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_moe_sink_gate_router
struct Struct_moe_sink_gate_router
Registers the mo.moe.sink.gate.router graph op with the graph compiler.
Implemented traits
Methods
execute
static def execute[scores_type: DType, bias_type: DType, //, n_routed_experts: Int, n_experts_per_tok: Int, n_shared_experts: Int, target: StringSpan[ImmStaticOrigin]](expert_indices: ManagedTensorSlice[IOSpec[_, _].Output, static_spec=expert_indices.static_spec], expert_weights: ManagedTensorSlice[IOSpec[_, _].Output, static_spec=expert_weights.static_spec], sink_weights: ManagedTensorSlice[IOSpec[_, _].Output, static_spec=sink_weights.static_spec], logits: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=logits.static_spec], expert_bias: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=expert_bias.static_spec], global_scale: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=global_scale.static_spec], route_scale: Float32, context: DeviceContext)