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 17, 04:15 UTC
[Minor] Fix bias in if to remove ambiguity (#3259)
Hui Liu committed
Mar 13, 2024 at 09:16 UTC
ba8dc958a3d8533a6e5b7debda47e4d42a062b78
1 file changed
+1
-1
vllm/model_executor/layers/linear.py
+1
-1
@@ -73,7 +73,7 @@ class UnquantizedLinearMethod(LinearMethodBase):
73
bias: Optional[torch.Tensor] = None) -> torch.Tensor:
74
weight = weights["weight"]
75
if self.separate_bias_add:
76
- if bias:
76
+ if bias is not None:
77
return F.linear(x, weight) + bias
78
return F.linear(x, weight)
79
return F.linear(x, weight, bias)