-
### Your current environment
```text
The output of `python collect_env.py`
Collecting environment information...
WARNING:root:libtpu.so and TPU device found. Setting PJRT_DEVICE=TPU.
INFO 11-04…
-
### Describe the issue
We are seeing an issue with a Transformer model which was exported using torch.onnx.export and then optimized with optimum ORTOptimizer. Inferencing seems to not be using GPU a…
-
### Your current environment
```text
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.4 LTS (x86_64)
GCC ve…
-
### Describe the issue
Small program
int main(int argc, char *argv[])
{
Ort::Env env;
Ort::SessionOptions session_options;
OrtCUDAProviderOptions cuda_options;
cuda_options.d…
-
I tried building an image with ROS2 Jazzy and Jax and it seems that OpenCV failed to install which stops me from creating the image.
I have also tried Humble, and it also fails on the same step if t…
-
### Description
Calling eigh() on the matrix
```
a = cupy.asarray([[ 2.0000100e+00, 0.0000000e+00, 0.0000000e+00,
1.0000000e+07, 0.0000000e+00],
[ 0.0000000e+00, 0…
-
Hi, thanks again for putting CUDA.jl together!
I found that the return type of the `sum!` function can be different between `Array` and `CuArray`:
the `Array` return type is the same as the left a…
-
### What is the issue?
Hardware has 11.1 GiB (RAM) + 1.9 GiB (GPU) = 13 GiB, but fails to run a 3B model.
Any idea why?
```
Nov 14 17:49:49 fedora ollama[1197]: r14 0x6
Nov 14 17:49:49 fedor…
-
### 🐛 Describe the bug
# Description
I tried to export a PyTorch model using `torch.nn.GroupNorm` to Core ML with ExecuTorch, but encountered a `ValueError: Unsupported fx node aten_native_group_nor…
-
I am having a lot of trouble with speaker diarization across lots of different platforms and models.
```toml
[target.'cfg(any(windows, target_os = "linux"))'.dependencies]
sherpa-rs = { version =…