Skip to content

Commit 8d259fa

Browse files
authored
Fix gpt oss weight loading with EP + bf16 (#28765)
Signed-off-by: ashors1 <ashors@nvidia.com>
1 parent 3bc1175 commit 8d259fa

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

vllm/model_executor/models/gpt_oss.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -494,8 +494,8 @@ def _load_weights_mxfp4(
494494

495495
def _load_weights_other(
496496
self,
497-
ep_rank_start: int,
498497
ep_rank_end: int,
498+
ep_rank_start: int,
499499
heads_per_rank: int,
500500
head_start: int,
501501
weights: Iterable[tuple[str, torch.Tensor]],

0 commit comments

Comments
 (0)