Revert "[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (#7527)" (#7764)

vllm/model_executor/model_loader/utils.py

@@ -23,11 +23,11 @@ def get_model_architecture(
     architectures = getattr(model_config.hf_config, "architectures", [])
     # Special handling for quantized Mixtral.
     # FIXME(woosuk): This is a temporary hack.
-    mixtral_supported = ["fp8", "compressed-tensors"]
     if (model_config.quantization is not None
-            and model_config.quantization not in mixtral_supported
+            and model_config.quantization != "fp8"
             and "MixtralForCausalLM" in architectures):
         architectures = ["QuantMixtralForCausalLM"]
+
     return ModelRegistry.resolve_model_cls(architectures)