remove GLM-4.5 quantization wrong Code (#21435)

vllm/entrypoints/openai/tool_parsers/glm4_moe_tool_parser.py

@@ -20,7 +20,7 @@ from vllm.transformers_utils.tokenizer import AnyTokenizer
 logger = init_logger(__name__)
 
 
-@ToolParserManager.register_module("glm4_moe")
+@ToolParserManager.register_module("glm45")
 class Glm4MoeModelToolParser(ToolParser):
 
     def __init__(self, tokenizer: AnyTokenizer):

vllm/model_executor/models/glm4_moe.py

@@ -390,7 +390,6 @@ class Glm4MoeModel(nn.Module):
             self.embed_tokens = VocabParallelEmbedding(
                 config.vocab_size,
                 config.hidden_size,
-                quant_config=quant_config,
                 prefix=f"{prefix}.embed_tokens")
         else:
             self.embed_tokens = PPMissingLayer()

vllm/reasoning/glm4_moe_reasoning_parser.py

@@ -14,7 +14,7 @@ from vllm.reasoning import ReasoningParser, ReasoningParserManager
 logger = init_logger(__name__)
 
 
-@ReasoningParserManager.register_module("glm4_moe")
+@ReasoningParserManager.register_module("glm45")
 class Glm4MoeModelReasoningParser(ReasoningParser):
     """
     Reasoning parser for the Glm4MoeModel model.