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

Struct_moe_sigmoid_gemv_single_group_router

struct Struct_moe_sigmoid_gemv_single_group_router

Registers the mo.moe.sigmoid.gemv.single.group.router graph op.

Fuses the router GEMV and sigmoid into the single-group router.

Implemented traitsโ€‹

AnyType, Deinitable, Movable

Methodsโ€‹

executeโ€‹

static def execute[hidden_type: DType, weight_type: DType, bias_type: DType, //, n_routed_experts: Int, n_experts_per_tok: Int, norm_weights: Bool, target: StaticString](expert_indices: ManagedTensorSlice[IOSpec[_, _].Output, static_spec=expert_indices.static_spec], expert_weights: ManagedTensorSlice[IOSpec[_, _].Output, static_spec=expert_weights.static_spec], hidden: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=hidden.static_spec], gate_weight: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=gate_weight.static_spec], expert_bias: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=expert_bias.static_spec], routed_scaling_factor: Float32, context: DeviceContext)

Was this page helpful?