layer_norm_gpu_block

layer_norm_gpu_block[type: DType, //, simd_width: UInt, input_fn: fn[Int](row: Int, col: Int) capturing -> SIMD[type, $0], gamma_fn: fn[Int, Int](IndexList[$1]) capturing -> SIMD[type, $0]](output: NDBuffer[type, 2, MutableAnyOrigin], beta: NDBuffer[type, 1, MutableAnyOrigin], epsilon: SIMD[type, 1])

Was this page helpful?

Thank you! We'll create more content like this.