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 13, 03:15 UTC
Fixed gpt-oss _load_weights_other() parameter position bug (#28715)
Co-authored-by: Dezhan Tu <dztu@meta.com>
Dezhan committed
Nov 16, 2025 at 01:46 UTC
af02c409702f2f41eb13471ce3224e3315e19d89
1 file changed
+1
-1
vllm/model_executor/models/gpt_oss.py
+1
-1
@@ -641,8 +641,8 @@ class GptOssModel(nn.Module):
641
)
642
else:
643
return self._load_weights_other(
644
- ep_rank_end,
644
ep_rank_start,
645
+ ep_rank_end,
646
heads_per_rank,
647
head_start,
648
weights,