Fix gpt oss weight loading with EP + bf16 (vllm-project#28765)

Signed-off-by: ashors1 <ashors@nvidia.com>

Author: ashors1

vllm/model_executor/models/gpt_oss.py

@@ -494,8 +494,8 @@ def _load_weights_mxfp4(
 
     def _load_weights_other(
         self,
-        ep_rank_start: int,
         ep_rank_end: int,
+        ep_rank_start: int,
         heads_per_rank: int,
         head_start: int,
         weights: Iterable[tuple[str, torch.Tensor]],