cugraph
cugraph copied to clipboard
rapidsai
cuGraph - RAPIDS Graph Analytics Library
### What is your question? Are there any functions in cuGraph or its dependency packages to force release CUDA memory after deleting variables? ### Code of Conduct - [x] I...
Disjoint sampling requires that each seed vertex have a separate, non-overlapping subgraph. Pseudocode: ``` (begin hop k; suppose fanout is [f, f, ...]) for each node n: u = get_all_neighbors(n)...
Support adjusting the behavior to allow vertices to be selected with timestamps `>` or `>=` the previous timestamp depending on a flag provided by the user.
Support selecting the *n* vertices with the latest timestamp, to allow the `temporal_strategy='last'` behavior in PyG. i.e. if fanout is [5, 5, 5] then on each hop for each vertex,...
This is intended to explore how we can use CUDASTF within cuGraph
### What is your question? I have followed the instructions here to generate the conda environment : https://docs.rapids.ai/api/cugraph/stable/installation/source_build/ I am facing `binutils` related error when building using 25.04 branch ```...
We continue to have issues with PyTorch in this repository's CI. In addition, the code that depends on PyTorch is really only used by cuGraph-GNN and does not really fit...
This will reduce compile time and binary size. This is a little tricky as currently the methods available on the graph object are subtly different in multi-gpu from single-gpu implementation.
**Describe the solution you'd like and any additional context** I'd like to be able to use [simple_cycles](https://networkx.org/documentation/stable/reference/algorithms/generated/networkx.algorithms.cycles.simple_cycles.html) like I can with NetworkX. ```python import networkx as nx edges =...
### Is this a new feature, an improvement, or a change to existing functionality? New Feature ### How would you describe the priority of this feature request Critical (currently preventing...
