metal : fix l2 norm scale (#20493)
This commit is contained in:
@@ -3006,7 +3006,7 @@ kernel void kernel_l2_norm_impl(
|
||||
sumf = shmem_f32[tiisg];
|
||||
sumf = simd_sum(sumf);
|
||||
|
||||
const float scale = 1.0f/sqrt(max(sumf, args.eps));
|
||||
const float scale = 1.0f/max(sqrt(sumf), args.eps);
|
||||
|
||||
for (int i00 = tpitg.x; i00 < args.ne00; i00 += ntg.x) {
|
||||
y[i00] = x[i00] * scale;
|
||||
|
||||
Reference in New Issue
Block a user