From 8d259fad6cd5a93bef04d00640e132e84c0c9b20 Mon Sep 17 00:00:00 2001
From: Anna Shors <ashors@nvidia.com>
Date: Sun, 16 Nov 2025 05:12:45 -0800
Subject: [PATCH] Fix gpt oss weight loading with EP + bf16 (#28765)

Signed-off-by: ashors1 <ashors@nvidia.com>
---
 vllm/model_executor/models/gpt_oss.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/vllm/model_executor/models/gpt_oss.py b/vllm/model_executor/models/gpt_oss.py
index 328c8c0ac4b76..7df3b087ccb88 100644
--- a/vllm/model_executor/models/gpt_oss.py
+++ b/vllm/model_executor/models/gpt_oss.py
@@ -494,8 +494,8 @@ class GptOssModel(nn.Module):
 
     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]],