Delio Vicini

Hi, That sounds great! Yes, I think the volume_optimization notebook should be a good starting point to work with the PRB version of the integrator. You should also take a...

I ran into this issue on a very similar multi GPU setup. I was able to work around it by explicitly setting the `OPTIX_CACHE_PATH` environment variable to `/tmp`. I don't...

That's a good point, so the tests will either way not cover the full set of permutations. I don't have a local GPU, so I was surprised to see that...

I am also unsure about the synchronization behavior of the default stream. Couldn't it be that the other framework (in this case Jax) launches some compute on a non-default stream...

This all makes sense to me. I agree that Dr.Jit should not be unnecessarily pessimistic. I will try to investigate on the Jax-side what's going on. One potential cause of...

I got some feedback from the Jax developers on what's going on here: The use of `from_dlpack(a.__dlpack__())` to create a Jax array from a Dr.Jit array uses the legacy interface,...

I see, yes it's good to be cautious. We don't want to have a performance cost for this. As you probably guessed, the reason I am fixing this is because...

Hi Merlin! I've been seeing this segfault for some time already. I checked to be sure, your commit doesn't seem to affect it. Before and after that fix I am...

Closing this issue as I can't reproduce the segfault anymore. This seems to have been fixed

No, nothing of that sort. We would not expect Dr.Jit to ever use another thread here right? All the references to the renderop and the scene object should be on...