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 function

naive_block_scaled_matmul

def naive_block_scaled_matmul[c_type: DType, a_type: DType, b_type: DType, a_scales_type: DType, b_scales_type: DType, //, *, scaling_kind: UMMAKind, SF_VECTOR_SIZE: Int, accum_type: DType = DType.float32, transpose_b: Bool = True, elementwise_lambda_fn: Optional[def[dtype: DType, width: SIMDSize, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing -> None] = None, BLOCK_DIM: Int = Int(16)](c: LayoutTensor[c_type, element_layout=c.element_layout, layout_int_type=c.layout_int_type, linear_idx_type=c.linear_idx_type, masked=c.masked, alignment=c.alignment], a: LayoutTensor[a_type, element_layout=a.element_layout, layout_int_type=a.layout_int_type, linear_idx_type=a.linear_idx_type, masked=a.masked, alignment=a.alignment], b: LayoutTensor[b_type, element_layout=b.element_layout, layout_int_type=b.layout_int_type, linear_idx_type=b.linear_idx_type, masked=b.masked, alignment=b.alignment], a_scales: LayoutTensor[a_scales_type, element_layout=a_scales.element_layout, layout_int_type=a_scales.layout_int_type, linear_idx_type=a_scales.linear_idx_type, masked=a_scales.masked, alignment=a_scales.alignment], b_scales: LayoutTensor[b_scales_type, element_layout=b_scales.element_layout, layout_int_type=b_scales.layout_int_type, linear_idx_type=b_scales.linear_idx_type, masked=b_scales.masked, alignment=b_scales.alignment], ctx: DeviceContext, alpha: Float32 = 1)

def naive_block_scaled_matmul[c_type: DType, a_type: DType, b_type: DType, a_scales_type: DType, b_scales_type: DType, //, *, scaling_kind: UMMAKind, SF_VECTOR_SIZE: Int, accum_type: DType = DType.float32, transpose_b: Bool = True, elementwise_lambda_fn: Optional[def[dtype: DType, width: SIMDSize, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing -> None] = None, BLOCK_DIM: Int = Int(16)](c: TileTensor[c_type, Storage=c.Storage, linear_idx_type=c.linear_idx_type, element_size=c.element_size], a: TileTensor[a_type, Storage=a.Storage, linear_idx_type=a.linear_idx_type, element_size=a.element_size], b: TileTensor[b_type, Storage=b.Storage, linear_idx_type=b.linear_idx_type, element_size=b.element_size], a_scales: TileTensor[a_scales_type, Storage=a_scales.Storage, linear_idx_type=a_scales.linear_idx_type, element_size=a_scales.element_size], b_scales: TileTensor[b_scales_type, Storage=b_scales.Storage, linear_idx_type=b_scales.linear_idx_type, element_size=b_scales.element_size], ctx: DeviceContext, alpha: Float32 = 1)

TileTensor overload for the naive reference block-scaled matmul.

The reference implementation remains LayoutTensor-based outside SM100. Keep that compatibility shim here so the SM100 testbed can stay TileTensor-native.