Mojo function
generic_flare_mla_prefill_ragged_paged_plan
generic_flare_mla_prefill_ragged_paged_plan[target: StringSlice[StaticConstantOrigin]](input_row_offsets: LayoutTensor[DType.uint32, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], kv_collection: PagedKVCacheCollection[dtype_, kv_params_, page_size], layer_idx: UInt32, buffer_token_size: UInt32, buffer_row_offsets: LayoutTensor[DType.uint32, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], cache_offsets: LayoutTensor[DType.uint32, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], buffer_lengths: LayoutTensor[DType.int32, layout, origin, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], context: DeviceContextPtr)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!