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, 07:15 UTC
[Doc]: Fix typo in fused_moe layer (#29731)
Signed-off-by: BowTen <bowten@qq.com>
朝 committed
Nov 30, 2025 at 14:29 UTC
9381b5cde09c542d74df835b2cba3225eff68d0e
1 file changed
+1
-1
vllm/model_executor/layers/fused_moe/layer.py
+1
-1
@@ -1422,7 +1422,7 @@ class FusedMoE(CustomOp):
1422
# do nothing.
1423
return p
1424
1425
- # Do not update the layer paramater as the layer's MoE operations would
1425
+ # Do not update the layer parameter as the layer's MoE operations would
1426
# expect the parameter's tensor to the same shape / stride. Instead,
1427
# make a new torch.nn.Parameter that is used just in the context of
1428
# EPLB.