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_varlen_fwd_cpu

def causal_conv1d_varlen_fwd_cpu[x_dtype: DType, weight_dtype: DType, bias_dtype: DType, output_dtype: DType, cu_seqlens_dtype: DType, cache_indices_dtype: DType, has_initial_state_dtype: DType, conv_states_dtype: DType](dim: Int, total_seqlen: Int, width: Int, batch: Int, x: TileTensor[x_dtype, address_space=x.address_space, linear_idx_type=x.linear_idx_type, element_size=x.element_size], weight: TileTensor[weight_dtype, address_space=weight.address_space, linear_idx_type=weight.linear_idx_type, element_size=weight.element_size], bias: TileTensor[bias_dtype, address_space=bias.address_space, linear_idx_type=bias.linear_idx_type, element_size=bias.element_size], query_start_loc: TileTensor[cu_seqlens_dtype, address_space=query_start_loc.address_space, linear_idx_type=query_start_loc.linear_idx_type, element_size=query_start_loc.element_size], cache_indices: TileTensor[cache_indices_dtype, address_space=cache_indices.address_space, linear_idx_type=cache_indices.linear_idx_type, element_size=cache_indices.element_size], has_initial_state: TileTensor[has_initial_state_dtype, address_space=has_initial_state.address_space, linear_idx_type=has_initial_state.linear_idx_type, element_size=has_initial_state.element_size], conv_states: TileTensor[conv_states_dtype, address_space=conv_states.address_space, linear_idx_type=conv_states.linear_idx_type, element_size=conv_states.element_size], output: TileTensor[output_dtype, address_space=output.address_space, linear_idx_type=output.linear_idx_type, element_size=output.element_size], x_dim_stride: UInt32, x_seqlen_stride: UInt32, weight_dim_stride: UInt32, weight_width_stride: UInt32, out_dim_stride: UInt32, out_seqlen_stride: UInt32, conv_states_batch_stride: UInt32, conv_states_dim_stride: UInt32, conv_states_width_stride: UInt32, silu_activation: Bool, pad_slot_id: Int32, has_cache_indices: Bool, has_initial_state_flag: Bool, has_conv_states: Bool, has_bias: Bool)

Forward pass for causal conv1d with variable length sequences.

Performs causal 1D convolution on variable length sequences that are concatenated together. Uses cumulative sequence lengths to identify sequence boundaries.