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_grouped_matmul

def naive_blockwise_scaled_fp8_grouped_matmul[c_type: DType, a_type: DType, b_type: DType, a_scales_type: DType, b_scales_type: DType, a_offsets_type: DType, expert_ids_type: DType, c_layout: Layout, a_layout: Layout, b_layout: Layout, a_scale_layout: Layout, b_scale_layout: Layout, a_offsets_layout: Layout, expert_ids_layout: Layout, //, BLOCK_DIM_N: Int = 32, BLOCK_DIM_M: Int = 16, transpose_b: Bool = True, scales_granularity_mnk: Optional[IndexList[3]] = None, elementwise_lambda_fn: Optional[def[dtype: DType, width: Int, *, alignment: Int = 1](IndexList[2], SIMD[dtype, width]) capturing -> None] = None](c: LayoutTensor[c_type, c_layout, address_space=c.address_space, 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, a_layout, address_space=a.address_space, 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, b_layout, address_space=b.address_space, 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, a_scale_layout, address_space=a_scales.address_space, 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, b_scale_layout, address_space=b_scales.address_space, 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], a_offsets: LayoutTensor[a_offsets_type, a_offsets_layout, address_space=a_offsets.address_space, element_layout=a_offsets.element_layout, layout_int_type=a_offsets.layout_int_type, linear_idx_type=a_offsets.linear_idx_type, masked=a_offsets.masked, alignment=a_offsets.alignment], expert_ids: LayoutTensor[expert_ids_type, expert_ids_layout, address_space=expert_ids.address_space, element_layout=expert_ids.element_layout, layout_int_type=expert_ids.layout_int_type, linear_idx_type=expert_ids.linear_idx_type, masked=expert_ids.masked, alignment=expert_ids.alignment], max_num_tokens_per_expert: Int, num_active_experts: Int, ctx: DeviceContext)