Add is_pp_missing_parameter to mamba weight loading

Signed-off-by: mzusman <[email protected]>

vllm/model_executor/models/mamba.py

@@ -25,7 +25,8 @@
 from vllm.model_executor.sampling_metadata import SamplingMetadata
 from vllm.sequence import IntermediateTensors
 
-from .utils import (make_empty_intermediate_tensors_factory, make_layers,
+from .utils import (is_pp_missing_parameter,
+                    make_empty_intermediate_tensors_factory, make_layers,
                     maybe_prefix)
 
 KVCache = Tuple[torch.Tensor, torch.Tensor]
@@ -268,6 +269,8 @@ def load_weights(self, weights: Iterable[Tuple[str, torch.Tensor]]):
             # Skip loading extra bias for GPTQ models.
             if name.endswith(".bias") and name not in params_dict:
                 continue
+            if is_pp_missing_parameter(name, self):
+                continue
 
             param = params_dict[name]
             weight_loader = getattr(param, "weight_loader",