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

grouped_matmul_sm100_persistent

def grouped_matmul_sm100_persistent[c_type: DType, a_type: DType, b_type: DType, transpose_b: Bool, *, config: MatmulConfig[a_type, b_type, c_type, transpose_b], cta_group: Int = Int(1), num_pipeline_stages: Optional[Int] = None, a_swizzle: TensorMapSwizzle = TensorMapSwizzle.SWIZZLE_128B, b_swizzle: TensorMapSwizzle = TensorMapSwizzle.SWIZZLE_128B, elementwise_lambda_fn: Optional[def[dtype: DType, width: SIMDSize, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing -> None] = None](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], a_offsets: TileTensor[DType.uint32, Storage=a_offsets.Storage, linear_idx_type=a_offsets.linear_idx_type, element_size=a_offsets.element_size], b: TileTensor[b_type, Storage=b.Storage, linear_idx_type=b.linear_idx_type, element_size=b.element_size], expert_ids: TileTensor[DType.int32, Storage=expert_ids.Storage, linear_idx_type=expert_ids.linear_idx_type, element_size=expert_ids.element_size], expert_usage_stats: TileTensor[DType.uint32, Storage=expert_usage_stats.Storage, linear_idx_type=expert_usage_stats.linear_idx_type, element_size=expert_usage_stats.element_size], ctx: DeviceContext)