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 struct
Struct_indexer_score_ragged_paged
struct Struct_indexer_score_ragged_paged
Registers the mo.indexer_score.ragged.paged graph op with the graph compiler.
DeepSeek-V4 lightning-indexer scores: every query row against the live
entries of one layer of a paged compressed leaf, relu'd, weighted per
head and summed over the given heads. See nn.attention.indexer_score.
Implemented traits
Methods
execute
static def execute[q_type: DType, kv_type: DType, //, num_heads: Int, target: StringSpan[ImmStaticOrigin]](output: ManagedTensorSlice[IOSpec[_, _].Output, static_spec=output.static_spec], q: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=q.static_spec], weights: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=weights.static_spec], input_row_offsets: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=input_row_offsets.static_spec], base: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=base.static_spec], cutoff: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=cutoff.static_spec], kv_blocks: ManagedTensorSlice[IOSpec[_, _].MutableInput, static_spec=kv_blocks.static_spec], page_stride: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=page_stride.static_spec], cache_lengths: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=cache_lengths.static_spec], kv_lookup_table: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=kv_lookup_table.static_spec], max_prompt_length: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=max_prompt_length.static_spec], max_cache_length: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=max_cache_length.static_spec], layer: UInt32, context: DeviceContext)