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
block_scaled_matmul_with_epilogue
def block_scaled_matmul_with_epilogue[c_type: DType, a_type: DType, b_type: DType, scales_dtype: DType, EpilogueFnType: ElementwiseEpilogueFn = inflated$def[comptime[dtype: DType, width: SIMDLength, *, alignment: Int] #kgen.func.symbol<@linalg::@utils::@"_no_epilogue_body[::DType,::SIMDLength,::SIMD[DType.int, 1],KGENParamList[::Intable & ::Defaultable & ::RegisterPassable & ::TrivialRegisterPassable & ::Writable & ::AnyType & ::Copyable & ::ImplicitlyCopyable & ::Deinitable & ::Movable & ::CoordLike],::TypeList[::Intable & ::Defaultable & ::RegisterPassable & ::TrivialRegisterPassable & ::Writable & ::AnyType & ::Copyable & ::ImplicitlyCopyable & ::Deinitable & ::Movable & ::CoordLike, $3]](::Coord[$3, $4],::SIMD[$0, $1])"<:!lit.struct<@std::@builtin::@dtype::@DType> dtype, :!lit.struct<@std::@builtin::@simd_length::@SIMDLength> width, :!lit.struct<@std::@simd::@SIMD<:!lit.struct<@std::@builtin::@dtype::@DType> {:dtype index}, :!lit.struct<@std::@builtin::@simd_length::@SIMDLength> {1}>> alignment, :param_list<trait<@std::@builtin::@int::@Intable, @std::@builtin::@value::@Defaultable, @std::@builtin::@value::@RegisterPassable, @std::@builtin::@value::@TrivialRegisterPassable, @std::@format::@__init__::@Writable, @std::@traits::@anytype::@AnyType, @std::@traits::@copyable::@Copyable, @std::@traits::@copyable::@ImplicitlyCopyable, @std::@traits::@deinitable::@Deinitable, @std::@traits::@movable::@Movable, @std::@utils::@coord::@CoordLike>> *?, :!lit.struct<@std::@builtin::@variadics::@TypeList<:meta<!lit.trait<@std::@traits::@anytype::@AnyType>> trait<@std::@builtin::@int::@Intable, @std::@builtin::@value::@Defaultable, @std::@builtin::@value::@RegisterPassable, @std::@builtin::@value::@TrivialRegisterPassable, @std::@format::@__init__::@Writable, @std::@traits::@anytype::@AnyType, @std::@traits::@copyable::@Copyable, @std::@traits::@copyable::@ImplicitlyCopyable, @std::@traits::@deinitable::@Deinitable, @std::@traits::@movable::@Movable, @std::@utils::@coord::@CoordLike>, :param_list<trait<@std::@builtin::@int::@Intable, @std::@builtin::@value::@Defaultable, @std::@builtin::@value::@RegisterPassable, @std::@builtin::@value::@TrivialRegisterPassable, @std::@format::@__init__::@Writable, @std::@traits::@anytype::@AnyType, @std::@traits::@copyable::@Copyable, @std::@traits::@copyable::@ImplicitlyCopyable, @std::@traits::@deinitable::@Deinitable, @std::@traits::@movable::@Movable, @std::@utils::@coord::@CoordLike>> *?>> *?>>], ComputeFnType: ElementwiseComputeFn = inflated$def[comptime[dtype: DType, width: SIMDLength, *, alignment: Int] #kgen.func.symbol<@linalg::@utils::@"identity_compute_fn[::DType,::SIMDLength,::SIMD[DType.int, 1],KGENParamList[::Intable & ::Defaultable & ::RegisterPassable & ::TrivialRegisterPassable & ::Writable & ::AnyType & ::Copyable & ::ImplicitlyCopyable & ::Deinitable & ::Movable & ::CoordLike],::TypeList[::Intable & ::Defaultable & ::RegisterPassable & ::TrivialRegisterPassable & ::Writable & ::AnyType & ::Copyable & ::ImplicitlyCopyable & ::Deinitable & ::Movable & ::CoordLike, $3]](::Coord[$3, $4],::SIMD[$0, $1])"<:!lit.struct<@std::@builtin::@dtype::@DType> dtype, :!lit.struct<@std::@builtin::@simd_length::@SIMDLength> width, :!lit.struct<@std::@simd::@SIMD<:!lit.struct<@std::@builtin::@dtype::@DType> {:dtype index}, :!lit.struct<@std::@builtin::@simd_length::@SIMDLength> {1}>> alignment, :param_list<trait<@std::@builtin::@int::@Intable, @std::@builtin::@value::@Defaultable, @std::@builtin::@value::@RegisterPassable, @std::@builtin::@value::@TrivialRegisterPassable, @std::@format::@__init__::@Writable, @std::@traits::@anytype::@AnyType, @std::@traits::@copyable::@Copyable, @std::@traits::@copyable::@ImplicitlyCopyable, @std::@traits::@deinitable::@Deinitable, @std::@traits::@movable::@Movable, @std::@utils::@coord::@CoordLike>> *?, :!lit.struct<@std::@builtin::@variadics::@TypeList<:meta<!lit.trait<@std::@traits::@anytype::@AnyType>> trait<@std::@builtin::@int::@Intable, @std::@builtin::@value::@Defaultable, @std::@builtin::@value::@RegisterPassable, @std::@builtin::@value::@TrivialRegisterPassable, @std::@format::@__init__::@Writable, @std::@traits::@anytype::@AnyType, @std::@traits::@copyable::@Copyable, @std::@traits::@copyable::@ImplicitlyCopyable, @std::@traits::@deinitable::@Deinitable, @std::@traits::@movable::@Movable, @std::@utils::@coord::@CoordLike>, :param_list<trait<@std::@builtin::@int::@Intable, @std::@builtin::@value::@Defaultable, @std::@builtin::@value::@RegisterPassable, @std::@builtin::@value::@TrivialRegisterPassable, @std::@format::@__init__::@Writable, @std::@traits::@anytype::@AnyType, @std::@traits::@copyable::@Copyable, @std::@traits::@copyable::@ImplicitlyCopyable, @std::@traits::@deinitable::@Deinitable, @std::@traits::@movable::@Movable, @std::@utils::@coord::@CoordLike>> *?>> *?>>], //, *, SF_VECTOR_SIZE: Int, transpose_b: Bool = True, has_epilogue_fn: Bool = False, has_compute_fn: Bool = False](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], a_scales: TileTensor[scales_dtype, Engine=a_scales.Engine, address_space=a_scales.address_space, linear_idx_type=a_scales.linear_idx_type], b_scales: TileTensor[scales_dtype, Engine=b_scales.Engine, address_space=b_scales.address_space, linear_idx_type=b_scales.linear_idx_type], tensor_sf: Float32, ctx: DeviceContext, epilogue_fn: EpilogueFnType = no_epilogue_fn, compute_fn: ComputeFnType = no_compute_fn)
Our sm100 block scaled matmul kernel still does not support fusion of elementwise operations. This is a temporary implementation that uses our sm100 block scaled matmul kernel and dispatch a separate epilogue kernel to apply the elementwise operations. Callers must allocate c; with has_epilogue_fn or has_compute_fn the matmul result is written into c and then read back by the closure.
Parameters:
- c_type (
DType): Element type of the output matrix (inferred). - a_type (
DType): Element type of the LHS input matrix (inferred). - b_type (
DType): Element type of the RHS input matrix (inferred). - scales_dtype (
DType): Element type of the block scale-factor tensors (inferred). - EpilogueFnType (
ElementwiseEpilogueFn): Type ofepilogue_fn(inferred). - ComputeFnType (
ElementwiseComputeFn): Type ofcompute_fn(inferred). - SF_VECTOR_SIZE (
Int): Number of elements covered by each block scale factor: 16 for NVFP4 or 32 for MXFP8. - transpose_b (
Bool): Whetherbis stored transposed (defaults toTrue). - has_epilogue_fn (
Bool): Whetherepilogue_fnreceives the matmul result after it is written toc. - has_compute_fn (
Bool): Whethercompute_fntransforms the matmul result inc.
Args:
- c (
TileTensor[c_type, Engine=c.Engine, address_space=c.address_space, linear_idx_type=c.linear_idx_type]): Output matrix of shape[M, N]. - a (
TileTensor[a_type, Engine=a.Engine, address_space=a.address_space, linear_idx_type=a.linear_idx_type]): LHS input matrix of shape[M, K]for FP8 or[M, K//2]for packed FP4uint8. - b (
TileTensor[b_type, Engine=b.Engine, address_space=b.address_space, linear_idx_type=b.linear_idx_type]): RHS input matrix of shape[N, K]for FP8 or[N, K//2]for packed FP4uint8, stored transposed. - a_scales (
TileTensor[scales_dtype, Engine=a_scales.Engine, address_space=a_scales.address_space, linear_idx_type=a_scales.linear_idx_type]): Block scale factors forain the 5D TCGEN interleaved layout. - b_scales (
TileTensor[scales_dtype, Engine=b_scales.Engine, address_space=b_scales.address_space, linear_idx_type=b_scales.linear_idx_type]): Block scale factors forbin the 5D TCGEN interleaved layout. - tensor_sf (
Float32): Scalar multiplier applied to the matmul result. - ctx (
DeviceContext): Device context used to enqueue kernels. - epilogue_fn (
EpilogueFnType): Withhas_epilogue_fn, receives each output value at its(m, n). - compute_fn (
ComputeFnType): Withhas_compute_fn, maps each output value before it is stored back intoc.