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, 23:30 UTC
[Bugfix] Fix typo in Qwen3 Next model executor (#28960)
Signed-off-by: Gleb Kurchanov <nepherpitou@gmail.com>
Gleb Kurchanov committed
Nov 19, 2025 at 08:21 UTC
73ff872db0d4e3f5e133d5d2a5307248619d93a6
1 file changed
+2
-2
vllm/model_executor/models/qwen3_next.py
+2
-2
@@ -1154,8 +1154,8 @@ class QwenNextMixtureOfExperts(MixtureOfExperts):
1154
example_moe = layer.mlp
1155
self.moe_layers.append(layer.mlp.experts)
1156
1157
- if example_moe is None:
1158
- raise RuntimeError("No Qwen3Next layer found in the model.layers.")
1157
+ if example_moe is None:
1158
+ raise RuntimeError("No Qwen3Next layer found in the model.layers.")
1159
1160
# Set MoE hyperparameters
1161
self.num_moe_layers = len(self.moe_layers)