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_blockwise_scaled_fp8_matmul

def naive_blockwise_scaled_fp8_matmul[c_type: DType, a_type: DType, b_type: DType, a_scales_type: DType, b_scales_type: DType, //, *, BLOCK_DIM: Int = Int(16), transpose_b: Bool = False, elementwise_lambda_fn: Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None] = None, accum_type: DType = get_accum_type[c_type](), scales_granularity_mnk: Optional[IndexList[Int(3)]] = None](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)

Dispatches the naive blockwise scaled FP8 matmul kernel on the GPU.

Converts the LayoutTensor operands to TileTensor views and enqueues naive_blockwise_scaled_fp8_matmul_kernel with a 2D grid of BLOCK_DIM-sized tiles covering the M x N output.

Args:

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]): Rank-2 output accumulator tensor.
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]): Rank-2 FP8 input matrix in K-major format.
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]): Rank-2 FP8 weight matrix; K-major when transpose_b is True, otherwise N-major.
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]): Rank-2 per-block scales for a in M-major format.
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]): Rank-2 per-block scales for b; K-major when transpose_b is True, otherwise N-major.
ctx (DeviceContext): Device context used to enqueue the kernel.