-
Right now, only the exponentiated-quadratic kernel is supported as it has a native implementation in Stan. However, there seem to be quite a few other kernels worth considering. This issue is ment to …
-
Hi there,
I have copied s4.py and the kernel extension into another repository I am working on. I had S4 components running (with CUDA), and then I installed the kernel extensions. The build output …
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
No
### Source
source
### TensorFlow version
v2.17.0
### Custom code
No
### OS platform and distribution
Ubuntu 22…
-
Can you please explain how to support shared memory in a kernel ? Does the warp compiler optimize a kernel with shared memory ? Thanks.
-
After every update of kernel-native it leaves behind old kernels at boot. Manual removal of them necessitates. This wasn't the case earlier I suppose.
-
在自己源码编译时,遇到了一些报错问题。同时发现在win10 22h2的wsl2 ubuntu2004下,会有一些驱动问题:
求问有没有相关的问题和解决文档
**无法正常找到模块**
[root@DESKTOP-6VT7GDB-LFS:torch_musa]# modprobe mtgpu
modprobe: FATAL: Module mtgpu not found in direct…
-
I'm creating this issue to capture any work that will need to be done post-merge, inevitably we've had to leave some stuff unfinished to make the ABI breaking window.
### Tasks from review
- [ ]…
-
In accordance with documentation [NEGEMMLowpMatrixMultiplyCore](https://arm-software.github.io/ComputeLibrary/v24.06/classarm__compute_1_1_n_e_g_e_m_m_lowp_matrix_multiply_core.xhtml) suports only lim…
-
https://github.com/cilium/cilium/pull/27622 lifted a limitation that requires Cilium-managed native devices (where `bpf_host` is attached) to have an ifindex = 5.10. But the [relevant patch](https://g…
-
## [CUDA] Add channels_last_3d support for commonly used modules
The goal is to add `channels_last_3d`, aka NDHWC, support on CUDA devices, and improve performance on 3D model training and inferenc…