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
enqueue_grouped_matmul2d_fp8
def enqueue_grouped_matmul2d_fp8[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>> *?>> *?>>], //, c_type: DType = .float32, block_m: Int = Int(64), block_n: Int = Int(64), block_k: Int = Int(16), sg_m: Int = Int(32), sg_n: Int = Int(32), 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[.bfloat16, Engine=a.Engine, address_space=a.address_space, linear_idx_type=a.linear_idx_type], b: TileTensor[.float8_e4m3fn, Engine=b.Engine, address_space=b.address_space, linear_idx_type=b.linear_idx_type], a_offsets: TileTensor[.uint32, Engine=a_offsets.Engine, address_space=a_offsets.address_space, linear_idx_type=a_offsets.linear_idx_type], expert_ids: TileTensor[.int32, Engine=expert_ids.Engine, address_space=expert_ids.address_space, linear_idx_type=expert_ids.linear_idx_type], max_num_tokens_per_expert: Int, num_active_experts: Int, ctx: DeviceContext, epilogue_fn: EpilogueFnType = no_epilogue_fn, compute_fn: ComputeFnType = no_compute_fn)
Enqueue the tiled grouped (MoE) W8A16 GEMM (transpose_b), raw/unscaled.
The FP8 analog of naive_grouped_matmul on the tiled simdgroup MMA: ONE
kernel dispatch handles all expert groups (grid block_idx.z selects the
group), so there is no host-side per-expert launch loop. a is the ragged
bf16 activation (total_M, K), b the FP8-E4M3 weight stack
(num_experts, N, K), c the ragged output (total_M, N). Each group z
reads its expert weight slab b[expert_ids[z]] and its token rows
[a_offsets[z], a_offsets[z+1]). bf16 A x fp8 B -> fp32 on the native Apple
MMA, direct DRAM B feed (no SMEM). The per-expert weight_scale folds
post-matmul (graph lowering), matching the dense Apple FP8 Linear.
With has_epilogue_fn, epilogue_fn stores each output at its
(row, col) in c instead; an inactive group passes it zeros. With
has_compute_fn, compute_fn maps each output before it is stored.
Raises:
If the attached GPU is older than Apple M5 (compute_capability >= 5).