Update README.md

README.md

@@ -151,7 +151,7 @@ def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]) -> set[str]:
                 continue  # skip spec decode layers for main model
         ...
 ``` 
-Finally, modify `vllm/model_executor/layers/quantization/quark/quark_moe.py` by forcing `self.emulate` to "True":
+Finally, modify `vllm/model_executor/layers/quantization/quark/quark_moe.py` by forcing `self.emulate` to "True" ([alternate resolution](https://github.com/vllm-project/vllm/pull/39436)):
 ```
 class QuarkOCP_MX_MoEMethod(QuarkMoEMethod):
     def __init__(...):