For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo function

causal_conv1d_channel_last_fwd_cpu

def causal_conv1d_channel_last_fwd_cpu[x_dtype: DType, weight_dtype: DType, output_dtype: DType, bias_dtype: DType](batch: Int, dim: Int, seqlen: Int, width: Int, x: TileTensor[x_dtype, Storage=x.Storage, address_space=x.address_space, linear_idx_type=x.linear_idx_type], weight: TileTensor[weight_dtype, Storage=weight.Storage, address_space=weight.address_space, linear_idx_type=weight.linear_idx_type], output: TileTensor[output_dtype, Storage=output.Storage, address_space=output.address_space, linear_idx_type=output.linear_idx_type], bias: TileTensor[bias_dtype, Storage=bias.Storage, address_space=bias.address_space, linear_idx_type=bias.linear_idx_type], x_batch_stride: UInt32, x_c_stride: UInt32, x_l_stride: UInt32, weight_c_stride: UInt32, weight_width_stride: UInt32, out_batch_stride: UInt32, out_c_stride: UInt32, out_l_stride: UInt32, silu_activation: Bool)

Optimized CPU implementation of causal conv1d for channel-last layout with bias.

Structured for potential SIMD optimizations. Currently similar to naive but organized for future vectorization improvements.