-
We need to fuse the dequantize and conv kernels in Unet int8 model in order to achieve memory bandwidth improvement on AMD GPUs. This issue is created for tracking the discussion about the possible w…
-
Playing any MP4 video on MFPlayer2 results in a crash in the d3d9.dll when selecting PLAY. Intel and AMD video plays fine.
In creating another set of basic test code using MFPCreateMediaPlayer() f…
-
### What is the issue?
Both Adrenalin Edition drivers (24.9.1 and 24.10.1) significantly slows windows performance. GPU acceleration appears disabled.
No issues with ollama on Adrenalin 24.8.1 (…
-
Is this what I think it is? An extension to make AUTOMATIC1111 webui run using [pytorch-directml](https://pypi.org/project/pytorch-directml/), _and thus potentially on AMD GPUs in Windows instead of u…
-
Hi,
I found your project reading softpedia news and thought it will solve my need:
namely with a system with a NV GPU and AMD GPU installed ability to select which binary driver to use..
your tool is …
-
hwloc provides interoperability with a bunch of GPU/heterogeneous system APIs. The amount of support code needed for each is small, but each will need to get a dedicated feature and suitable cfg+doc(c…
-
System: ArchLinux 5.11.15-zen1-2-zen
using the aur package opencl-amd what just updated to 21.10
./teamredminer --list_devices:
Team Red Miner version 0.8.1.1
[2021-04-21 15:53:17] Au…
-
Currently INQ can run on Nvidia GPUs through CUDA backend.
What would be the design requirements required for supporting a new backend, say Intel's SYCL or AMD's HIP?
Would migrating/porting the …
-
### Describe the bug
Running the example program produces an error for big enough arrays.
Program:
```
public class App
{
public static void parallelInitialization(VectorFloat8 data) {…
-
`u32::max` / `u32::min` cannot be used as they require `OpCapability U8`. They should just work out of the box.
**Workaround:** use `u32::clamp()` instead.
> It's the Ordering enum. it …