A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 12, 09:45 UTC
Fix parameter order in GPT-OSS weight loading function for non-MXFP4 weights (#29506)
Signed-off-by: Filipp Fisin <48059208+qGentry@users.noreply.github.com> Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Filipp Fisin committed
Nov 28, 2025 at 09:45 UTC
5f5521bd5d7d38d380640166294d97a839cf7ef9
1 file changed
+1
-1
vllm/model_executor/models/gpt_oss.py
+1
-1
@@ -647,8 +647,8 @@ class GptOssModel(nn.Module):
647
)
648
else:
649
return self._load_weights_other(
650
- ep_rank_start,
650
ep_rank_end,
651
+ ep_rank_start,
652
heads_per_rank,
653
head_start,
654
weights,