-
**Describe the bug**
There are two kinds of issues:
- conditional jump depends on uninitialized memory. `MakePacking` declares a variable which is only partially filled and then an uninitialized fie…
-
## Description
I run my onnx model with trtexec , and get failed.
Here are the details
## Environment
**TensorRT Version**: 8.2.1
**NVIDIA GPU**: GeForce RTX 3090
**NVIDIA Driver Vers…
-
Now I use fn.crop_mirror_normalize op to change the tensor layout. But I don't want the mirror and normalize ops. Just change the layout, how can I do. HWC to CHW. I use ```fronts = fn.reshape(fronts…
-
### Discussed in https://github.com/ggerganov/llama.cpp/discussions/6806
Originally posted by **Spider-netizen** April 21, 2024
Hi,
I am trying to build llama.cpp on my MacBook Pro using "m…
-
I have performed the training as instructed above [https://github.com/intel-analytics/analytics-zoo/tree/master/zoo/src/main/scala/com/intel/analytics/zoo/examples/objectdetection/finetune/ssd](https:…
-
**Describe the bug**
The following unit test hangs at the `.cpu()` call when run in fast dispatch:
```pytest tests/tt_eager/python_api_testing/unit_testing/test_untilize_with_halo_v2.py::test_genera…
-
Please forgive me for removing the non-onnx paths, and the reason I use DirectML is that it's probably the GPU provider easiest to setup on Windows.
I guess avoid the ndarray operations is the firs…
-
### Descripe the feature and motivation
Provide support for ReduceSum (or any for that matter) onnx reduction layer with parameters
axis = 1
keepdim = 1
for NCHW input
Currently, from what I …
-
I've got a brand new Orin AGX developer kit (64GB) and used the SDK Manager to download and flash the latest Ubuntu (22.04) and JetPack SDK (6.1).
I'm trying to build a container (I need diffusers …
-
### Describe the bug
The FMS shows the wrong time or arrival to the destination airport
### Steps to reproduce
Setup the FMC
Begin flight
### Expected behaviour
I found that when I set up the fm…