We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent d33aba1 commit d9c4f0bCopy full SHA for d9c4f0b
exllamav3/exllamav3_ext/libtorch/linear.cpp
@@ -10,7 +10,7 @@
10
11
void BC_LinearFP16::run_gr(const at::Tensor& x, at::Tensor& y, Graph* graph)
12
{
13
- if (x.dtype() == y.dtype() and !graph)
+ if (x.dtype() == y.dtype() && !graph)
14
at::matmul_out(weight, x, y);
15
else
16
hgemm_gr(x, weight, y, graph);
0 commit comments