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_amd

def grouped_matmul_amd[c_type: DType, a_type: DType, b_type: DType, *, transpose_b: Bool = True, block_tile_shape: IndexList[Int(3)] = Index[Int, Int, Int](Int(128), Int(128), Int(64)), elementwise_lambda_fn: Optional[def[dtype: DType, width: SIMDLength, *, alignment: Int = Int(1)](IndexList[Int(2)], SIMD[dtype, width]) capturing thin -> None] = None](c: TileTensor[c_type, Storage=c.Storage, linear_idx_type=c.linear_idx_type], a: TileTensor[a_type, Storage=a.Storage, linear_idx_type=a.linear_idx_type], a_offsets: TileTensor[DType.uint32, Storage=a_offsets.Storage, linear_idx_type=a_offsets.linear_idx_type], max_num_tokens_per_expert: Int, b: TileTensor[b_type, Storage=b.Storage, linear_idx_type=b.linear_idx_type], expert_ids: TileTensor[DType.int32, Storage=expert_ids.Storage, linear_idx_type=expert_ids.linear_idx_type], num_active_experts: Int, ctx: DeviceContext)

Launches the AMD grouped matmul kernel, selecting the best block-tile configuration for the runtime M dimension via dispatch_amd_matmul_by_block_shape.