw=video_grid_thw)
-            n_video_tokens = (input_ids == self.config.video_token_id).sum().item()
-            n_video_features = video_embeds.shape[0]
-            if n_video_tokens != n_video_features:
-                raise ValueError(
-                    f"Video features and video tokens do not match: tokens: {n_video_tokens}, features {n_video_features}"
-                )
-
-            mask = input_ids == self.config.video_token_id
-            mask_unsqueezed = mask.unsqueeze(-1)
-            mask_expanded = mask_unsqueezed.expand_as(inputs_embeds)
-            video_mask = mask_expanded.to(inputs_embeds.device)
-
-            video_embeds = video_embeds.to(inputs_embeds.device, inputs_embeds.dtype)
-            inputs_embeds = inputs_embeds.masked_scatter(video_mask, video_embeds)
-
-        if attention_mask is not None:
-            attention_mask = attention_mask.to(inputs_embeds.device)
-
-    # if we get 4D attention mask we cannot calculate rope deltas anymore. TODO @raushan fixme
-    if position_ids is None and (attention_mask is None or attention_mask.ndim == 2):
-        # calculate RoPE index once per generation in the pre-fill stage only
-        if (cache_position is not None and cache_position[0] == 0) or self.rope_deltas is None:
-            position_ids, rope_deltas = self.get_rope_index(
-                input_ids,
-                image_grid_thw,
-                video_grid_thw,
-                second_per_grid_ts,
-                attention_mask,
-            )
-            self.rope_deltas = rope_deltas
-        # then use the prev pre-calculated rope-deltas to get the correct position ids
-        else:
-            batch_size, seq_length, _ = inputs_embeds.shape
-            delta = (cache_position[0] + self.rope_deltas).to(inputs_embeds.device) if cache_position is not None else 0
-            position_ids = torch.arange(seq_length, device=inputs_embeds.device)
-            position_ids = position_ids.view(1, -1).expand(batch_size, -1)
-            if cache_position is not None:  # otherwise `deltas` is an int `0`
-                delta = delta.repeat_interleave(batch_size // delta.shape[0], dim=0)
-            position_ids = position_ids.add(delta)
-            position_ids = position_ids.unsqueeze(0).expand(3, -1, -1)
-
     outputs = self.model(
-        input_ids=None,
+        input_ids=input_ids,
+        pixel_values=pixel_values,
+        pixel_values_videos=pixel_values_videos,
+        image_grid_thw=image_grid_thw,
+        video_grid_thw=video_grid_thw,
+        second_per_grid_ts=second_per_grid_ts,
         position_ids=position_ids,
         attention_mask=attention_mask,
         past_key_values=past_key_values,
@@ -180,19 +131,10 @@ def lce_forward(
         )
     else:
         logits = self.lm_head(hidden_states)
+
+        loss = None
         if labels is not None:
-            # Upcast to float if we need to compute the loss to avoid potential precision issues
-            logits = logits.float()
-            # Shift so that tokens < n predict n
-            shift_logits = logits[..., :-1, :].contiguous()
-            shift_labels = labels[..., 1:].contiguous()
-            # Flatten the tokens
-            loss_fct = CrossEntropyLoss()
-            shift_logits = shift_logits.view(-1, self.config.vocab_size)
-            shift_labels = shift_labels.view(-1)
-            # Enable model parallelism
-            shift_labels = shift_labels.to(shift_logits.device)
-            loss = loss_fct(shift_logits, shift_labels)
+            loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size)
 
     if not return_dict:
         output = (logits,) + outputs[1:]
@@ -204,5 +146,5 @@ def lce_forward(
         past_key_values=outputs.past_key_values,
         hidden_states=outputs.hidden_states,
         attentions=outputs.attentions,
-        rope_deltas=rope_deltas,
+        rope_deltas=outputs.rope_deltas,
     )
diff --git a/src/liger_kernel/transformers/model/qwen2_vl.py b/src/liger_kernel/transformers/model/qwen2_vl.py
index fb30df11..342ace1a 100644
--- a/src/liger_kernel/transformers/model/qwen2_vl.py
+++ b/src/liger_kernel/transformers/model/qwen2_vl.py
@@ -5,14 +5,13 @@ from typing import Union
 
 import torch
 
-from packaging import version
-from torch.nn import CrossEntropyLoss
-from transformers import __version__ as transformers_version
 from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLCausalLMOutputWithPast
+from transformers.utils import can_return_tuple
 
 from liger_kernel.transformers.model.loss_utils import LigerForCausalLMLoss
 
 
+@can_return_tuple
 def lce_forward(
     self,
     input_ids: torch.LongTensor = None,
@@ -35,15 +34,20 @@ def lce_forward(
     **kwargs,
 ) -> Union[Tuple, Qwen2VLCausalLMOutputWithPast]:
     r"""
-    Copy paste Qwen2VL's forward but replace torch cross entropy with liger fused linear cross entropy
-
-    Args:
-        labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
-            Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
-            config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
-            (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
-
-    Returns:
+    labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
+        Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
+        config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
+        (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
+    pixel_values_videos (`torch.FloatTensor` of shape `(seq_length, num_channels * temporal_size * image_size * image_size)):
+        The tensors corresponding to the input videos. Pixel values can be obtained using
+        [`AutoImageProcessor`]. See [`Qwen2VLImageProcessor.__call__`] for details. [`Qwen2VLProcessor`] uses
+        [`Qwen2VLImageProcessor`] for processing videos.
+    image_grid_thw (`torch.LongTensor` of shape `(num_images, 3)`, *optional*):
+        The temporal, height and width of feature shape of each image in LLM.
+    video_grid_thw (`torch.LongTensor` of shape `(num_videos, 3)`, *optional*):
+        The temporal, height and width of feature shape of each video in LLM.
+    rope_deltas (`torch.LongTensor` of shape `(batch_size, )`, *optional*):
+        The rope index difference between sequence length and multimodal rope.
 
     Example:
 
@@ -75,80 +79,19 @@ def lce_forward(
     >>> tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
     "The image shows a street scene with a red stop sign in the foreground. In the background, there is a large red gate with Chinese characters ..."
     ```"""
+
     output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
     output_hidden_states = (
         output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
     )
     return_dict = return_dict if return_dict is not None else self.config.use_return_dict
 
-    if inputs_embeds is None:
-        inputs_embeds = self.model.embed_tokens(input_ids)
-        if pixel_values is not None:
-            pixel_values = pixel_values.type(self.visual.get_dtype())
-            image_embeds = self.visual(pixel_values, grid_thw=image_grid_thw)
-            n_image_tokens = (input_ids == self.config.image_token_id).sum().item()
-            n_image_features = image_embeds.shape[0]
-            if n_image_tokens != n_image_features:
-                raise ValueError(
-                    f"Image features and image tokens do not match: tokens: {n_image_tokens}, features {n_image_features}"
-                )
-            image_mask = (
-                (input_ids == self.config.image_token_id)
-                .unsqueeze(-1)
-                .expand_as(inputs_embeds)
-                .to(inputs_embeds.device)
-            )
-            image_embeds = image_embeds.to(inputs_embeds.device, inputs_embeds.dtype)
-            inputs_embeds = inputs_embeds.masked_scatter(image_mask, image_embeds)
-
-        if pixel_values_videos is not None:
-            pixel_values_videos = pixel_values_videos.type(self.visual.get_dtype())
-            video_embeds = self.visual(pixel_values_videos, grid_thw=video_grid_thw)
-            n_video_tokens = (input_ids == self.config.video_token_id).sum().item()
-            n_video_features = video_embeds.shape[0]
-            if n_video_tokens != n_video_features:
-                raise ValueError(
-                    f"Video features and video tokens do not match: tokens: {n_video_tokens}, features {n_video_features}"
-                )
-            video_mask = (
-                (input_ids == self.config.video_token_id)
-                .unsqueeze(-1)
-                .expand_as(inputs_embeds)
-                .to(inputs_embeds.device)
-            )
-            video_embeds = video_embeds.to(inputs_embeds.device, inputs_embeds.dtype)
-            inputs_embeds = inputs_embeds.masked_scatter(video_mask, video_embeds)
-
-        if attention_mask is not None:
-            attention_mask = attention_mask.to(inputs_embeds.device)
-
-    if version.parse(transformers_version) > version.parse("4.46.3"):
-        # NOTE: this bug fix for qwen2-vl is not applied until transformers 4.47.0
-        # https://github.com/huggingface/transformers/issues/33401
-        # While correct, this breaks equivalence with past versions of Qwen2-VL from
-        # transformers and leads to failed tests or users noticing differences in results.
-        # TODO: remove above conditional when liger drops support for transformers<4.47.0
-        # if we get 4D attention mask we cannot calculate rope deltas anymore. TODO @raushan fixme
-        if position_ids is None and (attention_mask is None or attention_mask.ndim == 2):
-            # calculate RoPE index once per generation in the pre-fill stage only
-            if (cache_position is not None and cache_position[0] == 0) or self.rope_deltas is None:
-                position_ids, rope_deltas = self.get_rope_index(
-                    input_ids, image_grid_thw, video_grid_thw, attention_mask
-                )
-                self.rope_deltas = rope_deltas
-            # then use the prev pre-calculated rope-deltas to get the correct position ids
-            else:
-                batch_size, seq_length, _ = inputs_embeds.shape
-                delta = cache_position[0] + self.rope_deltas if cache_position is not None else 0
-                position_ids = torch.arange(seq_length, device=inputs_embeds.device)
-                position_ids = position_ids.view(1, -1).expand(batch_size, -1)
-                if cache_position is not None:  # otherwise `deltas` is an int `0`
-                    delta = delta.repeat_interleave(batch_size // delta.shape[0], dim=0)
-                position_ids = position_ids.add(delta)
-                position_ids = position_ids.unsqueeze(0).expand(3, -1, -1)
-
     outputs = self.model(
-        input_ids=None,
+        input_ids=input_ids,
+        pixel_values=pixel_values,
+        pixel_values_videos=pixel_values_videos,
+        image_grid_thw=image_grid_thw,
+        video_grid_thw=video_grid_thw,
         position_ids=position_ids,
         attention_mask=attention_mask,
         past_key_values=past_key_values,
@@ -184,23 +127,10 @@ def lce_forward(
         )
     else:
         logits = self.lm_head(hidden_states)
-        if labels is not None:
-            # Upcast to float if we need to compute the loss to avoid potential precision issues
-            logits = logits.float()
-            # Shift so that tokens < n predict n
-            shift_logits = logits[..., :-1, :].contiguous()
-            shift_labels = labels[..., 1:].contiguous()
-            # Flatten the tokens
-            loss_fct = CrossEntropyLoss()
-            shift_logits = shift_logits.view(-1, self.config.vocab_size)
-            shift_labels = shift_labels.view(-1)
-            # Enable model parallelism
-            shift_labels = shift_labels.to(shift_logits.device)
-            loss = loss_fct(shift_logits, shift_labels)
 
-    if not return_dict:
-        output = (logits,) + outputs[1:]
-        return (loss,) + output if loss is not None else output
+        loss = None
+        if labels is not None:
+            loss = self.loss_function(logits=logits, labels=labels, vocab_size=self.config.vocab_size)
 
     return Qwen2VLCausalLMOutputWithPast(
         loss=loss,
@@ -208,5 +138,5 @@ def lce_forward(
         past_key_values=outputs.past_key_values,
         hidden_states=outputs.hidden_states,
         attentions=outputs.attentions,
-        rope_deltas=rope_deltas,
+        rope_deltas=outputs.rope_deltas,
     )
diff --git a/src/liger_kernel/transformers/monkey_patch.py b/src/liger_kernel/transformers/monkey_patch.py
index 3356ddac..3e93f5dd 100644
--- a/src/liger_kernel/transformers/monkey_patch.py
+++ b/src/liger_kernel/transformers/monkey_patch.py
@@ -1225,7 +1225,7 @@ def apply_liger_kernel_to_qwen2_vl(
 ) -> None:
     """
     Apply Liger kernels to replace original implementation in HuggingFace Qwen2-VL models.
-    NOTE: Qwen2-VL is not available in transformers<4.45.0
+    NOTE: Qwen2-VL is not supported in transformers<4.52.4
 
     Args:
         cross_entropy (bool): Whether to apply Liger's cross entropy loss. Default is False.
@@ -1239,12 +1239,19 @@ def apply_liger_kernel_to_qwen2_vl(
         model (PreTrainedModel): The model instance to apply Liger kernels to, if the model has already been
         loaded. Default is None.
     """
+    if transformer_version < version.parse("4.52.4"):
+        logger.warning("Qwen2-VL support is only compatible with transformers >= 4.52.4")
+        return
+
     assert not (cross_entropy and fused_linear_cross_entropy), (
         "cross_entropy and fused_linear_cross_entropy cannot both be True."
     )
 
     from transformers.models.qwen2_vl import modeling_qwen2_vl
+    from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VisionTransformerPretrainedModel
+    from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLForConditionalGeneration
     from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLModel
+    from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLTextModel
 
     from liger_kernel.transformers.model.qwen2_vl import lce_forward as qwen2_vl_lce_forward
 
@@ -1266,24 +1273,38 @@ def apply_liger_kernel_to_qwen2_vl(
         # The model instance already exists, so we need to additionally patch the
         # instance variables that reference already-instantiated modules
 
-        # get the base model from the model instance
-        base_model: Qwen2VLModel = getattr(model, model.base_model_prefix, model)
+        if isinstance(model, (Qwen2VLForConditionalGeneration, Qwen2VLModel)):
+            # Note: language_model and visual properties can be accessed throught conditional class for BC.
+            # Not sure if it is subject to changes in the future.
+            # Reference: https://github.com/huggingface/transformers/blob/v4.52.4/src/transformers/models/qwen2_vl/modeling_qwen2_vl.py#L1698
+            text_model: Qwen2VLTextModel = model.language_model
+            vision_model: Qwen2VisionTransformerPretrainedModel = model.visual
+        elif isinstance(model, Qwen2VLTextModel):
+            text_model: Qwen2VLTextModel = model
+            vision_model = None
+        else:
+            # Note: Currently there's no support for patching vision model only. Feel free to raise an issue if needed.
+            raise TypeError(
+                f"Unsupported Qwen2VL model type. `model` must be `Qwen2VLForConditionalGeneration`, `Qwen2VLModel` or `Qwen2VLTextModel`. Got: {type(model)}"
+            )
 
-        if hasattr(model, "visual"):
-            # Patch Qwen2VisionTransformerPretrainedModel
-            for vision_block in model.visual.blocks:
+        # Patch Qwen2VisionTransformerPretrainedModel
+        if vision_model is not None:
+            for vision_block in vision_model.blocks:
                 if layer_norm:
                     _patch_layer_norm_module(vision_block.norm1)
                     _patch_layer_norm_module(vision_block.norm2)
 
-        if rms_norm:
-            _patch_rms_norm_module(base_model.norm)
-        for decoder_layer in base_model.layers:
-            if swiglu:
-                _patch_swiglu_module(decoder_layer.mlp, LigerSwiGLUMLP)
+        # Patch Qwen2VisionTextModel
+        if text_model is not None:
             if rms_norm:
-                _patch_rms_norm_module(decoder_layer.input_layernorm)
-                _patch_rms_norm_module(decoder_layer.post_attention_layernorm)
+                _patch_rms_norm_module(text_model.norm)
+            for decoder_layer in text_model.layers:
+                if swiglu:
+                    _patch_swiglu_module(decoder_layer.mlp, LigerSwiGLUMLP)
+                if rms_norm:
+                    _patch_rms_norm_module(decoder_layer.input_layernorm)
+                    _patch_rms_norm_module(decoder_layer.post_attention_layernorm)
 
 
 def apply_liger_kernel_to_qwen2_5_vl(
@@ -1309,12 +1330,19 @@ def apply_liger_kernel_to_qwen2_5_vl(
         model (PreTrainedModel): The model instance to apply Liger kernels to, if the model has already been
         loaded. Default is None.
     """
+    if transformer_version < version.parse("4.52.4"):
+        logger.warning("Qwen2.5-VL support is only compatible with transformers >= 4.52.4")
+        return
+
     assert not (cross_entropy and fused_linear_cross_entropy), (
         "cross_entropy and fused_linear_cross_entropy cannot both be True."
     )
 
     from transformers.models.qwen2_5_vl import modeling_qwen2_5_vl
+    from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VisionTransformerPretrainedModel
+    from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLForConditionalGeneration
     from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLModel
+    from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLTextModel
 
     from liger_kernel.transformers.model.qwen2_5_vl import lce_forward as qwen2_5_vl_lce_forward
 
@@ -1333,24 +1361,37 @@ def apply_liger_kernel_to_qwen2_5_vl(
         # The model instance already exists, so we need to additionally patch the
         # instance variables that reference already-instantiated modules
 
-        # get the base model from the model instance
-        base_model: Qwen2_5_VLModel = getattr(model, model.base_model_prefix, model)
+        if isinstance(model, (Qwen2_5_VLForConditionalGeneration, Qwen2_5_VLModel)):
+            # Note: language_model and visual properties can be accessed throught conditional class for BC.
+            # Not sure if it is subject to changes in the future.
+            # Reference: https://github.com/huggingface/transformers/blob/v4.52.4/src/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py#L1823
+            text_model: Qwen2_5_VLTextModel = model.language_model
+            vision_model: Qwen2_5_VisionTransformerPretrainedModel = model.visual
+        elif isinstance(model, Qwen2_5_VLTextModel):
+            text_model: Qwen2_5_VLTextModel = model
+            vision_model = None
+        else:
+            # Note: Currently there's no support for patching vision model only. Feel free to raise an issue if needed.
+            raise TypeError(
+                f"Unsupported Qwen2VL model type. `model` must be `Qwen2VLForConditionalGeneration`, `Qwen2VLModel` or `Qwen2VLTextModel`. Got: {type(model)}"
+            )
 
-        if hasattr(model, "visual"):
+        if vision_model is not None:
             # Patch Qwen2_5_VisionTransformerPretrainedModel
             for vision_block in model.visual.blocks:
                 if rms_norm:
                     _patch_rms_norm_module(vision_block.norm1)
                     _patch_rms_norm_module(vision_block.norm2)
 
-        if rms_norm:
-            _patch_rms_norm_module(base_model.norm)
-        for decoder_layer in base_model.layers:
-            if swiglu:
-                _patch_swiglu_module(decoder_layer.mlp, LigerSwiGLUMLP)
+        if text_model is not None:
             if rms_norm:
-                _patch_rms_norm_module(decoder_layer.input_layernorm)
-                _patch_rms_norm_module(decoder_layer.post_attention_layernorm)
+                _patch_rms_norm_module(text_model.norm)
+            for decoder_layer in text_model.layers:
+                if swiglu:
+                    _patch_swiglu_module(decoder_layer.mlp, LigerSwiGLUMLP)
+                if rms_norm:
+                    _patch_rms_norm_module(decoder_layer.input_layernorm)
+                    _patch_rms_norm_module(decoder_layer.post_attention_layernorm)
 
 
 def apply_liger_kernel_to_phi3(
@@ -1571,7 +1612,9 @@ MODEL_TYPE_TO_APPLY_LIGER_FN = {
     "qwen3": apply_liger_kernel_to_qwen3,
     "qwen3_moe": apply_liger_kernel_to_qwen3_moe,
     "qwen2_vl": apply_liger_kernel_to_qwen2_vl,
+    "qwen2_vl_text": apply_liger_kernel_to_qwen2_vl,
     "qwen2_5_vl": apply_liger_kernel_to_qwen2_5_vl,
+    "qwen2_5_vl_text": apply_liger_kernel_to_qwen2_5_vl,
     "phi3": apply_liger_kernel_to_phi3,
     "paligemma": apply_liger_kernel_to_paligemma,
 }
diff --git a/test/convergence/bf16/test_mini_models.py b/test/convergence/bf16/test_mini_models.py
index a4395822..17a2a621 100644
--- a/test/convergence/bf16/test_mini_models.py
+++ b/test/convergence/bf16/test_mini_models.py
@@ -69,20 +69,26 @@ except ImportError:
     MLLAMA_AVAILABLE = False
 
 try:
-    # Qwen2-VL is only available in transformers>4.44.2
+    # Qwen2-VL is only available in transformers>4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2_vl.configuration_qwen2_vl import Qwen2VLConfig
     from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLForConditionalGeneration
 
-    QWEN2_VL_AVAILABLE = True
+    QWEN2_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_VL_AVAILABLE = False
 
 try:
-    # Qwen2.5-VL is only available in transformers>4.48.2
+    # Qwen2.5-VL is only available in transformers>4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2_5_vl.configuration_qwen2_5_vl import Qwen2_5_VLConfig
     from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLForConditionalGeneration
 
-    QWEN2_5_VL_AVAILABLE = True
+    QWEN2_5_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_5_VL_AVAILABLE = False
 
diff --git a/test/convergence/bf16/test_mini_models_multimodal.py b/test/convergence/bf16/test_mini_models_multimodal.py
index a0499687..1cf4d4db 100644
--- a/test/convergence/bf16/test_mini_models_multimodal.py
+++ b/test/convergence/bf16/test_mini_models_multimodal.py
@@ -35,26 +35,34 @@ from test.utils import supports_bfloat16
 from test.utils import train_bpe_tokenizer
 
 try:
-    # Qwen2-VL is only available in transformers>=4.45.0
+    # Qwen2-VL is only available in transformers>=4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2.tokenization_qwen2_fast import Qwen2TokenizerFast
     from transformers.models.qwen2_vl.configuration_qwen2_vl import Qwen2VLConfig
     from transformers.models.qwen2_vl.image_processing_qwen2_vl import Qwen2VLImageProcessor
     from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLForConditionalGeneration
     from transformers.models.qwen2_vl.processing_qwen2_vl import Qwen2VLProcessor
+    from transformers.models.qwen2_vl.video_processing_qwen2_vl import Qwen2VLVideoProcessor
 
-    QWEN2_VL_AVAILABLE = True
+    QWEN2_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_VL_AVAILABLE = False
 
 try:
-    # Qwen2.5-VL is only available in transformers>4.48.2
+    # Qwen2.5-VL is only available in transformers>4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2.tokenization_qwen2_fast import Qwen2TokenizerFast
     from transformers.models.qwen2_5_vl.configuration_qwen2_5_vl import Qwen2_5_VLConfig
     from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLForConditionalGeneration
     from transformers.models.qwen2_5_vl.processing_qwen2_5_vl import Qwen2_5_VLProcessor
     from transformers.models.qwen2_vl.image_processing_qwen2_vl import Qwen2VLImageProcessor
+    from transformers.models.qwen2_vl.video_processing_qwen2_vl import Qwen2VLVideoProcessor
 
-    QWEN2_5_VL_AVAILABLE = True
+    QWEN2_5_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_5_VL_AVAILABLE = False
 
@@ -504,7 +512,12 @@ def create_processor(model_name: str):
         )
         qwen_tokenizer = Qwen2TokenizerFast(tokenizer_object=tokenizer_base, **tokenizer_config)
         image_processor = Qwen2VLImageProcessor()
-        return Qwen2VLProcessor(image_processor=image_processor, tokenizer=qwen_tokenizer)
+        video_processor = Qwen2VLVideoProcessor()
+        return Qwen2VLProcessor(
+            image_processor=image_processor,
+            video_processor=video_processor,
+            tokenizer=qwen_tokenizer,
+        )
 
     elif model_name == "mini_qwen2_5_vl":
         tokenizer_config = load_tokenizer_config(
@@ -521,7 +534,12 @@ def create_processor(model_name: str):
         )
         qwen_tokenizer = Qwen2TokenizerFast(tokenizer_object=tokenizer_base, **tokenizer_config)
         image_processor = Qwen2VLImageProcessor()
-        return Qwen2_5_VLProcessor(image_processor=image_processor, tokenizer=qwen_tokenizer)
+        video_processor = Qwen2VLVideoProcessor()
+        return Qwen2_5_VLProcessor(
+            image_processor=image_processor,
+            video_processor=video_processor,
+            tokenizer=qwen_tokenizer,
+        )
 
     elif model_name == "mini_llava":
         tokenizer_config = load_tokenizer_config(
diff --git a/test/convergence/bf16/test_mini_models_with_logits.py b/test/convergence/bf16/test_mini_models_with_logits.py
index 4781195a..0a6f61eb 100644
--- a/test/convergence/bf16/test_mini_models_with_logits.py
+++ b/test/convergence/bf16/test_mini_models_with_logits.py
@@ -69,20 +69,26 @@ except ImportError:
     MLLAMA_AVAILABLE = False
 
 try:
-    # Qwen2-VL is only available in transformers>4.44.2
+    # Qwen2-VL is only available in transformers>4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2_vl.configuration_qwen2_vl import Qwen2VLConfig
     from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLForConditionalGeneration
 
-    QWEN2_VL_AVAILABLE = True
+    QWEN2_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_VL_AVAILABLE = False
 
 try:
-    # Qwen2.5-VL is only available in transformers>4.48.2
+    # Qwen2.5-VL is only available in transformers>4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2_5_vl.configuration_qwen2_5_vl import Qwen2_5_VLConfig
     from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLForConditionalGeneration
 
-    QWEN2_5_VL_AVAILABLE = True
+    QWEN2_5_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_5_VL_AVAILABLE = False
 
diff --git a/test/convergence/fp32/test_mini_models.py b/test/convergence/fp32/test_mini_models.py
index e5250cf5..3a9c9e57 100644
--- a/test/convergence/fp32/test_mini_models.py
+++ b/test/convergence/fp32/test_mini_models.py
@@ -68,20 +68,26 @@ except ImportError:
     MLLAMA_AVAILABLE = False
 
 try:
-    # Qwen2-VL is only available in transformers>4.44.2
+    # Qwen2-VL is only available in transformers>4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2_vl.configuration_qwen2_vl import Qwen2VLConfig
     from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLForConditionalGeneration
 
-    QWEN2_VL_AVAILABLE = True
+    QWEN2_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_VL_AVAILABLE = False
 
 try:
-    # Qwen2.5-VL is only available in transformers>4.48.2
+    # Qwen2.5-VL is only available in transformers>4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2_5_vl.configuration_qwen2_5_vl import Qwen2_5_VLConfig
     from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLForConditionalGeneration
 
-    QWEN2_5_VL_AVAILABLE = True
+    QWEN2_5_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_5_VL_AVAILABLE = False
 
diff --git a/test/convergence/fp32/test_mini_models_multimodal.py b/test/convergence/fp32/test_mini_models_multimodal.py
index 54f6067f..fe543136 100644
--- a/test/convergence/fp32/test_mini_models_multimodal.py
+++ b/test/convergence/fp32/test_mini_models_multimodal.py
@@ -34,26 +34,34 @@ from test.utils import set_seed
 from test.utils import train_bpe_tokenizer
 
 try:
-    # Qwen2-VL is only available in transformers>=4.45.0
+    # Qwen2-VL is only available in transformers>=4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2.tokenization_qwen2_fast import Qwen2TokenizerFast
     from transformers.models.qwen2_vl.configuration_qwen2_vl import Qwen2VLConfig
     from transformers.models.qwen2_vl.image_processing_qwen2_vl import Qwen2VLImageProcessor
     from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLForConditionalGeneration
     from transformers.models.qwen2_vl.processing_qwen2_vl import Qwen2VLProcessor
+    from transformers.models.qwen2_vl.video_processing_qwen2_vl import Qwen2VLVideoProcessor
 
-    QWEN2_VL_AVAILABLE = True
+    QWEN2_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_VL_AVAILABLE = False
 
 try:
     # Qwen2.5-VL is only available in transformers>4.48.2
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2.tokenization_qwen2_fast import Qwen2TokenizerFast
     from transformers.models.qwen2_5_vl.configuration_qwen2_5_vl import Qwen2_5_VLConfig
     from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLForConditionalGeneration
     from transformers.models.qwen2_5_vl.processing_qwen2_5_vl import Qwen2_5_VLProcessor
     from transformers.models.qwen2_vl.image_processing_qwen2_vl import Qwen2VLImageProcessor
+    from transformers.models.qwen2_vl.video_processing_qwen2_vl import Qwen2VLVideoProcessor
 
-    QWEN2_5_VL_AVAILABLE = True
+    QWEN2_5_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_5_VL_AVAILABLE = False
 
@@ -501,7 +509,12 @@ def create_processor(model_name: str):
         )
         qwen_tokenizer = Qwen2TokenizerFast(tokenizer_object=tokenizer_base, **tokenizer_config)
         image_processor = Qwen2VLImageProcessor()
-        return Qwen2VLProcessor(image_processor=image_processor, tokenizer=qwen_tokenizer)
+        video_processor = Qwen2VLVideoProcessor()
+        return Qwen2VLProcessor(
+            image_processor=image_processor,
+            video_processor=video_processor,
+            tokenizer=qwen_tokenizer,
+        )
 
     elif model_name == "mini_qwen2_5_vl":
         tokenizer_config = load_tokenizer_config(
@@ -518,7 +531,12 @@ def create_processor(model_name: str):
         )
         qwen_tokenizer = Qwen2TokenizerFast(tokenizer_object=tokenizer_base, **tokenizer_config)
         image_processor = Qwen2VLImageProcessor()
-        return Qwen2_5_VLProcessor(image_processor=image_processor, tokenizer=qwen_tokenizer)
+        video_processor = Qwen2VLVideoProcessor()
+        return Qwen2_5_VLProcessor(
+            image_processor=image_processor,
+            video_processor=video_processor,
+            tokenizer=qwen_tokenizer,
+        )
 
     elif model_name == "mini_llava":
         tokenizer_config = load_tokenizer_config(
diff --git a/test/convergence/fp32/test_mini_models_with_logits.py b/test/convergence/fp32/test_mini_models_with_logits.py
index 83eb542f..457df66d 100644
--- a/test/convergence/fp32/test_mini_models_with_logits.py
+++ b/test/convergence/fp32/test_mini_models_with_logits.py
@@ -68,20 +68,26 @@ except ImportError:
     MLLAMA_AVAILABLE = False
 
 try:
-    # Qwen2-VL is only available in transformers>4.44.2
+    # Qwen2-VL is only available in transformers>4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2_vl.configuration_qwen2_vl import Qwen2VLConfig
     from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLForConditionalGeneration
 
-    QWEN2_VL_AVAILABLE = True
+    QWEN2_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_VL_AVAILABLE = False
 
 try:
-    # Qwen2.5-VL is only available in transformers>4.48.2
+    # Qwen2.5-VL is only available in transformers>4.52.4
+    import transformers
+
+    from packaging import version
     from transformers.models.qwen2_5_vl.configuration_qwen2_5_vl import Qwen2_5_VLConfig
     from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLForConditionalGeneration
 
-    QWEN2_5_VL_AVAILABLE = True
+    QWEN2_5_VL_AVAILABLE = version.parse(transformers.__version__) >= version.parse("4.52.4")
 except ImportError:
     QWEN2_5_VL_AVAILABLE = False
 
diff --git a/test/transformers/test_monkey_patch.py b/test/transformers/test_monkey_patch.py
index de806368..bbd988d8 100644
--- a/test/transformers/test_monkey_patch.py
+++ b/test/transformers/test_monkey_patch.py
@@ -870,7 +870,7 @@ def test_apply_liger_kernel_to_instance_for_qwen3_moe():
 
 
 @pytest.mark.skipif(not is_qwen2_vl_available(), reason="qwen2_vl module not available")
-def test_apply_liger_kernel_to_instance_for_qwen2_vl():
+def test_apply_liger_kernel_to_instance_for_qwen2_vl_for_conditional_generation():
     # Ensure any monkey patching is cleaned up for subsequent tests
     with patch("transformers.models.qwen2_vl.modeling_qwen2_vl"):
         from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLForConditionalGeneration
@@ -899,8 +899,10 @@ def test_apply_liger_kernel_to_instance_for_qwen2_vl():
         assert isinstance(dummy_model_instance, Qwen2VLForConditionalGeneration)
 
         # Check that model instance variables are not yet patched with Liger modules
-        assert inspect.getsource(dummy_model_instance.model.norm.forward) != inspect.getsource(LigerRMSNorm.forward)
-        for layer in dummy_model_instance.model.layers:
+        assert inspect.getsource(dummy_model_instance.language_model.norm.forward) != inspect.getsource(
+            LigerRMSNorm.forward
+        )
+        for layer in dummy_model_instance.language_model.layers:
             assert inspect.getsource(layer.mlp.forward) != inspect.getsource(LigerSwiGLUMLP.forward)
             assert inspect.getsource(layer.input_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
             assert inspect.getsource(layer.post_attention_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
@@ -912,8 +914,10 @@ def test_apply_liger_kernel_to_instance_for_qwen2_vl():
         _apply_liger_kernel_to_instance(model=dummy_model_instance)
 
         # Check that the model's instance variables were correctly patched with Liger modules
-        assert inspect.getsource(dummy_model_instance.model.norm.forward) == inspect.getsource(LigerRMSNorm.forward)
-        for layer in dummy_model_instance.model.layers:
+        assert inspect.getsource(dummy_model_instance.language_model.norm.forward) == inspect.getsource(
+            LigerRMSNorm.forward
+        )
+        for layer in dummy_model_instance.language_model.layers:
             assert inspect.getsource(layer.mlp.forward) == inspect.getsource(LigerSwiGLUMLP.forward)
             assert inspect.getsource(layer.input_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
             assert inspect.getsource(layer.post_attention_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
@@ -927,8 +931,178 @@ def test_apply_liger_kernel_to_instance_for_qwen2_vl():
             pytest.fail(f"An exception occured in extra_expr: {type(e).__name__} - {e}")
 
 
+@pytest.mark.skipif(not is_qwen2_vl_available(), reason="qwen2_vl module not available")
+def test_apply_liger_kernel_to_instance_for_qwen2_vl():
+    # Ensure any monkey patching is cleaned up for subsequent tests
+    with patch("transformers.models.qwen2_vl.modeling_qwen2_vl"):
+        from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLModel
+
+        # Instantiate a dummy model
+        config = transformers.models.qwen2_vl.configuration_qwen2_vl.Qwen2VLConfig(
+            torch_dtype=torch.bfloat16,
+            rms_norm_eps=1e-5,
+            hidden_size=32,
+            intermediate_size=48,
+            embed_dim=16,
+            hidden_act="silu",
+            num_hidden_layers=2,
+            num_attention_heads=2,
+            max_position_embeddings=128,
+            vocab_size=1000,
+            vision_config={
+                "depth": 4,
+                "embed_dim": 128,
+                "num_heads": 8,
+                "hidden_size": 1024,
+            },
+        )
+        dummy_model_instance = Qwen2VLModel._from_config(config)
+
+        assert isinstance(dummy_model_instance, Qwen2VLModel)
+
+        # Check that model instance variables are not yet patched with Liger modules
+        assert inspect.getsource(dummy_model_instance.language_model.norm.forward) != inspect.getsource(
+            LigerRMSNorm.forward
+        )
+        for layer in dummy_model_instance.language_model.layers:
+            assert inspect.getsource(layer.mlp.forward) != inspect.getsource(LigerSwiGLUMLP.forward)
+            assert inspect.getsource(layer.input_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
+            assert inspect.getsource(layer.post_attention_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
+        for vision_block in dummy_model_instance.visual.blocks:
+            assert inspect.getsource(vision_block.norm1.forward) != inspect.getsource(LigerLayerNorm.forward)
+            assert inspect.getsource(vision_block.norm2.forward) != inspect.getsource(LigerLayerNorm.forward)
+
+        # Test applying kernels to the model instance
+        _apply_liger_kernel_to_instance(model=dummy_model_instance)
+
+        # Check that the model's instance variables were correctly patched with Liger modules
+        assert inspect.getsource(dummy_model_instance.language_model.norm.forward) == inspect.getsource(
+            LigerRMSNorm.forward
+        )
+        for layer in dummy_model_instance.language_model.layers:
+            assert inspect.getsource(layer.mlp.forward) == inspect.getsource(LigerSwiGLUMLP.forward)
+            assert inspect.getsource(layer.input_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
+            assert inspect.getsource(layer.post_attention_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
+        for vision_block in dummy_model_instance.visual.blocks:
+            assert inspect.getsource(vision_block.norm1.forward) == inspect.getsource(LigerLayerNorm.forward)
+            assert inspect.getsource(vision_block.norm2.forward) == inspect.getsource(LigerLayerNorm.forward)
+
+        try:
+            print(dummy_model_instance)
+        except Exception as e:
+            pytest.fail(f"An exception occured in extra_expr: {type(e).__name__} - {e}")
+
+
+@pytest.mark.skipif(not is_qwen2_vl_available(), reason="qwen2_vl module not available")
+def test_apply_liger_kernel_to_instance_for_qwen2_vl_text():
+    # Ensure any monkey patching is cleaned up for subsequent tests
+    with patch("transformers.models.qwen2_vl.modeling_qwen2_vl"):
+        from transformers.models.qwen2_vl.modeling_qwen2_vl import Qwen2VLTextModel
+
+        # Instantiate a dummy model
+        config = transformers.models.qwen2_vl.configuration_qwen2_vl.Qwen2VLTextConfig(
+            torch_dtype=torch.bfloat16,
+            rms_norm_eps=1e-5,
+            hidden_size=32,
+            intermediate_size=48,
+            embed_dim=16,
+            hidden_act="silu",
+            num_hidden_layers=2,
+            num_attention_heads=2,
+            max_position_embeddings=128,
+            vocab_size=1000,
+        )
+        dummy_model_instance = Qwen2VLTextModel._from_config(config)
+
+        assert isinstance(dummy_model_instance, Qwen2VLTextModel)
+
+        # Check that model instance variables are not yet patched with Liger modules
+        assert inspect.getsource(dummy_model_instance.norm.forward) != inspect.getsource(LigerRMSNorm.forward)
+        for layer in dummy_model_instance.layers:
+            assert inspect.getsource(layer.mlp.forward) != inspect.getsource(LigerSwiGLUMLP.forward)
+            assert inspect.getsource(layer.input_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
+            assert inspect.getsource(layer.post_attention_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
+
+        # Test applying kernels to the model instance
+        _apply_liger_kernel_to_instance(model=dummy_model_instance)
+
+        # Check that the model's instance variables were correctly patched with Liger modules
+        assert inspect.getsource(dummy_model_instance.norm.forward) == inspect.getsource(LigerRMSNorm.forward)
+        for layer in dummy_model_instance.layers:
+            assert inspect.getsource(layer.mlp.forward) == inspect.getsource(LigerSwiGLUMLP.forward)
+            assert inspect.getsource(layer.input_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
+            assert inspect.getsource(layer.post_attention_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
+
+        try:
+            print(dummy_model_instance)
+        except Exception as e:
+            pytest.fail(f"An exception occured in extra_expr: {type(e).__name__} - {e}")
+
+
 @pytest.mark.skipif(not is_qwen2_5_vl_available(), reason="qwen2_5_vl module not available")
 def test_apply_liger_kernel_to_instance_for_qwen2_5_vl():
+    # Ensure any monkey patching is cleaned up for subsequent tests
+    with patch("transformers.models.qwen2_5_vl.modeling_qwen2_5_vl"):
+        from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLModel
+
+        # Instantiate a dummy model
+        config = transformers.models.qwen2_5_vl.configuration_qwen2_5_vl.Qwen2_5_VLConfig(
+            torch_dtype=torch.bfloat16,
+            rms_norm_eps=1e-5,
+            hidden_size=32,
+            intermediate_size=48,
+            embed_dim=16,
+            hidden_act="silu",
+            num_hidden_layers=2,
+            num_attention_heads=2,
+            max_position_embeddings=128,
+            vocab_size=1000,
+            vision_config={
+                "depth": 4,
+                "embed_dim": 128,
+                "num_heads": 8,
+                "hidden_size": 1024,
+            },
+        )
+        dummy_model_instance = Qwen2_5_VLModel._from_config(config)
+
+        assert isinstance(dummy_model_instance, Qwen2_5_VLModel)
+
+        # Check that model instance variables are not yet patched with Liger modules
+        assert inspect.getsource(dummy_model_instance.language_model.norm.forward) != inspect.getsource(
+            LigerRMSNorm.forward
+        )
+        for layer in dummy_model_instance.language_model.layers:
+            assert inspect.getsource(layer.mlp.forward) != inspect.getsource(LigerSwiGLUMLP.forward)
+            assert inspect.getsource(layer.input_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
+            assert inspect.getsource(layer.post_attention_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
+        for vision_block in dummy_model_instance.visual.blocks:
+            assert inspect.getsource(vision_block.norm1.forward) != inspect.getsource(LigerRMSNorm.forward)
+            assert inspect.getsource(vision_block.norm2.forward) != inspect.getsource(LigerRMSNorm.forward)
+
+        # Test applying kernels to the model instance
+        _apply_liger_kernel_to_instance(model=dummy_model_instance)
+
+        # Check that the model's instance variables were correctly patched with Liger modules
+        assert inspect.getsource(dummy_model_instance.language_model.norm.forward) == inspect.getsource(
+            LigerRMSNorm.forward
+        )
+        for layer in dummy_model_instance.language_model.layers:
+            assert inspect.getsource(layer.mlp.forward) == inspect.getsource(LigerSwiGLUMLP.forward)
+            assert inspect.getsource(layer.input_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
+            assert inspect.getsource(layer.post_attention_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
+        for vision_block in dummy_model_instance.visual.blocks:
+            assert inspect.getsource(vision_block.norm1.forward) == inspect.getsource(LigerRMSNorm.forward)
+            assert inspect.getsource(vision_block.norm2.forward) == inspect.getsource(LigerRMSNorm.forward)
+
+        try:
+            print(dummy_model_instance)
+        except Exception as e:
+            pytest.fail(f"An exception occured in extra_expr: {type(e).__name__} - {e}")
+
+
+@pytest.mark.skipif(not is_qwen2_5_vl_available(), reason="qwen2_5_vl module not available")
+def test_apply_liger_kernel_to_instance_for_qwen2_5_vl_for_conditional_generation():
     # Ensure any monkey patching is cleaned up for subsequent tests
     with patch("transformers.models.qwen2_5_vl.modeling_qwen2_5_vl"):
         from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLForConditionalGeneration
@@ -957,8 +1131,10 @@ def test_apply_liger_kernel_to_instance_for_qwen2_5_vl():
         assert isinstance(dummy_model_instance, Qwen2_5_VLForConditionalGeneration)
 
         # Check that model instance variables are not yet patched with Liger modules
-        assert inspect.getsource(dummy_model_instance.model.norm.forward) != inspect.getsource(LigerRMSNorm.forward)
-        for layer in dummy_model_instance.model.layers:
+        assert inspect.getsource(dummy_model_instance.language_model.norm.forward) != inspect.getsource(
+            LigerRMSNorm.forward
+        )
+        for layer in dummy_model_instance.language_model.layers:
             assert inspect.getsource(layer.mlp.forward) != inspect.getsource(LigerSwiGLUMLP.forward)
             assert inspect.getsource(layer.input_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
             assert inspect.getsource(layer.post_attention_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
@@ -970,8 +1146,10 @@ def test_apply_liger_kernel_to_instance_for_qwen2_5_vl():
         _apply_liger_kernel_to_instance(model=dummy_model_instance)
 
         # Check that the model's instance variables were correctly patched with Liger modules
-        assert inspect.getsource(dummy_model_instance.model.norm.forward) == inspect.getsource(LigerRMSNorm.forward)
-        for layer in dummy_model_instance.model.layers:
+        assert inspect.getsource(dummy_model_instance.language_model.norm.forward) == inspect.getsource(
+            LigerRMSNorm.forward
+        )
+        for layer in dummy_model_instance.language_model.layers:
             assert inspect.getsource(layer.mlp.forward) == inspect.getsource(LigerSwiGLUMLP.forward)
             assert inspect.getsource(layer.input_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
             assert inspect.getsource(layer.post_attention_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
@@ -985,6 +1163,52 @@ def test_apply_liger_kernel_to_instance_for_qwen2_5_vl():
             pytest.fail(f"An exception occured in extra_expr: {type(e).__name__} - {e}")
 
 
+@pytest.mark.skipif(not is_qwen2_5_vl_available(), reason="qwen2_5_vl module not available")
+def test_apply_liger_kernel_to_instance_for_qwen2_5_vl_text():
+    # Ensure any monkey patching is cleaned up for subsequent tests
+    with patch("transformers.models.qwen2_5_vl.modeling_qwen2_5_vl"):
+        from transformers.models.qwen2_5_vl.modeling_qwen2_5_vl import Qwen2_5_VLTextModel
+
+        # Instantiate a dummy model
+        config = transformers.models.qwen2_5_vl.configuration_qwen2_5_vl.Qwen2_5_VLTextConfig(
+            torch_dtype=torch.bfloat16,
+            rms_norm_eps=1e-5,
+            hidden_size=32,
+            intermediate_size=48,
+            embed_dim=16,
+            hidden_act="silu",
+            num_hidden_layers=2,
+            num_attention_heads=2,
+            max_position_embeddings=128,
+            vocab_size=1000,
+        )
+        dummy_model_instance = Qwen2_5_VLTextModel._from_config(config)
+
+        assert isinstance(dummy_model_instance, Qwen2_5_VLTextModel)
+
+        # Check that model instance variables are not yet patched with Liger modules
+        assert inspect.getsource(dummy_model_instance.norm.forward) != inspect.getsource(LigerRMSNorm.forward)
+        for layer in dummy_model_instance.layers:
+            assert inspect.getsource(layer.mlp.forward) != inspect.getsource(LigerSwiGLUMLP.forward)
+            assert inspect.getsource(layer.input_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
+            assert inspect.getsource(layer.post_attention_layernorm.forward) != inspect.getsource(LigerRMSNorm.forward)
+
+        # Test applying kernels to the model instance
+        _apply_liger_kernel_to_instance(model=dummy_model_instance)
+
+        # Check that the model's instance variables were correctly patched with Liger modules
+        assert inspect.getsource(dummy_model_instance.norm.forward) == inspect.getsource(LigerRMSNorm.forward)
+        for layer in dummy_model_instance.layers:
+            assert inspect.getsource(layer.mlp.forward) == inspect.getsource(LigerSwiGLUMLP.forward)
+            assert inspect.getsource(layer.input_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
+            assert inspect.getsource(layer.post_attention_layernorm.forward) == inspect.getsource(LigerRMSNorm.forward)
+
+        try:
+            print(dummy_model_instance)
+        except Exception as e:
+            pytest.fail(f"An exception occured in extra_expr: {type(e).__name__} - {e}")
+
+
 def test_apply_liger_kernel_to_instance_for_phi3():
     # Ensure any monkey patching is cleaned up for subsequent tests
     with patch("transformers.models.phi3.modeling_phi3"):