pub fn compute_logistic(input: &[f32], output: &mut [f32])Expand description
Compute the elementwise logistic (sigmoid) output = 1 / (1 + exp(-input))
over equal-length contiguous f32 slices using MLAS’s SIMD sigmoid. Single
threaded; callers shard across threads themselves when needed.
This is the vectorized primitive behind SiLU (x * sigmoid(x)), replacing a
scalar expf loop that LLVM cannot autovectorize.