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_ep_dispatch_mxfp4_expert_load

struct Struct_ep_dispatch_mxfp4_expert_load

Registers ep.dispatch.mxfp4.expert_load: ep.dispatch.mxfp4 that also adds each local expert's routed-token count to an EPLB load tally.

Implemented traitsโ€‹

AnyType, Deinitable, Movable

Methodsโ€‹

executeโ€‹

static def execute[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, skip_a2a: Bool, allreduce_world_size: Int, //, *, MX_FORMAT: StaticString = "auto"](output_tokens: T, output_scales: T, row_offsets: T, expert_ids: T, src_info: T, atomic_counters: T, input_tokens: T, topk_ids: T, send_ptrs: T, recv_ptrs: T, recv_count_ptrs: T, expert_load: T, layer_idx: T, context: DeviceContext)

Runs ep.dispatch.mxfp4 and adds each local expert's routed-token count to row layer_idx[0] of the [layers, n_local_experts] uint64 expert_load tally.

Was this page helpful?