-
# Module: get-started-openai
## Lab/Demo: Get started with Azure OpenAI service
### Task: Deploy a model
#### Step: 2
Description of issue
I am trying the labs for the AI-102 certification but …
-
| --- | --- |
| Bugzilla Link | [467683](https://bugs.eclipse.org/bugs/show_bug.cgi?id=467683) |
| Status | NEW |
| Importance | P3 normal |
| Reported | May 20, 2015 05:47 EDT |
| Modified | Mar…
-
**Description**
When testing the [GitHub Models example](https://github.com/Azure-Samples/netaivideoanalyzer?tab=readme-ov-file#run-github-models-samples), after running `dotnet user-secrets set "GIT…
-
With the following repro, the Tags property has IsPrimitiveCollection=true, but when a compiled model is generated, IsPrimitiveCollection is false.
```c#
await using var context = new MainDbContext()…
-
## Description
I tried to convert the Flux Dit model on L40S with TensorRT10.5, and found that the peak gpu memory exceeded 46068MiB, but 23597MiB gpu memory was occupied during inference. Is this n…
-
### Description
RiveView is using the deprecated CVDisplayLink to manage refresh rates on macOS. Because CVDisplayLink lacks support for a `preferredFrameRate`, Rive cannot set this on macOS and is *…
-
| --- | --- |
| Bugzilla Link | [427289](https://bugs.eclipse.org/bugs/show_bug.cgi?id=427289) |
| Status | NEW |
| Importance | P3 normal |
| Reported | Feb 03, 2014 11:24 EDT |
| Modified | Mar…
-
## Description
NMS Layers are much slower on TensorRT than on PyTorch (44% of the performance) and I'm looking for any possible workaround. This seems to be acknowledged as a known issue in the Tenso…
-
Run DDP with a shared buffer (different TorchDynamo `Source`):
Repro Script
```
"""
torchrun --standalone --nproc_per_node=1 test/dup_repro.py
TORCH_LOGS=aot,dynamo torchrun --standalone --…
-
From user empathy day 11-13-24
### 🐛 Describe the bug
Script to generate aoti artifact:
```
from transformers import T5Tokenizer, T5ForConditionalGeneration
import os
tokenizer = T5Tokenizer…