diff --git a/vllm/model_executor/models/mixtral.py b/vllm/model_executor/models/mixtral.py
index d3471959a1766..1cdf1c5f18ca5 100644
--- a/vllm/model_executor/models/mixtral.py
+++ b/vllm/model_executor/models/mixtral.py
@@ -450,8 +450,8 @@ def __init__(
         lora_config: Optional[LoRAConfig] = None,
     ) -> None:
         super().__init__()
-        # TODO keep the fused mixtral_quant codepath around as long as we don't
-        # support all quant_types
+        # TODO keep the unfused mixtral_quant-like codepath around as long as
+        # we don't support all quant_types
         self.is_compressed = isinstance(quant_config, CompressedTensorsConfig)
         self.use_fused_moe = (
             self.is_compressed