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 struct
Struct_kv_cache_ragged_paged_2m_iadd
struct Struct_kv_cache_ragged_paged_2m_iadd
Implemented traits
AnyType,
ImplicitlyDestructible
Methods
execute
static def execute[dtype: DType, //, target: StringSlice[StaticConstantOrigin]](kv: ManagedTensorSlice[Input, static_spec=kv.static_spec], kv_blocks: ManagedTensorSlice[MutableInput, static_spec=kv_blocks.static_spec], cache_lengths: ManagedTensorSlice[Input, static_spec=cache_lengths.static_spec], kv_lookup_table: ManagedTensorSlice[Input, static_spec=kv_lookup_table.static_spec], max_lengths: ManagedTensorSlice[Input, static_spec=max_lengths.static_spec], input_row_offsets: ManagedTensorSlice[Input, static_spec=input_row_offsets.static_spec], lora_end_idx: ManagedTensorSlice[Input, static_spec=lora_end_idx.static_spec], batch_seq_len: ManagedTensorSlice[Input, static_spec=batch_seq_len.static_spec], layer_idx: UInt32, context: DeviceContext)
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!