L3tum

Unless you have a breakthrough I'll try the same with rav1e and dav1d through libheif tomorrow to see if the issue persists. I'll also set up libheif and its heif-enc...

Hey @jcupitt, the saga continues 😆 We have an "older" service still running while dealing with this problem. This service is similarly to the prebuilt Windows binaries on libvips 8.12.2...

I'll see if I can get the lib and its dependencies at least, most of them are dynamic. The build itself is pretty old so I don't think I can...

I got the lib, in case it may help, but looking at the dependencies it doesn't seem anything simple like that. They hardly changed between the two builds. Here's a...

Here's the build script, you can basically substitue `LIBVIPS_VERSION`, `LIBSPNG_VERSION`, `LIBHEIF_VERSION` and `LIBAOM_VERSION` for any version you want. In this case we were using, LIBVIPS_VERSION=8.13.0, LIBSPNG_VERSION=0.7.2, LIBHEIF_VERSION=1.12.0 and LIBAOM_VERSION=3.4.0. The...

Hey @jcupitt, I've dropped you a link via e-mail to our custom-built libvips. I hope it helps, I couldn't really figure out a difference.

Hey, I need some help with middlewares in this. From what I can see they aren't being registered but are being executed. At least the "Registering Middleware" log entry is...

I've been on PyTorch Preview with ROCm 5.7 for ~a month now, seems to work fine. Around 4it/s IIRC for 1024x1024 SDXL on my 6950XT. Edit: I can attest to...

@Soulreaver90 Not sure about this one, but the exact same issues happen to me on *Windows*. Even if I use ZLUDA, or the normal DirectML way, the exact same issues...

While ARM-Neon is certainly interesting, I have no way to record a reference value currently (short of running Qemu to simulate the processor)