Leo Fang
Leo Fang
Update: we get admin approval to use GitHub-hosted Windows GPU runner as a stop gap solution. This is temporarily unblocked. The condition was to test only 1 Python version x...
> Update: we get admin approval to use GitHub-hosted Windows GPU runner as a stop gap solution. This is temporarily unblocked. The condition was to test only 1 Python version...
@vzhurba01 I hope this is a simple one-liner change to the codegen and the remaining task is on verifying the generated headers. Could you take a look?
It is unclear to me if we still need this done if we want to go by the route of #564. @oleksandr-pavlyk @shwina WDYT?
Sorry I somehow dropped the ball and Sasha reminded me about this with a use case in mind (accessing `cuda.bindings` types in pybind11). @shwina You're absolutely right. And it turns...
@vzhurba01 I will provide needed code change (as part of #91) for you to incorporate into the codegen 🙂
The first four tasks are done (single-GPU CI for all supported platforms + multi-GPU CI for linux-64), see #267 (build) & #124 (test). The remaining two tasks are currently blocked...
This should be done indeed. IIRC NumPy etc do this too by uploading artifacts. @jakirkham any chance you know off top of your head a reference for us to follow?...
@sandeepd-nv Would you take a look when you have a chance plz? 🙂 Thanks!
cc @m3vaz for vis