gfxenjoyer

@xiaodou29, @NeuroLord In your ComfyUI's python `..\python_embeded\Lib\site-packages\nvdiffrast\torch\ops.py` on `line 47`, you can change ``` opts = ['-DNVDR_TORCH'] ``` to ``` opts = ['-DNVDR_TORCH', '-D_ALLOW_COMPILER_AND_STL_VERSION_MISMATCH=1', '-allow-unsupported-compiler'] ``` You might also want...

Trying to run `mistralrs-server` on **Windows** with ``` cargo run --features cuda -- -i vision-plain -m EricB/Llama-3.2-11B-Vision-Instruct-UQFF --from-uqff llam3.2-vision-instruct-q4k.uqff ``` results in `Error: Expected file with extension one of .safetensors,...

Ignore the comment above. I was able to get it running with the latest commits. I did notice that `residual.safetensors` was downloaded before the uqff model.

The dependency on Tealr seems to be a blocker. Luau would probably need to be added separately like rune or rhai.

I had a similar issue and was able to build nvdiffrast. See this issue https://github.com/MrForExample/ComfyUI-3D-Pack/issues/220#issuecomment-2334815082. It may also help to enable long paths on your machine [see this](https://learn.microsoft.com/en-us/windows/win32/fileio/maximum-file-path-limitation?tabs=powershell#enable-long-paths-in-windows-10-version-1607-and-later). I have...

`kernels/marlin/marlin_kernel.cu` fails to compile on `--gpu-architecture=sm_75`. Seems to work fine for `80`, `86`, `89`, and `90`. I manually tested by setting `$env:CUDA_COMPUTE_CAP="75"`.

egui had the same issue and fixed it by setting the window invisible until first render. https://github.com/emilk/egui/pull/3631

Raph mentioned two-way interoperability with bevy in his [RustLab Vello talk](https://www.youtube.com/watch?v=mmW_RbTyj8c&t=948s). My goal is to make a Xilem app that can embed various small bevy applets for 3D features. I'm...

Checking [Cuda Math API](https://docs.nvidia.com/cuda/cuda-math-api/group__CUDA__MATH__DOUBLE.html) and [cmath](https://cplusplus.com/reference/cmath), there is no `isnanf` only `isnan`. It compiles if you remove the `f`. In your `%HOME%\.cargo\git\checkouts\candle-\\candle-kernels\src\cuda-utils.cuh` remove the `f` in `line 238` like so:...