[Bugfix] Support other quantization methods in glm41v (#36321)

Signed-off-by: g00887675/loganJane <g00887675/loganJane73@hotmail.com>
Co-authored-by: g00887675/loganJane <g00887675/loganJane73@hotmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

vllm/model_executor/models/glm4_1v.py

@@ -63,6 +63,9 @@ from vllm.model_executor.layers.linear import (
     RowParallelLinear,
 )
 from vllm.model_executor.layers.quantization import QuantizationConfig
+from vllm.model_executor.layers.quantization.compressed_tensors import (
+    compressed_tensors,
+)
 from vllm.model_executor.layers.rotary_embedding import get_rope
 from vllm.model_executor.layers.rotary_embedding.common import (
     ApplyRotaryEmb,
@@ -280,7 +283,9 @@ class Glm4vVisionAttention(nn.Module):
             bias=False,
             quant_config=quant_config,
             # Change qkv prefix to align with GLM-4.5V-FP8 quantization cfg
-            prefix=f"{prefix}.qkv_proj" if quant_config else f"{prefix}.qkv",
+            prefix=f"{prefix}.qkv_proj"
+            if isinstance(quant_config, compressed_tensors.CompressedTensorsConfig)
+            else f"{prefix}.qkv",
             disable_tp=use_data_parallel,
         )
         self.proj = RowParallelLinear(