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

Mojo function

generic_cross_attention_kv_cache

def generic_cross_attention_kv_cache[collection_t: KVCollectionT, dtype: DType, //, target: StringSlice[StaticConstantOrigin], mask_str: StringSlice[StaticConstantOrigin], local_window_size: Int = Int(-1), output_dtype: DType = dtype](q: LayoutTensor[dtype, element_layout=q.element_layout, layout_int_type=q.layout_int_type, linear_idx_type=q.linear_idx_type, masked=q.masked, alignment=q.alignment], q_input_row_offsets: LayoutTensor[DType.uint32, element_layout=q_input_row_offsets.element_layout, layout_int_type=q_input_row_offsets.layout_int_type, linear_idx_type=q_input_row_offsets.linear_idx_type, masked=q_input_row_offsets.masked, alignment=q_input_row_offsets.alignment], q_max_seq_len: LayoutTensor[DType.uint32, element_layout=q_max_seq_len.element_layout, layout_int_type=q_max_seq_len.layout_int_type, linear_idx_type=q_max_seq_len.linear_idx_type, masked=q_max_seq_len.masked, alignment=q_max_seq_len.alignment], kv_input_row_offsets: LayoutTensor[DType.uint32, element_layout=kv_input_row_offsets.element_layout, layout_int_type=kv_input_row_offsets.layout_int_type, linear_idx_type=kv_input_row_offsets.linear_idx_type, masked=kv_input_row_offsets.masked, alignment=kv_input_row_offsets.alignment], kv_collection: collection_t, layer_idx: UInt32, scale: Float32, output: LayoutTensor[output_dtype, element_layout=output.element_layout, layout_int_type=output.layout_int_type, linear_idx_type=output.linear_idx_type, masked=output.masked, alignment=output.alignment], context: DeviceContext, sink_weights: OptionalReg[LayoutTensor[dtype, Layout.row_major(Int(-1)), ImmutAnyOrigin]] = None)