-
### Is this a duplicate?
- [x] I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cccl/issues) for this request and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.m…
-
**Describe the bug**
The power of the adjoint of a `CuSparseMatrix` does not work anymore. It is only related to Julia v1.10 and not to previous versions.
**To reproduce**
The Minimal Worki…
-
## Feature
It would be great if a GPU accelerated sparse matrix library can be incorporated into GTSAM. These libraries include: AMD ROCM's [rocSPARSE](https://rocmdocs.amd.com/en/latest/ROCm_L…
-
Error in installation of torchac_cuda = 0.2.5
`pip install torchac-cuda
Collecting torchac-cuda
Using cached torchac_cuda-0.2.5.tar.gz (8.7 kB)
Installing build dependencies ... done
…
-
error happens when
cmake --build . --target plc
/cuPDLP-C/cupdlp/cuda/cupdlp_cudalinalg.cu(18): error: identifier "CUSPARSE_SPMV_CSR_ALG2" is undefined
-
```
/home/groupc/cwpears/kokkos-kernels/perf_test/sparse/KokkosSparse_sptrsv_aux.hpp(271): error: identifier "csrsv2Info_t" is undefined
csrsv2Info_t infoL = 0;
^
/home/groupc/cwpears/ko…
-
**Describe the bug 🐞**
The LinearExponential() fails, if the ODEProblem is based on a MatrixOperator with a CuSparseMatrixCSC.
**Expected behavior**
The ODE should be successfully solved. Th…
-
### 🐛 Describe the bug
PyTorch 2.5.0 and latest 2.5.1 releases revive #111469 and so breaks when importing.
Temporary fix: getting back to 2.4.1
### Versions
PyTorch version: N/A
Is debug b…
-
### Describe the issue
Issue:“pip install flash-attn --no-build-isolation”
“Collecting flash-attn
Using cached flash_attn-2.6.3.tar.gz (2.6 MB)
Preparing metadata (setup.py) ... error
error…
-
We currently expect cusparse to provide standard spmv capability but the raft cusparse wrappers are hidden behind the the `detail` API. We should expose an "official" (stable) public API for computing…