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_matmul_dynamic_block_scaled_mxfp4

struct Struct_matmul_dynamic_block_scaled_mxfp4[lane_bytes: Int = Int(16)]

Registers the mo.matmul.dynamic.block.scaled.mxfp4 graph op with the graph compiler.

Parameters

• ​lane_bytes (Int): Operand bytes per lane per MFMA — 16 for MXFP4 (default) or 32 for MXFP8. The kernel reads a/b as raw bytes, so this rather than the operand dtype selects the format, and with it the K extent (K at MXFP8, K // 2 at MXFP4).

Implemented traits

AnyType, Deinitable, Movable

Methods

execute

static def execute[c_type: DType, a_type: DType, b_type: DType, //, target: StringSpan[ImmStaticOrigin]](c: ManagedTensorSlice[IOSpec[_, _].Output, static_spec=c.static_spec], a: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=a.static_spec], b: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=b.static_spec], a_scales: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=a_scales.static_spec], b_scales: ManagedTensorSlice[IOSpec[_, _].Input, static_spec=b_scales.static_spec], context: DeviceContext)