Optimize For Gpu

cuGraph Reference

Review: 2026-10-01. Code below is illustrative unless explicitly described as CPU-tested. GPU execution, performance, GDS, and multi-GPU behavior require validation on target hardware.

cuGraph is NVIDIA's GPU-accelerated graph analytics library within the RAPIDS ecosystem. It supports both a direct Python API and an nx-cugraph NetworkX backend. Performance depends on algorithm, graph topology and size, graph-construction cost, fallback behavior, and GPU hardware, so benchmark the complete workload instead of promising a fixed speedup.

Full documentation: https://docs.nvidia.com/cugraph/26.08/ Version target: 26.08 Repository: https://github.com/rapidsai/cugraph

Table of Contents

1. Installation and Setup

2. Two Usage Modes

3. nx-cugraph: Zero-Code-Change NetworkX Backend

4. Direct cuGraph API

5. Graph Creation and Data Loading

6. Supported Graph Types

7. Algorithm Catalog

8. Multi-GPU Support with Dask

9. GNN Support (cugraph-pyg and WholeGraph)

10. Performance Characteristics and Benchmarks

11. Memory Management

12. Interoperability

13. Known Limitations vs NetworkX

14. Common Migration Patterns

Installation and Setup

Use uv add in standalone examples; follow the user's existing project package manager when one is already configured.

uv add --extra-index-url=https://pypi.nvidia.com "cugraph-cu12==26.8.*"    # Core cuGraph for CUDA 12.x
uv add --extra-index-url=https://pypi.nvidia.com "nx-cugraph-cu12==26.8.*" # NetworkX backend
# For CUDA 13.x, use the -cu13 packages: cugraph-cu13, nx-cugraph-cu13

26.08 cuGraph and nx-cugraph wheels are published on PyPI. The NVIDIA index is optional for these current packages; historical releases may still use stub distributions.

Platform: Linux and WSL2 only (no native macOS or Windows). Requires: Python >= 3.11, NVIDIA GPU with CUDA 12.x or 13.x support, NetworkX >= 3.2 (>= 3.5 recommended for optimal nx-cugraph).

Verify:

import cugraph
print(cugraph.__version__)

# Quick test with built-in dataset
from cugraph.datasets import karate
G = karate.get_graph()
result = cugraph.degree_centrality(G)
print(result.head())

Two Usage Modes

Mode 1: nx-cugraph Backend (Zero Code Change)

Accelerate existing NetworkX code by setting one environment variable. No code changes required.

NX_CUGRAPH_AUTOCONFIG=True python my_networkx_script.py

Mode 2: Direct cuGraph API

Use cuGraph's native API for maximum control, working directly with cuDF DataFrames and cuGraph graph objects.

import cugraph
import cudf

edges = cudf.DataFrame({
    "src": [0, 1, 2, 0],
    "dst": [1, 2, 3, 3],
    "weight": [1.0, 2.0, 1.5, 3.0]
})
G = cugraph.Graph()
G.from_cudf_edgelist(edges, source="src", destination="dst", edge_attr="weight")
result = cugraph.pagerank(G)

When to use which:

• nx-cugraph: Existing NetworkX codebases, rapid prototyping, when you want zero migration effort

• Direct API: Maximum performance, multi-GPU workflows, integration with cuDF/cuML pipelines, GNN training

nx-cugraph: Zero-Code-Change NetworkX Backend

nx-cugraph is a NetworkX backend that transparently redirects supported algorithm calls to GPU-accelerated cuGraph implementations.

How It Works

NetworkX >= 3.2 has a backend dispatch system. When nx-cugraph is installed and enabled, NetworkX automatically redirects supported function calls to GPU implementations. Unsupported calls fall back to default NetworkX.

Three Ways to Enable

1. Environment Variable (recommended for zero code change):

export NX_CUGRAPH_AUTOCONFIG=True
python my_script.py
# OR inline:
NX_CUGRAPH_AUTOCONFIG=True python my_script.py

2. Keyword Argument (explicit per-call):

import networkx as nx
result = nx.betweenness_centrality(G, k=10, backend="cugraph")

3. Type-Based Dispatch (explicit graph conversion):

import networkx as nx
import nx_cugraph as nxcg

G_nx = nx.karate_club_graph()
G_gpu = nxcg.from_networkx(G_nx)  # Convert once, reuse for multiple algorithms
result = nx.pagerank(G_gpu)       # Automatically dispatched to GPU

Since 26.04, GPU-backed graphs can also be constructed directly, e.g. nx.Graph(backend="cugraph").

Supported Algorithms in nx-cugraph

Centrality:

• betweenness_centrality, edge_betweenness_centrality

• degree_centrality, in_degree_centrality, out_degree_centrality

• eigenvector_centrality, katz_centrality

Community:

• louvain_communities, leiden_communities

Components:

• connected_components, is_connected, number_connected_components

• node_connected_component

• weakly_connected_components, is_weakly_connected, number_weakly_connected_components

Clustering:

• average_clustering, clustering, transitivity, triangles

Core:

• core_number, k_truss

Link Analysis:

• pagerank, hits

Link Prediction:

• jaccard_coefficient

Shortest Paths (23+ functions):

• shortest_path, shortest_path_length

• has_path, all_pairs_shortest_path, all_pairs_shortest_path_length

• dijkstra_path, dijkstra_path_length, all_pairs_dijkstra, all_pairs_dijkstra_path_length

• bellman_ford_path, bellman_ford_path_length, all_pairs_bellman_ford_path_length

• single_source_shortest_path, single_source_shortest_path_length

• single_source_dijkstra, single_source_dijkstra_path, single_source_dijkstra_path_length

• single_source_bellman_ford, single_source_bellman_ford_path, single_source_bellman_ford_path_length

• single_target_shortest_path_length

Traversal:

• bfs_edges, bfs_layers, bfs_predecessors, bfs_successors, bfs_tree

• generic_bfs_edges, descendants_at_distance

DAG:

• ancestors, descendants

Bipartite:

• betweenness_centrality (bipartite), biadjacency_matrix

• complete_bipartite_graph, from_biadjacency_matrix

Tree:

• is_arborescence, is_branching, is_forest, is_tree

Operators:

• complement, reverse

Reciprocity:

• overall_reciprocity, reciprocity

Isolate:

• is_isolate, isolates, number_of_isolates

Lowest Common Ancestors:

• lowest_common_ancestor

Layout:

• forceatlas2_layout

Graph Generators: Various generators are also supported for creating graphs directly on GPU.

Direct cuGraph API

Quick Example

import cugraph
import cudf

# Load edges from cuDF DataFrame
edges = cudf.DataFrame({
    "source": [0, 1, 2, 3, 0, 2],
    "destination": [1, 2, 3, 4, 4, 1],
    "weight": [1.0, 2.0, 1.0, 3.0, 0.5, 1.5]
})

G = cugraph.Graph(directed=True)
G.from_cudf_edgelist(edges, source="source", destination="destination", edge_attr="weight")

# Run algorithms
pr = cugraph.pagerank(G)
bc = cugraph.betweenness_centrality(G)
components = cugraph.weakly_connected_components(G)

Graph Creation and Data Loading

From cuDF DataFrame (Primary Method)

import cudf, cugraph

df = cudf.DataFrame({"src": [0, 1, 2], "dst": [1, 2, 3], "wt": [1.0, 2.0, 3.0]})

# Unweighted
G = cugraph.Graph()
G.from_cudf_edgelist(df, source="src", destination="dst")

# Weighted
G = cugraph.Graph()
G.from_cudf_edgelist(df, source="src", destination="dst", edge_attr="wt")

# Directed
G = cugraph.Graph(directed=True)
G.from_cudf_edgelist(df, source="src", destination="dst")

From Pandas DataFrame

import pandas as pd, cugraph

df = pd.DataFrame({"src": [0, 1, 2], "dst": [1, 2, 3]})
G = cugraph.Graph()
G.from_pandas_edgelist(df, source="src", destination="dst")

From cuDF Adjacency List

G = cugraph.Graph()
G.from_cudf_adjlist(offsets, indices, values)  # CSR format

From NumPy Array

import numpy as np
adj_matrix = np.array([[0, 1, 0], [1, 0, 1], [0, 1, 0]])
G = cugraph.Graph()
G.from_numpy_array(adj_matrix)

From Pandas Adjacency Matrix

G = cugraph.Graph()
G.from_pandas_adjacency(adj_df)

From Dask-cuDF (Multi-GPU)

G = cugraph.Graph()
G.from_dask_cudf_edgelist(dask_cudf_df, source="src", destination="dst")

From Built-in Datasets

from cugraph.datasets import karate, dolphins, polbooks, netscience
G = karate.get_graph()

Symmetrization (Undirected Graphs)

# Ensure all edges are bidirectional
sym_df = cugraph.symmetrize_df(df, "src", "dst")

# Or symmetrize a graph directly
sym_df = cugraph.symmetrize(source_col, dest_col, weight_col)

Vertex Renumbering

cuGraph internally renumbers vertices to contiguous integers starting from 0. Native high-level algorithms such as PageRank already restore external IDs. Do not unrenumber those results twice:

result = cugraph.pagerank(G)
# Use G.unrenumber only for an explicitly internal-ID table from a lower-level API.

Supported Graph Types

Important: cuGraph uses a CSR (Compressed Sparse Row) internal representation. Graphs are immutable after creation -- you cannot dynamically add/remove individual edges after calling from_cudf_edgelist(). To modify a graph, reconstruct it from a new DataFrame.

Algorithm Catalog

The multi-GPU column uses callable aliases exported by import cugraph.dask. Namespace subpackages may instead expose modules or single-GPU imports; do not construct an API path by inserting centrality, community, or components. Column entries identify APIs, not interchangeable return schemas or weight support.

Centrality

Community Detection

Clustering Analysis:

• cugraph.analyzeClustering_edge_cut(G, n_clusters, clustering)

• cugraph.analyzeClustering_modularity(G, n_clusters, clustering)

• cugraph.analyzeClustering_ratio_cut(G, n_clusters, clustering)

Traversal

Link Analysis

Link Prediction / Similarity

NetworkX-compatible wrappers: cugraph.jaccard_coefficient(G, ebunch), cugraph.overlap_coefficient(G, ebunch), cugraph.sorensen_coefficient(G, ebunch)

Components

Cores

Sampling

Layout

Tree

Linear Assignment

Utilities

Multi-GPU Support with Dask

cuGraph supports multi-GPU computation through Dask for graphs that exceed single-GPU memory or need faster processing.

Setup

from dask.distributed import Client
from dask_cuda import LocalCUDACluster
import cugraph
import cugraph.dask as dask_cugraph
import dask_cudf

# Initialize multi-GPU cluster
cluster = LocalCUDACluster()
client = Client(cluster)
import cugraph.dask.comms.comms as Comms
Comms.initialize(p2p=True)

# Load distributed edge list
ddf = dask_cudf.read_csv("large_graph.csv", names=["src", "dst", "weight"])

# Create distributed graph
G = cugraph.Graph(directed=True)
G.from_dask_cudf_edgelist(ddf, source="src", destination="dst", edge_attr="weight")

# Run multi-GPU algorithms
pr = dask_cugraph.pagerank(G)
components = dask_cugraph.weakly_connected_components(G)
# Materialize or write distributed outputs before teardown.
pr_local = pr.compute()
Comms.destroy()
client.close()
cluster.close()

Algorithms with Multi-GPU Support

The following algorithms have Dask-based multi-GPU implementations:

• Centrality: Betweenness, Edge Betweenness, Eigenvector, Katz

• Community: Louvain, Leiden, ECG, K-Truss, Triangle Counting, EgoNet, Induced Subgraph

• Components: Weakly Connected Components

• Cores: Core Number, K-Core

• Link Analysis: PageRank, HITS

• Link Prediction: Overlap, Sorensen

• Sampling: Random Walks, Biased Random Walks, Uniform Random Walks, Node2Vec, Neighborhood Sampling

• Traversal: BFS, SSSP

• Utilities: Renumbering, Symmetrize, Path Extraction, Two-Hop Neighbors, RMAT Generator

GNN Support

cugraph-pyg (PyTorch Geometric Integration)

As of release 25.06, cugraph-pyg is the recommended GNN framework integration (cuGraph-DGL has been removed).

cugraph-pyg provides native GPU-accelerated implementations of PyG's core interfaces:

• GraphStore: GPU-accelerated graph storage using cuGraph's CSR representation

• FeatureStore: GPU-resident feature storage for node/edge features

• Sampler/Loader: GPU-accelerated neighborhood sampling with configurable fan-out

uv add --extra-index-url=https://pypi.nvidia.com "cugraph-pyg-cu12==26.8.*"

Key capabilities:

• Heterogeneous graph sampling (multiple node/edge types)

• Multi-GPU distributed sampling

• Direct integration with PyG's NeighborLoader and training loops

• GPU-accelerated centrality, community detection, and other analytics within PyG workflows

Repository: https://github.com/rapidsai/cugraph-gnn

WholeGraph (Distributed GPU Memory for GNNs)

WholeGraph provides distributed GPU memory management for large-scale GNN training through its WholeMemory abstraction.

uv add --extra-index-url=https://pypi.nvidia.com "pylibwholegraph-cu12==26.8.*"

Core concepts:

• WholeMemory: A unified view of GPU memory distributed across multiple GPUs. Each GPU sees the entire memory space through a single abstraction, even though data is physically distributed.

• WholeMemory Communicator: Defines the set of GPUs that collaborate, with one process per GPU.

• WholeMemory Tensor: Like PyTorch tensors but distributed; supports 1D and 2D data with first dimension partitioned across GPUs.

• WholeMemory Embedding: 2D tensor variant with built-in cache policies and sparse optimizers (SGD, Adam, RMSProp, AdaGrad).

Memory modes:

Storage locations: Host memory (pinned) or device/GPU memory.

Graph storage: CSR format with ROW_INDEX and COL_INDEX as WholeMemory Tensors for efficient distributed graph management.

Cache policies: Device-cached host memory, local-cached global memory -- critical for handling graphs larger than GPU memory.

Target hardware: NVLink systems like DGX A100/H100 servers for optimal performance.

cuGraph-DGL (DEPRECATED)

cuGraph-DGL has been removed as of release 25.06. Users should migrate to cugraph-pyg. The cuGraph team is not planning further work in the DGL ecosystem.

Performance Characteristics and Benchmarks

Benchmark with the user's actual topology and algorithm:

1. Check that the requested NetworkX algorithm dispatches to nx-cugraph rather than falling back to CPU.

2. Measure graph construction and conversion separately from repeated algorithm calls, then report both warm algorithm time and end-to-end time.

3. Warm the CUDA context before collecting timed repetitions.

4. Verify output semantics, convergence tolerance, sampled-algorithm parameters, and floating-point tolerance against the CPU implementation.

5. Record vertices, edges, directedness, weight dtype, GPU model, CPU baseline, software versions, and whether the graph was already device-resident.

6. Use multi-GPU only after estimating graph and temporary-memory requirements and measuring the communication cost.

Small or one-shot graphs can lose to NetworkX after setup and transfer. Large device-resident graphs with supported algorithms are better candidates, but graph size alone does not establish a speedup.

Memory Management

GPU Memory Considerations

• cuGraph stores graphs in CSR format on GPU memory

• Estimate CSR storage from offset/index/weight dtypes, edge symmetrization, renumber maps and retained edge lists. Peak construction/algorithm memory can be much larger than final CSR storage.

• Algorithm working memory varies; some algorithms (like betweenness centrality) need additional O(V) or O(E) temporary space

Strategies for Large Graphs

1. Use multi-GPU via Dask for graphs exceeding single GPU memory

2. Use WholeGraph for GNN workloads that need distributed feature/graph storage

3. Use rmm (RAPIDS Memory Manager) for fine-grained GPU memory control:

   Copy

   import rmm
   rmm.reinitialize(pool_allocator=True, initial_pool_size=2**30)  # 1 GB pool

4. Monitor memory with nvidia-smi or cupy.cuda.runtime.memGetInfo() (device free/total, not per-process peak)

5. Delete intermediate results explicitly: del result; import gc; gc.collect()

Interoperability

With cuDF

cuGraph natively consumes and produces cuDF DataFrames. Algorithm results are returned as cuDF DataFrames with vertex/edge columns.

import cudf, cugraph
# Create graph from cuDF
edges = cudf.read_csv("edges.csv")
G = cugraph.Graph()
G.from_cudf_edgelist(edges, source="src", destination="dst")

# Results come back as cuDF DataFrames
pr = cugraph.pagerank(G)  # cuDF DataFrame with 'vertex' and 'pagerank' columns

With cuML

Pipe graph analytics results into cuML for downstream ML:

import cuml
# Use graph embeddings (e.g., from Node2Vec) as features for cuML
# Or use community labels as features for classification
louvain_result = cugraph.louvain(G)
# Feed partition labels into cuML models

With CuPy / SciPy

# cuGraph can work with CuPy and SciPy sparse matrices as input data
import cupy, scipy

With NetworkX

import networkx as nx
import nx_cugraph as nxcg

# Convert once when repeated algorithms justify keeping the graph on GPU.
G_nx = nx.karate_club_graph()
G_gpu = nxcg.from_networkx(G_nx)
result = nx.pagerank(G_gpu)

With PyTorch Geometric

# Via cugraph-pyg (see GNN Support section)
from cugraph_pyg.data import GraphStore, FeatureStore
from cugraph_pyg.loader import NeighborLoader

With Pandas

import pandas as pd
df = pd.DataFrame({"src": [0, 1, 2], "dst": [1, 2, 3]})
G = cugraph.Graph()
G.from_pandas_edgelist(df, source="src", destination="dst")

Known Limitations vs NetworkX

1. Immutable graphs: Cannot add/remove individual edges after graph creation. Must reconstruct from DataFrame.

2. No node/edge attributes on Graph object: cuGraph stores structure only. Node/edge properties must be maintained separately (e.g., in cuDF DataFrames). The nx-cugraph backend handles attribute mapping transparently.

3. Vertex types: Vertices must be integers (or will be renumbered to integers internally). String vertex IDs are renumbered automatically.

4. Not all NetworkX algorithms supported: Check the nx-cugraph supported algorithms list. Unsupported calls fall back to CPU NetworkX.

5. Numerical precision: GPU floating-point results may differ slightly from CPU results due to parallel reduction ordering.

6. No dynamic graphs: cuGraph is designed for static graph analytics, not streaming/dynamic graph updates.

7. Strongly Connected Components: Single-GPU only (no multi-GPU Dask variant).

8. Spectral Clustering: Single-GPU only.

9. Minimum/Maximum Spanning Tree: Single-GPU only.

10. Force Atlas 2 layout: Single-GPU only.

11. Compatibility doc: The official list of NetworkX APIs accelerated by nx-cugraph is maintained at https://docs.nvidia.com/cugraph/26.08/nx_cugraph/supported-algorithms/ (~80 algorithms plus generators and utilities).

Common Migration Patterns

NetworkX to nx-cugraph (Zero Effort)

# Before (CPU):
import networkx as nx
G = nx.from_pandas_edgelist(df, "src", "dst")
pr = nx.pagerank(G)

# After (GPU, no code changes):
# Just set: NX_CUGRAPH_AUTOCONFIG=True
# Same code runs on GPU automatically

NetworkX to Direct cuGraph API

# Before (NetworkX):
import networkx as nx
G = nx.from_pandas_edgelist(df, "src", "dst")
pr = nx.pagerank(G, alpha=0.85)
bc = nx.betweenness_centrality(G)  # Exact baseline; use matched sampling for large graphs
communities = nx.community.louvain_communities(G, resolution=1.0)

# After (cuGraph):
import cudf, cugraph
edges = cudf.from_pandas(df)
G = cugraph.Graph()
G.from_cudf_edgelist(edges, source="src", destination="dst")
pr = cugraph.pagerank(G, alpha=0.85)
bc = cugraph.betweenness_centrality(G)
parts, modularity = cugraph.louvain(G, resolution=1.0)

Pandas to cuDF + cuGraph Pipeline

# Before:
import pandas as pd
import networkx as nx
df = pd.read_csv("edges.csv")
G = nx.from_pandas_edgelist(df, "source", "target", "weight")
result = nx.pagerank(G)

# After:
import cudf
import cugraph
df = cudf.read_csv("edges.csv")
G = cugraph.Graph()
G.from_cudf_edgelist(df, source="source", destination="target", edge_attr="weight")
result = cugraph.pagerank(G)

Adding Multi-GPU to Existing cuGraph Code

# Before (single-GPU):
import cugraph
G = cugraph.Graph()
G.from_cudf_edgelist(edges, source="src", destination="dst")
result = cugraph.pagerank(G)

# After (multi-GPU):
from dask.distributed import Client
from dask_cuda import LocalCUDACluster
import cugraph, cugraph.dask as dcg
import dask_cudf

cluster = LocalCUDACluster()
client = Client(cluster)
import cugraph.dask.comms.comms as Comms
Comms.initialize(p2p=True)

ddf = dask_cudf.from_cudf(edges, npartitions=len(cluster.workers))
G = cugraph.Graph()
G.from_dask_cudf_edgelist(ddf, source="src", destination="dst")
result = dcg.pagerank(G)
result_local = result.compute()  # Only if the result fits one GPU
Comms.destroy()
client.close()
cluster.close()