IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /max/get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
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_mla_decode_ragged_paged_scaled

struct Struct_mla_decode_ragged_paged_scaled

Implemented traitsโ€‹

AnyType, ImplicitlyDestructible

Methodsโ€‹

executeโ€‹

static def execute[dtype: DType, q_dtype: DType, kv_dtype: DType, //, mask_str: StringSlice[StaticConstantOrigin], target: StringSlice[StaticConstantOrigin], per_token_scale_rope_aware: Int = 0, quantization_granularity: Int = 640](output: ManagedTensorSlice[Output, static_spec=output.static_spec], q: ManagedTensorSlice[Input, static_spec=q.static_spec], input_row_offsets: ManagedTensorSlice[Input, static_spec=input_row_offsets.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], kv_scales: ManagedTensorSlice[MutableInput, static_spec=kv_scales.static_spec], q_scales: ManagedTensorSlice[Input, static_spec=q_scales.static_spec], layer_idx: UInt32, scale: Float32, scalar_args: ManagedTensorSlice[Input, static_spec=scalar_args.static_spec], context: DeviceContext)