as_adjacency_matrix     Extract a graph adjacency matrix
as_coo                  Convert sparse storage format
cuda_available          Detect a usable CUDA backend
cuda_diagnostics        Diagnose the optional CUDA runtime
cuda_diffusion_map      Diffusion-map-style embedding
cuda_distance           Pairwise distances with an optional CUDA
                        backend
cuda_kmeans             GPU-aware k-means clustering
cuda_knn                k-nearest neighbours
cuda_knn_graph          Build a sparse graph from nearest neighbours
cuda_leiden             Cluster a graph with Leiden
cuda_louvain            Cluster a graph with Louvain
cuda_memory_info        Inspect CUDA memory
cuda_pca                GPU-aware principal component analysis
cuda_provenance         Inspect actual compute provenance
cuda_select_device      Select a computation device without hiding
                        fallback
cuda_sparse             Create a GPU-aware sparse matrix
cuda_stage              Record one compute stage
cuda_svd                GPU-aware singular value decomposition
cuda_tensor             Create a GPU-aware tensor
cuda_tsne               t-SNE embedding
cuda_umap               UMAP embedding
cudatensor-operators    Arithmetic operators for GPU-aware tensors
cudatensor-subset       Subset and replace tensor values
dimnames.cudasparse     Inspect sparse matrix dimension labels
dimnames.cudatensor     Inspect tensor dimension labels
embedding_coordinates   Extract embedding coordinates
predict.cuda_kmeans     Assign observations with a fitted CUDA-aware
                        k-means model
predict.cuda_pca        Project observations with a fitted CUDA-aware
                        PCA model
sparse_info             Inspect sparse matrix metadata
sparse_matmul_dense     Sparse matrix by dense matrix multiplication
sparse_matvec           Sparse matrix-vector multiplication
sparse_normalize        Normalize sparse rows or columns without
                        densifying
sparse_row_sums         Sparse row and column reductions
t.cudasparse            Transpose a GPU-aware sparse matrix
tensor_broadcast_to     Broadcast a tensor to a compatible shape
tensor_device           Inspect tensor device and backend
tensor_matmul           Matrix multiplication for tensors
tensor_reshape          Reshape a tensor without changing its values
tensor_shape            Inspect tensor shape
tensor_sum              Tensor reductions
to_cpu                  Transfer tensor data to base R
to_device               Transfer a tensor to a device
to_dgCMatrix            Convert to an R sparse matrix
