Leo Fang
xref: https://github.com/NVIDIA/cuda-python/issues/1124#issuecomment-3391662807
Assigning to @mdboom to assess the condition of closing this issue, since Mike already has done some work recently (#1340).
@kkraus14 has done most of the work. We can improve the templates gradually. Let me use this issue to note that I need users to report their Python environment (`pip...
Based on offline discussions a possible theory why we had to add xfail was because cuFILE does not (yet) support containers (overlayfs). We will be able to test this theory...
> Current implementation uses pytest, which does not offer the same granularity of nvbench. What does this mean? Also, nvbench is tailored for the cases where one has custom CUDA...
@adii-n interesting, thanks! Could you post the benchmark code that you used?
The tooling was set up like this for a reason. Unfortunately I am in a hurry now and can't find a reference from a quick cursory search. Please shoot a...
Blocked by #863 (unless we're willing to use nvidia-ml-py as stop-gap).
During the meeting the preliminary idea is to allow users to (optionally) register - C/C++ types on the device side - Python types on the host side similar to what...
/ok to test [4b77378](https://github.com/NVIDIA/cuda-python/pull/1468/commits/4b7737820f35daecc8f37643cb15b65e835e323c)