-
MWE:
```julia
using CUDA, SparseArrays, LinearAlgebra
CUDA.allowscalar(false)
W = CUDA.CUSPARSE.CuSparseMatrixCSR(sprand(100,100,0.1))
```
Now if you factorize you get CPU fallbacks:
```j…
-
I believe there is currently no sparse matrix capability in Metal.jl. What is the easiest way to get some basic things working?
Perhaps a bigger question is whether we can have a generic sparse mat…
-
@kangshiyin, there is something I need to be done in the 'rnnlm' branch.
We'll need the cuSPARSE library. It will include some changes to the headers and the Makefiles.
Also, there seems to be som…
-
I was trying to write a tutorial on using CUDA and CuSparse for PDEs but found that CuSparse was a bit too incomplete. The setup was fine:
```julia
using OrdinaryDiffEq, LinearAlgebra, SparseArray…
-
The program run too slow when using cusparse because cusparse did not converge very frequently as shown in terminal
```
cusparse did not converge, now trying Dune to solve current linear system...
…
-
# Issue description
## Expected behavior:
1. We can install `lightning.gpu` and `lightning.tensor` in a GPU-enabled google colab runtime (T4 GPU)
2. PennyLane can create a device using `lightni…
-
- I have installed `pyculib` as `pip install pyculib`
- When I import it in python shell then it is raising error that `cusparse` not found
```python
>>> import pyculib
```
- Error
```bash
Trac…
-
**Describe the bug**
Install of FATE from PyPI (recommended procedure), as described at https://github.com/FederatedAI/FATE/tree/master/deploy/standalone-deploy, fails during "pip install fate_client…
-
I'm having a problem where CUDA_cusparse_LIBRARY linked by target "THCUNN" is not found when installing cunn (As shown below). I'm on Ubuntu 14.04.
### admin@admin:/usr/local/cunn$ sudo luarocks …
-
### Description
Quite a bit of the cusparse API is exposed, but we have a need for SDDMM for a particular ML-related application and found that cupy does not expose this method. Is anyone looking int…