-
- [x] Create a new driver `manual_graph_testing.cc`\
- [x] Create kernels for: the basic for loop, matrix multiply, matrix vector multiply (spmv and dense from the paper), matrix addition
- [x] Each k…
-
Hey team, I'm suffering high triton kernel launch overhead. Here's my nsys capture:
![CleanShot 2023-11-10 at 10 28 53](https://github.com/openai/triton/assets/552990/d62f05c8-b00c-43fc-b1c7-0680a998…
-
### Describe the problem the feature is intended to solve
TensorFlow's pluggable device architecture offers a plugin mechanism for registering devices with TensorFlow without the need to make chan…
-
ACL 24.07
ACL build command:
```
scons neon=1 opencl=0 openmp=1 cppthreads=0 os=linux data_layout_support=all arch=arm64-v8.2-a build=native --jobs=64 build=native --silent fixed_format_kernels=Tru…
-
This issue tracks progress on graph breaks removal for the v2 transforms.
Restricting to pure tensors input (images) for now, we can figure out the TVTensors and arbitrary structures later.
#### K…
-
We need a way to pass a custom temp-allocator to XLA:GPU, right now we always allocate memory through a default stream executor device memory allocator
-
Hello,
My installation was successful. I setup the environment using environment.yml file. Previously, I ran this code of testing and training without any errors. Suddenly, I came across this error…
-
Build failure for kokkos-kernels@3.5.00 using spack on cascadelake CPU with the CUDA backend. Build error is:
```
==> Installing kokkos-kernels-3.5.00-6qlawlqf43snj4qgc36lv7dz42lvog2t
==> No binary…
-
Codes and the model for reproducing can be found [here](https://drive.google.com/open?id=1MeTuNPeI7d0P__uUw0BuNxsEKb2bzw56), I am using webdnn with commit `f403a30da36b6741bc857c21c3ca1e65af8fbac9`
…
-
File "", line 1, in
runfile('D:/PhD/Literature/NeuroNER-master/src/main.py', wdir='D:/PhD/Literature/NeuroNER-master/src')
File "C:\ProgramData\Anaconda3\lib\site-packages\spyder_kernel…