GLM-4.5V with new class name at transformers (#22520)

Signed-off-by: zRzRzRzRzRzRzR <[email protected]>
Signed-off-by: Isotr0py <[email protected]>
Co-authored-by: Isotr0py <[email protected]>

Author: zRzRzRzRzRzRzR

docs/models/supported_models.md

@@ -352,6 +352,7 @@ th {
 | `Gemma3nForConditionalGeneration` | 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. | ✅︎ | ✅︎ | ✅︎ |
 | `GPT2LMHeadModel` | GPT-2 | `gpt2`, `gpt2-xl`, etc. | | ✅︎ | ✅︎ |
 | `GPTBigCodeForCausalLM` | StarCoder, SantaCoder, WizardCoder | `bigcode/starcoder`, `bigcode/gpt_bigcode-santacoder`, `WizardLM/WizardCoder-15B-V1.0`, etc. | ✅︎ | ✅︎ | ✅︎ |
 | `GPTJForCausalLM` | GPT-J | `EleutherAI/gpt-j-6b`, `nomic-ai/gpt4all-j`, etc. | | ✅︎ | ✅︎ |
@@ -609,8 +610,7 @@ These models primarily accept the [`LLM.generate`](./generative_models.md#llmgen
 | `Gemma3ForConditionalGeneration` | Gemma 3 | T + I<sup>+</sup> | `google/gemma-3-4b-it`, `google/gemma-3-27b-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. | ✅︎ | ✅︎ | ✅︎ |
-| `Glm4MoeForCausalLM` | GLM-4.5 | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.5`, etc. | ✅︎ | ✅︎ | ✅︎ |
-| `Glm4v_moeForConditionalGeneration` | GLM-4.5V | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.5V`, etc. | ✅︎ | ✅︎ | ✅︎ |
+| `Glm4vMoeForConditionalGeneration` | GLM-4.5V | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.5V`, etc. | ✅︎ | ✅︎ | ✅︎ |
 | `GraniteSpeechForConditionalGeneration` | Granite Speech | T + A | `ibm-granite/granite-speech-3.3-8b` | ✅︎ | ✅︎ | ✅︎ |
 | `H2OVLChatModel` | H2OVL | T + I<sup>E+</sup> | `h2oai/h2ovl-mississippi-800m`, `h2oai/h2ovl-mississippi-2b`, etc. | | ✅︎ | ✅︎ |
 | `Idefics3ForConditionalGeneration` | Idefics3 | T + I | `HuggingFaceM4/Idefics3-8B-Llama3`, etc. | ✅︎ | | ✅︎ |

tests/models/registry.py

@@ -396,7 +396,7 @@ def check_available_online(
                                         trust_remote_code=True,
                                         hf_overrides={"architectures": ["GLM4VForCausalLM"]}),  # noqa: E501
     "Glm4vForConditionalGeneration": _HfExamplesInfo("zai-org/GLM-4.1V-9B-Thinking"),  # noqa: E501
-    "Glm4v_moeForConditionalGeneration": _HfExamplesInfo("zai-org/GLM-4.5V",
+    "Glm4vMoeForConditionalGeneration": _HfExamplesInfo("zai-org/GLM-4.5V",
                                           is_available_online=False),   # noqa: E501
     "H2OVLChatModel": _HfExamplesInfo("h2oai/h2ovl-mississippi-800m",
                                       trust_remote_code=True,

vllm/model_executor/models/glm4_moe.py

@@ -372,7 +372,13 @@ def forward(
         return hidden_states, residual
 
 
-@support_torch_compile
+@support_torch_compile(
+    dynamic_arg_dims={
+        "input_ids": 0,
+        "positions": -1,
+        "intermediate_tensors": 0,
+        "inputs_embeds": 0,
+    })
 class Glm4MoeModel(nn.Module):
 
     def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):

vllm/model_executor/models/registry.py

@@ -207,7 +207,7 @@
     "Gemma3ForConditionalGeneration": ("gemma3_mm", "Gemma3ForConditionalGeneration"),  # noqa: E501
     "GLM4VForCausalLM": ("glm4v", "GLM4VForCausalLM"),
     "Glm4vForConditionalGeneration": ("glm4_1v", "Glm4vForConditionalGeneration"),  # noqa: E501
-    "Glm4v_moeForConditionalGeneration": ("glm4_1v", "Glm4vForConditionalGeneration"),  # noqa: E501
+    "Glm4vMoeForConditionalGeneration": ("glm4_1v", "Glm4vForConditionalGeneration"),  # noqa: E501
     "GraniteSpeechForConditionalGeneration": ("granite_speech", "GraniteSpeechForConditionalGeneration"),  # noqa: E501
     "H2OVLChatModel": ("h2ovl", "H2OVLChatModel"),
     "InternVLChatModel": ("internvl", "InternVLChatModel"),

vllm/transformers_utils/config.py

@@ -254,7 +254,8 @@ def _uses_mrope(config: PretrainedConfig) -> bool:
 
 def uses_mrope(config: PretrainedConfig) -> bool:
     """Detect if the model with this config uses M-ROPE."""
-    return _uses_mrope(config) or thinker_uses_mrope(config)
+    return _uses_mrope(config) or _uses_mrope(
+        config.get_text_config()) or thinker_uses_mrope(config)
 
 
 def thinker_uses_mrope(config: PretrainedConfig) -> bool: