IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /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. /get-started.md).

Mojo struct

LayerNormRopeRagged

struct LayerNormRopeRagged

Registers the mo.composite.layer_norm_rope_ragged graph op with the graph compiler.

Fuses LayerNorm with ragged RoPE applied to the leading freqs_cis-width columns of the normalized output; the remaining columns pass through unrotated.

Implemented traitsโ€‹

AnyType, Deinitable, Movable

Methodsโ€‹

executeโ€‹

static def execute[input_dtype: DType, output_dtype: DType, freq_dtype: DType, rank: Int, target: StringSpan[ImmStaticOrigin], interleaved: Bool](output: ManagedTensorSlice[IOSpec[_, _].FusedOutput, static_spec=output.static_spec], input: ManagedTensorSlice[IOSpec[_, _].FusedInput, static_spec=input.static_spec], gamma: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=gamma.static_spec], beta: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=beta.static_spec], epsilon: Float32, input_row_offsets: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=input_row_offsets.static_spec], start_pos: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=start_pos.static_spec], freqs_cis: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=freqs_cis.static_spec], ctx: DeviceContext)