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_dispatch_async_mxfp4
struct Struct_ep_dispatch_async_mxfp4
Implemented traits
AnyType,
ImplicitlyDestructible
Methods
execute
static def execute[input_dtype: DType, dispatch_dtype: DType, dispatch_scale_dtype: DType, hidden_size: Int, top_k: Int, n_experts: Int, max_token_per_rank: Int, n_gpus_per_node: Int, n_nodes: Int, //, target: StringSlice[StaticConstantOrigin]](atomic_counters: ManagedTensorSlice[MutableInput, static_spec=atomic_counters.static_spec], input_tokens: ManagedTensorSlice[Input, static_spec=input_tokens.static_spec], topk_ids: ManagedTensorSlice[Input, static_spec=topk_ids.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], context: DeviceContext)
Execute the Expert Parallelism async dispatch kernel. Tokens are transferred in MXFP4 format with per-token even-mode scales packed alongside the FP4 quants in the send buffer.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!