Mojo function
rms_norm_fused_residual_add_gpu
rms_norm_fused_residual_add_gpu[dtype: DType, rank: Int, //, input_fn: fn[Int, Int](IndexList[$1]) capturing -> SIMD[dtype, $0], residual_input_fn: fn[Int, Int](IndexList[$1]) capturing -> SIMD[dtype, $0], output_residual_fn: fn[Int, Int](IndexList[rank], SIMD[dtype, $0]) capturing -> None, output_fn: fn[Int, Int](IndexList[rank], SIMD[dtype, $0]) capturing -> None, multiply_before_cast: Bool](shape: IndexList[rank, element_type=element_type], gamma1: NDBuffer[dtype, 1, origin], epsilon1: SIMD[dtype, 1], weight_offset1: SIMD[dtype, 1], gamma2: NDBuffer[dtype, 1, origin], epsilon2: SIMD[dtype, 1], weight_offset2: SIMD[dtype, 1], ctx: DeviceContext)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!