-
Key Points for Summary:
- Cloud-Native Security: Cloud-native applications bring new security challenges like securing microservices, containers, and API communications.
- Zero-Trust Architec…
-
### Describe the issue
I found that the Java dependency of onnxruntime-gpu 1.18.0 does not work properly on CUDA 11. Is there a parameter that can allow it to run correctly on CUDA 11? If not, could …
-
### Describe the issue
Compiling with unit test enabled or running simile resnet50 through onnxruntime_perf_test gives cpuinfo error.
Error in cpuinfo: Unknown chip model name 'Snapdragon(R) X Eli…
-
### Describe the issue
The CPU implementation of LayerNormalization occasionally produces `nan` when computing the square root of variance. This occurs when the input variance is extremely small, p…
-
~~Avec la refonte et l'ajout du dossier `src/dataProviders` je pense que l'archi `src/modules/providers` devient trop lourde. Est-ce qu'on pourrait imaginer `src/providers` ? mais en même temps ça fai…
-
### Describe the issue
Lets' say I have an onnx model that takes an input 1x3x224x224. I want to change the model such that I can do batch inference. The two ways, I could do it is setting the first …
-
### Terraform Core Version
1.5.7
### AWS Provider Version
5.44.0
### Affected Resource(s)
* aws_ecr_repository
### Expected Behavior
With an ECR on which we are pushing multi-architecture image…
-
### Describe the issue
When traying to run basic sample, form the Phi 3 Cookbook [https://github.com/microsoft/Phi-3CookBook/blob/main/md/07.Labs/Csharp/src/LabsPhi301/Program.cs](https://github.com/…
-
There are situations whereby a user can end up unable to update a Pulumi program because old versions of providers are being used on resources but that provider is no longer accessible. A good example…
-
### Describe the issue
When running an inference session with a binding to GPU memory and using the CPU execution provider, onnxruntime will segfault. I would expect a helpful error message instead…