Leo Fang
FYI @miscco I merged with the latest main and yet still seeing a lot of CI pipelines fired up, not sure if this is expected as of today? (I lost...
It seems the Python CI is not run...?
> It seems the Python CI is not run...? nvm it's here https://github.com/NVIDIA/cccl/actions/runs/11377383986/job/31651464063?pr=2335
This is ready. Ping: - @conda-forge/help-python-c for reviewing `nvmath-python` - @conda-forge/help-c-cpp for reviewing `mathdx` - @conda-forge/cuda for vis FYI: > * Detected pure Python wheel(s) in source: `https://files.pythonhosted.org/packages/py3/n/nvidia-mathdx/nvidia_mathdx-24.4.0-py3-none-any.whl`. This is...
There seems to be non-deterministic overlinking errors... Are there known bugs in conda-build?
Pair-reviewed and discussed with @jakirkham offline. To deal with the sporadic, stochastic CI errors, we decided to shrink the initial support matrix of nvmath-python, thereby reducing the amount of Jinja...
@conda-forge/help-python-c @conda-forge/help-c-cpp the CI is green now 🙂 See also https://github.com/conda-forge/staged-recipes/pull/26820#issuecomment-2201223982
@conda-forge/help-python-c @conda-forge/help-c-cpp friendly nudge :)
`cuda.cooperative` is a Python module that offers callable CUB warp/block routines for Numba CUDA kernels (https://github.com/NVIDIA/cccl/pull/1973). In this case, CCCL headers are a **run-time** dependency of `cuda-cooperative`. Currently for the...