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 function

sm100_heuristic_and_outliers_dispatch

def sm100_heuristic_and_outliers_dispatch[c_type: DType, a_type: DType, b_type: DType, ComputeFnType: ElementwiseComputeFn, //, transpose_b: Bool = True, elementwise_lambda_fn: Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None] = None, pdl_level: PDLLevel = PDLLevel(), has_epilogue_tensor: Bool = False, epilogue_is_1d: Bool = False, EpilogueEngine: TensorEngine = DefaultEngine, has_compute_fn: Bool = True](c: TileTensor[c_type, Engine=c.Engine, address_space=c.address_space, linear_idx_type=c.linear_idx_type], a: TileTensor[a_type, Engine=a.Engine, address_space=a.address_space, linear_idx_type=a.linear_idx_type], b: TileTensor[b_type, Engine=b.Engine, address_space=b.address_space, linear_idx_type=b.linear_idx_type], compute_fn: ComputeFnType, ctx: DeviceContext, epilogue_tensor: OptionalReg[TileTensor[c_type, Layout[TypeList[Int64, Int64](), TypeList[Int64, ComptimeInt[Int(1)]]()], ImmutAnyOrigin, Engine=EpilogueEngine]] = None) -> Int

Dispatches an SM100 matmul with a compute epilogue closure through the heuristic outlier config set.

Wraps select_and_launch_sm100_config with a launch callback that invokes blackwell_matmul_tma_umma_warp_specialized directly, passing through the elementwise epilogue lambda and compute_fn.

Parameters:

• ​c_type (DType): Output element type (inferred).
• ​a_type (DType): Element type of the LHS operand a (inferred).
• ​b_type (DType): Element type of the RHS operand b (inferred).
• ​ComputeFnType (ElementwiseComputeFn): Type of the compute epilogue closure (inferred).
• ​transpose_b (Bool): Whether b is stored transposed (defaults to True).
• ​elementwise_lambda_fn (Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None]): Optional epilogue applied to each output element (defaults to None).
• ​pdl_level (PDLLevel): Programmatic dependent launch level for the dispatched kernel (defaults to PDLLevel()).
• ​has_epilogue_tensor (Bool): Whether an epilogue tensor is supplied for the TMA epilogue load path (defaults to False).
• ​epilogue_is_1d (Bool): Whether the epilogue tensor is treated as 1D rather than row-major 2D (defaults to False).
• ​EpilogueEngine (TensorEngine): Engine of the epilogue tensor (defaults to DefaultEngine[element_width=1]).
• ​has_compute_fn (Bool): Whether to apply compute_fn. When False, compute_fn is ignored (defaults to True).

Returns:

Int: DISPATCH_HIT when a kernel was launched, DISPATCH_MISS otherwise.