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_ep_combine_skip_a2a
struct Struct_ep_combine_skip_a2a
Implemented traits
AnyType,
ImplicitlyDestructible
Methods
execute
static def execute[combine_dtype: DType, router_weights_dtype: DType, hidden_size: Int, top_k: Int, n_experts: Int, max_token_per_rank: Int, n_gpus_per_node: Int, n_nodes: Int, fused_shared_expert: Bool, lambdas_have_fusion: Bool, skip_a2a: Bool, allreduce_world_size: Int, //, target: StringSlice[StaticConstantOrigin]](output_tokens: ManagedTensorSlice[FusedOutput, static_spec=output_tokens.static_spec], atomic_counters: ManagedTensorSlice[MutableInput, static_spec=atomic_counters.static_spec], input_tokens: ManagedTensorSlice[Input, static_spec=input_tokens.static_spec], src_info: ManagedTensorSlice[Input, static_spec=src_info.static_spec], send_ptrs: ManagedTensorSlice[Input, static_spec=send_ptrs.static_spec], recv_ptrs: ManagedTensorSlice[Input, static_spec=recv_ptrs.static_spec], recv_count_ptrs: ManagedTensorSlice[Input, static_spec=recv_count_ptrs.static_spec], router_weights: ManagedTensorSlice[Input, static_spec=router_weights.static_spec], topk_ids: ManagedTensorSlice[Input, static_spec=topk_ids.static_spec], context: DeviceContext)
Execute the fused Expert Parallelism combine kernel.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!